Camera coverage detection method, device, equipment and storage medium

Abstract

The embodiment of the present invention provides a camera coverage detection method, device, equipment and storage medium, the method comprising: sampling the video captured by the camera to obtain multiple frames of images; detecting the target object on the multiple frames of images respectively to obtain multiple target areas containing the target object; determining the target physical size corresponding to the target pixel according to the preset physical size of the target object and the pixel size corresponding to each of at least one target area covering the target pixel; determining the coverage area of ​​the camera according to the target physical size corresponding to each of the multiple target pixels. The coverage area is determined only based on the image captured by the camera, does not rely on the internal and external parameters of the camera, and eliminates the interference of environmental occlusion, lighting, etc., so the accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a camera coverage detection method, device, equipment and storage medium. Background Art

[0002] Currently, cameras are deployed in many scenarios to collect videos of the surrounding environment, so as to achieve purposes such as video surveillance.

[0003] In practical applications, there is a need to determine the coverage area of ​​the camera. For example, when multiple cameras need to be deployed in a certain area, it is necessary to know the coverage area of ​​each camera in order to reasonably locate the deployment position of the camera to avoid excessive overlap of the coverage areas of two adjacent cameras or a large uncovered area.

[0004] Currently, a commonly used method to determine the coverage area of ​​a camera is to perform mathematical modeling on its coverage area based on the internal and external parameters of the camera to obtain its coverage area, wherein internal parameters include, for example, focal length, and external parameters include, for example, the height of the camera from the ground, the angle with the horizontal plane or vertical plane, etc.

[0005] What is obtained through the above mathematical modeling is a static analytical solution, that is, the theoretical maximum coverage area. Moreover, the accuracy of the determination result is affected by the accuracy of the above internal and external parameters adopted, and the measurement results of the internal and external parameters are likely to be inaccurate. Summary of the invention

[0006] The embodiments of the present invention provide a camera coverage range detection method, device, equipment and storage medium, which can improve the accuracy of camera coverage area determination results.

[0007] In a first aspect, an embodiment of the present invention provides a camera coverage range detection method, the method comprising:

[0008] Sampling the video captured by the camera to obtain multiple frames of images;

[0009] Detecting target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects;

[0010] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object and a pixel size corresponding to each of at least one target area covering the target pixel;

[0011] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to each of the plurality of target pixels.

[0012] In a second aspect, an embodiment of the present invention provides a camera coverage range detection device, the device comprising:

[0013] An image acquisition module is used to sample the video captured by the camera to obtain multiple frames of images;

[0014] An object detection module, used to detect target objects on the multiple frames of images respectively, so as to obtain multiple target areas containing the target objects;

[0015] The area determination module is used to determine the target physical size corresponding to the target pixel according to the preset physical size of the target object and the pixel size corresponding to at least one target area covering the target pixel; and determine the coverage area of ​​the camera according to the target physical size corresponding to each of the multiple target pixels.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the camera coverage range detection method as described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the camera coverage range detection method as described in the first aspect.

[0018] In a fifth aspect, an embodiment of the present invention provides a camera coverage range detection method, the method comprising:

[0019] Sampling the video captured by the camera to obtain multiple frames of images;

[0020] Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects;

[0021] Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target object;

[0022] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object corresponding to each of the at least one group of target areas, a pixel size of the target area included in each of the at least one group of target areas, and the number of target areas included in each of the at least one group of target areas;

[0023] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to each of the plurality of target pixels.

[0024] In a sixth aspect, an embodiment of the present invention provides a camera coverage range detection device, the device comprising:

[0025] An image acquisition module is used to sample the video captured by the camera to obtain multiple frames of images;

[0026] An object detection module is used to detect multiple types of target objects on the multiple frames of images respectively, so as to obtain multiple target areas corresponding to the multiple types of target objects;

[0027] A region selection module, configured to determine at least one group of target regions covering target pixels from the plurality of target regions, wherein the group of target regions corresponds to a type of target object;

[0028] The area determination module is used to determine the target physical size corresponding to the target pixel according to the preset physical size of the target object corresponding to each of the at least one group of target areas, the pixel size of the target area contained in each of the at least one group of target areas, and the number of target areas contained in each of the at least one group of target areas; and determine the coverage area of ​​the camera according to the target physical size corresponding to each of the multiple target pixels.

[0029] In the seventh aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the camera coverage range detection method as described in the fifth aspect.

[0030] In an eighth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the camera coverage range detection method as described in the fifth aspect.

[0031] In a ninth aspect, an embodiment of the present invention provides a camera coverage range detection method, comprising:

[0032] Receive a request to call a target service, wherein the request includes a video captured by a camera;

[0033] Use the resources corresponding to the target service to perform the following steps:

[0034] Sampling the video captured by the camera to obtain multiple frames of images;

[0035] Detecting target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects;

[0036] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object and a pixel size corresponding to each of at least one target area covering the target pixel;

[0037] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to each of the plurality of target pixels.

[0038] In a tenth aspect, an embodiment of the present invention provides a camera coverage range detection method, comprising:

[0039] Receive a request to call a target service, wherein the request includes a video captured by a camera;

[0040] Use the resources corresponding to the target service to perform the following steps:

[0041] Sampling the video captured by the camera to obtain multiple frames of images;

[0042] Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects;

[0043] Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target object;

[0044] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object corresponding to each of the at least one group of target areas, a pixel size of the target area included in each of the at least one group of target areas, and the number of target areas included in each of the at least one group of target areas;

[0045] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to each of the plurality of target pixels.

[0046] The camera coverage detection scheme provided in the embodiment of the present invention is used to determine the effective coverage area of ​​the camera. In fact, there may be some interference factors irrelevant to the application purpose within the shooting range of the camera. The coverage area determined by this scheme eliminates the interference of these irrelevant factors. Among them, the application purpose refers to which or which category of target objects the camera is deployed for video acquisition. Assuming that the purpose of deploying the camera is mainly to focus on a certain type of target object, in order to determine the effective coverage area of ​​the camera, the video captured by the camera within a period of time can be obtained, and the video is sampled to obtain multiple frames of images. Each frame of the image is detected for this type of target object, so as to obtain a target area containing the target object in each frame of the image, and the target areas detected in all the multiple frames of the image can be summarized to obtain multiple target areas. Afterwards, for a pixel (referred to as a target pixel) at any position within the coverage range of the multiple target areas, at least one target area covering the target pixel in the multiple target areas is determined, and then, according to the preset physical size of the target object and the pixel size corresponding to each of the at least one target area, the target physical size corresponding to the target pixel is determined. The above processing is performed on each pixel covered by the above multiple target areas, and the target physical size of each pixel can be obtained. Finally, the coverage area of ​​the camera is determined by combining the target physical sizes corresponding to the multiple target pixels (such as the covered pixels) covered by the multiple target areas. The coverage area is determined only based on the image captured by the camera and does not rely on the internal and external parameters of the camera, so the accuracy is improved. In addition, since the coverage area is determined based on the target object detection result of the image, the interference of factors such as occlusion and lighting in the environment and other non-objects of interest is excluded, so that the coverage area finally determined is the accurate effective coverage area of ​​the camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a camera coverage detection method provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of a target area provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of a process for determining a target physical size of a target pixel in a single type of target object scene provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of a camera coverage area detection scenario provided by an embodiment of the present invention;

[0052] Figure 5 A flowchart of a camera coverage detection method provided by an embodiment of the present invention;

[0053] Figure 6 A schematic diagram of a process for determining a target physical size of a target pixel in a multi-type target object scene provided by an embodiment of the present invention;

[0054] Figure 7 A schematic diagram of the structure of a camera coverage range detection device provided by an embodiment of the present invention;

[0055] Figure 8 For Figure 7 A schematic diagram of the structure of an electronic device corresponding to the camera coverage range detection device provided in the illustrated embodiment;

[0056] Fig. 9 A schematic diagram of the structure of a camera coverage range detection device provided by an embodiment of the present invention;

[0057] Fig.10 For Fig. 9 A schematic structural diagram of an electronic device corresponding to the camera coverage range detection device provided in the illustrated embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0060] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0061] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0062] The camera coverage range detection solution provided by the embodiment of the present invention is used to determine the effective coverage area of ​​the camera.

[0063] First, the meaning of the above-mentioned effective coverage area is explained.

[0064] It is understandable that in actual applications, the purpose of deploying cameras in different application scenarios may be different. For example, the purpose of deploying cameras on the roads in the city is to achieve road monitoring, that is, to monitor the vehicles and pedestrians on the road. For another example, the purpose of deploying cameras inside or at the entrance and exit of a public place may be to monitor the flow of people entering and leaving the public place.

[0065] That is to say, in different application scenarios, the purpose of deploying cameras is often to focus on different categories of target objects. For example, in the above-mentioned road traffic scenario, two target objects may be involved, namely people and cars. In the above-mentioned application scenario summary of public places, target objects such as people are involved. In some other application scenarios, for example, other categories of target objects such as human faces and certain animals may also be involved.

[0066] However, the actual situation may be that for a certain camera, in addition to one or several types of target objects that need to be paid attention to, there may also be some non-target objects within its shooting range. For example, in a road traffic scene, there may be some road infrastructure and trees within the shooting range of a certain camera. In addition, due to factors such as environmental occlusion and lighting, even if there is a target object located in a certain position area within the camera's shooting range, the image collected by the camera cannot clearly see the existence of the target object.

[0067] In summary, the purpose of deploying cameras in different application scenarios is to clearly capture a certain type or several types of target objects that need to be paid attention to through the camera. Therefore, the area that can meet this requirement within the entire shooting range of the camera is effective, that is, the effective coverage area of ​​the camera is the area of ​​this area. The location areas where clear imaging cannot be obtained due to factors such as occlusion and lighting, as well as the location areas where non-interested objects are located, are invalid location areas and are not included in the effective coverage area of ​​the camera.

[0068] Note that the camera coverage area mentioned below refers to the effective coverage area mentioned above. In addition, the coverage area in this article refers to the actual physical ground area, not the pixel area.

[0069] In practical applications, the purpose of determining the coverage area of ​​a camera can be: when a camera is expected to cover a specific area, the area that the camera can actually cover is determined to find out whether the coverage requirement of the specific area is met. If not, the coverage of the specific area can be achieved by adjusting the deployment position and shooting angle of the camera.

[0070] The purpose of determining the coverage area of ​​the camera can also be: when multiple cameras need to be deployed in a certain application scenario, it is often hoped that the coverage areas of two adjacent cameras will not overlap too much to cause repeated shooting, and it is also hoped that the coverage areas of two adjacent cameras will not be too far apart to cause shooting loopholes. Therefore, the determination result based on the coverage area of ​​each camera can help determine the deployment position of each camera.

[0071] Based on the examples above, it can be seen that in actual applications, in some application scenarios, a camera needs to focus on a certain type of target object, while in some application scenarios, a camera needs to focus on multiple types of target objects. Therefore, in the embodiments of the present invention, solutions for determining the camera coverage area are provided for these two situations.

[0072] The camera coverage detection method provided in the embodiment of the present invention can be executed by an electronic device, which can be a terminal device such as a PC, a laptop, etc., or a server in the cloud. The server can be a physical server including an independent host, or a virtual server, or a cloud server.

[0073] Figure 1 A flowchart of a camera coverage detection method provided by an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0074] 101. Sample the video captured by the camera to obtain multiple frames of images.

[0075] 102. Detect target objects on multiple image frames respectively to obtain multiple target regions containing target objects.

[0076] 103. Determine a target physical size corresponding to the target pixel according to a preset physical size of the target object and a pixel size corresponding to each of at least one target area covering the target pixel.

[0077] 104. Determine a coverage area of ​​the camera according to target physical sizes corresponding to each of the plurality of target pixels.

[0078] For a camera, the objects it captures at different times are different. In order to accurately determine the coverage area of ​​the camera, it is necessary to use the video captured by the camera within a period of time. The length of the time period can be set according to demand.

[0079] Afterwards, the video is sampled to obtain multiple frames of images. For example, the video can be segmented to obtain all or part of the multiple frames of images obtained by segmentation as the multiple frames of images. It is understood that the multiple frames of images have the same size.

[0080] In this embodiment, it is assumed that the purpose of deploying the above-mentioned camera in a certain application scenario is to use the camera to focus on a certain type of target object, such as a person.

[0081] Therefore, after obtaining the above-mentioned multiple frames of images, the target object is detected for each of the multiple frames to detect the target area containing the target object in each frame of the image. Multiple target areas can be obtained by summarizing the target areas detected in all the multiple frames of images. In practical applications, each target area can be defined by its vertex coordinates to define the pixel position range it covers. For example, the pixel position range covered by the target area can be represented by the coordinates of the upper left corner and the coordinates of the lower right corner.

[0082] In an optional embodiment, when detecting the target object in each frame image, a rectangular area containing the target object, that is, the smallest rectangular area containing the target object, can be detected, thereby using multiple rectangular areas detected from multiple frames of images as the above-mentioned multiple target areas.

[0083] In another optional embodiment, after obtaining the above-mentioned multiple rectangular areas, for each rectangular area, the area from its bottom to a preset height can be cut out, and the cut-out multiple areas are used as the above-mentioned multiple target areas. The above-mentioned preset height can be a set ratio such as 10% of the full height of the corresponding rectangular area.

[0084] For ease of understanding, for example, Figure 2As shown in , assuming that a rectangular area A containing a target object is detected in a certain frame image, a lower sub-area B is cut out from the rectangular area A, and the height of the sub-area B is 10% of the height of the rectangular area A. At this time, the sub-area B will be used as a target area.

[0085] The above-mentioned area is intercepted because the camera generally shoots from a bird's-eye view. For the calculation of the camera's coverage area, it is sufficient to focus on the part of the target object that is closer to the ground. Therefore, only intercepting the lower part of the above-mentioned rectangular area can reduce the amount of subsequent calculations.

[0086] In addition, based on the above two optional embodiments, optionally, the target area can be scaled at a set ratio to compress the size of the target area, which can also reduce the amount of calculation for subsequent calculations.

[0087] For ease of understanding, the following Figure 3 The example in is used to illustrate the execution process of the above step 103.

[0088] exist Figure 3 In the above example, it is assumed that the above multi-frame images are Figure 3 The image 1, image 2 and image 3 shown in FIG. 1 are composed of target regions Q1 and Q2, target regions Q3 are detected in image 2, and target regions Q4 are detected in image 3.

[0089] Depend on Figure 3 As can be seen from the diagram in , in the above images, pixels at some positions will be covered by multiple target areas (indicating that target objects have been detected multiple times at these pixel positions), such as pixel i shown in the figure; pixels at some positions may be covered by only one target area (indicating that target objects have been detected only once at these pixel positions), such as pixel j shown in the figure; pixels at some other positions may not be covered by any target area (indicating that target objects have not been detected at these pixel positions), such as pixel k shown in the figure.

[0090] It is worth noting that the pixel in this article should be understood as the pixel corresponding to a certain position in the pixel coordinate system, and should not be understood as a certain pixel in a specific frame of the image. For example, taking the above pixel i as an example, pixel i refers to the pixel at Figure 3 The pixel at the same position in all the images shown in , in simple terms, these frames of images all contain the pixel i corresponding to the same position.

[0091] In this embodiment, the target pixel refers to a pixel covered by at least one of the above-mentioned multiple target areas, for example, pixel i and pixel j can both be used as the target pixel.

[0092] For any target pixel, first, at least one target area covering the target pixel is determined from all the obtained target areas. Figure 3 In the example, assuming that the target pixel is pixel i, the at least one target region includes target region Q1, target region Q3 and target region Q4. Then, the target physical size corresponding to the target pixel is determined according to the preset physical size of the target object and the pixel size corresponding to each of the at least one target region covering the target pixel.

[0093] There are several concepts involved here that need to be explained:

[0094] Preset physical size of the target object: The preset physical size of the target object includes the preset physical length of the target object in the preset direction, and the preset direction includes the length direction or the width direction. In simple terms, it refers to the value of the length or width of such target object obtained through pre-statistics. For example, for example, the average body width of a person is 50 cm.

[0095] The pixel size corresponding to the target area refers to the number of pixels contained in the target area corresponding to the preset direction. Figure 3 The pixel width of the target area Q1 is 50 (i.e., 50 pixels, commonly known as 50 pixel width), the pixel width of the target area Q2 is 60, the pixel width of the target area Q3 is 40, and the pixel width of the target area Q4 is 100.

[0096] The target physical size corresponding to the target pixel: refers to the physical length corresponding to the target pixel and the preset direction. In the above example of human body width, the target physical size of the target pixel is the actual physical length corresponding to the target pixel. It is worth noting that the word "target" in the target physical size here mainly emphasizes the physical size corresponding to the target pixel that is finally determined. In the process of determining the target physical size, it is also necessary to calculate the physical size of the target pixel for a certain target area, which can be considered as an intermediate variable.

[0097] Based on the above description of the concept, optionally, the target physical size corresponding to the target pixel can be determined in the following manner:

[0098] For any target area in at least one target area covering the target pixel, determining a quotient of a preset physical size of the target object and a pixel size corresponding to the any target area as the physical size corresponding to the target pixel in the any target area;

[0099] According to the physical sizes respectively corresponding to the target pixels in the at least one target area, a target physical size corresponding to the target pixel is determined.

[0100] Optionally, the target physical size corresponding to the target pixel may be determined as: an average value of physical sizes corresponding to the target pixels in the at least one target region.

[0101] For ease of explanation and understanding, Figure 3 The illustrated case is used as an example to illustrate. Assume that the target pixel is Figure 3 The target object is a person, and the average body width of a person is preset to be 50 cm. Figure 3 As shown in the diagram, the pixel width of the target area Q1 covering the pixel i is 50, the pixel width of the target area Q3 is 40, and the pixel width of the target area Q4 is 100.

[0102] For target area Q1, the physical size s1=50cm / 50=1cm corresponding to pixel i in target area Q1. Similarly, for target area Q3, the physical size s2=50cm / 40=1.25cm corresponding to pixel i in target area Q3. For target area Q4, the physical size s3=50cm / 100=0.5cm corresponding to pixel i in target area Q4.

[0103] Finally, by calculating the average of these three physical dimensions, the target physical dimension of pixel i can be obtained as: (1 cm + 1.25 cm + 0.5 cm) / 3 = 0.92 cm.

[0104] The above calculation process is performed on other pixels covered by one or more target areas, and the target physical size corresponding to each pixel covered by all target areas can be obtained.

[0105] Finally, the coverage area of ​​the camera can be determined based on the physical size of the target corresponding to all these pixels.

[0106] For example, the coverage area of ​​the camera can be determined as: the sum of the squares of the target physical lengths corresponding to the multiple target pixels. The multiple target pixels include all pixels covered by the multiple target areas. Taking pixel i as an example, the square of the target physical length corresponding to pixel i is used to represent the physical area corresponding to pixel i.

[0107] It can be seen from the above scheme that, assuming that the video used to determine the above coverage area is a video captured from time T1 to time T2, then the coverage area of ​​the camera obtained above can be considered as the effective coverage area of ​​the camera during this period. Assuming that the coverage area of ​​the camera from time T2 to T3 needs to be obtained, the coverage area of ​​the camera during this period can be further determined based on the video captured from time T1 to T3, so that the coverage area corresponding to the camera from time T1 to T3 is subtracted from the coverage area corresponding to the camera from time T1 to T2, and the coverage area corresponding to the camera from time T2 to T3 can be obtained.

[0108] In summary, when the purpose of deploying a camera is to focus on a certain type of target object, the above scheme can be used to determine the effective coverage area of ​​the camera. The coverage area determined by this scheme excludes the influence of the irrelevant factors mentioned above. Specifically, areas that cannot be clearly imaged in the image due to occlusion or lighting, as well as non-objects of interest, will not be detected as target areas during the detection of the target object, and thus will not be used as calculation objects for the coverage area. In addition, this scheme determines the coverage area directly based on the image taken by the camera, does not rely on the internal and external parameters of the camera, and also helps to improve the accuracy of the coverage area determination results.

[0109] Combine the following Figure 4 To illustrate the process of determining the coverage area of ​​a camera in an application scenario.

[0110] exist Figure 4 In the example, it is assumed that the target object is a person, and the camera C1 is deployed in a station platform to monitor the platform. In order to determine whether the actual coverage area of ​​the camera C1 can meet the required coverage area of ​​the platform, the coverage area of ​​the camera C1 needs to be calculated.

[0111] To this end, the video captured by the camera C1 within a period of time is obtained, and multiple frames of images are sampled therefrom. The target area containing the target object, i.e., a person, in each frame of the image is detected to obtain multiple target areas. For any pixel within the coverage range of the multiple target areas, the target physical length corresponding to the pixel is determined according to the pixel width corresponding to each of at least one target area covering the pixel and the preset average body width of the human body. The square sum of the target physical lengths corresponding to each of the pixels within the coverage range of the multiple target areas is calculated, and the calculation result is the coverage area of ​​the camera C1.

[0112] As mentioned above, the camera coverage detection method provided by the present invention can be executed in the cloud, and a number of computing nodes can be deployed in the cloud, each of which has computing, storage and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service, and of course, a computing node can also provide one or more services.

[0113] For the solution provided by the present invention, the cloud can provide a service for detecting camera coverage, which is called a target service. When a user needs to detect camera coverage, the target service is called to trigger a request to the cloud to call the target service, and the request carries a video captured by a camera. The cloud determines the computing node that responds to the request and uses the resources in the computing node to perform the following steps:

[0114] Sampling the video captured by the camera to obtain multiple frames of images;

[0115] Detecting target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects;

[0116] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object and a pixel size corresponding to each of at least one target area covering the target pixel;

[0117] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to the multiple target pixels.

[0118] The specific implementation methods of the above steps can refer to the relevant descriptions in other aforementioned embodiments and will not be repeated here.

[0119] The above embodiments introduce the situation where the camera is used to focus on only one type of target object. When it is necessary to focus on multiple types of target objects through the camera, the Figure 5 The solution provided by the illustrated embodiment.

[0120] Figure 5 A flowchart of a camera coverage detection method provided by an embodiment of the present invention, such as Figure 5 As shown, the method comprises the following steps:

[0121] 501. Sample the video captured by the camera to obtain multiple frames of images.

[0122] 502. Detect multiple types of target objects on multiple frames of images respectively to obtain multiple target regions corresponding to the multiple types of target objects.

[0123] 503. Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target objects.

[0124] 504. Determine a target physical size corresponding to a target pixel according to a preset physical size of a target object corresponding to each of the at least one group of target areas, a pixel size of a target area included in each of the at least one group of target areas, and the number of target areas included in each of the at least one group of target areas.

[0125] 505. Determine the coverage area of ​​the camera according to the target physical sizes corresponding to the multiple target pixels.

[0126] The solution provided in this embodiment is applicable to application scenarios where attention needs to be paid to multiple types of target objects captured by cameras. For example, in road traffic scenarios, relevant agencies such as traffic control need to pay attention to multiple types of target objects such as vehicles and people on the road.

[0127] In this embodiment, after the above-mentioned multiple frames of images are obtained according to the method described above, detection of preset multiple types of target objects is performed on each frame of image to determine the target area corresponding to each type of target object in each frame of image.

[0128] Similar to the scenario of detecting a single type of target object, optionally, multiple types of target objects may be detected on multiple frames of images respectively to obtain multiple rectangular areas containing any type of target object, and these rectangular areas are directly used as target areas.

[0129] Optionally, the lower area of ​​each rectangular area may be further cut out as the target area, wherein the height of the cut out lower area may be a preset ratio of the height of the corresponding rectangular area, and the preset ratio is less than 1.

[0130] It can be understood that, assuming that the multiple categories of target objects include the first category of target objects and the second category of target objects, in the process of acquiring the target area, it can be detected whether each frame of the image includes these two categories of target objects, and when they are included, the target area corresponding to each category of target objects can be determined. In this way, by summarizing the multiple target areas corresponding to the two categories of target objects in all images, all the target areas detected in all images are obtained. That is, assuming that the target areas corresponding to the first category of target objects detected in each frame of the image are summarized, N1 target areas are obtained; the target areas corresponding to the second category of target objects detected in each frame of the image are summarized, N2 target areas are obtained. Then, all the target areas detected in all images are composed of these N1 target areas and N2 target areas.

[0131] In this embodiment, since multiple types of target objects are concerned, at this time, the determination of the target physical size corresponding to a pixel needs to consider two factors: first, the number of occurrences of each type of target object at the pixel; second, the physical size of the pixel corresponding to each type of target object.

[0132] Since the influence of the first factor mentioned above needs to be considered, for a target pixel, at least one group of target areas covering the target pixel can be determined from all detected target areas, wherein a group of target areas corresponds to a type of target object. In other words, according to the inclusion relationship between each target area and the target pixel and the target object category corresponding to each target area, the target areas covering the target pixel and corresponding to the same target object category are determined as a group of target areas.

[0133] The target pixel may be a pixel at any position in the pixel coordinate system corresponding to the above-mentioned multiple frames of images, or simply referred to as a pixel at any position in the image.

[0134] Of course, it is understandable that for pixels at some positions, any type of target object covering the pixel may not be detected in all the multiple frames of images, and these pixels will not be used in the calculation process of the camera coverage area, and therefore can be ignored. Therefore, in this embodiment, the target pixel can be a pixel covered by one or more detected target areas, and the pixel not covered by any target area can be ignored.

[0135] After obtaining at least one group of target areas covering the target pixel, the target physical size corresponding to the target pixel can be determined based on the preset physical size of the target object corresponding to each of the at least one group of target areas, the pixel size of the target area each included in the at least one group of target areas, and the number of target areas each included in the at least one group of target areas.

[0136] Similar to the definition in the above embodiment, in this embodiment, the preset physical size of the target object includes a preset physical length in a preset direction of the target object, and the preset direction includes a length direction or a width direction. For example, when a certain type of target object is a person, the preset physical length may be the average body width of a human body: 50 cm. For another example, when a certain type of target object is a car, the preset physical length may be the average width of a car body: 160 cm.

[0137] Similarly, the pixel size corresponding to the target area includes: the number of pixels contained in the target area and corresponding to the preset direction, such as the pixel width of the target area.

[0138] The target physical size corresponding to the target pixel includes: the physical length of the target pixel corresponding to the preset direction.

[0139] Optionally, the process of determining the target physical size corresponding to the target pixel includes:

[0140] Determining physical sizes corresponding to target pixels under at least one type of target object according to preset physical sizes of target objects corresponding to the at least one group of target areas and pixel sizes of target areas included in the at least one group of target areas, wherein the at least one type of target object corresponds to the at least one group of target areas in a one-to-one manner;

[0141] Determining weights of physical sizes corresponding to target pixels of at least one type of target object according to the number of target areas included in each of the at least one group of target areas;

[0142] The physical sizes corresponding to the target pixels are weightedly summed according to the weights to determine the target physical size corresponding to the target pixel.

[0143] Wherein, optionally, according to the preset physical size of the target object corresponding to each of the at least one group of target areas and the pixel size of the target area respectively included in the at least one group of target areas, determining the physical size corresponding to each of the target pixels under at least one type of target object can be implemented as follows:

[0144] For any group of target areas among the at least one group of target areas, determining the quotient of the preset physical size of the target object corresponding to the any group of target areas and the pixel size of each target area included in the any group of target areas as the physical size corresponding to the target pixel in each target area;

[0145] According to the physical sizes respectively corresponding to the target pixels in the target areas, the physical sizes corresponding to the target pixels in the target object category corresponding to any group of target areas are determined.

[0146] Optionally, the physical size corresponding to the target pixel in the target object category corresponding to any group of target regions may be determined as: the average value of the physical sizes corresponding to the target pixel in each target region.

[0147] Optionally, determining the weights of the physical sizes respectively corresponding to the target pixels under at least one type of target object according to the number of target areas respectively included in the at least one group of target areas may be implemented as follows:

[0148] Determining a total number of target areas corresponding to the at least one group of target areas according to the number of target areas each included in the at least one group of target areas;

[0149] For any group of target areas in the at least one group of target areas, the weight of the physical size corresponding to the target pixel under the target object category corresponding to the any group of target areas is determined as: the ratio of the number of target areas included in the any group of target areas to the total number of target areas.

[0150] To facilitate understanding of the determination process of the target physical size corresponding to the target pixel, Figure 6 To illustrate by way of example.

[0151] exist Figure 6 In the above example, it is assumed that the above multi-frame images are Figure 6 Assume that the multi-class target objects include the following two types of target objects: people and cars. Assume that a target area Z1 containing people and a target area Z2 containing cars are detected in image a, a target area Z3 containing people is detected in image b, and a target area Z4 containing cars is detected in image c. Assume that the preset average body width of a human body is 50 cm and the average body width of a car is 160 cm. Assume that the pixel width of target area Z1 is 50, the pixel width of target area Z2 is 160, the pixel width of target area Z3 is 40, and the pixel width of target area Z4 is 200.

[0152] for Figure 6 For the pixel i shown in the figure, it is covered by the target area Z1, the target area Z3 and the target area Z4; for the pixel j, it is covered by the target area Z2 and the target area Z4.

[0153] Based on the above hypothetical situation, assuming that the target pixel is pixel i, for pixel i, since the target object category corresponding to target area Z1 and target area Z3 is "person", and the target object category corresponding to target area Z4 is "car", therefore, target area Z1 and target area Z3 constitute a group of target areas corresponding to pixel i, and target area Z4 serves as another group of target areas corresponding to pixel i.

[0154] The process of determining the physical length corresponding to pixel i in the category of "people" is as follows: first, the physical lengths corresponding to pixel i in target area Z1 and target area Z3 are determined according to the pixel widths corresponding to each of target area Z1 and target area Z3 and the preset average body width of the human body. Specifically, the physical length corresponding to pixel i in target area Z1 is: 50cm / 50=1cm, and the physical length corresponding to pixel i in target area Z3 is: 50cm / 40=1.25cm.

[0155] Based on the physical lengths corresponding to the pixel i in the above two target areas, the physical length corresponding to the pixel i in the "person" category is determined to be: (1cm+1.25cm) / 2=1.125cm, which is the average of the above two physical lengths.

[0156] Similarly, the process of determining the physical length corresponding to pixel i in the "car" category is as follows: since the only target area covering pixel i in the "car" category is target area Z4, the physical length corresponding to pixel i in the "car" category is the physical length corresponding to pixel i in target area Z4, specifically: 160cm / 200=0.8cm.

[0157] Since the target object categories covering pixel i include "people" and "cars", a group of target areas corresponding to the "people" category are target area Z1 and target area Z3, and the target area corresponding to the "car" category is target area Z4. Therefore, the weights of the physical lengths corresponding to pixel i in the two target object categories of "people" and "cars" are determined to be: 2 / 3, 1 / 3.

[0158] Based on the above weights and the physical lengths of 1.125 cm and 0.8 cm corresponding to pixel i in the two target object categories of "person" and "car" respectively, it is determined that the target physical length corresponding to pixel i is: 1.125*2 / 3+0.8*1 / 3=1.02 cm.

[0159] The above describes the process of determining the corresponding target physical length when the target pixel is pixel i.

[0160] Similarly, assuming that the target pixel is pixel j, for pixel j, target area Z2 and target area Z4 constitute a group of target areas corresponding to pixel j, and the corresponding target object category is "car".

[0161] The physical length corresponding to pixel j in target area Z2 is: 160 cm / 160 = 1 cm. The physical length corresponding to pixel j in target area Z4 is: 160 cm / 200 = 0.8 cm.

[0162] Since pixel j is only covered by the target area corresponding to the same target object category, the target physical length corresponding to pixel j is the average of the physical lengths corresponding to the multiple target areas covering it: (1 cm + 0.8 cm) / 2 = 0.9 cm.

[0163] For each pixel covered by each detected target area, the corresponding target physical length can be determined through the above process.

[0164] Finally, the coverage area of ​​the camera can be determined as: the sum of the squares of the physical lengths of the target corresponding to each of the plurality of target pixels, wherein the plurality of target pixels include all pixels covered by the entire target area.

[0165] In summary, when the purpose of deploying a camera is to focus on multiple types of target objects, the above scheme can be used to determine the effective coverage area of ​​the camera. The coverage area determined by this scheme excludes the influence of the irrelevant factors mentioned above. Specifically, areas that cannot be clearly imaged in the image due to occlusion and lighting, as well as non-objects of interest, will not be detected as target areas during the detection of target objects, and thus will not be used as calculation objects for the coverage area. In addition, this scheme determines the coverage area directly based on the image taken by the camera, does not rely on the internal and external parameters of the camera, and also helps to improve the accuracy of the coverage area determination results.

[0166] As mentioned above, the camera coverage detection method provided by the present invention can be executed in the cloud, and a number of computing nodes can be deployed in the cloud, each of which has computing, storage and other processing resources. In the cloud, multiple computing nodes can be organized to provide a certain service, and of course, a computing node can also provide one or more services.

[0167] For the solution provided by the present invention, the cloud can provide a service for detecting camera coverage, which is called a target service. When a user needs to detect camera coverage, the target service is called to trigger a request to the cloud to call the target service, and the request carries a video captured by a camera. The cloud determines the computing node that responds to the request and uses the resources in the computing node to perform the following steps:

[0168] Sampling the video captured by the camera to obtain multiple frames of images;

[0169] Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects;

[0170] Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target object;

[0171] Determining a target physical size corresponding to the target pixel according to a preset physical size of the target object corresponding to each of the at least one group of target areas, a pixel size of the target area included in each of the at least one group of target areas, and the number of target areas included in each of the at least one group of target areas;

[0172] The coverage area of ​​the camera is determined according to the target physical sizes corresponding to the multiple target pixels.

[0173] The specific implementation methods of the above steps can refer to the relevant descriptions in other aforementioned embodiments and will not be repeated here.

[0174] The following will describe in detail the camera coverage detection device of one or more embodiments of the present invention. Those skilled in the art will appreciate that these devices can be configured using commercially available hardware components through the steps taught in this solution.

[0175] Figure 7 A schematic diagram of the structure of a camera coverage detection device provided by an embodiment of the present invention is shown in FIG. Figure 7 As shown, the device includes: an image acquisition module 11, an object detection module 12, and an area determination module 13.

[0176] The image acquisition module 11 is used to sample the video captured by the camera to obtain multiple frames of images.

[0177] The object detection module 12 is used to detect target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects.

[0178] The area determination module 13 is used to determine the target physical size corresponding to the target pixel according to the preset physical size of the target object and the pixel size corresponding to at least one target area covering the target pixel; and determine the coverage area of ​​the camera according to the target physical size corresponding to each of the multiple target pixels.

[0179] Optionally, the multiple target pixels include all pixels covered by the multiple target areas.

[0180] Optionally, the preset physical size of the target object includes: a preset physical length in a preset direction of the target object, where the preset direction includes a length direction or a width direction; the pixel size corresponding to the target area includes: the number of pixels contained in the target area corresponding to the preset direction; the target physical size corresponding to the target pixel includes: the physical length of the target pixel corresponding to the preset direction.

[0181] Optionally, the area determination module 13 may be specifically configured to determine the coverage area of ​​the camera as the sum of squares of target physical lengths corresponding to each of the plurality of target pixels.

[0182] Optionally, the object detection module 12 can be specifically used to: detect target objects on the multiple frames of images respectively to obtain multiple rectangular areas containing the target objects; for each rectangular area, cut out the area from the bottom to a preset height; and determine the cut out multiple areas as the multiple target areas.

[0183] Optionally, the area determination module 13 can be specifically used to: for any target area in the at least one target area, determine the quotient of the preset physical size and the pixel size corresponding to the any target area as the physical size corresponding to the target pixel in the any target area; and determine the target physical size corresponding to the target pixel according to the physical sizes respectively corresponding to the target pixel in the at least one target area.

[0184] Optionally, the area determination module 13 may be specifically configured to: determine the target physical size corresponding to the target pixel as: an average value of the physical sizes corresponding to the target pixel in the at least one target area.

[0185] Figure 7 The device shown can perform the aforementioned Figures 1 to 4 The camera coverage range detection method provided in the illustrated embodiment, the detailed execution process and technical effects can be found in the description of the aforementioned embodiment, which will not be repeated here.

[0186] In one possible design, the above Figure 7 The structure of the camera coverage detection device shown can be implemented as an electronic device, such as Figure 8 As shown, the electronic device may include: a first processor 21 and a first memory 22. The first memory 22 stores executable code. When the executable code is executed by the first processor 21, the first processor 21 can at least implement the above-mentioned Figures 1 to 4 The camera coverage range detection method provided in the illustrated embodiment.

[0187] Optionally, the electronic device may further include a first communication interface 23 for communicating with other devices.

[0188] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein an executable code is stored on the non-transitory machine-readable storage medium. When the executable code is executed by a processor of an electronic device, the processor can at least implement the above-mentioned Figures 1 to 4 The camera coverage range detection method provided in the illustrated embodiment.

[0189] Fig. 9 A schematic diagram of the structure of a camera coverage detection device provided by an embodiment of the present invention is shown in FIG. Fig. 9 As shown, the device includes: an image acquisition module 31, an object detection module 32, a region selection module 33, and an area determination module 34.

[0190] The image acquisition module 31 is used to sample the video acquired by the camera to obtain multiple frames of images.

[0191] The object detection module 32 is used to detect multiple types of target objects on the multiple frames of images respectively, so as to obtain multiple target areas corresponding to the multiple types of target objects.

[0192] The region selection module 33 is used to determine at least one group of target regions covering target pixels from the multiple target regions, wherein a group of target regions corresponds to a type of target object.

[0193] The area determination module 34 is used to determine the target physical size corresponding to the target pixel according to the preset physical size of the target object corresponding to each of the at least one group of target areas, the pixel size of the target area contained in each of the at least one group of target areas, and the number of target areas contained in each of the at least one group of target areas; and determine the coverage area of ​​the camera according to the target physical size corresponding to each of the multiple target pixels.

[0194] Optionally, the multiple target pixels include all pixels covered by the multiple target areas.

[0195] Optionally, the preset physical size of the target object includes: a preset physical length in a preset direction of the target object, where the preset direction includes a length direction or a width direction; the pixel size corresponding to the target area includes: the number of pixels contained in the target area corresponding to the preset direction; the target physical size corresponding to the target pixel includes: the physical length of the target pixel corresponding to the preset direction.

[0196] Optionally, the area determination module 34 may be specifically configured to determine the coverage area of ​​the camera as the sum of squares of target physical lengths corresponding to each of the plurality of target pixels.

[0197] Optionally, the object detection module 32 can be specifically used to: detect multiple types of target objects on the multiple frames of images respectively to obtain multiple rectangular areas containing any type of target objects; for each of the multiple rectangular areas, cut out the area from the bottom to a preset height; determine the multiple cut-out areas as multiple target areas corresponding to any type of target objects.

[0198] Optionally, the area determination module 34 can be specifically used to: determine the physical sizes corresponding to the target pixels under at least one type of target object according to preset physical sizes of the target objects corresponding to each of the at least one group of target areas and the pixel sizes of the target areas contained in each of the at least one group of target areas, wherein the at least one type of target object corresponds one-to-one to the at least one group of target areas; determine the weights of the physical sizes corresponding to the target pixels under at least one type of target object according to the number of target areas contained in each of the at least one group of target areas; and perform weighted summation of the physical sizes corresponding to the target pixels according to the weights to determine the target physical size corresponding to the target pixels.

[0199] Optionally, the area determination module 34 can be specifically used to: for any group of target areas among the at least one group of target areas, determine the quotient of a preset physical size of the target object corresponding to the any group of target areas and the pixel size of each target area included in the any group of target areas as the physical size corresponding to the target pixel in each target area; and determine the physical size corresponding to the target pixel under the target object category corresponding to the any group of target areas based on the physical sizes corresponding to the target pixel in each target area.

[0200] Optionally, the area determination module 34 may be specifically configured to determine that the physical size corresponding to the target pixel in the target object category corresponding to any group of target regions is: the average of the physical sizes corresponding to the target pixel in each target region.

[0201] Optionally, the area determination module 34 can be specifically used to: determine the total number of target areas corresponding to the at least one group of target areas according to the number of target areas contained in each of the at least one group of target areas; for any group of target areas in the at least one group of target areas, determine that the weight of the physical size corresponding to the target pixel under the target object category corresponding to the any group of target areas is: the ratio of the number of target areas contained in any group of target areas to the total number of target areas.

[0202] Fig. 9 The device shown can perform the aforementioned Figures 5 and 6 The camera coverage range detection method provided in the illustrated embodiment, the detailed execution process and technical effects can be found in the description of the aforementioned embodiment, which will not be repeated here.

[0203] In one possible design, the above Fig. 9 The structure of the camera coverage detection device shown can be implemented as an electronic device, such as Fig.10As shown, the electronic device may include: a second processor 41 and a second memory 42. The second memory 42 stores executable code. When the executable code is executed by the second processor 41, the second processor 41 can at least implement the above-mentioned Figures 5 and 6 A camera coverage range detection method is provided in an embodiment.

[0204] Optionally, the electronic device may further include a second communication interface 43 for communicating with other devices.

[0205] In addition, an embodiment of the present invention provides a non-transitory machine-readable storage medium, wherein an executable code is stored on the non-transitory machine-readable storage medium. When the executable code is executed by a processor of an electronic device, the processor can at least implement the above-mentioned Figures 5 and 6 A camera coverage range detection method is provided in an embodiment.

[0206] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0207] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A camera coverage detection method, characterized in that: include: Sampling the video captured by the camera to obtain multiple frames of images; Detecting target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects; For any target area in at least one target area covering the target pixel, a quotient of a preset physical size of the target object and a pixel size corresponding to the any target area is used as a physical size corresponding to the target pixel in the any target area; Determine a target physical size corresponding to the target pixel according to physical sizes respectively corresponding to the target pixel in the at least one target area; Determine the physical area corresponding to each of the pixels covered by the multiple target areas according to the target physical size corresponding to each of the pixels, and determine the coverage area of ​​the camera according to the physical area corresponding to each of the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

2. The method according to claim 1, characterized in that The preset physical size of the target object includes: a preset physical length of the target object in a preset direction, wherein the preset direction includes a length direction or a width direction; The pixel size corresponding to the target area includes: the number of pixels contained in the target area corresponding to the preset direction; The target physical size corresponding to the target pixel includes: a physical length of the target pixel corresponding to the preset direction.

3. The method according to claim 2, characterized in that The determining the coverage area of ​​the camera according to the target physical size corresponding to each of the plurality of target pixels includes: The coverage area of ​​the camera is determined as: the sum of the squares of the target physical lengths corresponding to the plurality of target pixels.

4. The method according to claim 1, characterized in that: The detecting of target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects includes: Detecting target objects on the multiple frames of images respectively to obtain multiple rectangular areas containing the target objects; For each rectangular area, cut out the area from the bottom to the preset height; The multiple cut-out regions are determined as the multiple target regions.

5. The method according to claim 1, characterized in that Determining the target physical size corresponding to the target pixel according to the physical sizes respectively corresponding to the target pixel in the at least one target area includes: The target physical size corresponding to the target pixel is determined as: an average value of physical sizes respectively corresponding to the target pixels in the at least one target area.

6. A camera coverage detection method, characterized in that: include: Sampling the video captured by the camera to obtain multiple frames of images; Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects; Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target object; Determining the physical sizes corresponding to the target pixels under at least one type of target object according to the preset physical sizes of the target objects corresponding to the at least one group of target areas and the pixel sizes of the target areas included in the at least one group of target areas; Determining, according to the number of target areas respectively included in the at least one group of target areas, the weights of the physical sizes respectively corresponding to the target pixels under at least one type of target object; Performing weighted summation of the physical sizes corresponding to the target pixels respectively according to the weights to determine the target physical size corresponding to the target pixel; Determine the physical area corresponding to each of the pixels covered by the multiple target areas according to the target physical size corresponding to each of the pixels, and determine the coverage area of ​​the camera according to the physical area corresponding to each of the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

7. The method according to claim 6, characterized in that The preset physical size of the target object includes: a preset physical length of the target object in a preset direction, wherein the preset direction includes a length direction or a width direction; The pixel size corresponding to the target area includes: the number of pixels contained in the target area corresponding to the preset direction; The target physical size corresponding to the target pixel includes: a physical length of the target pixel corresponding to the preset direction.

8. The method according to claim 7, characterized in that The determining the coverage area of ​​the camera according to the target physical size corresponding to each of the plurality of target pixels includes: The coverage area of ​​the camera is determined as: the sum of the squares of the target physical lengths corresponding to the plurality of target pixels.

9. The method according to claim 6, characterized in that The detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects respectively includes: Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple rectangular areas containing any type of target objects; For each of the plurality of rectangular areas, cutting out an area from the bottom to a preset height; The multiple intercepted regions are determined as multiple target regions corresponding to any type of target object.

10. The method according to claim 6, characterized in that The determining, according to the preset physical size of the target object corresponding to each of the at least one group of target areas and the pixel size of the target area included in each of the at least one group of target areas, the physical size corresponding to each of the target pixels under at least one type of target object comprises: For any group of target areas among the at least one group of target areas, determining the quotient of the preset physical size of the target object corresponding to the any group of target areas and the pixel size of each target area included in the any group of target areas as the physical size corresponding to the target pixel in each target area; According to the physical sizes respectively corresponding to the target pixels in the target areas, the physical sizes corresponding to the target pixels in the target object categories corresponding to any group of target areas are determined.

11. The method according to claim 10, characterized in that Determining the physical size corresponding to the target pixel in the target object category corresponding to any group of target areas according to the physical sizes respectively corresponding to the target pixels in the target areas includes: The physical size corresponding to the target pixel under the target object category corresponding to any one group of target regions is determined as: the average value of the physical sizes corresponding to the target pixel in each target region.

12. The method according to claim 6, characterized in that The determining, according to the number of target areas respectively included in the at least one group of target areas, the weights of the physical sizes respectively corresponding to the target pixels under at least one type of target object comprises: Determining a total number of target areas corresponding to the at least one group of target areas according to the number of target areas each included in the at least one group of target areas; For any group of target areas in the at least one group of target areas, the weight of the physical size corresponding to the target pixel under the target object category corresponding to the any group of target areas is determined as: the ratio of the number of target areas included in the any group of target areas to the total number of target areas.

13. A camera coverage detection device, characterized in that: include: An image acquisition module is used to sample the video captured by the camera to obtain multiple frames of images; An object detection module, used to detect target objects on the multiple frames of images respectively, so as to obtain multiple target areas containing the target objects; an area determination module, configured to determine, for any target area in at least one target area covering a target pixel, a quotient of a preset physical size of the target object and a pixel size corresponding to the any target area as a physical size corresponding to the target pixel in the any target area, and determine a target physical size corresponding to the target pixel according to the physical sizes respectively corresponding to the target pixel in the at least one target area; And, according to the target physical sizes corresponding to all the pixels covered by the multiple target areas, determining the physical areas corresponding to all the pixels, and determining the coverage area of ​​the camera according to the physical areas corresponding to all the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

14. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the camera coverage range detection method as described in any one of claims 1 to 5.

15. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor executes the camera coverage range detection method as described in any one of claims 1 to 5.

16. A camera coverage detection device, characterized in that: include: An image acquisition module is used to sample the video captured by the camera to obtain multiple frames of images; An object detection module is used to detect multiple types of target objects on the multiple frames of images respectively, so as to obtain multiple target areas corresponding to the multiple types of target objects; A region selection module, configured to determine at least one group of target regions covering target pixels from the plurality of target regions, wherein the group of target regions corresponds to a type of target object; An area determination module, for determining the physical sizes corresponding to the target pixels under at least one type of target object according to the preset physical sizes of the target objects corresponding to the at least one group of target areas and the pixel sizes of the target areas respectively included in the at least one group of target areas, and for determining the weights of the physical sizes corresponding to the target pixels under at least one type of target object according to the number of target areas respectively included in the at least one group of target areas, and for performing weighted summation of the physical sizes corresponding to the target pixels according to the weights to determine the target physical sizes corresponding to the target pixels; and for determining the physical areas corresponding to all the pixels covered by the multiple target areas according to the target physical sizes corresponding to all the pixels, and for determining the coverage area of ​​the camera according to the physical areas corresponding to all the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

17. An electronic device, characterized in that: include: A memory and a processor; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the camera coverage range detection method as described in any one of claims 6 to 12.

18. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor executes the camera coverage range detection method as described in any one of claims 6 to 12.

19. A camera coverage detection method, characterized in that: include: Receive a request to call a target service, wherein the request includes a video captured by a camera; Use the resources corresponding to the target service to perform the following steps: Sampling the video captured by the camera to obtain multiple frames of images; Detecting target objects on the multiple frames of images respectively to obtain multiple target areas containing the target objects; For any target area in at least one target area covering the target pixel, a quotient of a preset physical size of the target object and a pixel size corresponding to the any target area is used as a physical size corresponding to the target pixel in the any target area; Determine a target physical size corresponding to the target pixel according to physical sizes respectively corresponding to the target pixel in the at least one target area; Determine the physical area corresponding to each of the pixels covered by the multiple target areas according to the target physical size corresponding to each of the pixels, and determine the coverage area of ​​the camera according to the physical area corresponding to each of the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

20. A camera coverage detection method, characterized in that: include: Receive a request to call a target service, wherein the request includes a video captured by a camera; Use the resources corresponding to the target service to perform the following steps: Sampling the video captured by the camera to obtain multiple frames of images; Detecting multiple types of target objects on the multiple frames of images respectively to obtain multiple target areas corresponding to the multiple types of target objects; Determine at least one group of target areas covering target pixels from the multiple target areas, wherein the group of target areas corresponds to a type of target object; Determine the physical sizes corresponding to the target pixels under at least one type of target object according to preset physical sizes of the target objects corresponding to the at least one group of target areas and the pixel sizes of the target areas included in the at least one group of target areas, determine the weights of the physical sizes corresponding to the target pixels under at least one type of target object according to the number of target areas included in the at least one group of target areas, and perform weighted summation of the physical sizes corresponding to the target pixels according to the weights to determine the target physical size corresponding to the target pixels; Determine the physical area corresponding to each of the pixels covered by the multiple target areas according to the target physical size corresponding to each of the pixels, and determine the coverage area of ​​the camera according to the physical area corresponding to each of the pixels; The preset physical size, the pixel size and the target physical size correspond to the same size measurement direction.

Images