KR102633950B1 - Method and electronic device for measuring velocity of object using cctv video - Google Patents

Abstract

According to various embodiments, an electronic device may include: a camera; a memory; and a processor operatively connected to the camera and the memory. According to one embodiment, the processor may identify a region of interest set based on an image captured using the camera. The processor may identify a first region corresponding to at least one object included in the image. The processor may identify a first coordinate point and a second coordinate point where a first boundary line of the first region and a second boundary line of the region of interest intersect each other in response to an event in which the identified first region at least partially overlaps the region of interest. The processor may determine a first reference point based on the identified first coordinate point and second coordinate point. The processor may identify a first time point at which the first reference point is determined and a second time point at which the first reference point leaves the region of interest. The processor can measure a velocity of the at least one object based on a first distance from a first point in a time to a second point in the time and the first distance traveled by the first reference point during a first time. Various other embodiments are possible.

Description

Method and electronic device for measuring the speed of an object using CCTV video {METHOD AND ELECTRONIC DEVICE FOR MEASURING VELOCITY OF OBJECT USING CCTV VIDEO}

Various embodiments of the present invention relate to a method of measuring the speed of an object using CCTV images and an electronic device implementing the same.

Recently, various electronic devices (e.g., server devices, management devices) can capture surrounding situations using PTZ cameras (pan-tilt-zoom cameras) (e.g., pan-tilt-zoom cameras). A PTZ camera may include a closed circuit television (CCTV) (e.g., closed circuit television, CCTV device), and an electronic device may acquire image information (e.g., video, image, image) captured using the CCTV. . For example, CCTV can be placed in a specific place at a specific angle, capture images in real time, and transmit the captured images to an electronic device (eg, a server device). The electronic device can control the shooting angle of the camera included in the CCTV and the zoom-in/zoom-out of the lens. Electronic devices can at least partially control the operation and functions of CCTV. CCTV can acquire images captured in real time and transmit the acquired images to an electronic device (eg, a server). Electronic devices can provide images captured using CCTV to users in real time.

An electronic device can at least partially control CCTV and capture images in real time. CCTV can encode captured images and provide them to electronic devices (e.g. servers) through streaming in real time.

The above information may be provided as background art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing can be applied as prior art to the present disclosure.

Republic of Korea Patent Publication No. 10-2020-0052862 (2020.04.29)

Electronic devices (eg, server devices and/or management devices) may analyze images captured based on CCTV (eg, camera devices, CCTV devices). For example, the electronic device can measure at least one pixel value corresponding to a captured image and analyze the image based on the measured pixel value. Electronic devices can add information related to shooting to images based on OSD (on screen display) technology. For example, when displaying the image through a display, the electronic device may also display information related to capturing the image (eg, information related to a region of interest (ROI)). For example, the region of interest (ROI) may be set to be fixed to the position and area initially set in the image, regardless of the location and shape of the object (e.g., car) included in the image. For example, the region of interest (ROI) may be displayed in a form that at least partially obscures the object and/or background included in the image, or may be displayed in a form that at least partially overlaps the background. When an electronic device displays an image captured using a camera, it may also display a region of interest (ROI).

According to one embodiment, the electronic device can recognize at least one object (e.g., a car) included in an image, and when the recognized object at least partially passes through a region of interest included in the image, the recognized object You can measure the speed of an object. According to one embodiment, a method and electronic device for measuring the speed of an object in response to an event in which the object passes while at least partially overlapping a region of interest may be provided.

The technical challenges sought to be achieved in this document are not limited to the technical challenges mentioned above, and other technical challenges not mentioned can be clearly understood by those skilled in the art of this document from the description below. There will be.

According to various embodiments, an electronic device may include a camera, a memory, and a processor operatively connected to the camera and the memory. According to one embodiment, the processor may check a region of interest set based on an image captured using a camera. The processor may check the first area corresponding to at least one object included in the image. In response to an event that the identified first region at least partially overlaps a region of interest, the processor may generate a first coordinate point and a second coordinate point at which a first boundary line of the first region and a second boundary line of the region of interest intersect each other. can confirm. The processor may determine the first reference point based on the confirmed first and second coordinate points. The processor may check a first time point at which the first reference point is determined and a second time point at which the first reference point leaves the region of interest. The processor may measure the speed of at least one object based on the first distance from the first viewpoint to the second viewpoint and the first distance the first reference point moves during the first time.

A method of measuring the speed of an object according to various embodiments includes an operation of checking a region of interest set based on an image captured using a camera, an operation of checking a first region corresponding to at least one object included in the image, and confirmation. In response to an event in which a first region at least partially overlaps a region of interest, a first coordinate point and a second coordinate point are set at which a first boundary line of the first region and a second boundary line of the region of interest intersect each other. An operation of confirming, an operation of determining a first reference point based on the confirmed first coordinate point and the second coordinate point, a first time point at which the first reference point is determined, and a second reference point at which the first reference point is outside the region of interest. An operation of checking a viewpoint, and determining the speed of the at least one object based on a first distance from the first viewpoint to the second viewpoint and a first distance moved by the first reference point during the first time. It may include measuring actions.

In various embodiments of the present invention, when an electronic device captures an image using a CCTV, capture-related information (eg, region of interest (ROI)) based on OSD technology may be added to the image. According to one embodiment, the electronic device may measure at least one pixel data (e.g., coordinate information) corresponding to a captured image, and based on the measured pixel data, at least one boundary line indicating a region of interest ( Example: corners) can be detected. Based on the region of interest, the electronic device can recognize an object passing through the region of interest while at least partially overlapping the region of interest, and measure the speed of the recognized object.

According to one embodiment, the electronic device may add shooting-related information (e.g., text, icon, content, object, and/or area of interest) based on OSD technology to the captured image. The electronic device can determine a reference point of an object that at least partially passes through the area of interest, and measure the movement distance and movement time of the determined reference point. The electronic device can measure the speed of the object based on the measured movement distance and movement time. One embodiment may provide a method of more accurately measuring the speed of an object based on images captured using CCTV. In addition, various effects that can be directly or indirectly identified through this document may be provided.

The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

In relation to the description of the drawings, identical or similar reference numerals may be used for identical or similar components.
Figure 1 shows a network environment between electronic devices and CCTV according to various embodiments of the present invention.
Figure 2 is a block diagram of an electronic device according to various embodiments of the present invention.
Figure 3 is a flowchart of a method for measuring the speed of an object included in an image based on an image captured using CCTV according to various embodiments of the present invention.
Figure 4 is a diagram illustrating an example in which a region of interest is set in a captured image according to various embodiments of the present invention.
FIG. 5 is a diagram illustrating a first scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention.
FIG. 6 is a diagram illustrating a second scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention.
FIG. 7 is a diagram illustrating a third scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention.
Figure 8 is a diagram illustrating an example in which a plurality of regions of interest are set in a captured image according to various embodiments of the present invention.
FIG. 9A is a diagram illustrating a first embodiment of measuring the speed of an object in response to an event in which objects overlap based on a set area of interest according to various embodiments of the present invention.
FIG. 9B is a diagram illustrating a second embodiment of measuring the speed of an object in response to an event in which objects overlap based on a set area of interest according to various embodiments of the present invention.

Figure 1 shows a network environment between an electronic device 101 and a CCTV 110 according to various embodiments of the present invention.

Referring to FIG. 1, an electronic device 101 (e.g., a server device, a management device, a cloud server, a computer, and/or a manager device that manages images transmitted from a plurality of CCTVs 110) in a network environment. Can communicate with another electronic device (e.g., CCTV 110) through a first network (e.g., short-range wireless communication network) and a second network (e.g., long-distance wireless communication network). For example, the electronic device 101 may acquire an image 102 captured using the CCTV 110 from the CCTV 110 and analyze the acquired image 102. The electronic device 101 may at least partially control the operation and functions of the CCTV 110. According to one embodiment, there may be a plurality of CCTVs 110, and each CCTV 110 may communicate directly or indirectly with the electronic device 101. According to one embodiment, the electronic device 101 and the CCTV 110 may establish a direct (eg, wired) communication channel or a wireless communication channel, and/or perform communication through the established communication channel. For example, CCTV 110 may include cameras (e.g., pan-tilt-zoom (PTZ) cameras, embedded pan-tilt-zoom (ePTZ) cameras, and/or virtual pan-tilt-zoom (VPTZ) cameras. It may include a camera device (e.g., closed circuit television (CCTV)).

According to one embodiment, the electronic device 101 (eg, a server device) may transmit commands and/or data to the CCTV 110, or may receive commands and/or data from the CCTV 110. The electronic device 101 may exchange data with the CCTV 110 based on wireless communication, or may be directly connected to the CCTV 110 to exchange data (eg, captured image data). For example, the CCTV 110 can capture the external environment while being fixed at a set location, store the captured images 102 in memory, or transmit them to the electronic device 101 in real time. The captured image 102 may include at least one object 103. The electronic device 101 may recognize at least one object 103 based on the image 102 captured by the CCTV 110. The electronic device 101 can obtain captured images by streaming through the CCTV 110 and analyze the captured images in real time.

According to one embodiment, the CCTV 110 may include a camera device (eg, a camera, PTZ camera, ePTZ camera, and/or VPTZ camera) for capturing still images or moving images. The CCTV 110 may include a closed circuit television (CCTV) device and/or an electronic device including a camera capable of changing the shooting direction up/down/left/right. For example, the CCTV 110 can capture a specific area (e.g., external environment) containing at least one object 103 based on the set location and angle of view, and encode the captured image to transmit it to an electronic device ( 101), streaming can be transmitted.

For example, the electronic device 101 may receive streaming of encoded image data transmitted from the CCTV 110, decode the received encoded image data, and display the electronic device 101 (e.g., display The captured image can be displayed through the module (module, display device). For example, the electronic device 101 can run a specific application to play back images captured by the CCTV 110, and play the images captured by the CCTV 110 in real time based on the specific application. .

According to one embodiment, the electronic device 101 can receive images captured in CCTV 110 in real time, and store the captured images in a storage device (e.g., digital video recorder (DVR), digital image storage device). You can save it. According to one embodiment, the electronic device 101 may compare or analyze images received from a plurality of CCTVs 110. For example, the electronic device 101 may acquire a plurality of images taken of the same specific area from different directions, and may display the plurality of acquired images on one screen.

According to one embodiment, the electronic device 101 may set some areas as a region of interest (ROI) based on the image captured by the CCTV 110. The electronic device 101 may set the captured image as a region of interest (ROI). At least one object 103 (e.g., a car) included in can be individually recognized, and a situation (e.g., an event) in which at least one object 103 at least partially overlaps a set region of interest (ROI) can be recognized. It can be detected.

According to one embodiment, the electronic device 101 can analyze captured images (e.g., a plurality of image frames) in real time and detect an event (e.g., IOU (IOU)) in which at least one object 103 overlaps an area of interest. intersection of union area event) can be detected. In response to detection of an event, the electronic device 101 may determine a reference point within an overlapping area and check the movement direction, movement time, movement distance, and/or movement speed of the determined reference point. For example, the reference point may include reference coordinate information corresponding to at least one object 103. The electronic device 101 can check the movement distance and movement time of the reference point within the area of interest, and measure the speed with respect to the reference point based on the confirmed movement distance and movement time. The speed with respect to the reference point may mean the speed of the object corresponding to the reference point.

According to one embodiment, the electronic device 101 can communicate with a plurality of CCTVs 110 and control each of the plurality of CCTVs 110 at least partially. For example, the electronic device 101 can distinguish and display a plurality of images acquired through a plurality of CCTVs 110, and select at least one of the plurality of CCTVs 110 to select a desired captured image. It can be displayed by enlarging or reducing it. According to one embodiment, the electronic device 101 and a plurality of CCTVs 110 may be configured as one system.

According to one embodiment, the electronic device 101 can encode an image captured using the CCTV 110 and obtain image data through the encoding process. The image data may include digital images. For example, CCTV 110 may encode captured image data and transmit streaming to the electronic device 101, and the electronic device 101 may decode the transmitted image data and display a display device (e.g., display). ), display module), the decoded video data can be displayed. According to one embodiment, when displaying image data, the electronic device 101 may also display the speed of the object 103 included in the image data. For example, the electronic device 101 can detect an event in which the object 103 passes while overlapping, and measure the speed of the object 103, based on a region of interest set in the image data. When displaying image data, the electronic device 101 may also display the measured speed of the object 103.

Figure 2 is a block diagram of an electronic device 101 according to various embodiments of the present invention.

According to one embodiment, the electronic device 101 (e.g., a server device, a management device) includes a processor 120, a communication circuit 190, and a memory 130 (e.g., a digital video recorder (DVR), a digital image storage device). ), and may include a camera 180. In some embodiments, in the electronic device 101, at least one of these components may be omitted, or one or more other components may be added. For example, at least one component may be an external device that operates independently. In some embodiments, some of these components may be implemented as a single integrated circuit. Referring to FIG. 2, the electronic device 101 is shown as including a camera 180, but the camera 180 may include a CCTV (eg, CCTV 110 in FIG. 1). For example, the electronic device 101 may be operatively connected to the camera 180 and acquire an image captured using the camera 180.

According to one embodiment, the electronic device 101 may photograph a specific area using a camera 180 (eg, CCTV 110, PTZ camera, ePTZ camera, and/or VPTZ camera). According to one embodiment, the electronic device 101 can photograph a specific area, encode the captured image, and store it in the memory 230 (e.g., a storage device and/or a digital video recorder (DVR)). . According to one embodiment, the memory 230 may include an external storage device (eg, DVR, storage device) functionally connected to the electronic device 101. According to one embodiment, the processor 120 of the electronic device 101 is functionally connected to the CCTV 110 through the communication circuit 190, can perform communication, and captures images captured using the CCTV 110. Image data can be acquired. According to one embodiment, the electronic device 101 may receive image data transmitted from the CCTV 110, decode the received image data, and display the image through a display device (e.g., display, display module). Data can be displayed.

The processor 120 of the electronic device 101, for example, executes software (e.g., a program, an application) to control at least one other component (e.g., a hardware or software component) connected to the processor 120. and can perform various data processing or calculations. According to one embodiment, as at least part of data processing or computation, the processor 120 stores commands or data received from other components (e.g., communication circuit 190, camera 180) in memory 130 (e.g., : Can be saved to DVR (digital video recorder), digital video storage device. According to one embodiment, the processor 120 is a main processor (e.g., a central processing unit (CPU) and/or an application processor (AP)) and/or an auxiliary processor that can operate independently or together with the main processor. May include a processor (e.g., a graphics processing unit (GPU), an image signal processor, a sensor hub processor, and/or a communication processor (CP)). . Additionally or alternatively, a coprocessor may be configured to use less power than the main processor or to specialize in designated functions. The auxiliary processor may be implemented separately from the main processor or as part of it.

According to one embodiment, the processor 120 may include an image processing module 201, and the image processing module 201 may include a graphics processing unit (GPU) and/or an image signal processor. According to one embodiment, the image processing module 201 may analyze a specific image (e.g., an image captured using the camera 180) and at least one pixel data (e.g., pixel) included in the specific image. value) can be measured. According to one embodiment, the image processing module 201 includes luminance information, brightness information, contrast information, RGB (red-green-blue) information, size information, and At least one piece of information among the top/bottom size information of the specific image can be extracted, and based on the extracted information, shooting-related information included in the captured image (e.g., object (e.g., car), People, boundaries of region of interest (ROI) can be detected. For example, the image processing module 201 may detect at least one object and at least one region of interest (ROI) included in the captured image. For example, a region of interest (ROI) may be set by the user as an arbitrary region or area in a captured image.

According to one embodiment, the image processing module 201 may recognize at least one object and a region of interest based on a specific image (e.g., a plurality of image frames captured using the camera 180), Pixel data (eg, pixel value) corresponding to the at least one object and the region of interest may be measured. For example, the image processing module 201 may obtain coordinate information corresponding to each of a plurality of image frames. The image processing module 201 may obtain first coordinate information corresponding to at least one object included in an image frame and second coordinate information corresponding to the region of interest. The image processing module 201 may detect an event (e.g., intersection of union area (IOU) event) in which at least one object at least partially overlaps the region of interest, based on coordinate information for each image frame. . The image processing module 201 may check a situation in which an object is moving within at least one region of interest included in the specific image, based on the measured pixel data.

According to one embodiment, the communication circuit 190 establishes a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device 101 (e.g., a server device) and the CCTV 110 (e.g., a CCTV device). , and/or may support conducting communications through established communication channels. Communication circuitry 190 may operate independently of processor 120 (e.g., an application processor) and may include one or more communication processors (CPs) that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication circuit 190 may include a wireless communication module (eg, a cellular communication module, a short-range wireless communication module, and/or a global navigation satellite system (GNSS) communication module). Communication circuitry 190 may be connected to a first network (e.g., a short-range communication network such as Bluetooth, WiFi direct, or infrared data association (IrDA)) and/or a second network (e.g., a cellular network, the Internet, and/or a computer network (e.g., It is possible to communicate with the CCTV 110 through a long-distance communication network such as LAN or WAN. The communication circuit 190 may be integrated into one component (eg, a single chip), or may be implemented as a plurality of separate components (eg, multiple chips). The communication circuit 190 uses subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in a subscriber identification module (e.g., SIM card) to detect CCTV (CCTV) within a communication network, such as a first network and/or a second network. 110) can be confirmed and authenticated.

According to one embodiment, the memory 130 may store various data used by at least one component (eg, the processor 120, the camera 180, and/or the image processing module 201). Data may include, for example, input data or output data for software (e.g., programs and/or applications) and instructions associated therewith. Memory 130 may include volatile memory and/or non-volatile memory. According to one embodiment, the memory 130 may store various data related to shooting. For example, the memory 130 may store region-of-interest-related information 211, object-related information 212, and/or speed-related information 213.

According to one embodiment, when the processor 120 generates image data by encoding a captured image, the processor 120 determines the region of interest included in the captured image based on the region-of-interest related information 211 stored in the memory 130. (ROI) can be checked. For example, the area-of-interest-related information 211 includes the size (e.g. area), location (e.g. coordinate information), slope, actual size, vertical length, horizontal length, diagonal length, and width of the area of interest based on the captured image. , may include at least one piece of information among the widths. According to one embodiment, the area of interest may be arbitrarily set or changed by the user. When the region of interest changes, the processor 120 may update the region-of-interest related information 211 based on the changed region of interest.

According to one embodiment, the region-of-interest-related information 211 may include actual data measured based on the region of interest in an actual external environment corresponding to the captured image. The processor 120 may compare or analyze a first region of interest identified based on a captured image and a second region of interest based on measured actual data. If an error is identified by comparing the first region of interest and the second region of interest, the processor 120 may reflect the identified error based on the first region of interest and update information related to the first region of interest. You can.

According to one embodiment, when generating image data of a captured image, the processor 120 generates image data of the captured image based on the object-related information 212 stored in the memory 130, and selects an object (e.g., a car) included in the captured image. ) can be confirmed (e.g. recognized). For example, the object-related information 212 may include information (eg, object characteristic information) related to an object that is added or deleted from a captured image. For example, when the CCTV 110 photographs a road, the object-related information 212 may include at least one of a car, a motorcycle, a bus, and a person passing on the road. The object-related information 212 may include characteristic information for individually recognizing each of the above-described objects. According to one embodiment, the processor 120 may detect at least one object that appears in the captured image based on the object-related information 212. The processor 120 may measure the ratio of the area occupied by at least one object in the captured image based on the object-related information 212.

According to one embodiment, the processor 120 generates image data of a captured image, based on the speed-related information 213 stored in the memory 130, and selects an object (e.g., a car) included in the captured image. ) can be measured. For example, when an object passes through the area of interest in a manner that at least partially overlaps the area of interest, the processor 120 may check the moving distance and movement time of the object within the area of interest and measure the speed of the object. can do.

According to one embodiment, the processor 120 of the electronic device 101 can acquire images captured using the camera 180 in real time and analyze the acquired images. The processor 120 may detect an event in which at least one object 103 at least partially overlaps a set region of interest (ROI). In response to detecting an event, the processor 120 may determine a reference point within an overlapping area and check the movement direction, movement time, movement distance, and/or movement speed of the determined reference point. For example, the reference point may include reference coordinate information corresponding to at least one object 103. The electronic device 101 can check the movement distance and movement time of the reference point within the area of interest, and measure the speed of the reference point (eg, object) based on the confirmed movement distance and movement time. The speed with respect to the reference point may mean the speed of the object corresponding to the reference point.

Figure 3 is a flowchart of a method for measuring the speed of an object included in an image based on an image captured using CCTV according to various embodiments of the present invention.

In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

According to one embodiment, operations 301 to 315 will be understood as being performed by a processor (e.g., processor 120 of FIG. 2) of an electronic device (e.g., electronic device 101 of FIGS. 1 and 2). You can.

The electronic device 101 of FIG. 3 may be at least partially similar to the electronic device 101 of FIGS. 1 and 2 or may further include other embodiments of the electronic device. The electronic device 101 may acquire a captured image (e.g., a plurality of image frames) using an operatively connected camera (e.g., the camera 180 of FIG. 2), and based on the captured image, A set region of interest (ROI) and at least one object can be recognized. The electronic device 101 may detect an event in which a recognized object at least partially overlaps a region of interest (ROI) (e.g., an intersection of union area (IOU) event), and the object moves within the region of interest. Depending on the situation, the speed of the object can be measured.

In operation 301, the processor 120 may set at least one region of interest based on an image (eg, image frame) captured using the camera 180. For example, the processor 120 may set at least one region of interest in a captured image and check coordinate information related to the at least one region of interest. For example, coordinate information related to the region of interest may be stored as region-of-interest related information 211 in a memory (eg, memory 130 in FIG. 2). Coordinate information related to the region of interest may include coordinate information corresponding to boundary lines, vertices, corners, sides, and internal areas of the region of interest.

In operation 303, the processor 120 may identify a first area corresponding to an object (eg, car, vehicle) included in the image. For example, the processor 120 can identify an object included in an image and recognize the area occupied by the object within the image as the first area. The processor 120 may check coordinate information corresponding to the first area. For example, coordinate information corresponding to the first area may include a set boundary line of the first area. For example, when an object moves per unit time, the size and location of the first area may also change. According to one embodiment, the processor 120 may check a situation in which the position of the first area changes based on a plurality of captured images (image frames), and determine the movement direction of the first area and the first area. You can check the speed of .

In operation 305, the processor 120 may identify an event (e.g., an intersection of union area (IOU) event) in which the identified first area (e.g., object, vehicle, automobile) at least partially overlaps the area of interest. For example, a region of interest may remain fixed at a set location within the image. The region of interest may be set as a fixed area in each of a plurality of images. For example, if the captured image corresponds to a part of a road along which a car (eg, an object) moves, a part of the road may be set as an area of interest. The processor 120 detects an event (e.g., IOU event) in which an object at least partially overlaps the area of interest based on first coordinate information corresponding to the first area and second coordinate information corresponding to the area of interest. You can.

In operation 307, in response to detection of an event, the processor 120 may check the first and second coordinate points where the first area and the area of interest overlap. For example, the processor 120 may identify at least two intersection points where a boundary line of the first area and a boundary line of the region of interest intersect. In a situation where the first area and the area of interest at least partially overlap, at least two intersection points (eg, a first coordinate point and a second coordinate point) may be identified. According to one embodiment, the processor 120 may set one of the two identified intersection points as a first coordinate point and set the other as a second coordinate point.

In operation 309, the processor 120 may determine the first reference point based on the first coordinate point and the second coordinate point. For example, the processor 120 may check at least two intersection points in a situation where the first area and the area of interest at least partially overlap (eg, confirmation of an IOU event). The intersection point may include coordinate information at a point where the boundary line of the first area and the boundary line of the area of interest intersect. The processor 120 may determine the midpoint between the first and second coordinate points as the third coordinate point, and may set the third coordinate point as the first reference point. For example, the first reference point may be relative coordinate information included in an area where the first area and the area of interest overlap, and may be used to measure the location and movement direction of the object. The first reference point may mean coordinate information corresponding to a relative position based on the first area. According to one embodiment, the method in which the first reference point is determined is not limited to a specific method, and any coordinate point included in the area where the first area and the region of interest overlap may be determined as the first reference point. According to one embodiment, the processor 120 may determine the first reference point based on a first time point (eg, a time point when an IOU event is first detected) where the first area and the area of interest at least partially overlap.

According to one embodiment, the first reference point may include relative coordinate information corresponding to a relative position based on a plurality of pieces of coordinate information included in the first area. The first reference point may include relative coordinate information corresponding to the relative position with respect to the first area for each frame constituting the image. For example, when the first area moves, the first reference point may also be moved according to the movement direction and distance of the first area. For example, when the first area moves to the 1-1 area, the first reference point for the first area may move to the 1-1 reference point for the 1-1 area. The first reference point may be determined as a relative position with respect to the first area, and the 1-1 reference point may be determined as a relative position with respect to the 1-1 area. For example, the relative coordinate information of the first reference point included in the first area may be substantially the same as the relative coordinate information of the 1-1 reference point included in the 1-1 area.

In operation 311, the processor 120 may check the movement distance and movement time of the object (e.g., the first reference point) based on the first time point at which the first reference point is determined and the second time point when the first reference point is outside the region of interest. . For example, the first time point may be a time point when an event where the first area overlaps with the area of interest is confirmed, and the second time point may be a time point when an event where the first reference point deviates from the area of interest is confirmed. At a second viewpoint, the processor 120 may determine relative coordinate information where the first reference point is located as the second reference point. For example, the position of the object may be changing from the first viewpoint to the second viewpoint, and as the position of the object changes, the relative coordinate information corresponding to the first reference point may also continuously change. According to one embodiment, the movement distance of the object includes the distance from the first reference point at the first viewpoint to the second reference point at the second viewpoint, and the movement time of the object is the time interval from the first viewpoint to the second viewpoint. Includes. For example, the first area may be implemented based on the size of the object, and the first reference point may be determined as relative position coordinates within the first area. The absolute coordinate information of the first reference point may change as the location of the object changes. However, within the first area, the relative coordinate information of the first reference point determined as the relative position may be fixed to the relative position within the first area even if the position of the object changes. According to one embodiment, the first reference point may be determined as relative coordinate information within the first area containing the object, and may mean representative coordinate information indicating the location of the object.

In operation 313, the processor 120 may measure the speed of the object based on the confirmed movement distance and movement time. For example, the processor 120 may measure the speed of an object by dividing the moving distance of the object by the moving time of the object. For example, the moving distance of the object may include the distance between first absolute coordinate information corresponding to the first reference point, confirmed at the first viewpoint, and second absolute coordinate information corresponding to the second reference point, confirmed at the second viewpoint. You can. The movement time of an object may include a time interval from a first viewpoint to a second viewpoint.

According to one embodiment, when measuring speed in the electronic device 101, the following equation can be used. (Equation 1) to (Equation 5) are attached below.

For example, if arbitrary coordinates are (x, y), (x’, y’) corresponding to the actual coordinates can be converted using (Equation 1). If the formula of (Equation 1) is reflected in (x’, y’), it can be converted as (Equation 2) and (Equation 3) below.

If you solve (Equation 2) and write it, it can be converted like (Equation 4), and if you solve (Equation 3) and write it, it can be converted like (Equation 5).

According to one embodiment, the electronic device 101 may reflect arbitrary coordinates (x, y) in the equation based on (Equation 1) to (Equation 5), and calculate the actual coordinates corresponding to the actual distance. Coordinates (x', y') can be obtained. The electronic device 101 can measure the actual moving distance of an object (car, vehicle) using (x’, y’) corresponding to actual coordinates.

For example, the variables “a” to “h” used in (Equation 1) to (Equation 5) can be confirmed using (Equation 6) below. For example, the coordinates of about four vertices for a set region of interest are (x ₁ , y ₁ ), (x ₂ , y ₂ ), (x ₃ , y ₃ ), (x ₄ , y ₄ ), and The actual vertex coordinates of the vertex coordinates may be (x ₁ ', y ₁ '), (x ₂ ', y ₂ '), (x ₃ ', y ₃ '), and (x4', y ₄ ').

The electronic device 101 can calculate the inverse matrix of an 8*8 matrix using Gaussian elimination, based on (Equation 6), and the function You can obtain parameters for (e.g. variables “a” to “h”). According to one embodiment, the electronic device 101 may reflect the obtained parameters (e.g., variables “a” to “h”) in (Equation 1) to (Equation 5), and (Equation 1) ) to (Equation 5). Actual coordinate information can be obtained.

For example, the electronic device 101 may select (x _p , y _p ) (e.g., : You can check pixel coordinates, pixel coordinate information). The electronic device 101 can confirm (x _r , y _r ), which is actual coordinate information, by reflecting the confirmed (x _p , y _p ) in (Equation 1) to (Equation 3). Below, the pixel coordinates (x _p , y _p ) are reflected in (Equation 2) and (Equation 3), and the actual coordinates (x _r , y _r ) are confirmed by (Equation 7) and (Equation 8) is attached.

According to one embodiment, the electronic device 101 uses (Equation 7) and (Equation 8) in which (x _p , y _p ) corresponding to pixel coordinates are reflected in (Equation 2) and (Equation 3). Based on , you can check (x _r , y _r ) corresponding to the actual coordinates.

According to one embodiment, the electronic device ₁₀₁ determines a first reference point (x _s , y Based on the second reference point (x _e , y _e ) determined at _s ) and the second time point (t _e ) (e.g., the time point at which the event that the first reference point falls outside the region of interest is confirmed), (Equation 9) below Using , the calculation speed (V ₀ ) of the object can be obtained.

The electronic device 101 may obtain the calculation speed (V ₀ ) of the object according to the captured image (eg, a plurality of image frames) using Equation 9. For example, the electronic device 101 may acquire the actual speed (V _r ) corresponding to the actually measured speed inside the object using a speed measurement program. The electronic device 101 may compare or analyze the calculated speed (V ₀ ) and the actual speed (V _r ) and correct the horizontal and vertical lengths of the set region of interest.

According to one embodiment, in a situation where the first and second reference points are determined, the horizontal and vertical lengths of the region of interest may be set to (x ₀ , y ₀ ). According to one embodiment, the electronic device 101 obtains the actual horizontal length (x _r ) and actual vertical length (y _r ) related to the region of interest using (Equation 10) and (Equation 11) below. can do.

In a situation where an object moves in the horizontal direction corresponding to the horizontal length, the electronic device 101 may obtain the actual horizontal length (xr) using Equation (10). The electronic device 101 may obtain the actual vertical length (yr) using Equation 11 in a situation where the object moves in the vertical direction corresponding to the vertical length. According to one embodiment, the electronic device 101 reflects the actual horizontal length (x _r ) and actual vertical length (y _r ) obtained based on (Equation 10) and (Equation 11) in the speed correction algorithm. And when measuring the speed of an object, the speed correction algorithm can be utilized. According to one embodiment, the electronic device 101 can measure the speed of an object more accurately based on a speed correction algorithm.

According to one embodiment, the electronic device 101 may set at least one region of interest based on an image (e.g., a plurality of image frames) captured using the camera 180, and the set at least one region of interest The movement of an object (e.g., first area) passing through can be detected. The processor 120 may measure the speed of the object by considering coordinate information corresponding to the area of interest, coordinate information corresponding to the object, coordinate information changed according to the movement of the object, and information on the time required to move the object. . According to one embodiment, the electronic device 101 can precisely analyze a captured image and check the location of an object (eg, first area) included in the image for each image frame. The electronic device 101 can detect a situation in which an object (eg, first area) is moving based on the set area of interest and accurately measure the speed of the object.

Figure 4 is a diagram illustrating an example in which a region of interest is set in a captured image according to various embodiments of the present invention.

The electronic device 101 of FIG. 4 may be at least partially similar to the electronic device 101 of FIGS. 1 and 2 or may further include other embodiments of the electronic device. The electronic device 101 may acquire a captured image using an operatively connected camera (e.g., the camera 180 of FIG. 2) and, based on the captured image, determine at least one region of interest (ROI) ( 410) can be set.

Referring to FIG. 4 , the processor of the electronic device 101 (e.g., the processor 120 of FIG. 2 ) may set a certain area as the area of interest 410 based on the captured image. For example, the captured image is an image that includes a roadway, and a partial area of the roadway may be set as the area of interest 410. According to one embodiment, the processor 120 may set a partial area of the roadway as the area of interest 410 and measure the speed of a vehicle (eg, an object) passing through the area of interest 410.

Referring to FIG. 4 , the area of interest 410 may be set based on the first road width 411 and the first road length 412. The area of interest 410 appears to have a trapezoidal shape based on the captured image, but may actually have a rectangular shape. According to one embodiment, a vehicle passing on the road may at least partially pass through the set area of interest 410.

FIG. 5 is a diagram illustrating a first scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention. FIG. 6 is a diagram illustrating a second scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention. FIG. 7 is a diagram illustrating a third scene in which an object overlaps a region of interest set based on a captured image according to various embodiments of the present invention.

The electronic device 101 of FIGS. 5 to 7 may be at least partially similar to the electronic device 101 of FIGS. 1 and 2 or may further include other embodiments of the electronic device. The electronic device 101 may acquire a captured image (e.g., a plurality of image frames) using an operatively connected camera (e.g., the camera 180 of FIG. 2), and based on the captured image, At least one region of interest (ROI) 410 can be set.

Referring to FIG. 5 , the processor 120 of the electronic device 101 may set a certain area as a region of interest (ROI) 410 based on the captured image. For example, the processor 120 may obtain coordinate information corresponding to the region of interest 410. Coordinate information corresponding to the region of interest 410 may include absolute coordinate information whose position is fixed within the image frame. The captured image (eg, a plurality of image frames) includes images captured using a CCTV fixedly installed at a specific location, and the angle of view in FIGS. 5 to 7 may be maintained constant. A substantially identical region of interest 410 may be set for each of a plurality of image frames. The processor 120 may recognize at least one object 403 in addition to the region of interest 410 . The processor 120 may recognize an area (eg, coordinate information) corresponding to at least one object 403.

The processor 120 may check the 1-1 area 420-1 corresponding to at least one object 403 (eg, vehicle, truck, automobile). For example, the 1-1 area 420-1 may be determined based on the size of the object 403. The processor 120 may check the 1-1 coordinate information corresponding to the 1-1 area 420-1. When the size of the object 403 increases, the area corresponding to the object 403 may also increase at the same rate as the increase in size of the object 403.

The processor 120 may check 1-1 coordinate information corresponding to the 1-1 area 420-1 and second coordinate information corresponding to the region of interest 410. Based on the 1-1 coordinate information and the second coordinate information, the processor 120 generates an event (e.g., intersection of union area (IOU)) in which the 1-1 area 420-1 at least partially overlaps the area of interest. ) event) can be detected. For example, the processor 120 may check whether absolute coordinate information according to the 1-1 coordinate information is included in the second coordinate information, and determine whether the 1-1 coordinate information is at least partially included in the second coordinate information. If included, it can be determined that the event has occurred.

In response to detection of the event, the processor 120 creates at least two intersection points 421 and 422 where the first boundary line of the 1-1 area 420-1 and the second boundary line of the area of interest intersect each other. )can confirm. The processor 120 may set one of the at least two confirmed intersection points as the first coordinate point 421 and the other as the second coordinate point 422. For example, the first coordinate point 421 and the second coordinate point 422 may be included in the first boundary line of the 1-1 region 420-1 and the second boundary line of the region of interest 410. may be included in

The processor 120 may determine the first reference point 423 based on the first coordinate point 421 and the second coordinate point 422. For example, the processor 120 may determine the midpoint between the first coordinate point 421 and the second coordinate point 422 as the first reference point 423. The first reference point 423 may mean relative coordinate information corresponding to a relative position based on the 1-1 area 420-1. For example, the first reference point 423 may mean coordinate information corresponding to a relative position based on the overall size of the 1-1 area 420-1. According to one embodiment, the processor 120 may determine the first reference point 423 according to the first time when an event (e.g., IOU event) is detected. According to one embodiment, the first reference point 423 ) is determined is not limited to a specific method, and any coordinate point included in the area where the 1-1 region 420-1 and the region of interest 410 overlap may be determined as the first reference point 423. .

Referring to FIG. 5, the processor 120 provides at least two pieces of coordinate information where the boundary line of the 1-1 region 420-1 and the boundary line of the region of interest 410 intersect (e.g., cross) each other. It is decided to use coordinate information 421 and second coordinate information 422, but is not limited thereto.

According to one embodiment, the first coordinate information 421 and the second coordinate information 422 may be determined in various ways, and based on the first coordinate information 421 and the second coordinate information 422, the first coordinate information 421 and the second coordinate information 422 may be determined in various ways. The first reference point 423 included in the -1 area 420-1 may be determined. For example, the first reference point 423 may be determined to have coordinate information corresponding to the relative position within the 1-1 area 420-1. For example, the first reference point 423 may be set to (first relative abscissa, first relative abscissa) based on coordinate information relative to the 1-1 area 420-1. According to one embodiment, in a situation where the 1-1 area 420-1 moves to the 1-2 area 420-2, the first reference point 423 is located at the 1-2 area 420-2. ) may be changed to (first relative abscissa, first relative abscissa) based on relative coordinate information. For example, when the 1-1 area 420-1 moves to the 1-2 area 420-2, the position of the first reference point 423 is moved to the second reference point 424 according to the movement rate. You can move.

According to one embodiment, in response to the occurrence of an event (e.g., a first viewpoint), the processor 120 selects at least two coordinates included in an area where the first region 420-1 and the region of interest 410 overlap. Information (e.g., first coordinate point 421 and second coordinate point 422) can be confirmed, and the first reference point 423 can be determined using the two confirmed coordinate information. For example, the position of the first reference point may be set to a specific position corresponding to the relative position within the 1-1 area 420-1. According to one embodiment, the 1-1 area 420-1 may be moved according to the movement of the object 403, and according to the movement of the 1-1 area 420-1, the first reference point ( 423) can also be moved in the same way. For example, when the size of the object 403 in the captured image increases, the area of the 1-1 region 420-1 may also expand. When the area of the 1-1 area 420-1 is expanded, the absolute coordinate information about the first reference point 423 may be changed based on the expanded horizontal and vertical lengths. Based on the size of the 1-1 area 420-1, relative position information of the first reference point 423 may be maintained.

Referring to FIG. 6, it shows an image captured at a set time point after FIG. 5 was captured. For example, if Figure 5 is a first image frame, Figure 6 may be a second image frame. Since the object 403 in FIG. 6 moves along the road direction, it may appear to have a relatively increased size compared to FIG. 5 . The 1-1 area 420-1 in FIG. 5 may be at least partially expanded in area to the 1-2 area 420-2 in FIG. 6. As the object 403 moves, the 1-1 area 420-1 also moves to the 1-2 area 420-2, and the first reference point 423 can also move to the second reference point 424. there is. For example, the relative coordinate information of the first reference point 423 based on the 1-1 area 420-1 is the relative coordinate information of the second reference point 424 based on the 1-2 area 420-2. may be substantially the same. The relative position of the first reference point 423 may be determined based on the horizontal and vertical lengths of the 1-1 area 420-1. The relative position of the second reference point 424 may be determined based on the horizontal and vertical lengths of the 1-2 area 420-2.

According to one embodiment, the processor 120 can measure the distance traveled by the first reference point 423 to the second reference point 424 and measure the speed of the object 403 during a set time. . For example, the processor 120 moves the object 403 for a set time based on first coordinate information corresponding to the first reference point 423 and second coordinate information corresponding to the second reference point 424. A distance can be measured. The processor 120 may check the moving direction and moving speed of the object 403 based on at least two image frames.

Referring to FIG. 7, it shows an image captured at a set time point after FIG. 6 was captured. For example, if Figure 5 is the first image frame and Figure 6 is the second image frame, Figure 7 may be the third image frame. Referring to FIGS. 5 to 7 , the object 403 is moving along the road direction 432, and the size of the object 403 can be seen to gradually increase. The 1-1 area 420-1 in FIG. 5 is expanded in area to the 1-2 area 420-2 in FIG. 6, and extends to the 1-3 area 420-3 in FIG. 7. The area can be further expanded. Since the object 403 is moving along the road direction 432, the 1-1 area 420-1 has also moved to the 1-3 area 420-3, and the first reference point 423 has also moved to the second area 420-3. After passing the reference point 424, it can move to the third reference point 425.

According to one embodiment, the processor 120 calculates the movement distance by which the first reference point 423 moves to the third reference point 425 along the road direction 432 within the area of interest 410 431) can be measured. For example, the processor 120 calculates the movement distance 431 of the object 403 based on the first absolute coordinate information corresponding to the first reference point 423 and the third coordinate information corresponding to the third reference point 425. ) can be measured. The processor 120 may measure the movement time of the object 403 based on the first time point at which the first reference point 432 is determined and the third time point at which the third reference point 425 is determined. The processor 120 may measure the speed of the object 403 using the movement time and movement distance 431 of the object 403. For example, the processor 120 determines the movement direction and movement speed of the object 403 based on the first coordinate information corresponding to the first reference point 423 and the third coordinate information corresponding to the third reference point 425. You can check.

According to one embodiment, the processor 120 of the electronic device 101 may analyze an image (e.g., a plurality of image frames) captured using the camera 180, and a region of interest 410 included in the image. ) Based on this, the movement of an object 403 (eg, a vehicle) passing through the area of interest 410 can be detected. The processor 120 may measure the speed of the object by considering coordinate information corresponding to the area of interest, coordinate information corresponding to the object, coordinate information changed according to the movement of the object, and information on the time required to move the object. . The processor 120 has an area (e.g., a 1-1 area 420-1, a 1-2 area 420-2, and a 1-3 area 420-3) corresponding to the object 403. A region (e.g., a second region) where the region of interest 410 at least partially overlaps can be confirmed, and at least one reference point (e.g., a first reference point 423, a second reference point 424) can be identified based on the overlapping region. ), the third reference point 425) can be determined. The processor 120 can track the movement of the reference point and measure the speed of the object 403 corresponding to the reference point based on the movement distance and movement time of the reference point.

According to one embodiment, the electronic device 101 accurately measures the speed of the object 403 included in the image based on the image (e.g., a plurality of image frames) captured using the camera 180. You can. One embodiment can accurately measure the speed of the vehicle 403 (e.g., an object) within a set area (e.g., area of interest) and more accurately determine whether the driver driving the vehicle 403 violates the speed. there is. Convenience and accuracy can be improved in detecting vehicles that violate the speed limit.

Figure 8 is a diagram illustrating an example in which a plurality of regions of interest are set in a captured image according to various embodiments of the present invention.

The electronic device 101 of FIG. 8 may be at least partially similar to the electronic device 101 of FIGS. 1 and 2 or may further include other embodiments of the electronic device. The electronic device 101 may acquire a captured image (e.g., a plurality of image frames) using an operatively connected camera (e.g., the camera 180 of FIG. 2), and based on the captured image, At least one region of interest (ROI) (811, 812, 813) can be set.

Referring to FIG. 8, the processor (e.g., processor 120 of FIG. 2) of the electronic device 101 selects a plurality of regions of interest (e.g., a first region of interest 811 and a second region of interest) based on the captured image. (812), a third area of interest (813)) can be set. For example, the captured image is an image that includes a roadway, and a partial area of the roadway may be set as an area of interest. The processor 120 may check coordinate information corresponding to each of a plurality of regions of interest. According to one embodiment, the processor 120 may measure the speed of a vehicle (eg, an object) passing through a plurality of areas of interest 811, 812, and 813.

Referring to FIG. 8, three regions of interest (e.g., a first region of interest 811, a second region of interest 812, and a third region of interest 813) are set, but the present invention is not limited thereto. A plurality of areas of interest may be integrated into one area of interest, or may be used individually as each area of interest. For example, when a plurality of regions of interest are set, the processor 120 may measure the speed of the object individually for each region of interest in response to the occurrence of an event in which an object (e.g., a vehicle) overlaps at least partially. You can. For example, processor 120 measures a first speed of the vehicle based on the first area of interest 811, measures a second speed of the vehicle based on the second area of interest 812, and measures a third speed of the vehicle based on the first area of interest 811. The third speed of the vehicle may be measured based on the area 813. The processor 120 may determine the average speed of the vehicle based on the measured first, second, and third speeds. The processor 120 can utilize a plurality of areas of interest (811, 812, and 813) to measure a plurality of speed values corresponding to each area of interest, and accurately determine the speed of the object based on the plurality of speed values. It can be measured. For example, the processor 120 may measure the speed of an object as an average value of a plurality of measured speed values.

FIG. 9A is a diagram illustrating a first embodiment of measuring the speed of an object in response to an event in which objects overlap based on a set area of interest according to various embodiments of the present invention. FIG. 9B is a diagram illustrating a second embodiment of measuring the speed of an object in response to an event in which objects overlap based on a set area of interest according to various embodiments of the present invention.

The electronic device 101 of FIGS. 9A and 9B may be at least partially similar to the electronic device 101 of FIGS. 1 and 2 or may further include other embodiments of the electronic device. The electronic device 101 may acquire captured images (e.g., a plurality of image frames) using an operatively connected camera (e.g., camera 180 of FIG. 2), and based on the captured images, at least One region of interest (ROI) 910 can be set. Referring to FIGS. 9A and 9B , within a captured image (e.g., intersection road), an intersection may be set as an area of interest 910.

Referring to FIGS. 9A and 9B , the processor 120 of the electronic device 101 may set a certain area (eg, an intersection) as a region of interest (ROI) 910 based on the captured image. For example, the processor 120 may obtain coordinate information corresponding to the region of interest 910 (e.g., coordinate information corresponding to a boundary line, vertex, corner, or side line). The captured video shows an intersection road captured using a CCTV fixedly installed at a specific location, and shows that the intersection of the intersection road has been set as the area of interest (910). The processor 120 may detect at least one object (eg, a vehicle) that at least partially overlaps the region of interest 910 . The processor 120 may recognize an area (eg, a first area 901 and a second area 902) corresponding to at least one object 403.

Referring to FIG. 9A, in response to a situation where the first area 901 corresponding to the object at least partially overlaps the area of interest 910 (e.g., confirmation of an intersection of union area (IOU) event), the processor 120 ) can confirm the first coordinate point 911 and the second coordinate point 912, and the third coordinate point 913 corresponding to the center point based on the first coordinate point 911 and the second coordinate point 912 )can confirm. The processor 120 may determine the third coordinate point 913 as the first reference point. For example, in a situation where the first area 901 and the area of interest 910 overlap, the processor 120 determines the first boundary line of the first area 901 and the second boundary line of the area of interest 910. At least two intersection points 911 and 912 that intersect each other can be identified. The processor 120 may set one of the at least two confirmed intersection points as the first coordinate point 421 and the other as the second coordinate point 422. The middle coordinate point corresponding to the midpoint between the first coordinate point and the second coordinate point may be determined as the third coordinate point 913 (eg, the first reference point). The first reference point 423 may mean relative coordinate information corresponding to a relative position based on the first area 901. According to one embodiment, the location (eg, coordinate information) of the first reference point 423 may change according to the movement of the first area 901 corresponding to the object.

Referring to FIG. 9A , an object (eg, a vehicle) may be passing through a region of interest 910 along a first direction 915 . For example, the first area 901 may move to the second area 902 along the first direction 915 in the same way that an object moves. According to one embodiment, the processor 120 may check a situation in which the first reference point 913 moves to the second reference point 914 along the first direction 915.

According to one embodiment, the processor 120 may check the first reference point for each of a plurality of image frames and determine that the object is moving along the movement direction of the first reference point.

Referring to FIG. 9A, the processor 120 detects an event (e.g., intersection of union area (IOU) event) where the first region 901 at least partially overlaps the region of interest 910, at a first time point. The first reference point 913 can be determined. The processor 120 may determine a second reference point 914 at a second viewpoint where the first reference point 913 is outside the region of interest 910 along the first direction 915 . Referring to FIG. 9A, a plurality of image frames may exist between the first and second viewpoints, and the movement of the object may be continuously tracked.

According to one embodiment, coordinate information about the first reference point 913 may be continuously updated in accordance with the movement of the object. The processor 120 may continuously update coordinate information about the first reference point 913 for each image frame. According to one embodiment, the processor 120 may detect an event in which the first reference point 913 deviates from the inside of the region of interest 910 to the outside, and may determine the point in time at which the event is detected as the second point in time. . For example, the first reference point 913 at the second viewpoint may be determined as the second reference point 914.

According to one embodiment, the processor 120 may track the movement of the first reference point 913 in response to each of a plurality of image frames, and the first reference point 913 may be converted to the second reference point 914. When moving, you can check the moving distance and moving time. The processor 120 may measure the speed of an object (eg, a vehicle) based on the confirmed movement distance and movement time.

Referring to FIG. 9B, in response to a situation where the third area 903 corresponding to the object at least partially overlaps the area of interest 910 (e.g., occurrence of an intersection of union area (IOU) event), the processor 120 ) can determine the 3-1 reference point (921-1). For example, in a situation where the third area 903 and the area of interest 910 overlap, the processor 120 creates at least an area where the boundary line of the third area 903 and the area of interest 910 intersect. Two intersection points can be identified. The processor 120 may determine the 3-1 reference point 921-1 corresponding to the midpoint based on the two confirmed intersection points.

Referring to FIG. 9B , an object (eg, a vehicle) may be passing through the region of interest 910 along the second direction 923 . For example, the third area 903 may move to the fourth area 904, the fifth area 905, and the sixth area 906 along the second direction 923. For example, the 3-1 reference point 921-1 passes the 3-2 reference point 921-2 and the 3-3 reference point 921-3 along the second direction 923. -4 can be moved to the reference point (921-4). According to one embodiment, the processor 120 may periodically recognize a situation in which the 3-1 reference point 921-1 moves to the 3-4 reference point 921-4 along the second direction 923. You can. The 3-1 reference point 921-1 may be determined at the first point in time when the IOU event occurs. The 3-4th reference point 921-4 may be determined at the second viewpoint in response to a situation in which an object (eg, a vehicle) leaves the region of interest 910. According to one embodiment, the third to sixth areas 903 to 906 may be determined for each image frame and corresponding to an object (eg, a vehicle). According to one embodiment, the processor 120 may track the movement of an object based on the movement of an area set to correspond to the object or the movement of a reference point set to correspond to the object.

According to one embodiment, the processor 120 may check the distance traveled by the reference point when the 3-1 reference point 921-1 moves to the 3-4 reference point 921-4. The processor 120 may check the travel time from the first time point at which the 3-1 reference point 921-1 is determined to the second time point at which the 3-4 reference point 921-4 is determined. The processor 120 may measure the speed of an object (eg, a vehicle) based on the confirmed movement distance and movement time.

According to one embodiment, the electronic device 101 can accurately measure the speed of an object (eg, vehicle, automobile) included in the image based on the image captured using the camera 180. One embodiment can accurately measure the speed of a car (eg, object) within a set area (eg, area of interest 910) and more accurately determine whether the driver driving the car commits a speed violation. Convenience can be improved in detecting cars that violate the speed limit.

Electronic devices according to various embodiments disclosed in this document may be of various types. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to embodiments of this document are not limited to the above-described devices.

The various embodiments of this document and the terms used herein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various changes, equivalents, or replacements of the embodiments. In connection with the description of the drawings, similar reference numbers may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the above items, unless the relevant context clearly indicates otherwise. As used herein, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof. Terms such as "first", "second", or "first" or "second" may be used simply to distinguish one component from another, and to refer to that component in other respects (e.g., importance or order) is not limited. One (e.g., first) component is said to be “coupled” or “connected” to another (e.g., second) component, with or without the terms “functionally” or “communicatively.” When mentioned, it means that any of the components can be connected to the other components directly (e.g. wired), wirelessly, or through a third component.

The term “module” used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and is interchangeable with terms such as logic, logic block, component, or circuit, for example. It can be used as A module may be an integrated part or a minimum unit of the parts or a part thereof that performs one or more functions. For example, according to one embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of the present document are one or more instructions stored in a storage medium (e.g., built-in memory 136 or external memory 138) that can be read by a machine (e.g., electronic device 101). It may be implemented as software (e.g., program 140) including these. For example, a processor (e.g., processor 120) of a device (e.g., electronic device 101) may call at least one command among one or more commands stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves), and this term refers to cases where data is semi-permanently stored in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in this document may be provided and included in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store (e.g. Play StoreTM) or on two user devices (e.g. It can be distributed (e.g. downloaded or uploaded) directly between smart phones) or online. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

According to various embodiments, each component (e.g., module or program) of the above-described components may include a single or plural entity, and some of the plurality of entities may be separately placed in other components. there is. According to various embodiments, one or more of the components or operations described above may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (eg, modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each component of the plurality of components in the same or similar manner as those performed by the corresponding component of the plurality of components prior to the integration. . According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, or omitted. Alternatively, one or more other operations may be added.

In addition, the embodiments of the present invention disclosed in the specification and drawings are merely provided as specific examples to easily explain the technical content according to the embodiments of the present invention and to aid understanding of the embodiments of the present invention, and limit the scope of the embodiments of the present invention. It is not intended to be limiting. Therefore, the scope of the various embodiments of the present invention should be interpreted as including all changes or modified forms derived based on the technical idea of the various embodiments of the present invention in addition to the embodiments disclosed herein.

101: electronic device 120: processor
130: Memory 180: Camera
190: Communication circuit 201: Image processing module
211: Area of interest related information 212: Object related information
213: Speed related information

Claims (20)

In electronic devices,
camera;
Memory; and
a processor operatively coupled to the camera and the memory;
The processor,
Confirm the area of interest set based on the image captured using the camera,
Confirming a recognized first area based on the area occupied by at least one object in the image,
In response to an event in which the identified first region at least partially overlaps the region of interest, a first coordinate point and a second coordinate point at which a first boundary line of the first region and a second boundary line of the region of interest intersect each other Check the coordinate points,
Determining a first reference point based on an intermediate coordinate point between the confirmed first coordinate point and the second coordinate point,
According to the first viewpoint at which the first reference point is determined and the movement of the at least one object, confirming a second viewpoint at which the first reference point moves and leaves the region of interest,
An electronic device that measures the speed of the at least one object based on a first time from the first time point to the second time point and a first distance moved by the first reference point during the first time. According to claim 1,
The processor,
In response to the event, confirming two intersection points where a first boundary line of the first area and a second boundary line of the area of interest intersect each other,
Set one of the two identified intersection points as the first coordinate point,
An electronic device that sets the other of the two identified intersection points as a second coordinate point. According to claim 1,
The area of interest includes at least partially a path along which the at least one object passes. According to claim 1,
The first reference point is based on a second area corresponding to an area where the first area and the area of interest at least partially overlap, and is included in the second area. delete According to claim 1,
The first reference point includes coordinate information corresponding to a relative position based on the coordinate information included in the first area, and the coordinate information corresponding to the first reference point is updated for each frame of the image. . According to claim 1,
The processor,
At the second point in time when the first reference point is outside the region of interest, a second reference point is determined using coordinate information corresponding to the first reference point,
Measure the first distance based on the first reference point and the second reference point,
An electronic device that measures the first time based on the first time point and the second time point. According to claim 7,
The processor,
Based on the first distance and the first time, measure the speed at which the first reference point moves to the second reference point,
The measured speed is a speed at which the at least one object moves from the first reference point to the second reference point. According to claim 7,
The processor,
Confirming a first direction from the first reference point to the second reference point,
The at least one object moves along the identified first direction. According to claim 1,
The camera includes a closed circuit television (CCTV) operatively connected to the electronic device,
An electronic device wherein the at least one object includes at least one vehicle. In the method of measuring the speed of an object,
An operation to check a set area of interest based on an image captured using a camera;
Confirming a first area recognized based on an area occupied by at least one object in the image;
In response to an event in which the identified first region at least partially overlaps the region of interest, a first coordinate point and a second coordinate point at which a first boundary line of the first region and a second boundary line of the region of interest intersect each other An operation to check coordinate points;
An operation of determining a first reference point based on an intermediate coordinate point between the confirmed first coordinate point and the second coordinate point;
An operation of determining a second viewpoint at which the first reference point leaves the region of interest according to a first viewpoint at which the first reference point is determined and movement of the at least one object; and
measuring the speed of the at least one object based on a first time from the first time point to the second time point and a first distance moved by the first reference point during the first time; How to include . According to claim 11,
In response to the event, confirming two intersection points where a first boundary line of the first area and a second boundary line of the area of interest intersect each other;
An operation of setting one of the two identified intersection points as a first coordinate point; and
An operation of setting the other one of the two identified intersection points as a second coordinate point; How to include more. According to claim 11,
The method wherein the region of interest at least partially includes a path along which the at least one object passes. According to claim 11,
The method wherein the first reference point is included in the second area based on a second area corresponding to an area where the first area and the area of interest at least partially overlap.
delete According to claim 11,
The first reference point includes coordinate information corresponding to a relative position based on coordinate information included in the first area, and the coordinate information corresponding to the first reference point is updated for each frame of the image. According to claim 11,
An operation of determining a second reference point using coordinate information corresponding to the first reference point at the second viewpoint when the first reference point is outside the region of interest;
An operation of measuring the first distance based on the first reference point and the second reference point; and
measuring the first time based on the first time point and the second time point; How to include more. According to claim 17,
Measuring a speed at which the first reference point moves to the second reference point based on the first distance and the first time; It further includes,
The measured speed is a speed at which the at least one object moves from the first reference point to the second reference point. According to claim 17,
An operation of confirming a first direction from the first reference point to the second reference point; It further includes,
The method characterized in that the at least one object moves along the identified first direction. According to claim 11,
The method of claim 1, wherein the camera includes a closed circuit television (CCTV), and the at least one object includes at least one vehicle.

Images