Monitoring point location selection method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention discloses a monitoring point location selection method and device, electronic equipment and a readable storage medium, after multiple monitoring videos sent by multiple monitoring point locations are received, the monitoring content of each monitoring video can be analyzed to obtain a video analysis result corresponding to each monitoring point location. Then, a genetic algorithm, a preset constraint condition and a pre-constructed target function can be utilized to automatically process the video analysis result corresponding to each monitoring point location so as to obtain an optimal selection result of the monitoring point locations, so that the screening efficiency of the monitoring point locations can be improved. Meanwhile, the target of the target function comprises the number of the target objects corresponding to the monitoring point position which is selected to the maximum, so that compared with other selection results of the monitoring point positions which meet the preset constraint condition, the number of the target objects corresponding to the optimal selection result of the monitoring point position is the maximum; therefore, the monitoring effect generated by the selected monitoring point location can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of monitoring technology, and in particular to a method, device, electronic device and readable storage medium for selecting monitoring points. Background Art

[0002] In scenes with a large number of people (such as campus scenes), when monitoring the movement trajectories of people, it is necessary to use multiple monitoring points (with cameras installed at the monitoring points) to capture the positions of people in real time, and then analyze the positions of people at each time to generate the movement trajectories of people.

[0003] However, when selecting appropriate monitoring points from multiple monitoring points in a specific scene, currently, the monitoring videos generated by each monitoring point are generally manually viewed, and manually detected and screened, so as to screen out the monitoring videos that meet the preset conditions, and then select the corresponding monitoring points. For example, the monitoring video that meets the preset conditions is that, when the number of selected monitoring points is less than the preset number, the sum of the number of target objects (specifically, the target objects may be people) that can be monitored by the selected monitoring points is the largest, so as to achieve the best monitoring effect.

[0004] When there are a huge number of monitoring points, manual detection and screening of surveillance videos is not only inefficient, but also the monitoring effects of the selected monitoring points are often poor due to the unscientific and unreasonable selection methods. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and readable storage medium for selecting monitoring points, which can not only improve the screening efficiency of monitoring points, but also improve the monitoring effect produced by the selected monitoring points.

[0006] In a first aspect, an embodiment of the present application provides a method for selecting a monitoring point, including:

[0007] Receiving multiple surveillance videos sent by multiple surveillance points; the multiple surveillance videos all include surveillance content within a preset time period;

[0008] Analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0009] Using a genetic algorithm, preset constraints and a pre-constructed objective function, the video analysis results corresponding to each of the monitoring points are processed to obtain an optimal selection result of the monitoring points;

[0010] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0011] Optionally, the preset constraint condition includes: the number of the selected monitoring points is less than a first preset number.

[0012] Optionally, the preset constraint condition includes: the shooting range of the selected monitoring points can cover a preset geographical range.

[0013] Optionally, the method includes: receiving a configuration file sent by a user terminal, and configuring the type of the genetic algorithm and / or the preset geographical range according to the configuration file.

[0014] Optionally, the objective of the objective function includes: minimizing the number of selected monitoring points.

[0015] Optionally, the video analysis result also includes the picture quality of the surveillance video; the objective of the objective function also includes: optimizing the average picture quality of the surveillance video corresponding to the selected surveillance points.

[0016] Optionally, after analyzing the monitoring contents of each monitoring video to obtain the video analysis results corresponding to each monitoring point, the method further includes: screening the video analysis results corresponding to each monitoring point according to a preset rule to obtain a screened video analysis result; wherein the preset rule includes: the number of target objects appearing within a preset time period is greater than a second preset number, and / or the picture quality of the monitoring video is higher than a preset quality standard;

[0017] The processing of the video analysis results corresponding to each of the monitoring points includes: processing the screened video analysis results.

[0018] Optionally, the genetic algorithm is a multi-objective genetic algorithm;

[0019] The method of processing the video analysis results corresponding to each monitoring point by using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain the optimal selection result of the monitoring point includes:

[0020] According to the preset constraint conditions and the multi-objective genetic algorithm, obtaining the initial selection result of the monitoring point;

[0021] Based on the initial selection results of the monitoring points, at least one optimized selection result of the monitoring points is obtained through selection, crossover, mutation and elite retention mechanisms in population evolution;

[0022] According to a pre-constructed objective function, performing fitness evaluation on at least one optimization selection result of the monitoring point to generate a fitness evaluation result;

[0023] According to the fitness evaluation result, the optimal selection result of the monitoring point is determined.

[0024] In a second aspect, an embodiment of the present application provides a method for selecting a monitoring point, which is applied to a terminal device, comprising: receiving a plurality of monitoring videos sent by a plurality of monitoring points; the plurality of monitoring videos all include monitoring content within a preset time period;

[0025] Analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0026] Sending the video analysis results corresponding to each of the monitoring points to the server, so that the server can process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain the optimal selection result of the monitoring point;

[0027] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0028] Optionally, the video analysis result also includes the picture quality of the monitoring video.

[0029] In a third aspect, an embodiment of the present application provides a device for selecting a monitoring point, including:

[0030] A first receiving module is used to receive multiple monitoring videos sent by multiple monitoring points; the multiple monitoring videos all include monitoring content within a preset time period;

[0031] An analysis module, used to analyze the monitoring content of each monitoring video to obtain a video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0032] A processing module, used to process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-constructed objective function, so as to obtain an optimal selection result of the monitoring points;

[0033] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0034] In a fourth aspect, an embodiment of the present application provides a monitoring point selection device, which is arranged in a terminal device, and includes:

[0035] A first receiving module is used to receive multiple monitoring videos sent by multiple monitoring points; the multiple monitoring videos all include monitoring content within a preset time period;

[0036] An analysis module, used to analyze the monitoring content of each monitoring video to obtain a video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0037] A sending module, used for sending the video analysis results corresponding to each of the monitoring points to the server, so that the server can process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-built objective function to obtain the optimal selection result of the monitoring points;

[0038] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0039] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the aforementioned method for selecting monitoring points.

[0040] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the aforementioned method for selecting monitoring points is implemented.

[0041] The monitoring point selection method, device, electronic device and readable storage medium provided in the embodiments of the present application can analyze the monitoring content of each monitoring video after receiving multiple monitoring videos sent by multiple monitoring points to obtain the video analysis results corresponding to each monitoring point. Then, the video analysis results corresponding to each monitoring point can be automatically processed using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain the optimal selection result of the monitoring point, thereby improving the screening efficiency of the monitoring point. At the same time, since the goal of the objective function includes maximizing the number of target objects corresponding to the selected monitoring point, the number of target objects corresponding to the optimal selection result of the monitoring point is the largest compared to other selection results of the monitoring point that meets the preset constraints, thereby improving the monitoring effect of the selected monitoring point. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a schematic diagram of an implementation environment applicable to the method for selecting monitoring points provided in an embodiment of the present application;

[0044] Figure 2 This is a flow chart of a method for selecting monitoring points provided in an embodiment of the present application;

[0045] Figure 3 This is another schematic diagram of an implementation environment applicable to the method for selecting monitoring points provided in the embodiment of the present application;

[0046] Figure 4 This is a structural schematic diagram of a monitoring point selection device provided in an embodiment of the present application;

[0047] Figure 5 This is another structural schematic diagram of the monitoring point selection device provided in the embodiment of the present application;

[0048] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] At present, for security reasons, video surveillance equipment is increasingly being used in people's daily lives. In order to improve the monitoring effect, when selecting appropriate monitoring points from multiple monitoring points in a specific scene, it is generally done by manually viewing the monitoring videos generated by each monitoring point, and performing manual detection and screening to select appropriate monitoring points to meet the user's monitoring needs.

[0050] However, when there are a huge number of monitoring points, manual detection and screening of surveillance videos is not only inefficient, but also the monitoring effects of the selected monitoring points are often poor due to the unscientific and unreasonable selection methods.

[0051] Based on this, the embodiments of the present application provide a method, device, electronic device and readable storage medium for selecting monitoring points to improve the screening efficiency of monitoring points and the monitoring effect produced by the selected monitoring points.

[0052] Figure 1 This is a schematic diagram of the implementation environment applicable to the method for selecting monitoring points provided in the embodiment of the present application. Figure 1The implementation environment may include multiple monitoring points, each of which is provided with a camera 11, which can record monitoring videos of the surrounding environment. When a person enters the monitoring range of the camera 11, the monitoring video will include relevant images of the person.

[0053] The implementation environment may also include a monitoring point selection system 12. Exemplarily, the monitoring point selection system 12 specifically includes a terminal device 121 or a server 122. In addition, the monitoring point selection system 12 may also include a terminal device 121 and a server 122 at the same time. Figure 1 shown.

[0054] The terminal device 121 can be a smart interactive tablet, a laptop computer, a desktop computer, a mobile phone, a tablet computer or an edge smart terminal, etc., which is not limited in the embodiments of the present application.

[0055] The server 122 may be an independent physical server, a server cluster consisting of multiple servers, or a cloud server with cloud computing capabilities, etc., which is not limited by the embodiments of the present application.

[0056] Below, based on Figure 1 The implementation environment shown is used to describe in detail the method for selecting monitoring points in the embodiment of the present application. For example, the method for selecting monitoring points provided in the embodiment of the present application can be performed jointly by the terminal device 121 and the server 122, such as Figure 2 It is understandable that the monitoring point selection method provided in the embodiment of the present application can also be executed by the terminal device 121 or the server 122 alone, and the specific implementation principle has no substantial difference.

[0057] like Figure 2 As shown, the method for selecting monitoring points provided in the embodiment of the present application may include the following steps:

[0058] S21. The terminal device 121 receives multiple monitoring videos sent from multiple monitoring points; wherein the multiple monitoring videos all include monitoring contents within a preset time period.

[0059] For example, in a campus scenario, 100 monitoring points are respectively set at different locations of the campus, each monitoring point is set with a camera 11, and all cameras 11 are connected to the terminal device 121 through a wired network or a wireless network. Each camera 11 can record monitoring video of the surrounding environment in real time and send the monitoring video to the terminal device 121. Specifically, the camera 11 can send the monitoring video to the terminal device 121 according to the Real-time Streaming Protocol (RTSP).

[0060] The monitoring video selected in the embodiment of the present application may include monitoring content within a preset time period. Specifically, the user can set the specific time range of the preset time period according to actual needs. For example, the actual need of the user is to monitor the campus when the school is in session. Accordingly, the user can set the 24 hours of a certain day that is in session in the near future as the preset time period.

[0061] S22, the terminal device 121 analyzes the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point, and sends it to the server 122.

[0062] Correspondingly, the server 122 will receive multiple video analysis results corresponding to multiple monitoring points.

[0063] In this step, the terminal device 121 can analyze the monitoring content of each monitoring video, so as to obtain the video analysis results corresponding to each monitoring point, and the video analysis results may include the number of target objects monitored by the monitoring point within a preset period of time. The target object can be any object in a stationary state or an object in a moving state, such as a tree or a moving vehicle. The embodiment of the present application does not limit the type of the target object. The following is a detailed description of the case where the target object is a person.

[0064] Using the previous example, the 100 monitoring points are monitoring point 1, monitoring point 2, monitoring point 3, and finally monitoring point 100. In the video analysis results corresponding to monitoring point 1, the number of people appearing in the preset time period is 100, and in the video analysis results corresponding to monitoring points 2 to 10, the number of people appearing in the preset time period is 80, 120, 90, 110, 85, 95, 105, 75, and 115 respectively.

[0065] S23, the server 122 uses a genetic algorithm, preset constraints and a pre-constructed objective function to process the video analysis results corresponding to each of the monitoring points to obtain the optimal selection results of the monitoring points; wherein the goal of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0066] In this step, the genetic algorithm is a meta-heuristic algorithm inspired by the natural selection process and belongs to the general category of evolutionary algorithms. Genetic algorithms usually rely on biologically inspired operators such as mutation, crossover, and selection to generate high-quality solutions to optimization and search problems. Users can set the type and constraints of the genetic algorithm in advance according to their actual needs, as well as the goal of the objective function.

[0067] After receiving multiple video analysis results, the server 122 can automatically process each video analysis result using a genetic algorithm, preset constraints, and a pre-constructed objective function to obtain an optimal selection result of a monitoring point according to the number of target objects corresponding to each video analysis result, and the optimal selection result meets the preset constraints. Since the goal of the objective function includes maximizing the number of target objects corresponding to the selected monitoring point, compared with other selection results of monitoring points that meet the preset constraints, the number of target objects corresponding to the optimal selection result of the monitoring point is the largest, so the best monitoring effect can be achieved.

[0068] The embodiment of the present application provides a method for selecting monitoring points. After receiving multiple monitoring videos sent by multiple monitoring points, the monitoring content of each monitoring video can be analyzed to obtain the video analysis results corresponding to each monitoring point. Then, the video analysis results corresponding to each monitoring point can be automatically processed using a genetic algorithm, preset constraints, and a pre-constructed objective function to obtain the optimal selection result of the monitoring point, thereby improving the screening efficiency of the monitoring point. At the same time, since the goal of the objective function includes maximizing the number of target objects corresponding to the selected monitoring point, the number of target objects corresponding to the optimal selection result of the monitoring point is the largest compared to other selection results of the monitoring point that meets the preset constraints, thereby improving the monitoring effect of the selected monitoring point.

[0069] The user can set the constraint conditions according to their actual needs to limit the number of monitoring points. Therefore, in some embodiments of the present application, the preset constraint conditions may include: the number of the selected monitoring points is less than the first preset number.

[0070] Using the previous example, the total number of monitoring points is 100, and the user can set the first preset number to 70, so that the number of selected monitoring points should be less than 70, so that the optimal selection result of the monitoring points that meets the constraint condition can be obtained. Compared with other possible selection results of monitoring points that meet the constraint condition, the number of target objects corresponding to the optimal selection result of the monitoring point is the largest, so the best monitoring effect can be achieved.

[0071] It is understandable that, in addition to the optimal selection result of monitoring points, any monitoring point selection scheme where the number of selected monitoring points is less than 70 belongs to other possible selection results of monitoring points described herein, for example, all possible selection schemes where the number of monitoring points is 69, all possible selection schemes where the number of monitoring points is 68, all possible selection schemes where the number of monitoring points is 67, etc.

[0072] In some embodiments of the present application, when setting constraints, the user can select the corresponding geographical range in advance according to the actual needs of the monitoring range, and set the shooting range of the selected monitoring points to cover the above geographical range as a constraint. In this way, the optimal selection result of the monitoring points obtained according to the constraint can meet the above constraint.

[0073] In one example, a user hopes to monitor the entire campus in all directions without blind spots. Therefore, the shooting range of the selected monitoring points can be set as a constraint condition to cover the geographical range of the entire campus.

[0074] In another example, the user focuses on the situation of students participating in sports activities on the playground in the campus. Therefore, the shooting range of the selected monitoring points can be set as a constraint condition to cover the geographical range of the playground in the campus.

[0075] In addition, the user can also set multiple constraints at the same time, so that the optimal selection result of the monitoring point can meet multiple constraints at the same time. The embodiment of the present application does not limit the number of constraints.

[0076] In some embodiments of the present application, Figure 3 As shown, the user terminal 13 can be connected to the server 122 in communication, and the two can be connected through a wired network or a wireless network. The user terminal 13 can be a laptop, desktop, mobile phone or other electronic device used by the user.

[0077] The user can configure the relevant parameters in the configuration file according to his actual needs at the user terminal 13, and send the corresponding configuration file to the server 122 through the user terminal 13, so that the server 13 can configure the type of genetic algorithm according to the configuration file. In turn, the server 13 can obtain the optimal acquisition result of the corresponding monitoring point according to the genetic algorithm configured by the user. Among them, the genetic algorithm can be specifically a multi-objective heuristic algorithm, a multi-objective genetic algorithm or an ant colony algorithm, etc., and the embodiment of the present application does not limit the type of genetic algorithm.

[0078] Similarly, the user can also send a corresponding configuration file to the server 122 through the user terminal 13, so that the server 13 can configure the preset geographical range according to the corresponding parameters in the configuration file. Then, the server 13 can obtain the optimal acquisition result of the corresponding monitoring point according to the geographical range configured by the user. In addition, the user can also configure the size of the first preset number in the same way. The specific configuration method can refer to the previous description content and will not be described in detail here.

[0079] In this way, the user can configure the above parameters conveniently and flexibly in the user terminal 13 according to his actual needs, so as to obtain the optimal selection result of the monitoring points that meet his actual needs.

[0080] It can be understood that when the monitoring point selection method provided in the embodiment of the present application is executed separately by the terminal device 121 or the server 122, the user terminal 13 can be communicated with the terminal device 121 or the server 122, and the corresponding configuration file sent to the terminal device 121 or the server 122. The implementation principle is the same as the above description and will not be described in detail here.

[0081] In some embodiments of the present application, when the user needs to use as few monitoring points as possible for economic cost considerations, the objective of the objective function can be set to minimize the number of selected monitoring points. In this way, the number of selected monitoring points can be minimized in the optimal selection result of monitoring points, thereby minimizing the economic cost of the user.

[0082] It should be noted that the embodiment of the present application can obtain multiple selection results of monitoring points based on the two goals of maximizing the number of target objects corresponding to the selected monitoring points and minimizing the number of selected monitoring points. Then, the multiple selection results of the monitoring points are evaluated, and the advantages and disadvantages of the multiple selection results are judged based on the evaluation results, and then the optimal selection result of the monitoring points can be determined. The present application does not limit the specific implementation of the evaluation method.

[0083] In some embodiments of the present application, the video analysis result may also include the picture quality of the surveillance video. The picture quality of the surveillance video refers to the picture clarity of the surveillance video. The higher the picture clarity, the higher the picture quality of the surveillance video.

[0084] If the user attaches great importance to the clarity of the surveillance video and hopes that the average picture quality of the surveillance video corresponding to the selected surveillance point is as high as possible, the target in the objective function can be set to optimize the average picture quality of the surveillance video corresponding to the selected surveillance point. In this way, in the optimal selection result of the surveillance point, the average picture quality of the surveillance video corresponding to the selected surveillance point is as high as possible, thereby satisfying the user's demand for surveillance picture clarity to the greatest extent.

[0085] It should be noted that the objective in the objective function may include, in addition to optimizing the average picture quality of the monitoring video corresponding to the selected monitoring points, minimizing the number of selected monitoring points. In addition, the objective in the objective function may also include maximizing the number of target objects corresponding to the selected monitoring points. Based on the above requirements, the embodiment of the present application can obtain multiple selection results for monitoring points. Then, the multiple selection results for monitoring points are evaluated, and based on the evaluation results, the pros and cons of the multiple selection results are judged, and then the optimal selection result for the monitoring points can be determined. This application does not limit the specific implementation method of the evaluation method.

[0086] For example, there are currently four results for selecting monitoring points, namely the first selection result, the second selection result, the third selection result, and the fourth selection result. In the first selection result, the number of selected monitoring points is 50, the average picture quality of the monitoring video is 0.83, and the sum of the number of target objects corresponding to the 50 monitoring points is 55,000. In the second selection result, the number of selected monitoring points is 48, the average picture quality of the monitoring video is 0.85, and the sum of the number of target objects corresponding to the 48 monitoring points is 53,000. In the third selection result, the number of selected monitoring points is 52, the average picture quality of the monitoring video is 0.81, and the sum of the number of target objects corresponding to the 52 monitoring points is 57,000. In the fourth selection result, the number of selected monitoring points is 49, the average picture quality of the monitoring video is 0.84, and the sum of the number of target objects corresponding to the 49 monitoring points is 54,000. By evaluating the above four selection results and based on the evaluation results, the optimal selection result of the monitoring points can be determined. Users can select corresponding evaluation methods according to their actual needs. When users adopt different evaluation methods, the optimal selection results of monitoring points will also be different.

[0087] In some embodiments of the present application, after receiving multiple video analysis results corresponding to multiple monitoring points, the server 122 can also filter the video analysis results corresponding to each monitoring point according to preset rules to obtain filtered video analysis results.

[0088] Then, the server 122 can process the video analysis results after screening. Among them, the preset rule can be that the number of target objects appearing in the preset time period is greater than the second preset number, and the user can set the size of the second preset number according to his actual needs. In addition, the preset rule can be that the picture quality of the monitoring video is higher than the preset quality standard, and the user can set the preset quality standard according to his actual needs. In this way, the video analysis results after screening do not include video analysis results that do not meet the actual needs of the user.

[0089] In this way, the server 122 does not need to process all the video analysis results, but only needs to process the video analysis results after the above screening, thereby reducing the number of video analysis results that need to be processed, thereby improving the processing efficiency of the video analysis results by the server 122. At the same time, since the video analysis results that are eliminated during the screening process do not meet the actual needs of the user, they will not affect the processing effect of the server 122 on the video analysis results.

[0090] Using the previous example, the number of people appearing in the video analysis results corresponding to monitoring points 1 to 10 are 100, 80, 120, 90, 110, 85, 95, 105, 75, and 115, respectively. The user can set the second preset number in the preset rule to 93. Then the video analysis results after screening are the video analysis results corresponding to monitoring point 1, monitoring point 3, monitoring point 5, monitoring point 7, monitoring point 8, and monitoring point 10, respectively. The server 122 only needs to process the above 6 screened video analysis results.

[0091] Using the previous example, in the video analysis results corresponding to monitoring points 1 to 10, the image quality of the monitoring videos is 0.81, 0.73, 0.92, 0.85, 0.88, 0.82, 0.86, 0.77, 0.91, and 0.84 respectively. The image quality here is represented by a numerical value, and the larger the value, the better the image quality.

[0092] The user can set the preset quality standard in the preset rule to 0.80. Then the video analysis results after screening are respectively the video analysis results corresponding to monitoring point 1, monitoring point 3, monitoring point 4, monitoring point 5, monitoring point 6, monitoring point 7, monitoring point 9, and monitoring point 10. The server 122 only needs to process the above 8 screened video analysis results.

[0093] It should be noted that the above-mentioned preset rules can include the above two preset rules at the same time. In this way, the server 122 can use the above two preset rules to filter the video analysis results. The specific filtering process is not described in detail in the embodiment of the present application. It is understandable that the user can also set other preset rules according to actual needs to filter the video analysis results, and the embodiment of the present application does not limit this.

[0094] In some embodiments of the present application, the aforementioned genetic algorithm can specifically be a multi-objective genetic algorithm (Multi-Objective Genetic Algorithm, MOGA). When the target of the objective function is multiple, the multi-objective genetic algorithm can be adopted. Exemplary, the target of the objective function can be the target in the aforementioned embodiment. The multi-objective genetic algorithm is a modeling method that simulates natural evolution, and is widely used in solving complex optimization problems, particularly multi-objective optimization problems. This algorithm is similar to a genetic algorithm, and it utilizes a genetic evolution algorithm and an adversarial evolutionary algorithm to search and optimize different targets. The multi-objective genetic algorithm draws on the evolutionary theory in biology, and simulates the idea of ​​natural evolution, and is used to solve complex multi-objective optimization problems.

[0095] Specifically, the server 122 can obtain the initial selection results of the monitoring points according to the preset constraints and the multi-objective genetic algorithm. Then, based on the initial selection results of the monitoring points, one or more optimized selection results of the monitoring points are obtained through the selection, crossover, mutation and elite retention mechanism in population evolution.

[0096] Next, the fitness evaluation can be performed on each optimization selection result of the monitoring point according to the objective function, so as to obtain the fitness evaluation result. By analyzing the fitness evaluation result, the optimal selection result of the monitoring point can be determined from each optimization selection result of the monitoring point.

[0097] like Figure 4 As shown, the embodiment of the present application further provides a device for selecting a monitoring point, and the device for selecting a monitoring point 4 may include:

[0098] The first receiving module 41 is used to receive multiple monitoring videos sent by multiple monitoring points; the multiple monitoring videos all include monitoring content within a preset time period;

[0099] The analysis module 42 is used to analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0100] The processing module 43 is used to process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain an optimal selection result of the monitoring points;

[0101] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0102] like Figure 5As shown, the embodiment of the present application further provides a monitoring point selection device, and the monitoring point selection device 5 can be set in the terminal device 121, including:

[0103] The first receiving module 41 is used to receive multiple monitoring videos sent by multiple monitoring points; the multiple monitoring videos all include monitoring content within a preset time period;

[0104] The analysis module 42 is used to analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period;

[0105] The sending module 44 is used to send the video analysis results corresponding to each of the monitoring points to the server 122, so that the server 122 uses the genetic algorithm, the preset constraints and the pre-constructed objective function to process the video analysis results corresponding to each of the monitoring points to obtain the optimal selection result of the monitoring points;

[0106] The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

[0107] See also Figure 6 The present application also provides an electronic device, the electronic device includes a memory and a processor, the memory is used to store a computer program, when the computer program is executed by the processor, the above-mentioned monitoring point selection method can be implemented, and the specific details can be referred to the description of the above-mentioned embodiment. The electronic device can be specifically the terminal device 121 or the server 122 in the above-mentioned embodiment.

[0108] Specifically, at the hardware level, the device may include a processor, an internal bus, and a memory. The memory may include a memory and a non-volatile memory. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it. It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the above device. Figure 6 More or fewer components shown in the figure may also include other processing hardware, such as a GPU (Graphics Processing Unit), or an external communication port, etc. Of course, in addition to the software implementation, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc.

[0109] In this embodiment, the processor may include a central processing unit (CPU) or a graphics processing unit (GPU), and of course may also include other single-chip microcomputers, logic gate circuits, integrated circuits, etc. with logic processing capabilities, or appropriate combinations thereof. The memory described in this embodiment may be a memory device for storing information. In a digital system, a device that can store binary data may be a memory; in an integrated circuit, a circuit with a storage function without a physical form may also be a memory, such as a RAM, a FIFO, etc.; in a system, a storage device with a physical form may also be called a memory, etc. When implemented, the memory may also be implemented in the form of a cloud storage, and the specific implementation method is not limited in this specification.

[0110] It should be noted that the specific implementation of the electronic device in this specification can refer to the description of the method implementation method, and will not be described in detail here.

[0111] The present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned methods for selecting monitoring points can be implemented.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for selecting monitoring points, characterized in that: include: Receive multiple surveillance videos sent from multiple monitoring points; The multiple surveillance videos all include surveillance content within a preset time period; Analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period; Using a genetic algorithm, preset constraints and a pre-constructed objective function, the video analysis results corresponding to each of the monitoring points are processed to obtain an optimal selection result of the monitoring points; The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

2. The method according to claim 1, characterized in that The preset constraints include: The number of the selected monitoring points is less than the first preset number.

3. The method according to claim 1, characterized in that The preset constraint conditions include: the shooting range of the selected monitoring points can cover a preset geographical range.

4. The method according to claim 3, characterized in that The method comprises: A configuration file sent by a user terminal is received, and according to the configuration file, the type of the genetic algorithm and / or the preset geographical range is configured.

5. The method according to claim 1, characterized in that The objective of the objective function includes: minimizing the number of the selected monitoring points.

6. The method according to claim 2, characterized in that The video analysis results also include the picture quality of the monitoring video; The objective of the objective function includes: optimizing the average picture quality of the monitoring video corresponding to the selected monitoring points.

7. The method according to claim 6, characterized in that After analyzing the monitoring contents of each monitoring video to obtain the video analysis results corresponding to each monitoring point, the method further includes: filtering the video analysis results corresponding to each monitoring point according to a preset rule to obtain a filtered video analysis result; wherein the preset rule includes: the number of target objects appearing within a preset time period is greater than a second preset number, and / or the picture quality of the monitoring video is higher than a preset quality standard; The processing of the video analysis results corresponding to each of the monitoring points includes: processing the screened video analysis results.

8. The method according to claim 1, characterized in that The genetic algorithm is a multi-objective genetic algorithm; The method of processing the video analysis results corresponding to each monitoring point by using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain the optimal selection result of the monitoring point includes: According to the preset constraint conditions and the multi-objective genetic algorithm, obtaining the initial selection result of the monitoring point; Based on the initial selection results of the monitoring points, at least one optimized selection result of the monitoring points is obtained through selection, crossover, mutation and elite retention mechanisms in population evolution; According to a pre-constructed objective function, performing fitness evaluation on at least one optimization selection result of the monitoring point to generate a fitness evaluation result; According to the fitness evaluation result, the optimal selection result of the monitoring point is determined.

9. A method for selecting monitoring points, characterized in that: Applied to terminal equipment, including: Receiving multiple surveillance videos sent by multiple surveillance points; the multiple surveillance videos all include surveillance content within a preset time period; Analyze the monitoring content of each monitoring video to obtain the video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period; Sending the video analysis results corresponding to each of the monitoring points to the server, so that the server can process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-constructed objective function to obtain the optimal selection result of the monitoring point; The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

10. The method according to claim 9, characterized in that The video analysis result also includes the picture quality of the monitoring video.

11. A device for selecting monitoring points, characterized in that: include: A first receiving module, used for receiving multiple monitoring videos sent by multiple monitoring points; The multiple surveillance videos all include surveillance content within a preset time period; An analysis module, used to analyze the monitoring content of each monitoring video to obtain a video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period; A processing module, used to process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-constructed objective function, so as to obtain an optimal selection result of the monitoring points; The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

12. A device for selecting monitoring points, characterized in that: Set in the terminal device, including: A first receiving module is used to receive multiple monitoring videos sent by multiple monitoring points; the multiple monitoring videos all include monitoring content within a preset time period; An analysis module, used to analyze the monitoring content of each monitoring video to obtain a video analysis result corresponding to each monitoring point; the video analysis result includes the number of target objects appearing in the preset time period; A sending module, used for sending the video analysis results corresponding to each of the monitoring points to the server, so that the server can process the video analysis results corresponding to each of the monitoring points using a genetic algorithm, preset constraints and a pre-built objective function to obtain the optimal selection result of the monitoring points; The objective of the objective function includes: maximizing the number of target objects corresponding to the selected monitoring points.

13. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 10.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images