CN120640133A

CN120640133A - PTZ camera automatic zoom method, device, equipment, storage medium and computer program product

Info

Publication number: CN120640133A
Application number: CN202510783943.4A
Authority: CN
Inventors: 游继安; 何文斌; 黄雅琦
Original assignee: College Of Technology Hubei Engineering University
Current assignee: College Of Technology Hubei Engineering University
Priority date: 2025-06-12
Filing date: 2025-06-12
Publication date: 2025-09-12

Abstract

The present application relates to the field of camera focusing technology, and in particular, to a PTZ camera automatic zooming method, apparatus, device, storage medium and computer program product. The method comprises the steps of inquiring a preset focal length and image size proportion set based on a current focal length to obtain a plurality of image size proportions, determining the current image size proportion according to the size of a current frame image and the size of a shooting target in the current frame image, obtaining a size focal length proportion set according to the plurality of image size proportions and the current image size proportion, wherein the size focal length proportion set comprises the image size proportions of the plurality of shooting targets under different focal lengths, searching in the size focal length proportion set based on the preset target size focal length proportion, determining a target focal length according to a searching result, and improving the automatic zooming performance of the PTZ camera.

Description

PTZ camera automatic zooming method, device, equipment, storage medium and computer program product

Technical Field

The present application relates to the field of camera focusing technology, and in particular, to a PTZ camera automatic zooming method, apparatus, device, storage medium and computer program product.

Background

PTZ (Pan-Tilt-Zoom) cameras are widely used in the fields of intelligent video monitoring, intelligent transportation, unmanned aerial vehicle aerial photography, industrial detection and the like. To ensure that the camera captures a clear image of the target in real time, it is often necessary to adjust the focal length according to the size change of the target in the picture to ensure that the target always maintains proper scale and resolution. The existing PTZ camera zoom control is only suitable for static monitoring scenes, cannot adapt to the change of the distance of a target, reduces the image definition or breaks away from a picture, or is poor in zoom performance due to complex calculation and slow zoom convergence speed by continuously adjusting the focal length and comparing the target size with a preset proportion after each adjustment until reaching a target size range. Therefore, how to improve the auto-zoom performance of the PTZ camera is a technical problem to be solved.

Disclosure of Invention

The application mainly aims to provide a PTZ camera automatic zooming method, a PTZ camera automatic zooming device, a PTZ camera automatic zooming equipment, a PTZ camera automatic zooming storage medium and a PTZ camera automatic zooming computer program product, and aims to solve the technical problem of improving the automatic zooming performance of a PTZ camera.

To achieve the above object, the present application provides a PTZ camera auto zoom method, the method comprising the steps of:

Inquiring a preset focal length and image size proportion set based on the current focal length to obtain a plurality of image size proportions;

determining the size proportion of the current image according to the size of the current frame image and the size of the shooting target in the current frame image;

Obtaining a size focal length proportion set according to the image size proportions and the current image size proportions, wherein the size focal length proportion set comprises the image size proportions of a plurality of shooting targets under different focal lengths;

searching in the size focal length proportion set based on a preset target size focal length proportion;

and determining the target focal length according to the search result.

In an embodiment, before the step of querying the preset focal length and image size proportion set based on the current focal length to obtain a plurality of image size proportions, the method further includes:

Acquiring the width and the height of a preset calibration plate in images shot under different focal lengths;

and carrying out normalization processing on the width and the height, and taking the preset calibration plate as a reference object to obtain the preset focal length and image size proportion set.

In an embodiment, before the step of determining the current image size ratio according to the size of the current frame image and the size of the shooting target in the current frame image, the method further includes:

Acquiring the current frame image shot by the PTZ camera, and identifying the size of the current frame image;

identifying the shooting target in the current frame image based on a preset target detection algorithm;

and determining the size of the shooting target in the current frame image according to the size of the current frame image.

In an embodiment, the step of searching in the size focal length proportion set based on the preset target size focal length proportion includes:

respectively calculating the difference value of each ratio in the preset target size focal length ratio and the size focal length ratio set;

determining a matching degree according to the difference value, wherein the matching degree is smaller as the difference value is larger;

and taking the ratio corresponding to the maximum value of the matching degree in the size focal length ratio set as a searching result.

In an embodiment, after the step of determining the target focal length according to the search result, the method further includes:

and verifying the target focal length, and transmitting the verified target focal length to the PTZ camera.

In an embodiment, before the step of obtaining the set of size focal length scales according to the plurality of image size scales and the current image size scale, the method further includes:

and smoothing the size of the current frame image and the size of the shooting target in the current frame image by adopting a Kalman filter.

In addition, to achieve the above object, the present application also proposes a PTZ camera auto zoom apparatus comprising:

the query module is used for querying a preset focal length and image size proportion set based on the current focal length to obtain a plurality of image size proportions;

the current proportion module is used for determining the current image size proportion according to the size of the current frame image and the size of the shooting target in the current frame image;

The size focal length proportion module is used for obtaining a size focal length proportion set according to the image size proportions and the current image size proportions, wherein the size focal length proportion set comprises the image size proportions of a plurality of shooting targets under different focal lengths;

The matching module is used for searching in the size focal length proportion set based on a preset target size focal length proportion;

And the target module is used for determining a target focal length according to the search result.

In addition, in order to achieve the aim, the application also provides PTZ camera automatic zooming equipment, which comprises a memory, a processor and a PTZ camera automatic zooming program which is stored on the memory and can run on the processor, wherein the PTZ camera automatic zooming program is configured to realize the steps of the PTZ camera automatic zooming method.

In addition, to achieve the above object, the present application also proposes a storage medium having stored thereon a PTZ camera auto zoom program which, when executed by a processor, implements the steps of the PTZ camera auto zoom method as described above.

Furthermore, to achieve the above object, the present application also proposes a computer program product comprising a computer program which, when executed by a processor, implements the steps of the PTZ camera auto zoom method as described above.

The method comprises the steps of inquiring a preset focal length and image size proportion set based on a current focal length to obtain a plurality of image size proportions, determining the current image size proportion according to the size of a current frame image and the size of a shooting target in the current frame image, obtaining a size focal length proportion set according to the plurality of image size proportions and the current image size proportion, wherein the size focal length proportion set comprises the image size proportions of the shooting targets under different focal lengths, searching in the size focal length proportion set based on the preset target size focal length proportion, and determining a target focal length according to a searching result. The method comprises the steps of obtaining image size ratios corresponding to a plurality of different focal lengths based on a current focal length through inquiring a preset focal length and image size ratio set, providing reference data for follow-up zooming calculation, guaranteeing stability of zooming calculation, obtaining the ratio of a target in a current frame image in real time through calculating the current frame image size ratio, enabling zooming calculation to be adaptive to different target sizes and image size changes, further combining the image size ratios and the current image size ratio set, constructing a size focal length ratio set which comprises size change rules of the target under different focal lengths, improving accuracy of focal length calculation and accuracy of zooming matching, then searching in the size focal length ratio set based on the preset target size focal length ratio, directly matching the closest proportion, avoiding a traditional low-efficiency calculation mode of gradually adjusting focal length, improving zooming rapidity and response speed, finally determining a target focal length according to a searching result, guaranteeing that the target size is stable in a zoomed picture, improving zooming accuracy and consistency, and further improving overall zooming performance of a PTZ camera.

Drawings

FIG. 1 is a flow chart of a first embodiment of the PTZ camera auto zoom method of the present application;

FIG. 2 is a schematic view of a sub-process in a second embodiment of the PTZ camera auto-zoom method of the present application;

FIG. 3 is a schematic view of a sub-process in a third embodiment of the automatic zooming method of the PTZ camera according to the present application;

FIG. 4 is a schematic block diagram of an automatic zooming device of a PTZ camera according to an embodiment of the present application;

Fig. 5 is a schematic device structure diagram of a hardware operating environment related to a PTZ camera auto-zoom method according to an embodiment of the present application.

The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

For a better understanding of the technical solution of the present application, the following detailed description will be given with reference to the drawings and the specific embodiments.

It should be noted that, the PTZ (Pan-Tilt-Zoom) camera is widely applied to the fields of intelligent video monitoring, intelligent traffic, unmanned aerial vehicle aerial photography, industrial detection, and the like. To ensure that the camera captures a clear image of the target in real time, it is often necessary to adjust the focal length according to the size change of the target in the picture to ensure that the target always maintains proper scale and resolution. The existing PTZ camera zoom control is only suitable for static monitoring scenes, cannot adapt to the change of the distance of a target, reduces the image definition or breaks away from a picture, or is poor in zoom performance due to complex calculation and slow zoom convergence speed by continuously adjusting the focal length and comparing the target size with a preset proportion after each adjustment until reaching a target size range. Therefore, how to improve the auto-zoom performance of the PTZ camera is a technical problem to be solved.

The main solution of the application is that a preset focal length and image size proportion set is inquired based on a current focal length to obtain a plurality of image size proportions, the current image size proportion is determined according to the size of a current frame image and the size of a shooting target in the current frame image, a size focal length proportion set is obtained according to the plurality of image size proportions and the current image size proportion, the size focal length proportion set comprises the image size proportions of the shooting targets under different focal lengths, the search is carried out in the size focal length proportion set based on the preset target size focal length proportion, and the target focal length is determined according to the search result.

The method comprises the steps of obtaining image size ratios corresponding to a plurality of different focal lengths based on a current focal length through inquiring a preset focal length and image size ratio set, providing reference data for follow-up zooming calculation, guaranteeing stability of zooming calculation, obtaining the ratio of a target in a current frame image in real time through calculating the current frame image size ratio, enabling zooming calculation to be adaptive to different target sizes and image size changes, further combining the image size ratios and the current image size ratio set, constructing a size focal length ratio set which comprises size change rules of the target under different focal lengths, improving accuracy of focal length calculation and accuracy of zooming matching, then searching in the size focal length ratio set based on the preset target size focal length ratio, directly matching the closest proportion, avoiding a traditional low-efficiency calculation mode of gradually adjusting focal length, improving zooming rapidity and response speed, finally determining a target focal length according to a searching result, guaranteeing that the target size is stable in a zoomed picture, improving zooming accuracy and consistency, and further improving overall zooming performance of a PTZ camera.

It should be noted that, the execution body of the method of this embodiment may be a computing service device having functions of data processing, network communication and program running, or may be the automatic zoom device of the PTZ camera having the same or similar functions. This embodiment and the following embodiments will be described taking a PTZ camera auto zoom apparatus as an example.

Based on this, a first embodiment of the PTZ camera auto-zoom method of the present application is presented, please refer to fig. 1, fig. 1 is a flow chart of the first embodiment of the PTZ camera auto-zoom method of the present application.

In this embodiment, the PTZ camera auto zoom method includes the steps of:

s1, inquiring a preset focal length and image size proportion set based on a current focal length to obtain a plurality of image size proportions;

The current focal length refers to an optical focal length value used by the PTZ camera at the current moment, and determines the magnification and the shooting angle of view of the camera. The preset focal length and image size proportion set refers to proportion data of image sizes under different focal lengths, which are prestored in a camera calibration stage, and describes the size change rule of a shooting target of the camera under different focal lengths. The image size ratio refers to the ratio of the size of the object to the entire image size at a specific focal length, and generally includes the ratio of the object width to the image width and the ratio of the object height to the image height.

Specifically, the current focal length value needs to be acquired first before the PTZ camera performs auto-zooming. And reading the focal length parameter of the current camera, and searching in the preset focal length and image size proportion set by utilizing the focal length value to find the image size proportion data corresponding to the current focal length. In addition, in order to obtain more comprehensive proportion information, proportion data corresponding to a plurality of focal length values adjacent to the current focal length are also queried, so that more accurate interpolation matching can be performed in the subsequent calculation process.

Further, after the query is completed, the image size ratios under a plurality of different focal lengths are returned. The scale data reflects the size change trend of the target under different focal lengths, and provides reference for subsequent zooming calculation. Because the preset proportion set is measured and stored in the calibration stage, the data is stable, the error is small, and reliable basic data can be provided for zoom calculation. By acquiring the proportion data of a plurality of focal lengths, interpolation calculation can be performed among different focal lengths, and more accurate and smooth zoom adjustment is ensured.

The image size proportion under a plurality of different focal lengths is acquired by inquiring the preset focal length and image size proportion set based on the current focal length, so that stability, accuracy and adaptability of zoom calculation are ensured. Compared with the traditional method, the method has the advantages that the current target size is directly measured, and the focal length is calculated, the calculation error is reduced by using the preset proportion data, and the stability of zooming calculation is improved. In addition, the image size proportion under a plurality of focal lengths is inquired, so that the system can more accurately predict the change of the size of the target under different focal lengths, the accuracy of zooming calculation is improved, the size of the target in the image is ensured to be more stable, accurate input data is provided for subsequent automatic zooming calculation, and zooming adjustment is more accurate, efficient and stable.

S2, determining the size proportion of the current image according to the size of the current frame image and the size of the shooting target in the current frame image;

The current frame image size refers to the entire width and height of a single frame image currently captured by the camera, and is usually expressed in units of pixels. This size is used to calculate the duty cycle of the object in the image. The shot target size refers to the width and height of the target in the current frame image detected by the camera, and is typically identified by a target detection algorithm (e.g., YOLO, fasterR-CNN). The current image size ratio refers to a ratio relationship between the size of a photographed object and the overall size of the current frame image, and generally includes a ratio of the object width to the image width, and a ratio of the object height to the image height, for describing the duty ratio of the object in the screen.

Specifically, after the current frame image is shot by the camera, the overall size information of the frame image, namely the width and the height of the image, is firstly obtained. These data are typically provided by the imaging module of the camera and serve as a reference basis for calculating the target scale. Then, the current frame image is analyzed using an object detection algorithm, the position of the photographed object is recognized, and the width and height of the object are acquired. The target detection algorithm can be based on deep learning (such as YOLO, fasterR-CNN) or traditional image processing (such as edge detection, color segmentation, etc.), and the specific method is selected according to application requirements.

Further, after the overall size and the target size of the current frame image are obtained, the duty ratio of the target size in the image, that is, the current image size proportion is calculated. The scale may be converted to a relative scale by a normalization method, such that the calculation result is not affected by the resolution of the image. The calculation result of the current image size ratio is used for subsequent zooming calculation and is matched with preset ratio data under different focal lengths so as to determine the optimal focal length.

The ratio information of the target in the current image is provided by calculating the proportional relation between the current frame image size and the target size, and key input data is provided for automatic zooming calculation. Compared with the traditional method, the method directly calculates the focal length based on the target absolute size, and the step ensures stronger adaptability and consistency of zoom calculation by calculating the duty ratio of the target size in the whole picture. The method can adapt to the changes of different resolutions, different target sizes and camera visual angles, so that the zoom calculation is more accurate. In addition, through matching with a preset focal length and image size proportion set, the proportion can be further used for focal length calculation, so that zoom adjustment is more stable, and the zoom precision and picture consistency of the PTZ camera are improved.

S3, obtaining a size focal length proportion set according to the image size proportions and the current image size proportions, wherein the size focal length proportion set comprises the image size proportions of a plurality of shooting targets under different focal lengths;

It should be noted that, the plurality of image size ratios refer to image size ratios corresponding to different focal lengths obtained by centralized query from preset focal lengths and image size ratios, and reflect the size change condition of the target under different focal lengths. The current image size ratio refers to a target size ratio calculated according to the size of the current frame image and the size of the shooting target, and represents the relative size of the target in the current frame image. The size focal length proportion set refers to a corresponding relation set of one generated target size and different focal lengths after combining a plurality of image size proportions and the current image size proportion, and is used for subsequent zooming calculation. The proportion set can reflect the size change trend of the target under different focal lengths, and provides reference data for accurately matching the optimal focal length.

Specifically, a set of dimensional focal length ratios is generated by combining the image size ratios at the plurality of focal lengths with the current image size ratio. The proportion set records the change trend of the target size under different focal lengths, and can be used for calculating the optimal focal length.

Optionally, the missing focal length-size proportion term in the proportion set is filled by a data interpolation method (such as linear interpolation or polynomial fitting), so that data are more continuous, and the accuracy of matching calculation is improved. If the current image size ratio fails to directly match a certain item in the ratio set, a closer ratio can be obtained through interpolation calculation to optimize the focal length calculation.

By integrating the image size proportion and the current image size proportion under a plurality of focal lengths, a complete size-focal length corresponding relation set is established, and high-precision reference data is provided for follow-up zooming calculation. Compared with the traditional method, the method only calculates the focal length based on the current target size, and the step combines the target size change trend under a plurality of focal lengths, so that the focal length calculation is ensured to be more accurate and stable. In addition, the matching precision can be optimized through data interpolation, and even if the target size proportion is not directly matched, the optimal focal length can be estimated through calculation, so that the zooming error caused by data loss is avoided. Finally, the step ensures the high efficiency, the precision and the stability of zooming calculation, improves the automatic zooming performance of the PTZ camera, ensures that the PTZ camera can always keep stable target size under the condition of different scenes and target size changes, and optimizes shooting quality.

S4, searching in the size focal length proportion set based on a preset target size focal length proportion;

And S5, determining a target focal length according to the search result.

The preset target size focal length ratio refers to an ideal size ratio of a preset target in a screen, that is, a size standard that the target is expected to keep in an image. This ratio is used to find the focal length that matches it. The search result refers to a matching item which is found in the size focal length proportion set and is closest to the preset target size focal length proportion, and a focal length value corresponding to the matching item is the basis of zoom adjustment. The target focal length refers to the optimal focal length calculated finally, so that the size of the target in the image accords with the set expected proportion, and the accurate zooming is realized.

Specifically, the target size ratio is preset to indicate the ideal size of the target in the final screen. For example, in intelligent monitoring systems, objects (e.g., pedestrians, vehicles) should occupy a proportion of the scene to ensure clarity and legibility. Searching a matching item closest to the preset target size proportion in the size focal length proportion set, and directly selecting a corresponding focal length if the proportion set has an item completely consistent with the preset proportion. If the item which is not completely matched is not found, the item with the smallest error of the proportion with the preset target size is searched and used as a preliminary matching result. If the target proportion falls between the two proportion items, calculating the optimal matching proportion by adopting an interpolation algorithm, calculating the focal length according to the optimal matching proportion, and improving the calculation accuracy.

Further, the corresponding focal length value is obtained by searching the matched proportion item. The focal length value is the optimal zoom parameter calculated by the system and is used for adjusting the focal length of the camera so that the target size meets the expectations. The calculated target focal length is transmitted to a zoom control module of the PTZ camera, and the camera is adjusted to the focal length value, so that the target size is consistent with a preset standard. The process can realize automation without manual intervention, ensure that the camera can adapt to the size change of the target in real time and keep stable monitoring or shooting quality.

The step ensures that the PTZ camera can automatically adjust the focal length by searching the item which is most matched with the preset target size proportion in the size focal length proportion set and calculating the target focal length, so that the size of the target in the picture accords with the set standard. Compared with the traditional method of manually adjusting or gradually exploring the focal length, the method has the advantages that the optimal focal length is rapidly determined through data matching and interpolation calculation, the iteration times of zooming calculation are reduced, and the zooming efficiency is improved. In addition, the zoom adjustment is more intelligent and standardized by combining the preset target size proportion, so that the problem of negligence of the target size caused by the change of the distance of the target is avoided. Finally, the zooming precision, the computing efficiency and the picture stability are improved, so that the PTZ camera can accurately keep the target size and improve the video shooting quality under the application scenes of intelligent monitoring, unmanned aerial vehicle tracking, traffic monitoring and the like.

The embodiment obtains a plurality of image size ratios by inquiring a preset focal length and image size ratio set based on a current focal length, determines the current image size ratio according to the size of a current frame image and the size of a shooting target in the current frame image, obtains a size focal length ratio set according to the plurality of image size ratios and the current image size ratio, wherein the size focal length ratio set comprises the image size ratios of the plurality of shooting targets under different focal lengths, searches in the size focal length ratio set based on the preset target size focal length ratio, and determines a target focal length according to a search result. According to the method, reference data are provided for subsequent zooming calculation by inquiring a preset focal length and image size proportion set, reference data are provided for subsequent zooming calculation, stability of zooming calculation is guaranteed, the duty ratio of a target in a current frame image is obtained in real time by calculating the current frame image size proportion, zooming calculation can adapt to different target sizes and image size changes, a size focal length proportion set is further constructed by combining the image size proportions and the current image size proportion set, the size focal length proportion set comprises size change rules of the target under different focal lengths, accuracy of focal length calculation and accuracy of zooming matching are improved, then searching is conducted in the size focal length proportion set based on the preset target size focal length proportion, closest proportion items are directly matched, a traditional low-efficiency calculation mode of gradually adjusting focal length is avoided, zooming rapidity and response speed are improved, finally, target focal length is determined according to search results, stability of the target size in a zoomed picture is guaranteed, zooming accuracy and consistency are improved, and overall zooming performance of a PTZ camera is improved.

Based on the above-described first embodiment, a second embodiment of the PTZ camera auto zoom method of the present application is proposed. Referring to fig. 2, fig. 2 is a schematic flow chart of a second embodiment of the automatic zooming method of the PTZ camera according to the present application.

As shown in fig. 2, in this embodiment, before step S1, the method further includes:

S1a, acquiring width and height of a preset calibration plate in images shot under different focal lengths;

And S1b, carrying out normalization processing on the width and the height, and taking the preset calibration plate as a reference object to obtain the preset focal length and image size proportion set.

It should be noted that the preset calibration plate is a standard reference object used in the camera focal length calibration process, and is usually a rectangular flat plate with a known size, and is used for measuring the image size change under different focal lengths. The normalization process refers to converting the measured image size into a relative scale, so that it is independent of the resolution and shooting conditions of the camera, and generally scales the width and height of the calibration plate to standardized values (e.g., 1), which are used as scale references.

Specifically, when the camera is mounted or calibrated, a preset calibration plate (for example, a square flat plate of 60cm×60 cm) with a fixed size is used as a reference, and the calibration plate is photographed at different focal lengths to obtain the width and height of the calibration plate in the image. The method comprises the steps of fixing the position and shooting angle of a camera, ensuring that the optical axis of the camera is vertically aligned with a calibration plate, avoiding perspective distortion, and adopting fixed illumination conditions, preventing measurement accuracy from being influenced by brightness change. And then the focal length is sequentially adjusted and the calibration plate image is shot, namely, one calibration plate image is shot after each focal length adjustment, for example, if a camera has 30 times of optical zooming, 30 images with different focal lengths are shot, and the width and the height of the calibration plate in a picture are measured in each image and data are recorded. The calibration plate was placed 120 m away from the camera for photographing.

Further, after the width and the height of the calibration plate under different focal lengths are obtained, the calibration plate is normalized so as to establish a general proportional relation between the focal length and the image size. The method comprises the steps of normalizing the size of a calibration plate, setting a standard value (for example, normalizing the width and the height of the calibration plate to 1), calculating the aspect ratio of the calibration plate in an image under each focal length, carrying out zooming calculation by using the same proportion data no matter how the resolution of a camera changes, and establishing a preset focal length and image size proportion set, namely, arranging the normalized width and the height under different focal lengths into a table to form a preset focal length and image size proportion set, wherein the data set is used as a matching basis in the follow-up automatic zooming, and is used for calculating the corresponding relation between the target size and the focal length, so that the proper focal length is accurately determined.

According to the method, the image size of the calibration plate is obtained under different focal lengths, normalization processing is carried out, a standardized focal length and image size proportion relation set is established, and accurate reference data is provided for follow-up zooming calculation. Compared with the traditional method which relies on successive adjustment of focal length to perform heuristic calculation, the method has the advantages that the focal length and image size proportion data table is constructed in advance through off-line calibration, so that the zoom calculation is more efficient and accurate. In addition, the method eliminates the influence of the camera resolution, illumination conditions and other environmental factors on the zoom calculation, improves the stability and consistency of calculation, and ensures that the PTZ camera can realize accurate automatic zooming in various application scenes.

Based on the above-described first embodiment, in the present embodiment, before step S2, further includes:

S2a, acquiring the current frame image shot by the PTZ camera, and identifying the size of the current frame image;

s2b, identifying the shooting target in the current frame image based on a preset target detection algorithm;

And S2c, determining the size of the shooting target in the current frame image according to the size of the current frame image.

It should be noted that the preset target detection algorithm is a preset YOLO (You Only Look Once) or fast R-CNN algorithm based on deep learning.

Specifically, the PTZ camera continues to operate, capturing a video stream at a set frame rate, and at a certain moment, acquiring a current frame image. The image contains the entire monitored scene or shot area, including the background, a plurality of possible targets, etc. The resolution information of the current frame image, i.e., the width (w_image) and the height (h_image) of the image is read for subsequent target size calculation by a camera system interface or image processing software. The current frame image is analyzed using a preset object detection algorithm to identify possible objects. The choice of the target detection algorithm depends on the application requirements, e.g. deep learning based target detection (e.g. YOLO, fasterR-CNN) is applicable to complex environments and multi-target detection, traditional target detection based on color, edge or shape is applicable to regular targets, e.g. industrial part detection. The object detection algorithm outputs a bounding box (Bounding Box) marking the position of the object in the image.

Further, the size of the object is determined by the bounding box of the object, and this size represents the actual pixel size of the object in the current frame image, which is a core parameter for the subsequent zoom calculation. After the calculation of the target size is completed, the target size is combined with the whole size of the current frame image to calculate the proportion of the target size in the picture, and the proportion is used as a key basis for zoom adjustment.

The step is to obtain the current frame image, apply the target detection algorithm to identify the target, and calculate the size of the target in the image, so as to provide key input data for automatic zooming. Compared with the traditional method relying on manual setting of the target size, the method can automatically detect the target in a dynamic environment and calculate the size of the target in real time, and the intelligent degree and the adaptability are improved. In addition, through the target detection algorithm that presets, can adapt to different scenes, such as intelligent monitoring, unmanned aerial vehicle target tracking, intelligent transportation etc. ensure that even if the target size changes, still can accurately discern the target to for follow-up zoom calculation provides stable, accurate input data, thereby promotes PTZ camera's automatic zoom precision and response speed.

Based on the above-described second embodiment, a third embodiment of the PTZ camera auto zoom method of the present application is proposed. Referring to fig. 3, fig. 3 is a schematic flow chart of a third embodiment of the automatic zooming method of the PTZ camera according to the present application.

In this embodiment, step S4 includes:

s41, respectively calculating the difference value of each ratio in the preset target size focal length ratio and the size focal length ratio set;

S42, determining the matching degree according to the difference value, wherein the matching degree is smaller as the difference value is larger;

and S43, taking the ratio corresponding to the maximum value of the matching degree in the size focal length ratio set as a search result.

It should be noted that, the difference refers to a numerical deviation between the preset target size focal length proportion and each proportion item in the size focal length proportion set, and is used for measuring the matching degree, and the smaller the difference, the higher the matching degree. The matching degree represents the similarity degree of the preset target size focal length proportion and each proportion in the size focal length proportion set, and the higher the matching degree is, the closer the proportion is to the target size proportion. The search result refers to a proportion item with highest matching degree in the size focal length proportion set, and the focal length corresponding to the proportion item is the final calculated target focal length.

Specifically, a preset target size focal length ratio is read. The scale is a target size criterion preset by the user and represents the optimal size of the target to be kept in the image. And sequentially reading each proportion item in the size focal length proportion set, and calculating the difference value between the size focal length proportion set and the preset target size focal length proportion. The difference value may be calculated using an absolute difference, ensuring that the numerical value is not influenced positively and negatively.

Further, the matching degree and the difference value are in inverse relation, namely, the smaller the difference value is, the higher the matching degree is, and the larger the difference value is, the lower the matching degree is. By calculating the degree of matching, it can be determined which scale terms are closest to the target size scale. And selecting a proportion item with the highest matching degree from all the calculated matching degrees, namely selecting the proportion item with the closest proportion to the preset target size. The focal length corresponding to the matching term will be used for subsequent zoom calculations. The focal length value corresponding to the search result is used as a final target focal length and is transmitted to the PTZ camera for automatic zoom adjustment.

According to the method, the difference value of each proportion item in the preset target size focal length proportion and the size focal length proportion set is calculated, the matching degree is calculated based on the difference value, and the proportion item with the highest matching degree is selected as a search result, so that the accuracy and stability of focal length calculation are ensured. Compared with the traditional method, the method has the advantages that the focal length is adjusted step by step and the target size is compared, the optimal focal length is determined rapidly through numerical matching, the iteration times of zooming calculation are reduced, and the efficiency of zooming calculation is improved. In addition, through matching degree calculation and minimum difference matching, optimal matching of the target size proportion and the ideal size proportion is ensured, and the problem that the target is negligibly small in a picture is avoided. Finally, the zooming precision, the response speed and the picture stability are improved, so that the PTZ camera can accurately keep the target size in the scenes of intelligent monitoring, automatic tracking, unmanned aerial vehicle aerial photographing and the like, and the video photographing quality is improved.

Based on the above-described second embodiment, in the present embodiment, after step S5, further includes:

And S5a, verifying the target focal length, and transmitting the verified target focal length to the PTZ camera.

It should be noted that verification means to perform rationality check on the target focal length, so as to ensure that the calculation result meets the physical limitation and practical application requirement of the camera, and avoid unstable zooming caused by calculation errors.

Specifically, the optical focal length range (e.g., 10mm-300 mm) of the PTZ camera is read, ensuring that the target focal length value is within that range. If the calculated target focal length exceeds the physical focal length limit of the camera, a correction process (e.g., set to a maximum or minimum support focal length) is performed. According to the focus of the target, the size of the target in the picture after the focus is adjusted is predicted, so that the target cannot exceed the picture or become too small due to excessive zooming. And if the size of the target does not accord with the set expected range, adjusting the focusing distance value to keep the proper size of the target in the image.

Further, the verified target focal length is sent to the zoom control module of the PTZ camera through a camera control interface (such as a serial port command, a network API, or a camera SDK). After the camera receives the focal length value, the focal length of the lens is adjusted, so that the target size meets the set requirement. After the focal length of the camera is adjusted, the target size can be obtained again, whether the target size reaches the set expected proportion is checked, if the target size still has deviation after adjustment, a compensation mechanism can be triggered, the focal length is recalculated, and fine adjustment is performed, so that the target size is ensured to be stable and consistent.

The method ensures accurate and stable zooming calculation results and accords with physical limitation by verifying the rationality of the target focal length and transmitting the target focal length passing the verification to the PTZ camera. Compared with the traditional method, the method directly applies the calculated focal length, and the rationality detection is firstly carried out in the step, so that the focal length is prevented from exceeding the range of the camera or causing the size abnormality of the target, and the reliability of zoom calculation is improved.

Based on the above-described second embodiment, in the present embodiment, before step S3, further includes:

And S3a, adopting a Kalman filter to carry out smoothing processing on the size of the current frame image and the size of the shooting target in the current frame image.

It should be noted that the kalman filter (KALMAN FILTER) is a recursive algorithm for state estimation, and can provide an optimal estimation of a true value in the case that measurement data is interfered by noise, and is widely used in object tracking, signal processing and vision systems. The smoothing process refers to that the dimension estimation is more stable and accurate by removing measurement errors and noise, and the zoom calculation errors caused by measurement fluctuation are avoided. The smoothing processing refers to making the target size estimation more stable by eliminating noise in the measurement data, reducing size fluctuation in a short time, thereby improving the accuracy and stability of the zoom calculation.

Specifically, the state variables are set, including a target size state (width, height) representing an estimated size of a current frame target in an image, and a state transition matrix assuming that the target size changes smoothly between adjacent frames, so that the state variables can be updated with time. The size of the current frame image and the target size provided by the target detection algorithm are used as measurement inputs of the filter. The kalman filter provides a more reliable size estimate by fusing multiple measurements, since the target detection may be noisy (e.g., the target is partially occluded, illumination changes cause detection errors). An initial state estimation value, that is, a target size detected in the first frame image is set. And setting a process noise covariance matrix and a measurement noise covariance matrix, and controlling the stability and response speed of filtering.

Further, the target size of the current frame is predicted according to the target size of the previous frame, and a prediction error covariance is calculated. Since the target size will not generally change drastically in a short time, the filter can reasonably predict the target size of the next frame, reducing the impact of transient errors on the zoom calculation. And comparing the target size detected by the current frame with a predicted value, calculating a Kalman gain, and adjusting the predicted value to be more approximate to the real target size. The Kalman gain can be dynamically adjusted according to the size of measurement noise, when the measurement data is stable, the gain is smaller, the filtering result is smoother, when the measurement data fluctuation is larger, the gain is larger, and the filter can rapidly respond to the change. After filtering treatment, the target size after smoothing treatment is finally obtained, the size is more stable, the error is smaller, and the method can be used for subsequent automatic zooming calculation.

According to the method, the Kalman filter is adopted to carry out smoothing treatment on the size of the current frame image and the size of the target, so that size fluctuation caused by factors such as target detection errors, illumination changes, shielding and the like is effectively reduced, and stability and accuracy of size estimation are improved. Compared with the method that unfiltered detection data is directly used for carrying out zooming calculation, the method enables target size estimation to be smoother, avoids zooming focal length jitter caused by measurement noise, and accordingly improves automatic zooming precision of a PTZ camera and stability of video pictures. In addition, the step can adapt to a dynamic environment, even if the size of a target changes in a short time, the filter can still provide stable and reliable size estimation, so that zoom calculation is more accurate, and the effects of intelligent monitoring, unmanned aerial vehicle tracking, automatic target recognition and other applications are improved.

An embodiment of the present application further provides an automatic zoom apparatus for a PTZ camera, referring to fig. 4, fig. 4 is a schematic block diagram of the automatic zoom apparatus for a PTZ camera according to the embodiment of the present application, where the automatic zoom apparatus for a PTZ camera includes:

a query module 401, configured to query a preset focal length and image size proportion set based on a current focal length, so as to obtain a plurality of image size proportions;

a current proportion module 402, configured to determine a current image size proportion according to a size of a current frame image and a size of a shooting target in the current frame image;

A size focal length proportion module 403, configured to obtain a size focal length proportion set according to the image size proportions and the current image size proportions, where the size focal length proportion set includes proportions of image sizes of the shooting targets under different focal lengths;

A matching module 404, configured to search in the size focal length proportion set based on a preset target size focal length proportion;

And the target module 405 is configured to determine a target focal length according to the search result.

The PTZ camera automatic zooming device provided by the embodiment of the application can solve the technical problem of improving the automatic zooming performance of the PTZ camera by adopting the PTZ camera automatic zooming method in the embodiment. Compared with the prior art, the PTZ camera automatic zooming device provided by the embodiment of the application has the same beneficial effects as the PTZ camera automatic zooming method provided by the embodiment, and other technical features in the PTZ camera automatic zooming device are the same as the features disclosed by the embodiment method, and are not repeated herein.

The application provides a PTZ camera automatic zooming device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the PTZ camera automatic zooming method in the embodiment.

Referring now to fig. 5, fig. 5 is a schematic device structure diagram of a hardware operating environment involved in a PTZ camera auto zoom method according to an embodiment of the present application, which shows a schematic device structure diagram of a PTZ camera auto zoom device suitable for implementing the embodiment of the present application. The PTZ camera auto zoom apparatus shown in fig. 5 is only one example and should not impose any limitation on the function and scope of use of the embodiments of the present application.

As shown in fig. 5, the PTZ camera auto zoom apparatus may include a processing device 1001 (e.g., a central processor, a graphic processor, etc.), which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access Memory (RAM: random Access Memory) 1004. In the RAM1004, various programs and data required for the operation of the PTZ camera auto zoom apparatus are also stored. The processing device 1001, the ROM1002, and the RAM1004 are connected to each other by a bus 1005. An input/output (I/O) interface 1006 is also connected to the bus. In general, a system including an input device 1007 such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc., an output device 1008 including a Liquid crystal display (LCD: liquid CRYSTAL DISPLAY), a speaker, a vibrator, etc., a storage device 1003 including a magnetic tape, a hard disk, etc., and a communication device 1009 may be connected to the I/O interface 1006. Communication means 1009 may allow the PTZ camera auto zoom device to communicate wirelessly or by wire with other devices to exchange data. While a PTZ camera auto zoom apparatus having various systems is shown, it should be understood that not all of the illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. The above-described functions defined in the method of the disclosed embodiment of the application are performed when the computer program is executed by the processing device 1001.

The PTZ camera automatic zooming equipment provided by the application adopts the PTZ camera automatic zooming method in the embodiment, so that the technical problem of how to improve the automatic zooming performance of the PTZ camera can be solved. Compared with the prior art, the PTZ camera automatic zooming device has the same beneficial effects as the PTZ camera automatic zooming method provided by the embodiment, and other technical features in the PTZ camera automatic zooming device are the same as those disclosed by the method of the previous embodiment, and are not repeated herein.

It is to be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon for performing the PTZ camera auto zoom method of the above-described embodiments.

The computer readable storage medium carries one or more programs, when the one or more programs are executed by the PTZ camera automatic zoom device, the PTZ camera automatic zoom device is enabled to search a preset focal length and image size proportion set based on a current focal length to obtain a plurality of image size proportions, the current image size proportion is determined according to the size of a current frame image and the size of a shooting target in the current frame image, a size focal length proportion set is obtained according to the plurality of image size proportions and the current image size proportion, the size focal length proportion set comprises the image sizes of a plurality of shooting targets under different focal lengths, searching is conducted in the size focal length proportion set based on the preset target size focal length proportion, and the target focal length is determined according to a searching result. Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of remote computers, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN: local Area Network) or a wide area network (WAN: wide Area Network), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules involved in the embodiments of the present application may be implemented in software or in hardware. Wherein the name of the module does not constitute a limitation of the unit itself in some cases.

The readable storage medium provided by the application is a computer readable storage medium, and the computer readable storage medium stores computer readable program instructions (namely computer programs) for executing the PTZ camera automatic zooming method, so that the technical problem of how to improve the automatic zooming performance of the PTZ camera can be solved. Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the application are the same as those of the PTZ camera automatic zooming method provided by the embodiment, and the detailed description is omitted.

An embodiment of the application provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a PTZ camera auto zoom method as described above.

The computer program product provided by the application can solve the technical problem of how to improve the automatic zooming performance of the PTZ camera. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the application are the same as those of the PTZ camera automatic zooming method provided by the embodiment, and the detailed description is omitted.

The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein, or any application, directly or indirectly, within the scope of the application.

Claims

1. A method for automatically zooming a PTZ camera, the method comprising:

and determining the target focal length according to the search result.

2. The method of claim 1, further comprising, prior to the step of querying a set of preset focal distances and image size ratios based on the current focal distance, a plurality of image size ratios:

3. The method of claim 1, further comprising, before the step of determining the current image size ratio based on the size of the current frame image and the size of the photographing target in the current frame image:

4. The method of claim 1, wherein the step of searching in the set of size focus ratios based on a preset target size focus ratio comprises:

5. The method of claim 3, further comprising, after the step of determining the target focal length based on the search result:

6. The method of claim 3, further comprising, prior to the step of deriving a set of focal length scale dimensions from the plurality of image scale dimensions and the current image scale dimension:

7. A PTZ camera auto zoom apparatus, the apparatus comprising:

8. A computer device, characterized in that it comprises a memory, a processor and a PTZ camera auto zoom program stored on the memory and executable on the processor, the PTZ camera auto zoom program being configured to implement the steps of the PTZ camera auto zoom method according to any of claims 1 to 6.

9. A storage medium having stored thereon a PTZ camera auto zoom program which when executed by a processor performs the steps of the PTZ camera auto zoom method of any one of claims 1 to 6.

10. A computer program product, characterized in that it comprises a computer program which, when executed by a processor, implements the steps of the PTZ camera auto zoom method according to any one of claims 1 to 6.