CN116168326A

CN116168326A - Object determination method and device, storage medium and electronic device

Info

Publication number: CN116168326A
Application number: CN202310162918.5A
Authority: CN
Inventors: 赵安宁; 陈明珠; 沈剑; 郑晓璇
Original assignee: Zhejiang Dahua Technology Co Ltd
Current assignee: Zhejiang Dahua Technology Co Ltd
Priority date: 2023-02-13
Filing date: 2023-02-13
Publication date: 2023-05-26

Abstract

The embodiment of the invention provides a method and a device for determining an object, a storage medium and an electronic device, wherein the method comprises the following steps: object detection is carried out on the current image frame to obtain a current detection result; when the current detection result comprises first information of a first object, determining whether a target file of the first object is included in a target platform, wherein the target file is obtained by performing file aggregation operation on the information of the first object in a preset time period in the past, and a first information set of the first object acquired in the preset time period is stored in the target file; when the target platform comprises a target file, storing first information into the target file to obtain an updated file, wherein the updated file comprises a second information set of the first object; and determining whether the first object is an object of a specified type according to the updated archive. The embodiment of the invention solves the problem of low determination efficiency of the object of the specified type in the related technology.

Description

Object determination method and device, storage medium and electronic device

Technical Field

The embodiment of the invention relates to the technical field of video monitoring, in particular to a method and a device for determining an object, a storage medium and an electronic device.

Background

Video monitoring technology has been widely used in many fields, for example, it can be used to monitor vehicles, personnel or alert areas, and video or image resources obtained by monitoring can be used to determine whether a vehicle is a problem vehicle causing an accident, or can be used to determine whether a child is a missing or a walking child reported by a parent, that is, can be used to determine whether a target object is an object of a specified type, and in the following description, it is determined whether a child is a walking child, and most towns currently have larger-scale video monitoring coverage, but the child is missing or is left endangered by the walking event. After the child is walked, the typical crutch seller will transfer the child to a different place at the fastest speed. If transferred successfully, it is difficult to find it out from the sea at the very large area.

In the related technology, the photo of the missing child and related identity information are uploaded to a remote management center, the mobile client displays the photo of the missing child to a user in real time, the user can shoot a clue photo of the child suspected to be missing or being taken by the user through the mobile client, the photo is uploaded to the remote management center for matching, and after the matching is successful, the matching result is uploaded to a management system of a related department. As can be seen, the solution in the related art requires the user to actively upload the photograph of the suspected missing or the children being walked, and the management system is passive when determining whether a certain child is the children being walked, that is, passive when determining whether a certain object is an object of the target specified type, and cannot autonomously analyze whether the certain object is the object of the target specified type, so that the method for determining whether the object is the object of the specified type in the related art has a problem of low efficiency.

For the problem of low determination efficiency of the object of the specified type existing in the related art, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the invention provides a method and a device for determining an object, a storage medium and an electronic device, which are used for at least solving the problem that the determining efficiency of an object of a specified type in the related technology is low.

According to an embodiment of the present invention, there is provided a method of determining an object, including: object detection is carried out on the current image frame to obtain a current detection result; determining whether a target file of a first object is included in a target platform or not under the condition that the current detection result comprises first information of the first object detected in the current image frame, wherein the first object is an object of a preset age range, the target file is obtained by performing file focusing operation on the information of the first object in a preset time period in the past, and a first information set of the first object acquired in the preset time period is stored in the target file; storing the first information into the target archive to obtain an updated archive, wherein the updated archive comprises a second information set of the first object, and the second information set comprises the first information set and the first information; and determining whether the first object is an object of a specified type according to the updated archive.

In an exemplary embodiment, the determining whether the first object is an object of a specified type according to the updated archive includes: determining a first duration of the first object in a target area according to the updated archive, wherein the first information set is information of the first object obtained by object detection of a group of image frames, and the group of image frames are image frames obtained by shooting the target area by a target camera before the current image frame; and determining whether the first object is an object of a specified type or not under the condition that the first time length is greater than or equal to a preset time length threshold value.

In an exemplary embodiment, the determining, according to the updated profile, a first time length when the first object appears in the target area includes: and determining a difference between a first time and a second time as the first duration, wherein the first time is a shooting time of the current image frame, the second time is a shooting time of a target image frame in the group of image frames, the target image frame is an earliest shot image frame in the group of image frames, the updated archive stores the first time corresponding to the first information and the second time corresponding to target information, and the target information is information of the first object obtained by performing object detection on the target image frame.

In an exemplary embodiment, the determining whether the first object is an object of a specified type includes: comparing the second information set of the first object with information of a group of objects included in a target comparison library acquired in advance to obtain a comparison result, wherein the group of objects included in the target comparison library are all objects of the appointed type; and determining that the first object is the object of the appointed type under the condition that the comparison result indicates that the similarity between the second information of the second object in the information of the group of objects and part or all of the information in the second information set is greater than or equal to a preset similarity threshold value.

In an exemplary embodiment, the determining whether the first object is an object of a specified type includes: acquiring a group of monitored objects associated with the first object, wherein the group of monitored objects are objects detected in the group of image frames and the current image frame and have a preset contact mode with the first object; acquiring family member information of each monitoring object in the group of monitoring objects to obtain a group of family member information; and determining whether the first object is the object of the specified type according to the group of family member information.

In an exemplary embodiment, the acquiring family member information of each subject in the set of subjects includes: searching files corresponding to each monitoring object in the group of monitoring objects in the existing file set on the target platform to obtain a group of files, wherein each file in the existing file set stores family member information of the corresponding object; or sending an information query request to a target device, wherein the information query request carries information of the group of objects, the information query request is used for requesting to acquire family member information of each object in the group of objects, the information of the group of objects is information of each object obtained by performing object detection on a second group of image frames, and the second group of image frames is an image frame of each object detected in the group of image frames and the current image frame; and acquiring family member information of each subject in the group of subjects sent by the target equipment, wherein the target equipment is used for searching the family member information of each subject in the group of subjects matched with the information of the group of subjects.

In an exemplary embodiment, the determining whether the first object is the object of the specified type according to the set of family member information includes: determining that the first object is the object of the specified type under the condition that no object of the preset age group is included in the group of family member information; or, in a case where the group of family member information includes the object of the predetermined age group but none of the objects includes the first object, determining that the first object is the object of the specified type.

In an exemplary embodiment, the method further comprises: and sending out an early warning notice under the condition that the first object is determined to be the object of the appointed type, wherein the early warning notice is used for prompting the first object to be the object of the appointed type.

According to another embodiment of the present invention, there is also provided an object determining apparatus including: the detection module is used for carrying out object detection on the current image frame to obtain a current detection result; a first determining module, configured to determine, if the current detection result includes first information of a first object detected in the current image frame, whether a target file of the first object is included in a target platform, where the first object is an object of a predetermined age group, the target file is a file obtained by performing a file focusing operation on information of the first object in a predetermined time period in the past, and the target file stores a first information set of the first object acquired in the predetermined time period; the obtaining module is used for storing the first information into the target archive to obtain an updated archive when the target archive is included in the target platform, wherein the updated archive comprises a second information set of the first object, and the second information set comprises the first information set and the first information; and the second determining module is used for determining whether the first object is an object of a specified type according to the updated archive.

According to a further embodiment of the invention, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

According to a further embodiment of the invention, there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

According to the invention, object detection is carried out on the current image frame to obtain a current detection result; determining whether a target file of the first object is included in the target platform or not under the condition that the current detection result comprises first information of the first object detected in the current image frame, wherein the first object is an object of a preset age group, the target file is a file obtained by performing file focusing operation on information of the first object in a preset time period in the past, and a first information set of the first object acquired in the preset time period is stored in the target file; under the condition that a target file is included in the target platform, storing first information into the target file to obtain an updated file, wherein the updated file comprises a second information set of the first object, and the second information set comprises a first information set and first information; and determining whether the first object is an object of a specified type according to the updated archive. That is, by performing object detection on the obtained current image frame, and performing file aggregation on the first information of the first object according to the first information of the first object included in the current detection result, when the target file of the first object is included in the target platform, the first information of the first object is stored in the target file to obtain an updated file, and then whether the first object is an object of a specified type can be determined according to the updated file. The problem that the determination efficiency of the object of the specified type is low due to the fact that the method of manually uploading the photo and then carrying out matching confirmation in the related art is mainly solved. Therefore, the problem of low determination efficiency of the specified type of object existing in the related art is solved, and the effect of improving the determination efficiency of the specified type of object is achieved.

Drawings

FIG. 1 is a block diagram of a mobile terminal hardware configuration of a method for determining an object according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of determining an object according to an embodiment of the invention;

FIG. 3 is an exemplary diagram of an environment topology according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a personnel information collection process according to an embodiment of the present invention;

FIG. 5 is a schematic diagram showing the judgment of a guardian according to an embodiment of the invention;

FIG. 6 is a flow chart of a child safety early warning according to an embodiment of the present invention;

fig. 7 is a block diagram of a structure of an object determining apparatus according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the operation on a mobile terminal as an example, fig. 1 is a block diagram of a mobile terminal hardware structure of a method for determining an object according to an embodiment of the present invention. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for determining an object in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In this embodiment, a method for determining an object is provided, fig. 2 is a flowchart of a method for determining an object according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:

step S202, performing object detection on a current image frame to obtain a current detection result;

step S204, determining whether a target file of a first object is included in a target platform or not when the current detection result includes first information of the first object detected in the current image frame, wherein the first object is an object of a predetermined age group, the target file is obtained by performing file focusing operation on the information of the first object in a past predetermined time period, and a first information set of the first object acquired in the predetermined time period is stored in the target file;

step S206, storing the first information into the target archive to obtain an updated archive, where the updated archive includes a second information set of the first object, and the second information set includes the first information set and the first information;

Step S208, determining whether the first object is an object of a specified type according to the updated archive.

Through the steps, the object detection is carried out on the current image frame, and the current detection result is obtained; determining whether a target file of the first object is included in the target platform or not under the condition that the current detection result comprises first information of the first object detected in the current image frame, wherein the first object is an object of a preset age group, the target file is a file obtained by performing file focusing operation on information of the first object in a preset time period in the past, and a first information set of the first object acquired in the preset time period is stored in the target file; under the condition that a target file is included in the target platform, storing first information into the target file to obtain an updated file, wherein the updated file comprises a second information set of the first object, and the second information set comprises a first information set and first information; and determining whether the first object is an object of a specified type according to the updated archive. That is, by performing object detection on the obtained current image frame, and performing file aggregation on the first information of the first object according to the first information of the first object included in the current detection result, when the target file of the first object is included in the target platform, the first information of the first object is stored in the target file to obtain an updated file, and then whether the first object is an object of a specified type can be determined according to the updated file. The problem that the determination efficiency of the object of the specified type is low due to the fact that the method of manually uploading the photo and then carrying out matching confirmation in the related art is mainly solved. Therefore, the problem of low determination efficiency of the specified type of object existing in the related art is solved, and the effect of improving the determination efficiency of the specified type of object is achieved.

The main execution body of the steps may be a platform, a cloud platform, a server, a terminal device, a processor with man-machine interaction capability configured on a storage device, a processing device or a processing unit with similar processing capability, or the like, but is not limited thereto.

In the step S202, object detection is performed on the current image frame to obtain a current detection result; optionally, in actual application, the front-end camera device may perform object detection on the image frame and upload the detection result to the target platform, or the front-end camera device may collect the image frame and upload the image frame to the target platform, and then the target platform performs object detection on the image frame to obtain the detection result;

as an optional implementation manner of the step S204, in a case where the current detection result includes first information of the first object detected in the current image frame, determining whether a target file of the first object is included in the target platform, where the first object is an object of a predetermined age group, the target file is a file obtained by performing a file focusing operation on information of the first object in a predetermined time period in the past, and the target file stores a first information set of the first object acquired in the predetermined time period; for example, the first object is a child (for example, a child aged 3-7), the current image frame may be an image acquired by a certain image capturing device in a certain area (for example, town T) and uploaded to the target platform, in practical application, the area (for example, town T) may include a plurality of image capturing devices, for example, 50 or 100 or others, and each image capturing device uploads the acquired image frame or video to the target platform, alternatively, the image capturing devices may upload the image frame or video in real time or may upload the image frame or video in a certain period; in practical application, the camera in the area can upload the image frames or videos of all the shot objects to the target platform, the target platform end can perform portrait filing according to the characteristic information of each object, for example, the characteristic information can include face and/or human characteristic information and/or age information, after the target platform performs filing, each object can be stored according to natural people in a snapshot under different time and space, namely, each object has a corresponding file, optionally, if the object is an adult in the local area (such as town T), the identity information and/or family member information of the object can be further determined according to the information of the related departments or platforms, for example, the province card, name, family member, and the like of the object can be confirmed according to the photos and other information in the public security system; when the first object is a child, for example, the first object is transferred to the local place (such as town T) from the outside, the target platform files the information of the first object after acquiring the information of the first object to form a file, if the image capturing device in the area may capture the first object one or more times and upload the information of the first object to the target platform for file gathering before the current image frame, then the target file may already exist at the target platform end;

As an optional implementation manner of the step S206, in the case that the target platform includes the target archive, the first information is stored in the target archive to obtain an updated archive, that is, the updated archive includes both the previous first information set and the first information of the first object obtained by detecting the current frame image; optionally, the updated archive has information of recording the first object acquired each time, for example, the updated archive may include feature information of the first object, and optionally, the archive may also include information of time, place, etc. of each time the first object is captured;

in the above step S208, it is determined whether the first object is an object of a specified type according to the updated profile. Taking the example that the first object is a child, there may be a plurality of different situations where the first object appears locally, such as a local walking relative from a foreign place or a local playing or being turned to a local place, etc., according to the updated file, the embodiment can further determine whether the first object is an object of a specified type; for example, the updated archive has recorded time, location information, etc. of each time the first object is captured locally (e.g. town T), and the local time of occurrence of the first object may be determined according to the updated archive, for example, the time of occurrence is one month or more than 2 months, etc. Optionally, the file of the first object (e.g. the target file, or the updated file) may further include information of other objects associated with the first object, for example, a child may be accompanied by a large person (e.g. object a), or may be accompanied by a guardian, and when the front-end camera captures the first object and determines that the object a may be a guardian, the information of the object a may be stored in the file of the first object, and since the first object may have one or more guardians (or suspected guardians), the target platform may create or generate a list about guardians, where the time, the location, and the information of the guardians that occur simultaneously with the first object may be recorded; in this way, it may be determined from the updated archive whether the first object is an object of a specified type, e.g., whether the first object is a child that is being walked.

Through the above embodiment, the object detection is performed on the obtained current image frame, and the first information of the first object is aggregated according to the first information of the first object included in the current detection result, when the target file of the first object is included in the target platform, the first information of the first object is stored in the target file to obtain an updated file, and then whether the first object is an object of a specified type can be determined according to the updated file. The problem that the determination efficiency of the object of the specified type is low due to the fact that the method of manually uploading the photo and then carrying out matching confirmation in the related art is mainly solved. Therefore, the problem of low determination efficiency of the specified type of object existing in the related art is solved, and the effect of improving the determination efficiency of the specified type of object is achieved.

In an alternative embodiment, the determining whether the first object is an object of a specified type according to the updated archive includes: determining a first duration of the first object in a target area according to the updated archive, wherein the first information set is information of the first object obtained by object detection of a group of image frames, and the group of image frames are image frames obtained by shooting the target area by a target camera before the current image frame; and determining whether the first object is an object of a specified type or not under the condition that the first time length is greater than or equal to a preset time length threshold value. In this embodiment, the first time period when the first object appears in the target area may be determined according to the updated archive, for example, the updated archive records information such as time, position, etc. when the first object appears in the target area each time, so the first time period may be determined according to the updated archive, for example, the first time period is 20 days (or 42 days, or 500 hours, or other time periods), the predetermined time period threshold may be set to 30 days, and when the first time period is greater than or equal to the predetermined time period threshold, whether the first object is an object of a specified type is determined according to the updated archive. The type of the first object is judged after the first object exceeds the threshold value of the preset duration, so that the problem that the workload is large easily caused by judging each occurrence is avoided.

In an optional embodiment, the determining, according to the updated profile, a first time length when the first object appears in the target area includes: and determining a difference between a first time and a second time as the first duration, wherein the first time is a shooting time of the current image frame, the second time is a shooting time of a target image frame in the group of image frames, the target image frame is an earliest shot image frame in the group of image frames, the updated archive stores the first time corresponding to the first information and the second time corresponding to target information, and the target information is information of the first object obtained by performing object detection on the target image frame. In this embodiment, when determining the first time period, the shooting time of the current image frame may be taken as the first time period, the shooting time corresponding to the image frame that is the earliest shot to the first object may be taken as the second time period, and then the difference between the first time period and the second time period may be taken as the first time period; in practical application, the updated file may include information such as shooting time and position of the first object when the first object is captured each time, the updated file may include one or more records, each record corresponds to the information of the first object obtained by detecting an image frame including the first object acquired by the front-end camera device each time, and the second moment may also be information of a middle captured one time included in the updated file; according to the embodiment, the purpose of the first duration of the first object in the target area is determined according to the updated file.

In an alternative embodiment, the determining whether the first object is an object of a specified type includes: comparing the second information set of the first object with information of a group of objects included in a target comparison library acquired in advance to obtain a comparison result, wherein the group of objects included in the target comparison library are all objects of the appointed type; and determining that the first object is the object of the appointed type under the condition that the comparison result indicates that the similarity between the second information of the second object in the information of the group of objects and part or all of the information in the second information set is greater than or equal to a preset similarity threshold value. In this embodiment, the second information set of the first object may be compared with information of a group of objects included in a target comparison library, for example, taking a case of judging whether the first object is a child that is being walked as an example, where the target comparison library may be a child missing library provided by a public security system or a platform, the child missing library may include information of children that are missing in regions of the whole country, and when a similarity between part of or all of the second information set and second information of the second object in the target comparison library is greater than or equal to a preset similarity threshold (e.g., 85% or 90%, or other), it may be determined that the first object is an object of a specified type, and the second object may be any object in the target comparison library. By the embodiment, the purpose of determining whether the first object is an object of a specified type or not by comparing the information of the first object with the information of the objects included in the target comparison library is achieved.

In an alternative embodiment, the determining whether the first object is an object of a specified type includes: acquiring a group of monitored objects associated with the first object, wherein the group of monitored objects are objects detected in the group of image frames and the current image frame and have a preset contact mode with the first object; acquiring family member information of each monitoring object in the group of monitoring objects to obtain a group of family member information; and determining whether the first object is the object of the specified type according to the group of family member information. In this embodiment, the image frames may be detected and analyzed to determine whether a predetermined contact pattern exists between the adult and the first object, for example, the predetermined contact pattern is that the adult a holds the first object or the adult a holds the first object, when the predetermined contact pattern exists, the adult a may be temporarily set as a patient of a first object, where the first object may be pulled or held by different adults in a predetermined period of time and shot by a front-end camera device, that is, one or more patient objects may exist in the group of patient objects, in general, the adult a is a local (such as the town T) person, and as long as the patient object appears locally one or more times (is acquired by the local front-end camera device), the target platform end also has an archive of the adult a, and then family member information of each patient object in the group of patient objects is acquired, for example, identity information or family member information of the adult a may be searched through a third party platform; optionally, in the case that the information of the patient (such as adult a) of the first object is acquired for the first time, a patient list of the first object may be generated on the target platform, and when the information of the patient (such as adult a or B or other) of the first object is acquired subsequently, the information of the patient is added to the patient list, optionally, the patient list may be put into a file corresponding to the first object; in practical application, when an image frame containing adult a is acquired for the first time, detecting the image frame to acquire information of adult a, then creating a file related to adult a by the target platform, and searching identity information and/or family member information of adult a by a third party platform (such as a public security system), optionally, storing the identity information and/or family member information of adult a into the file of adult a; in this way, family member information of each monitoring object in a group of monitoring objects can be obtained to obtain a group of family member information, wherein each family member information in the group of family member information corresponds to family member information of one monitoring object, and then whether the first object is an object of a specified type is determined according to the group of family member information. For example, it is determined that there are no children in each subject based on a set of family member information, and then it may be determined that the first subject is a subject of a specified type, i.e., it may be determined that the first subject is likely to be a child being walked. With this embodiment, it is determined whether the first object is an object of a specified type by acquiring family member information of a group of subjects.

In an alternative embodiment, the acquiring family member information of each subject in the set of subjects includes: searching files corresponding to each monitoring object in the group of monitoring objects in the existing file set on the target platform to obtain a group of files, wherein each file in the existing file set stores family member information of the corresponding object; or sending an information query request to a target device, wherein the information query request carries information of the group of objects, the information query request is used for requesting to acquire family member information of each object in the group of objects, the information of the group of objects is information of each object obtained by performing object detection on a second group of image frames, and the second group of image frames is an image frame of each object detected in the group of image frames and the current image frame; and acquiring family member information of each subject in the group of subjects sent by the target equipment, wherein the target equipment is used for searching the family member information of each subject in the group of subjects matched with the information of the group of subjects. In this embodiment, files corresponding to each of a group of objects can be searched in an existing file set on the target platform, and family member information corresponding to each object (such as the objects) is stored in each file of the existing file set; each archive in the existing archive set stores family member information of a corresponding object, and the family member information is acquired from the target device and corresponds to the information of the object stored in each archive; optionally, after determining the files of each subject in the target platform, an information query request is sent to the target device to request to obtain family member information of each subject in a group of subjects, for example, the information query request may carry information of each subject; and then acquiring family member information of each monitoring object in a group of monitoring objects sent by target equipment, wherein the target equipment can be citizen identity information management equipment, for example, the target equipment stores the identity information and family member information of all local resident people and the like. By the embodiment, the aim of acquiring the family member information of the monitored object is fulfilled.

In an alternative embodiment, the determining whether the first object is the object of the specified type according to the group of family member information includes: determining that the first object is the object of the specified type under the condition that no object of the preset age group is included in the group of family member information; or, in a case where the group of family member information includes the object of the predetermined age group but none of the objects includes the first object, determining that the first object is the object of the specified type. In this embodiment, when none of the family member information includes a subject of a predetermined age group (e.g., a child aged 3-7 or 3-5), it may be determined that the first subject is a subject of a specified type; alternatively, in the case where an object of a predetermined age group is included in the group of family member information, but the first object is not included, it may be determined that the first object is an object of a specified type at this time. By the embodiment, the purpose of determining whether the first object is the object of the specified type according to family member information of a group of guardianship objects is achieved.

In an alternative embodiment, the method further comprises: and sending out an early warning notice under the condition that the first object is determined to be the object of the appointed type, wherein the early warning notice is used for prompting the first object to be the object of the appointed type. In this embodiment, when the first object is determined to be an object of a specified type, the target platform may trigger an early warning notification, for example, to send the early warning notification to a third party platform (such as a public security system, or a lost child management platform).

It will be apparent that the embodiments described above are merely some, but not all, embodiments of the invention. The present invention will be specifically described with reference to examples. The following description will be given by taking an example of analyzing and judging whether a child is a walking child, which is only taken as an example and not limiting the scheme, and the embodiment of the present invention is equally applicable to determining other objects, for example, whether a certain object is an object of a specified type or not.

The embodiment of the invention provides a newly added child safety judging method based on portrait files, which mainly aims at solving the problem of difficulty in searching people across regions. And screening and judging children newly arrived in the region, analyzing and judging the children and guardianship respectively according to the information of the guardianship situation of the children, the residence time span of the children and the like, and checking and analyzing whether the children are walking children.

FIG. 3 is a diagram illustrating an example topology of a system environment according to an embodiment of the present invention, as shown in FIG. 3, the system includes a front-end camera, a large system cloud platform (or referred to as a cloud platform), wherein the front-end camera may include a plurality of cameras, which are mainly used to collect child and follower information, and the cloud platform mainly performs cluster analysis on the child (corresponding to the first object) and the follower (corresponding to the subject) to obtain a list of chaperones for each individual; the system can be deployed in the whole city, all camera acquisition data can be recorded by the cloud platform, the system is not limited by shooting access of a single camera, and the coverage is full.

The overall conception of the embodiment of the invention is as follows:

the embodiment of the invention is suitable for areas where the gear gathering algorithm is mature to run for more than a certain time (such as one year), and mainly aims at safety judgment of children (such as children between 3 and 7 years). The aim of the scheme is mainly to screen whether the local region stable resident has the child buying condition or not, and check and analyze the safety of the child newly reaching the local region.

All people in the front-end intelligent camera snap pictures form a personnel file through a cloud platform portrait filing algorithm. If the file of the child is new, the new file is marked, and the time length of the file of the child and the condition of the guardian are analyzed, so that whether the child is possibly in the way of being turned over or not is judged.

The embodiment of the invention mainly comprises a 3-part algorithm, which is respectively as follows:

(1) Social face personnel information acquisition

The social face camera collects the face and human body information of the person, including the face human body attributes such as the characteristic information and the age of the person, and provides the face human body attributes for the cloud platform to perform face image file gathering. After the gear is gathered, each person can store the snap shots under different time spaces according to natural people. Meanwhile, for adults in the system, personnel landing can be carried out according to the identity card information in the public security system, and the specific information of each person is clearly known.

As shown in fig. 4, the information collection procedure for the social meetings personnel includes:

s402, collecting human face and human body characteristics and information of a person in a picture;

s404, personnel fall to the ground according to the identity card information.

(2) Child guardian judgment

When a child aged 3-7 years goes out, the guardian has a high probability of pulling or holding the child. For this feature we can define an adult with the two types of limb contact patterns (corresponding to the predetermined contact patterns described above) with a child as his guardian and record the period of time that the guardian accompanies. Fig. 5 is a schematic diagram of a monitor according to an embodiment of the present invention, when it is determined that an adult (e.g., adult a) contacts with two limbs of a child, the adult a is added to the child monitor list.

(3) Child safety judgment

In general, children are present in another town, mainly in the following cases:

1) The children are left behind, and parents are found in towns during the fake-putting period;

2) The child is left behind and returns to the home of the parent;

3) Travel, learn, seek medical attention, or other transaction with the family;

4) During the fake-putting period, the relatives are temporarily held;

5) Moving the house with the family members;

6) Is turned around.

Analyzing the above cases, wherein the children in the cases 1) and 4) mainly come during the cold and summer holidays, and still return to home after learning; the child of case 3), 5) will be present in the new town together with the guardian; case 2) confirms the parent information, and knows that there are children in the name of the parent, and can be distinguished from case 6).

According to the occurrence time length of the child and the condition of the guardian, whether the child is suspected to be turned or not can be analyzed.

The overall decision flow for determining whether a child is at risk of being turned is as follows:

a) The portrait files mark the newly created child files (corresponding to the aforementioned target files).

b) For children files that are archived for more than one month, it is determined whether they still occur frequently in the next period of time (e.g., one month). In view of the high frequency and complex condition of children with cold summer-heat, if the children are in the cold summer-heat period, the judging time is prolonged.

c) For children appearing for a long time, judging whether a guardian appearing later is a local original fixed resident person. If so, it is further determined whether the person/family has children. If the guardian does not have a child, it may be determined that the child is at risk of being walked.

FIG. 6 is a flow chart of a child safety early warning according to an embodiment of the present invention, the flow comprising:

s602, capturing a picture of a person A, for example, a front-end camera collects the person A and uploads an image (or video) containing the person A to a cloud platform;

s604, judging whether the person A is a child;

s606, if the determination result in step S604 is no, ending the flow;

S608, if the judgment result in the step S604 is yes, further judging whether the personnel A has files, namely judging whether the cloud platform has files of the personnel A; s610, if the result of the step S608 is no, creating a new file, i.e. the person A may appear in the area (e.g. town T) for the first time, comparing the portrait information of the person A with other portrait files existing in the cloud platform, and there is no file of other person identical or similar to the person A, so that the person A needs to be created with the new file;

s612, marking the newly built file of the person A as a child file to be confirmed, namely, whether the person A is a child to be confirmed or not is a walking child;

s614, ending the current flow, and returning to the step S602 to continue to acquire the image (or video) of the person A;

s616, if the judgment result of the step S608 is yes, further judging whether the file of the person A is the "child file to be confirmed";

s618, if the judgment result in the step S616 is no, ending the current judgment flow, wherein the person A may be a child in the area;

s620, if the judgment result in the step S618 is yes, further judging whether the person A always appears for more than one month (other time periods are also possible), for example, the cloud platform can determine whether the time of the person A appearing in the area exceeds one month according to the received information of the person A acquired by the front-end camera in the area (such as town T) in the past period and uploaded to the cloud platform image or video, for example, the time of the person A appearing in the area can be determined according to the difference between the earliest appearing time and the time appearing in the current frame image;

S622, when the determination result in step S620 is no, the flow ends; explanatory person a may only briefly appear in the area, where further decisions may be made based on subsequent monitoring results;

s624, if the judgment result of the step S620 is yes, further judging whether the current state is summer-cold or summer-hot;

if the result of the determination in step S624 is yes, step S624 is continuously performed until the current date does not belong to the cold-summer fake period;

s626, when the judgment result in the step S624 is no, that is, the current date does not belong to the cold-summer holiday, such as 10-11 months, 3-4 months, or other dates, and the like, the child (namely the person A) is judged at this time;

s628, judging whether the child can be matched with the person in the child walk-away warehouse;

the child walk-away library may be provided by a public security system, alternatively, the cloud platform may query the child walk-away library over a network;

s630, if the judgment result in the step S628 is no, the direct judgment of the child can be ended, i.e. the process of judging whether the child is a walking child according to the child' S own information is stopped;

if the result of the step S628 is yes, then a child safety warning may be triggered, for example, the cloud platform may send a warning prompt to the public security system;

S632, if the judgment result in the step S624 is NO, optionally, the guardian of the recent child (namely the person A) can be selected to judge at the moment;

s634, judging whether the guardian (such as guardian G) is a local fixed resident;

if the determination result in step S634 is no, the process may be ended;

s636, if the judgment result in the step S634 is yes, it may be further judged whether the guardian (such as the guardian G) has children;

it should be noted that, in the above embodiment, a child (such as the person a) may correspond to one or more guardianship persons;

typically, if the guardian G is a local fixed resident, the identity information of the resident and the family member information, such as whether there are children, can be obtained through the public security system;

s638, when the determination result in step S636 is no, it may be determined that the child (i.e. the person a) may be at risk of being walked, and then the child safety warning may be triggered.

In the above embodiment, the person screening is performed on the newly added child files based on the portrait filing function. And a child guardian list and a accompanying time period thereof are automatically generated according to the contact judgment of the child and the accompanying person. The guardian list is updated in time according to the daily snapshot information. According to the generation time of the child files, the child files are screened, and the large-scale carpet type investigation is avoided. Suspicious children are screened in a targeted manner, and the suspicious children are automatically compared with personnel in a child lost warehouse, so that the comparison frequency is greatly reduced, and the comparison effectiveness is improved.

Compared with the related art, the embodiment of the invention adopts the child safety early warning scheme based on clustering result analysis, and has the following advantages: 1) The pertinence is strong: according to the scheme, only children newly added in the current region are arranged and judged, and resource waste caused by large-scale investigation and comparison is avoided. 2) Automatic maintenance of archive information: according to the monitoring information of daily social faces, personnel data can be updated in time, and a child supports multiple guardianship. 3) The coverage area is wide: the child information can be recorded without being affected by the illumination field of the single camera, as long as the child information appears under any one of the networked cameras. 4) Solves the problem of cross-region: the scheme is designed mainly for the problem that people are difficult to find across regions after being turned around. Through the state analysis of children and guardians, suspicious children are screened, and the difficulty of finding people and checking can be greatly reduced.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

Also provided in this embodiment is an object determining apparatus, fig. 7 is a block diagram of a structure of an object determining apparatus according to an embodiment of the present invention, as shown in fig. 7, the apparatus includes:

the detection module 702 is configured to perform object detection on a current image frame to obtain a current detection result;

a first determining module 704, configured to determine, if the current detection result includes first information of a first object detected in the current image frame, whether a target profile of the first object is included in a target platform, where the first object is an object of a predetermined age group, the target profile is a profile obtained by performing a file focusing operation on information of the first object in a predetermined time period in the past, and the target profile stores a first information set of the first object acquired in the predetermined time period;

an obtaining module 706, configured to store, if the target platform includes the target archive, the first information into the target archive, to obtain an updated archive, where the updated archive includes a second information set of the first object, and the second information set includes the first information set and the first information set;

A second determining module 708, configured to determine whether the first object is an object of a specified type according to the updated archive.

In an alternative embodiment, the second determining module 708 includes: a first determining submodule, configured to determine a first duration of occurrence of the first object in a target area according to the updated profile, where the first information set is information of the first object obtained by performing object detection on a group of image frames, and the group of image frames is an image frame obtained by shooting, by a target image capturing device, in the target area before the current image frame; and the second determining submodule is used for determining whether the first object is an object of a specified type or not under the condition that the first time length is greater than or equal to a preset time length threshold value.

In an alternative embodiment, the first determining submodule includes: a first determining unit, configured to determine a difference between a first time and a second time as the first duration, where the first time is a shooting time of the current image frame, the second time is a shooting time of a target image frame in the group of image frames, the target image frame is an image frame that is the earliest shot in the group of image frames, the updated archive stores the first time corresponding to the first information, and the second time corresponding to target information, and the target information is information of the first object obtained by performing object detection on the target image frame.

In an alternative embodiment, the second determining submodule includes: the comparison unit is used for comparing the second information set of the first object with information of a group of objects included in a target comparison library acquired in advance to obtain a comparison result, wherein the group of objects included in the target comparison library are all objects of the appointed type; and the second determining unit is used for determining that the first object is the object of the specified type under the condition that the similarity between the second information of the second object in the information of the group of objects indicated by the comparison result and part or all of the information in the second information set is greater than or equal to a preset similarity threshold value.

In an alternative embodiment, the second determining submodule includes: a first acquisition unit configured to acquire a set of monitored objects associated with the first object, where the set of monitored objects are objects detected in the set of image frames and the current image frame that have a predetermined contact manner with the first object; the second acquisition unit is used for acquiring family member information of each monitoring object in the group of monitoring objects to obtain a group of family member information; and a third determining unit, configured to determine whether the first object is the object of the specified type according to the group of family member information.

In an alternative embodiment, the second obtaining unit includes: a searching subunit, configured to search, in an existing archive set on the target platform, an archive corresponding to each of the objects in the group of objects to obtain a group of archive, where each archive in the existing archive set stores family member information of the corresponding object; or, a request subunit, configured to send an information query request to a target device, where the information query request carries information of the group of objects, where the information query request is used to request to obtain family member information of each object in the group of objects, where the information of the group of objects is information of each object obtained by performing object detection on a second group of image frames, and the second group of image frames is an image frame of each object detected in the group of image frames and the current image frame; and the acquisition subunit is used for acquiring the family member information of each subject in the group of subjects sent by the target equipment, wherein the target equipment is used for searching the family member information of each subject in the group of subjects matched with the information of the group of subjects.

In an alternative embodiment, the third determining unit includes: a first determining subunit, configured to determine, when none of the group of family member information includes an object of the predetermined age group, that the first object is the object of the specified type; or, a second determining subunit, configured to determine that the first object is the object of the specified type if the group of family member information includes the object of the predetermined age group, but none of the group includes the first object.

In an alternative embodiment, the apparatus further comprises: and the sending module is used for sending an early warning notice under the condition that the first object is determined to be the object of the appointed type, wherein the early warning notice is used for prompting the first object to be the object of the appointed type.

It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.

An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.

Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method of determining an object, comprising:

object detection is carried out on the current image frame to obtain a current detection result;

determining whether a target file of a first object is included in a target platform or not under the condition that the current detection result comprises first information of the first object detected in the current image frame, wherein the first object is an object of a preset age range, the target file is obtained by performing file focusing operation on the information of the first object in a preset time period in the past, and a first information set of the first object acquired in the preset time period is stored in the target file;

storing the first information into the target archive to obtain an updated archive, wherein the updated archive comprises a second information set of the first object, and the second information set comprises the first information set and the first information;

And determining whether the first object is an object of a specified type according to the updated archive.

2. The method of claim 1, wherein determining whether the first object is a specified type of object based on the updated profile comprises:

determining a first duration of the first object in a target area according to the updated archive, wherein the first information set is information of the first object obtained by object detection of a group of image frames, and the group of image frames are image frames obtained by shooting the target area by a target camera before the current image frame;

and determining whether the first object is an object of a specified type or not under the condition that the first time length is greater than or equal to a preset time length threshold value.

3. The method of claim 2, wherein determining a first time period for the first object to appear in the target area based on the updated profile comprises:

and determining a difference between a first time and a second time as the first duration, wherein the first time is a shooting time of the current image frame, the second time is a shooting time of a target image frame in the group of image frames, the target image frame is an earliest shot image frame in the group of image frames, the updated archive stores the first time corresponding to the first information and the second time corresponding to target information, and the target information is information of the first object obtained by performing object detection on the target image frame.

4. The method of claim 2, wherein the determining whether the first object is a specified type of object comprises:

comparing the second information set of the first object with information of a group of objects included in a target comparison library acquired in advance to obtain a comparison result, wherein the group of objects included in the target comparison library are all objects of the appointed type;

and determining that the first object is the object of the appointed type under the condition that the comparison result indicates that the similarity between the second information of the second object in the information of the group of objects and part or all of the information in the second information set is greater than or equal to a preset similarity threshold value.

5. The method of claim 2, wherein the determining whether the first object is a specified type of object comprises:

acquiring a group of monitored objects associated with the first object, wherein the group of monitored objects are objects detected in the group of image frames and the current image frame and have a preset contact mode with the first object;

acquiring family member information of each monitoring object in the group of monitoring objects to obtain a group of family member information;

And determining whether the first object is the object of the specified type according to the group of family member information.

6. The method of claim 5, wherein the obtaining family member information for each subject in the set of subjects comprises:

searching files corresponding to each monitoring object in the group of monitoring objects in the existing file set on the target platform to obtain a group of files, wherein each file in the existing file set stores family member information of the corresponding object; or alternatively

An information inquiry request is sent to target equipment, wherein the information inquiry request carries information of the group of objects, the information inquiry request is used for requesting to acquire family member information of each object in the group of objects, the information of the group of objects is information of each object obtained by object detection on a second group of image frames, and the second group of image frames is an image frame of each object detected in the group of image frames and the current image frame; and acquiring family member information of each subject in the group of subjects sent by the target equipment, wherein the target equipment is used for searching the family member information of each subject in the group of subjects matched with the information of the group of subjects.

7. The method of claim 5, wherein determining whether the first object is the specified type of object based on the set of family member information comprises:

determining that the first object is the object of the specified type under the condition that no object of the preset age group is included in the group of family member information; or,

and determining that the first object is the object of the specified type under the condition that the group of family member information comprises the object of the preset age range but does not comprise the first object.

8. The method according to any one of claims 1 to 7, further comprising:

and sending out an early warning notice under the condition that the first object is determined to be the object of the appointed type, wherein the early warning notice is used for prompting the first object to be the object of the appointed type.

9. An object determining apparatus, comprising:

the detection module is used for carrying out object detection on the current image frame to obtain a current detection result;

a first determining module, configured to determine, if the current detection result includes first information of a first object detected in the current image frame, whether a target file of the first object is included in a target platform, where the first object is an object of a predetermined age group, the target file is a file obtained by performing a file focusing operation on information of the first object in a predetermined time period in the past, and the target file stores a first information set of the first object acquired in the predetermined time period;

The obtaining module is used for storing the first information into the target archive to obtain an updated archive when the target archive is included in the target platform, wherein the updated archive comprises a second information set of the first object, and the second information set comprises the first information set and the first information;

and the second determining module is used for determining whether the first object is an object of a specified type according to the updated archive.

10. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, wherein the computer program, when being executed by a processor, implements the steps of the method according to any of the claims 1 to 8.

11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.