Monitoring equipment layout method, device and equipment and readable storage medium

Abstract

The invention provides a monitoring equipment layout method and device, equipment and a readable storage medium, and relates to the technical field of video surveillance, the method comprises the following steps: defining one or more groups of monitoring systems which respectively comprise one to N monitoring equipment, and different monitoring systems comprise different numbers of monitoring equipment; for each group of monitoring system, acquiring a monitoring coverage area of each monitoring device; based on the monitoring coverage area of each piece of monitoring equipment, adjusting the installation parameters of each piece of monitoring equipment until a preset optimization target is met; based on a preset target demand, selecting a target monitoring system from one or more groups of monitoring systems meeting a preset optimization target; and taking the number of the monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device as recommended monitoring device layout. According to the scheme, the monitoring equipment can be automatically arranged in a real scene according to monitoring requirements.

Description

Technical Field

[0001] The present application relates to the field of video surveillance technology, and in particular to a monitoring equipment layout method, apparatus, device and readable storage medium. Background Art

[0002] Closed Circuit TeleVision (CCTV), also known as video surveillance, is often used to enhance regional security. In some environments with high security requirements, it is necessary to install several monitoring devices, and these monitoring devices need to ensure that they can observe the areas that need to be monitored.

[0003] In the prior art, monitoring equipment is mainly laid out manually, but the manual design process takes too much time and effort, and the layout efficiency of the monitoring equipment is low. Summary of the invention

[0004] The present application provides a monitoring equipment layout method, apparatus, device and readable storage medium, which are used to solve the problem of low efficiency in the existing manual layout design of monitoring equipment.

[0005] In a first aspect, an embodiment of the present application provides a monitoring device layout method, including:

[0006] Define one or more monitoring systems each including one to N monitoring devices, where the number of monitoring devices included in different monitoring systems is different, and N is a preset positive integer;

[0007] For each group of monitoring systems:

[0008] Obtaining the monitoring coverage area of ​​each monitoring device;

[0009] Based on the monitoring coverage area of ​​each monitoring device, adjusting the installation parameters of each monitoring device until a preset optimization target is met;

[0010] Based on the preset target requirements, a target monitoring system is selected from one or more groups of monitoring systems that meet the preset optimization target;

[0011] The recommended monitoring device layout is based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

[0012] In a possible design of the first aspect, adjusting the installation parameters of each monitoring device based on the monitoring coverage area of ​​each monitoring device until a preset optimization goal is met includes:

[0013] Based on the monitoring coverage areas of the respective monitoring devices, determine a first area covered by i and only by i monitoring devices, a second area covered by i+j and only by i+j or more monitoring devices, and a third area not covered by the monitoring devices, where i and j are positive integers greater than or equal to 1;

[0014] Constructing a loss function based on the first region, the second region, and the third region;

[0015] The installation parameters of each monitoring device are adjusted until the loss function meets the optimization goal.

[0016] In another possible design of the first aspect, adjusting the installation parameters of each monitoring device until the loss function satisfies the optimization goal includes:

[0017] Obtaining a loss gradient of the loss function when the installation parameter is adjusted based on the gradient value;

[0018] Based on the loss gradient of the loss function, the installation parameters are adjusted until the loss function meets the optimization objective.

[0019] In another possible design of the first aspect, obtaining the monitoring coverage area of ​​each monitoring device includes:

[0020] Convert real 3D scenes into 2D scenes;

[0021] Meshing the two-dimensional scene;

[0022] Based on the installation parameters of each monitoring device, determine the grid position and the grid covered by each monitoring device in the gridded two-dimensional scene;

[0023] The grid covered by the monitoring device is taken as the monitoring coverage area.

[0024] In another possible design of the first aspect, obtaining the monitoring coverage area of ​​each monitoring device includes:

[0025] Based on the installation parameters of each monitoring device, determine the installation position of each monitoring device in the real three-dimensional scene;

[0026] Based on the installation location and the terrain features around the installation location in the real three-dimensional scene, the monitoring coverage area of ​​each monitoring device is determined.

[0027] In another possible design of the first aspect, obtaining a loss gradient of the loss function when the installation parameter is adjusted includes:

[0028] Performing a forward gradient adjustment on the installation parameter to obtain a first loss gradient of the loss function;

[0029] Performing negative gradient adjustment on the installation parameter to obtain a second loss gradient of the loss function;

[0030] Based on the first loss gradient and the second loss gradient, a loss gradient of the loss function is determined.

[0031] In yet another possible design of the first aspect, the installation parameters include: an installation position, an installation direction, and a field of view angle.

[0032] In another possible design of the first aspect, the adjusting the installation parameters includes:

[0033] Determine the area where monitoring equipment can be installed in a two-dimensional scene;

[0034] Obtaining the field of view angle range of the monitoring device;

[0035] Adjusting the installation position of the monitoring device within the area where the monitoring device can be installed;

[0036] Within the field of view angle range, the field of view angle of the monitoring device is adjusted.

[0037] In another possible design of the first aspect, the present invention further includes:

[0038] For each selected group of target monitoring systems, a layout evaluation is performed based on the area of ​​the monitoring coverage area of ​​each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result.

[0039] In another possible design of the first aspect, for each selected group of target monitoring systems, a layout evaluation is performed based on the area of ​​the monitoring coverage area of ​​each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result, including:

[0040] Acquire at least one of a first area, a second area, a third area, and a fourth area, wherein the first area is an area covered by at least one monitoring device, the second area is an area covered by at least two monitoring devices, the third area is an area not covered by the monitoring device or not reaching the required DORI level, and the fourth area is an area covered by two opposite monitoring devices;

[0041] Obtaining a ratio of at least one of the first area, the second area, the third area, and the fourth area to the total area of ​​the required monitoring area;

[0042] Based on the ratio, a layout evaluation result of the monitoring system is determined.

[0043] In a second aspect, an embodiment of the present application provides a monitoring device layout device, including:

[0044] A system definition module, used to define one or more monitoring systems each including one to N monitoring devices, wherein the number of monitoring devices included in different monitoring systems is different, and N is a preset positive integer;

[0045] An area acquisition module, used to acquire the monitoring coverage area of ​​each monitoring device;

[0046] An optimization and adjustment module, used to adjust the installation parameters of each monitoring device based on the monitoring coverage area of ​​each monitoring device until a preset optimization target is met;

[0047] A system determination module, used to select a target monitoring system from one or more groups of monitoring systems that meet a preset optimization target based on a preset target requirement;

[0048] The monitoring layout module is used to recommend the monitoring device layout based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described above.

[0050] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the above-mentioned method when executed by a processor.

[0051] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0052] The monitoring equipment layout method, apparatus, device and readable storage medium provided in the embodiments of the present application use the installation parameters of the monitoring equipment and the number of monitoring equipment as variables to optimize the monitoring coverage area until it reaches the optimization target, and then select the required number of monitoring equipment for layout. In this way, there is no need to manually design the layout of the monitoring equipment, and the monitoring equipment required by the target table can be quickly selected on the basis of ensuring that the monitoring covers the required area, and the installation layout of each monitoring equipment can be completed. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application;

[0054] Figure 1 A schematic diagram of application scenarios of CCTV provided in an embodiment of the present application;

[0055] Figure 2 A schematic diagram of a flow chart of a monitoring device layout method provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of monitoring coverage provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of area division provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the position change of the monitoring device provided in the embodiment of the present application;

[0059] Figure 6 A schematic diagram of a two-dimensional scene provided in an embodiment of the present application;

[0060] Figure 7 A schematic diagram of a scene grid provided in an embodiment of the present application;

[0061] Figure 8 A schematic diagram of monitoring coverage provided in an embodiment of the present application;

[0062] Fig. 9 A schematic diagram of a complete automated layout process provided by an embodiment of the present application;

[0063] Fig.10 A schematic diagram of the structure of the monitoring equipment layout device provided in an embodiment of the present application;

[0064] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0065] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0067] Closed Circuit TeleVision (CCTV), also known as video surveillance, is usually used to enhance regional security. In addition, CCTV can also be applied to some other scenarios. For example, CCTV can monitor and record the operating status of vehicles equipped with Advanced Driving Assistance System (ADAS). For example, Figure 1 The application scenario diagram of CCTV provided in the embodiment of the present application is as follows: Figure 1 As shown, CCTV can be used in vehicle driving areas to ensure that necessary vehicle activities can be observed.

[0068] In actual applications, since the monitoring range covered by each monitoring device is limited, and due to cost considerations, the number of monitoring devices that can be used is usually limited, while the vehicle driving area is usually relatively wide. For this reason, it is necessary to specify in advance where to arrange the monitoring devices in the vehicle driving area, that is, to design the layout of the monitoring devices to minimize the number of monitoring devices used, while ensuring that all necessary vehicle activities are observed. As mentioned above Figure 1 As shown in the figure, during the driving process of the vehicle, some locations need to be equipped with one or more monitoring devices, while some locations do not need to be equipped with monitoring devices. In addition, in order to make full use of each monitoring device, the overlap of the coverage of the monitoring devices should be avoided as much as possible. At present, the layout design of the monitoring equipment is done manually, and the whole process takes a lot of time and effort, and the efficiency is very low.

[0069] In response to the above-mentioned problems, the present application provides an automated solution for CCTV video surveillance layout design. The solution can continuously adjust the number and installation parameters of monitoring equipment through a model to meet the optimization goals (for example, the widest monitoring coverage can be achieved while using the least amount of monitoring equipment, and ensuring that the monitoring coverage is exactly the necessary activity range of the vehicle). In this way, it is only necessary to layout the monitoring equipment to the actual application scenario based on the optimized number and installation parameters of the monitoring equipment. Compared with the current manual layout of the monitoring equipment, checking the layout effect, and then using the layout effect as feedback to readjust the previous manual layout plan, this back and forth process takes a lot of time and effort. This solution has a more efficient layout efficiency.

[0070] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0071] Figure 2 This is a flow chart of a monitoring device layout method provided in an embodiment of the present application, which can be applied to electronic devices (such as computers, mobile terminals, etc.). Figure 2 As shown, the method may include the following steps:

[0072] Step S210: define one or more monitoring systems each including one to N monitoring devices.

[0073] The number of monitoring devices included in different monitoring systems is different, and N is a positive integer.

[0074] In this embodiment, each monitoring system includes a number of monitoring devices, and each monitoring device has its own installation parameters. Taking the need to deploy a monitoring system in area A as an example, based on the installation parameters carried by each monitoring device, it can be determined how each monitoring device is specifically deployed in area A (for example, where it is deployed in area A, which direction it faces, how large the field of view is configured, etc.). Among them, these installation parameters are random initial values, which may lead to unsatisfactory layout effects (for example, two monitoring devices may be installed in the same position), so these installation parameters need to be optimized. After optimizing the installation parameters of each monitoring device, each monitoring system can be regarded as a set of optimized layout schemes. Based on the optimized layout scheme, each monitoring device is deployed in the actual scene of area A, and the corresponding layout effect can be obtained.

[0075] Among them, when the number of monitoring devices in each monitoring system is different, after optimizing the installation parameters, the final layout effect of each monitoring system will also be different. Therefore, a target monitoring system that best meets the current actual needs can be selected as the final layout plan.

[0076] In this embodiment, N can be a positive integer greater than 1. For example, for the above-mentioned area A, it can be estimated how many monitoring devices are needed to fully cover the required monitoring area (such as the area where the vehicle carries out necessary activities). Specifically, it can be a numerical range. For example, the range is set to [a, b], that is, at least a monitoring devices are required, and at most b monitoring devices can be given. In this way, ba groups of monitoring systems can be configured. The first monitoring system contains a monitoring devices, the second monitoring system contains a+1 monitoring devices, and so on. The last monitoring system contains b monitoring devices.

[0077] In addition, N may also be 1. For example, when the number of monitoring devices is limited, an accurate value X is directly given in advance as the number of monitoring devices. In this case, only one set of monitoring systems needs to be configured, and the monitoring system includes X monitoring devices.

[0078] For each monitoring system, perform the following steps:

[0079] Step S220: Obtain the monitoring coverage area of ​​each monitoring device.

[0080] The installation parameters may refer to those parameters that affect the monitoring coverage area of ​​the monitoring device. When these installation parameters change, the original monitoring coverage area of ​​the monitoring device changes. For example, the area of ​​the monitoring coverage area becomes smaller or larger, or the monitoring coverage area moves.

[0081] In this embodiment, the number of installation parameters may include multiple ones, for example, the installation parameters of a monitoring device include: (1) installation position; (2) orientation; (3) field of view. Before the parameters are adjusted, the installation parameters of each monitoring device in the monitoring system can take random initial values. For example, the above (1) installation position can take a random initial value. In addition, usually after the monitoring device leaves the factory, the values ​​of some installation parameters (such as (2) orientation; (3) field of view, etc.) are also configured. Therefore, before the parameters are adjusted, some installation parameters of each monitoring device in the monitoring system can also use the factory settings.

[0082] In this embodiment, it is assumed that the area with monitoring coverage requirements is called the required area. Since in actual applications, the required area is usually three-dimensional, in order to facilitate the layout design of the monitoring equipment, the required area can be two-dimensionalized (refer to the current conversion of three-dimensional space into a two-dimensional map). Then, after determining all the installation parameters of each monitoring device, the three-dimensional space covered by the monitoring device can also be converted into a two-dimensional area, so that the monitoring coverage area and the monitoring uncovered area can be expressed in a two-dimensional form.

[0083] For example, Figure 3 A monitoring coverage diagram provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, assuming Figure 3 The demand area 30 is included, part of which is covered by the monitoring device 31, and part of which is covered by the monitoring device 32. Figure 3 It can be seen that there is an overlapping coverage area between monitoring device 31 and monitoring device 32. This is actually because the installation parameters of monitoring device 31 and monitoring device 32 have not reached the optimal value, resulting in repeated coverage and reduced monitoring utilization.

[0084] Step S230: Based on the monitoring coverage area of ​​each monitoring device, the installation parameters of each monitoring device are adjusted until a preset optimization target is met.

[0085] In this embodiment, the optimization target can be configured in combination with the actual situation. The following three optimization targets are provided: Optimization target ①: ensure that all required areas that need to be covered and monitored are covered by the monitoring equipment; Optimization target ②: avoid overlapping of the coverage areas of each monitoring equipment. Optimization target ③: ensure that all requirements are covered by the monitoring equipment, and avoid overlapping of the coverage areas of each monitoring equipment.

[0086] Among them, you can choose the corresponding optimization target based on actual needs. After determining the optimization target, refer to the above Figure 3 The monitoring coverage diagram shown can be used to adjust the installation parameters of each monitoring device in each monitoring system.

[0087] Step S240: Based on a preset target requirement, a target monitoring system is selected from one or more groups of monitoring systems that meet a preset optimization target.

[0088] Among them, the target demand can be determined based on the actual situation. For example, the number of monitoring devices required for the first monitoring system is a1, and the number of monitoring devices required for the second monitoring system is a2. However, they can both meet the above optimization goals, and a1 is less than a2. For cost considerations, the first monitoring system can be selected as the target monitoring system.

[0089] For another example, the number of monitoring devices required for the first group of monitoring systems is a1, and the number of monitoring devices required for the second group of monitoring systems is a2, and a1 is less than a2, but the first group of monitoring systems can only meet the above-mentioned optimization target ① or the above-mentioned optimization target ②, while the second group of monitoring systems can meet the above-mentioned optimization target ① and the above-mentioned optimization target ② at the same time, then the second group of monitoring systems can be selected as the target monitoring system.

[0090] Among them, the goal of selecting the target monitoring system is mainly to determine the number of monitoring devices for subsequent layout.

[0091] Step S250: Recommending a monitoring device layout based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

[0092] In this embodiment, the monitoring device is usually installed in a three-dimensional scene. When the monitoring device is laid out in the three-dimensional scene, it is necessary to combine the installation parameters to determine the position coordinates, orientation, etc. of the monitoring device in the three-dimensional scene to complete the installation of the monitoring device.

[0093] The embodiment of the present application uses the installation parameters of the monitoring equipment and the number of monitoring equipment as variables to optimize the monitoring coverage area until it reaches the optimization target, and then selects the required number of monitoring equipment for layout. In this way, there is no need to manually design the layout of the monitoring equipment, and the monitoring equipment required by the target table can be quickly selected on the basis of ensuring that the monitoring covers the required area, and the installation layout of each monitoring equipment can be completed.

[0094] Since it is time-consuming and laborious to manually design the layout of monitoring equipment, based on the logical principle of automatic layout of monitoring equipment mentioned above, the following will further explain in detail the parameter optimization in the automatic layout process through some embodiments.

[0095] In the process of automated layout, it is necessary to describe the layout effect and the variables that affect the layout effect (i.e., installation parameters) in a mathematical way, so that each step in the automated layout process can be executed on the electronic device. For example, the loss function is used to describe the layout effect, and the variables (x, y, Φ, FOV) are used to describe the installation parameters, and then these variables are optimized and adjusted so that the loss function can achieve the optimization goal.

[0096] In this embodiment, the following loss function can be constructed:

[0097]

[0098] In the above formula, Sone_ CAMmay represent a first area covered by i and only i monitoring devices, It can represent the second area covered by i+j and only by i+j or more monitoring devices, It may represent a third area not covered by the monitoring device.

[0099] For example, Figure 4 The schematic diagram of area division provided in the embodiment of the present application takes the values ​​of j and j as 1 as an example. Figure 4 As shown in the above Figure 3 Based on the above, we can see the area 301 covered by 1 monitoring device, the area 302 covered by 2 monitoring devices, and the area 303 not covered by any monitoring device.

[0100] Through the above Figure 4 For example, the first area, the second area and the third area can be determined. If a monitoring system includes N monitoring devices, a set of installation parameters (x1, y1, φ1, FoV1, x2, y2, φ2, FoV2, ..., x N ,y N ,φ N , FoV N ), by adjusting this set of installation parameters, the first area, the second area and the third area are changed (for example, area change, area displacement, etc.), thereby causing the loss function to change. Among them, the set of installation parameters can be adjusted by minimizing the loss function as an optimization goal.

[0101] Furthermore, in order to obtain the minimized loss function as accurately as possible, when adjusting the installation parameters, we can determine the influence of each variable (a total of four, namely x, y, Φ, FOV) on the loss function, that is, determine the loss gradient of the loss function when adjusting each variable. Then, based on the loss gradient corresponding to each variable, we can find the minimum value of the loss function (that is, find out when the loss function meets the optimization goal).

[0102] Exemplarily, taking the installation parameters including the installation position as an example, in a two-dimensional scenario, the installation position of the monitoring device can be divided into variables in the x-axis direction and variables in the y-axis direction. Figure 5 A schematic diagram of the position change of the monitoring device provided in the embodiment of the present application, such as Figure 5 As shown, when the position of one of the monitoring devices undergoes a gradient displacement in the positive direction of the x-axis, its monitoring coverage also shifts accordingly, which results in corresponding changes in the loss function for the first area, the second area, and the third area mentioned above.

[0103] Similarly, when the position of the monitoring device undergoes a gradient shift in the negative direction of the x-axis, its monitoring coverage also shifts accordingly, which will also cause the loss function of the first area, the second area, and the third area mentioned above to change accordingly. Similarly, when other installation parameters of the monitoring device undergo a gradient change, the loss function will also have a corresponding loss gradient.

[0104] As can be seen from the above, by adjusting the gradient of the installation parameters, the loss function will also change accordingly, so that the minimized loss function can be accurately found, that is, the loss function can meet the optimization goal.

[0105] Furthermore, the adjustment of the installation parameters can be divided into positive adjustment and negative adjustment (for example, positive adjustment can be understood as adjustment along the positive direction of the x-axis or y-axis, and negative adjustment can be understood as adjustment along the negative direction of the x-axis or y-axis). When the installation parameters are adjusted positively according to the gradient value, the first loss gradient of the loss function can be expressed as Loss + -Loss0 means that when the installation parameters are adjusted negatively according to the gradient value, the second loss gradient of the loss function can be expressed as Loss—-Loss0.

[0106] Refer to the above Figure 5 When adjusting the position of the monitoring device, the values ​​of the first loss gradient and the second loss gradient may be different (that is, when the installation parameters change by the same value in both the positive and negative directions, the loss gradients corresponding to the loss function are different). In order to ensure the accuracy of the adjustment of the loss function, a value can be selected from the first loss gradient and the second loss gradient as the final loss gradient of the variable on the loss function. The specific formula is as follows:

[0107]

[0108] In the above formula, It represents the loss gradient of the loss function when the variable x is adjusted in the positive direction by a gradient value. It indicates the loss gradient of the loss function when the variable x is adjusted in the negative direction by a gradient value. It indicates the value of the loss function when the variable x is adjusted in a positive direction by a gradient value. It represents the value of the loss function when the variable x is adjusted in the negative direction by a gradient value, Loss0 represents the value of the loss function when the variable x does not change, and Δx is the gradient value of the variable x. Represents the final loss gradient when the installation parameter is adjusted by a gradient value.

[0109] In this embodiment, the value to be selected as the final loss gradient can be determined by combining the values ​​of the first loss gradient and the second loss gradient in an actual process.

[0110] For example, when both the first loss gradient and the second loss gradient are negative values, the one with the largest absolute value can be selected from the first loss gradient and the second loss gradient as the final loss gradient. For another example, when both the first loss gradient and the second loss gradient are positive values, the one with the smallest value can be selected from the first loss gradient and the second loss gradient as the final loss gradient. For another example, when one of the first loss gradient and the second loss gradient is positive and negative, the one with the negative value is selected as the final loss gradient.

[0111] The above embodiment constructs a loss function, determines the loss gradient of the loss function, and then adjusts the installation parameters of the monitoring equipment according to the loss gradient. In this way, the loss function that meets the optimization goal can be accurately found to obtain the optimal installation parameters. On the basis of realizing the automatic layout of the monitoring equipment, the automatic layout effect of the monitoring equipment can be further improved.

[0112] Furthermore, the above embodiments introduce parameter optimization in the automatic layout process. However, before performing parameter optimization, it is necessary to use the monitoring coverage area of ​​the monitoring device. Therefore, the acquisition of the monitoring coverage area is described in detail below through several embodiments.

[0113] In some embodiments, since monitoring devices are usually arranged in a three-dimensional scene, in order to reduce complexity, this embodiment converts the three-dimensional scene into a two-dimensional scene, and then further determines the monitoring coverage area of ​​the monitoring device based on the two-dimensional scene. The specific steps are as follows:

[0114] Step (1) converting the real three-dimensional scene into a two-dimensional scene;

[0115] Step (2) gridding the two-dimensional scene;

[0116] Step (3) determining the grid position and the grid covered by each monitoring device in the two-dimensional scene based on the installation parameters of each monitoring device in the monitoring system;

[0117] Step (4) takes the grid covered by the monitoring device as the monitoring coverage area.

[0118] In this embodiment, the real three-dimensional scene may refer to a real environment that needs to be monitored and covered. For example, if a road intersection needs to be covered and monitored, the real three-dimensional scene may include the road intersection and the area around the intersection. The area that needs to be covered and monitored in the real three-dimensional scene can be mapped to the gridded two-dimensional scene, that is, the required range of coverage to be monitored can also be determined in the gridded two-dimensional scene.

[0119] Figure 6 A schematic diagram of a two-dimensional scene provided in an embodiment of the present application, such as Figure 6As shown, after converting the real three-dimensional scene into two-dimensional one, it is possible to determine which areas in the two-dimensional scene are areas that need to be monitored (i.e., the required range to be covered for monitoring) and which areas are areas where monitoring equipment can be installed. In addition, the following steps may also be included: Step (6) The grids not covered by the monitoring equipment in the required range are regarded as the uncovered monitoring areas.

[0120] After being converted into a two-dimensional scene, in order to more accurately describe the area that needs to be monitored and the area where monitoring equipment can be installed, the entire two-dimensional scene can be gridded. Figure 7 A schematic diagram of a scene grid provided in an embodiment of the present application, such as Figure 7 As shown, after gridding, the location of each small grid (which row and which column) can be used to describe which areas can be installed with monitoring equipment and which areas are the required ranges to be covered and monitored. At the same time, the location of the monitoring equipment can also be determined. In addition, it is also convenient to calculate the first area, the second area, and the third area mentioned above.

[0121] Furthermore, after converting the real 3D scene into a 2D scene, the monitoring coverage of the monitoring device also needs to be 2Dized. It is necessary to determine which installation parameters will have an impact on the 2Dized monitoring coverage area. For example, Figure 8 A schematic diagram of monitoring coverage provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, taking the installation parameters of the monitoring equipment including the installation position (Xi, Yi), the installation direction -Φi, and the field of view FOVi as an example, by adjusting the above installation parameters Xi, Yi, -Φi, FOVi, the monitoring coverage of the monitoring equipment can be adjusted.

[0122] In addition, when adjusting the above installation parameters, there are constraints (i.e., unlimited adjustment is not possible). The specific constraints include: (1) the area range where the monitoring equipment can be installed in the two-dimensional scene; and (2) the field of view range of the monitoring equipment.

[0123] Based on the above two constraints, when adjusting the installation position of the monitoring device, it should be within the area where the monitoring device can be installed. When adjusting the field of view of the monitoring device, it should be within the field of view defined by the monitoring device.

[0124] Among them, it is also possible to Figure 7 The gridded two-dimensional scene shown is used to determine the area where monitoring equipment can be installed.

[0125] The above-mentioned embodiment can simplify the three-dimensional space into a two-dimensional plane by converting the three-dimensional real scene into two-dimensional space, thereby reducing the complexity of data processing in the automatic layout process and improving the efficiency of the automatic layout of the monitoring equipment.

[0126] The above embodiment has described the use of a two-dimensional map to display the monitoring coverage area of ​​each monitoring device, and based on this, the adjustment of the installation parameters. In fact, this solution can also be further extended to a three-dimensional scene. The following is a further description of how to expand to a real three-dimensional scene through an embodiment.

[0127] In an actual three-dimensional scene, monitoring equipment may be installed on some vertical walls. Assuming that the x direction represents the horizontal direction of the three-dimensional scene, the y direction represents the longitudinal direction of the three-dimensional scene, and the z direction represents the vertical direction of the three-dimensional scene, then the installation position of the monitoring equipment installed on the wall can be represented by (x, z) or (y, z) (this is because the position of the monitoring equipment is restricted by the wall). In addition, even if it is not installed on the wall, the installation position of the monitoring equipment can be represented by (x, y, z). For this purpose, a virtual three-dimensional scene can also be established, and then based on the virtual three-dimensional scene and the installation parameters of each monitoring device in the monitoring system, the actual monitoring coverage area of ​​each monitoring device in the real three-dimensional scene can be determined.

[0128] Specifically, after constructing the virtual three-dimensional scene, we can first determine the installation position of the monitoring equipment in the real three-dimensional scene based on the installation parameters of the monitoring equipment; then determine the monitoring coverage area of ​​each monitoring device in each monitoring system based on the installation position and the terrain features around the installation position in the real three-dimensional scene.

[0129] In this embodiment, the area that can actually be observed by a single monitoring device (ie, the monitoring coverage area) may be affected by the actual terrain. For example, obstacles such as houses may exist around the monitoring device, which may affect the maximum observable range of the monitoring device.

[0130] Among them, using a two-dimensional map to display the monitoring coverage area of ​​each monitoring device is simpler and more convenient, which can improve layout efficiency and can be applied to some scenes with low monitoring requirements. By building a virtual three-dimensional scene to display the monitoring coverage area of ​​each monitoring device, the monitoring coverage area of ​​each monitoring device can be displayed more accurately, based on which the optimal layout effect can be obtained, which can be applied to some scenes with high monitoring requirements.

[0131] In addition, in the process of adjusting the installation parameters of the monitoring devices, the monitoring system formed by the monitoring devices after the installation parameters are adjusted can also be evaluated for layout, and a layout evaluation score (i.e., layout evaluation result) can be given. Subsequently, the monitoring system can be evaluated based on the layout evaluation score to determine whether it meets the target requirements, thereby determining whether it is suitable as a target monitoring system.

[0132] Specifically, when performing layout evaluation, a layout evaluation may be performed on each selected group of target monitoring systems based on the area of ​​monitoring coverage of each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result.

[0133] Furthermore, when performing layout evaluation, in order to ensure the accuracy of the evaluation, one or more of the following indicators can be introduced to accurately describe the layout evaluation results:

[0134] (1) The percentage of the area covered by at least one monitoring device;

[0135] (2) the percentage of area covered by two or more monitoring devices;

[0136] (3) the percentage of area not covered by monitoring equipment or the percentage of area not achieving the required DORI level;

[0137] (4) The percentage of area covered by monitoring equipment from different angles.

[0138] Among them, for the indicator (4), two monitoring devices with opposite angles (i.e., two opposite monitoring devices) can be set to obtain the area percentage of the two areas covered from opposite angles as an indicator for measuring the layout evaluation results.

[0139] Among them, DORI (Detection, Observation, Recognition, Identification) mentioned in indicator (3) is a standard system used to define the ability of a camera to distinguish between people or objects in the coverage area.

[0140] In addition, the areas mentioned in the above four indicators can be colored and highlighted with different colors to achieve a visualization effect.

[0141] The embodiment of the present application can quantify the layout evaluation results by utilizing the above-mentioned four qualitative and quantitative indicators, so that the specific layout effect of each monitoring system after the installation parameters are adjusted (that is, equivalent to a monitoring layout plan) can be more accurately grasped, so as to more accurately find a monitoring system that meets the target requirements, so as to improve the layout effect of the monitoring equipment in the actual application scenario.

[0142] The following is a detailed description of the entire automated layout process of the monitoring equipment through a complete embodiment. Fig. 9 A schematic diagram of a complete automated layout process provided by an embodiment of the present application, such as Fig. 9 As shown, it includes the following steps:

[0143] Step S910: system initialization;

[0144] Step S920: the number of monitoring devices is iterated from N1 to Nm;

[0145] Step S930: Initialize parameter values;

[0146] Step S940: Calculate the loss value;

[0147] Step S950: whether the loss is less than a threshold or reaches a maximum number of cycles;

[0148] Step S960: calculating the gradient;

[0149] Step S970: updating parameter values ​​under constraints;

[0150] Step S980: Determine whether all monitoring devices have completed iteration.

[0151] In this embodiment, in order to automate the layout design process of monitoring equipment, relevant preparations need to be done first, including (1) determining the area that needs to be monitored (for example, covering the driving route of the autonomous vehicle); (2) determining the area where the monitoring equipment can be installed. (3) Rasterizing the map to express the problem more conveniently. The density of the grid can be adjusted accordingly according to the system requirements (see the above Figure 7 ).

[0152] After completing the above preparations, you can define the optimization problem. First, you need to design variables. Among them, the variables are mainly those parameters that can affect the monitoring coverage of the monitoring equipment, which can include: (1) the number of monitoring devices; (2) the installation location and installation direction of the monitoring equipment; (3) the field of view FOV of the monitoring equipment. At the same time, it is also necessary to configure constraints for some variables, such as the installation location cannot exceed the defined area (that is, the area where the monitoring equipment can be installed), and the field of view of the monitoring equipment must be within the defined range.

[0153] After completing the definition of the above variables, construct the loss function mentioned above, and then try to optimize the variable values ​​​​to make the value of the loss function as small as possible to achieve the optimization goal.

[0154] Among them, the above Fig. 9 It also involves the iteration of the number of monitoring devices, that is, a range of [a, b] can be configured, and the number Ni can be iterated from a to b to generate multiple iterative results (equivalent to optimizing the installation parameters of each monitoring device in N monitoring systems to obtain N optimization results), and then the optimal iterative result (i.e., the target monitoring system) is selected from these iterative results. Based on the optimal iterative result, the monitoring devices are arranged in the original real three-dimensional scene.

[0155] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0156] Fig.10 This is a schematic diagram of the structure of the monitoring device layout device provided in the embodiment of the present application. The monitoring device layout device can be integrated on the above electronic device. Fig.10 As shown, the monitoring equipment layout device 1000 includes a system definition module 1010, a region acquisition module 1020, an optimization adjustment module 1030, a system determination module 1040 and a monitoring layout module 1050.

[0157] Among them, the system definition module 1010 is used to define one or more groups of monitoring systems each containing one to N monitoring devices. Among them, the number of monitoring devices contained in different monitoring systems is different, and N is a positive integer. For each group of monitoring systems, the area acquisition module 1020 is used to obtain the monitoring coverage area of ​​each monitoring device. The optimization and adjustment module 1030 is used to adjust the installation parameters of each monitoring device based on the monitoring coverage area of ​​each monitoring device until the preset optimization target is met. The system determination module 1040 is used to select a target monitoring system from one or more groups of monitoring systems that meet the preset optimization target based on the preset target requirements.

[0158] After the target monitoring system is determined, the monitoring layout module 1050 is used to recommend the monitoring device layout based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

[0159] Optionally, the optimization and adjustment module can be specifically used to: determine the first area covered by i and only i monitoring devices, the second area covered by i+j and only i+j or more monitoring devices, and the third area not covered by the monitoring devices based on the monitoring coverage area of ​​each monitoring device in each monitoring system; construct a loss function based on the first area, the second area, and the third area; adjust the installation parameters of each monitoring device in each monitoring system until the loss function meets the optimization target. Wherein, i and j are positive integers greater than or equal to 1.

[0160] Optionally, the optimization and adjustment module can be specifically used to: obtain the loss gradient of the loss function when the installation parameters are adjusted based on the gradient value; based on the loss gradient of the loss function, adjust the installation parameters until the loss function meets the optimization goal.

[0161] Optionally, the area acquisition module can be specifically used to: convert a real three-dimensional scene into a two-dimensional scene; grid the two-dimensional scene; determine the grid position and the grids covered by each monitoring device in the gridded two-dimensional scene based on the installation parameters of each monitoring device in the monitoring system; and use the grids covered by the monitoring device as the monitoring coverage area.

[0162] Optionally, the area acquisition module can be specifically used to: determine the installation position of each monitoring device in the real three-dimensional scene based on the installation parameters of each monitoring device in the monitoring system; determine the monitoring coverage area of ​​each monitoring device in each group of monitoring systems based on the installation position and the terrain features around the installation position in the real three-dimensional scene.

[0163] Optionally, the optimization and adjustment module can be specifically used to: perform positive gradient adjustment on the installation parameters to obtain a first loss gradient of the loss function; perform negative gradient adjustment on the installation parameters to obtain a second loss gradient of the loss function; and determine the loss gradient of the loss function based on the first loss gradient and the second loss gradient.

[0164] Optionally, the installation parameters include: installation position, installation direction and field of view angle.

[0165] Optionally, the optimization and adjustment module can be specifically used to: determine the area range where the monitoring equipment can be installed in a two-dimensional scene; obtain the field of view angle range of the monitoring equipment; adjust the installation position of the monitoring equipment within the area range where the monitoring equipment can be installed; adjust the field of view angle of the monitoring equipment within the field of view angle range.

[0166] Optionally, a layout evaluation module is also included, which is used to perform layout evaluation on each selected group of target monitoring systems based on the area of ​​the monitoring coverage area of ​​each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result.

[0167] Optionally, the layout assessment module can be specifically used to: obtain at least one of a first area, a second area, a third area and a fourth area, the first area being the area of ​​an area covered by at least one monitoring device, the second area being the area of ​​an area jointly covered by at least two monitoring devices, the third area being the area of ​​an area not covered by a monitoring device or not reaching a required DORI level, and the fourth area being the area of ​​an area covered by two opposite monitoring devices; obtain a ratio of at least one of the first area, the second area, the third area and the fourth area to the total area of ​​the required monitoring area; and determine a layout assessment result of the monitoring system based on the ratio.

[0168] The device provided in the embodiment of the present application can be used to execute the method in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0169] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the monitoring acquisition module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0170] Fig.11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.11 As shown, the electronic device 1100 includes: at least one processor 1101 , a memory 1102 , a bus 1103 and a communication interface 1104 . The processor 1101 , the communication interface 1104 and the memory 1102 communicate with each other via the bus 1103 .

[0171] The communication interface is used to communicate with other devices. The communication interface includes a communication interface for data transmission and a display interface or operation interface for human-computer interaction. The processor is used to execute computer-executable instructions stored in the memory, and specifically can execute the relevant steps in the method described in the above embodiment.

[0172] The processor may be a central processing unit, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0173] The memory is used to store computer executable instructions and may include high-speed RAM memory, or may also include non-volatile memory, such as at least one disk memory.

[0174] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When at least one processor of an electronic device executes the computer instructions, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0175] This embodiment also provides a computer program product, which includes computer instructions stored in a readable storage medium. At least one processor of the electronic device can read the computer instructions from the readable storage medium, and at least one processor executes the computer instructions so that the electronic device implements the methods provided in the above various embodiments.

[0176] In the present application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0177] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A monitoring equipment layout method, characterized in that: include: Define one or more monitoring systems each including one to N monitoring devices, where the number of monitoring devices included in different monitoring systems is different, and N is a preset positive integer; For each group of monitoring systems: Obtain the monitoring coverage area of ​​each monitoring device; Based on the monitoring coverage area of ​​each monitoring device, adjusting the installation parameters of each monitoring device until a preset optimization target is met; Based on the preset target requirements, a target monitoring system is selected from one or more groups of monitoring systems that meet the preset optimization target; The recommended monitoring device layout is based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

2. The method according to claim 1, characterized in that The adjusting, based on the monitoring coverage area of ​​each monitoring device, the installation parameters of each monitoring device until a preset optimization goal is met, includes: Based on the monitoring coverage areas of the respective monitoring devices, determine a first area covered by i and only by i monitoring devices, a second area covered by i+j and only by i+j or more monitoring devices, and a third area not covered by the monitoring devices, where i and j are positive integers greater than or equal to 1; Constructing a loss function based on the first region, the second region, and the third region; The installation parameters of each monitoring device are adjusted until the loss function meets the optimization goal.

3. The method according to claim 2, characterized in that The step of adjusting the installation parameters of each monitoring device until the loss function satisfies the optimization goal includes: Obtaining a loss gradient of the loss function when the installation parameter is adjusted based on the gradient value; Based on the loss gradient of the loss function, the installation parameters are adjusted until the loss function meets the optimization objective.

4. The method according to claim 1, characterized in that: The obtaining of the monitoring coverage area of ​​each monitoring device includes: Convert real 3D scenes into 2D scenes; Meshing the two-dimensional scene; Based on the installation parameters of each monitoring device, determine the grid position and the grid covered by each monitoring device in the gridded two-dimensional scene; The grid covered by the monitoring device is taken as the monitoring coverage area.

5. The method according to claim 1, characterized in that The obtaining of the monitoring coverage area of ​​each monitoring device includes: Based on the installation parameters of each monitoring device, determine the installation position of each monitoring device in the real three-dimensional scene; Based on the installation location and the terrain features around the installation location in the real three-dimensional scene, the monitoring coverage area of ​​each monitoring device is determined.

6. The method according to claim 3, characterized in that The obtaining the loss gradient of the loss function when the installation parameter is adjusted includes: Performing a forward gradient adjustment on the installation parameter to obtain a first loss gradient of the loss function; Performing negative gradient adjustment on the installation parameter to obtain a second loss gradient of the loss function; Based on the first loss gradient and the second loss gradient, a loss gradient of the loss function is determined.

7. The method according to any one of claims 1 to 6, characterized in that The installation parameters include: installation position, installation direction and viewing angle.

8. The method according to claim 7, characterized in that The installation parameters are adjusted, including: Determine the area where monitoring equipment can be installed in a two-dimensional scene; Obtaining the field of view angle range of the monitoring device; Adjusting the installation position of the monitoring device within the area where the monitoring device can be installed; Within the field of view angle range, the field of view angle of the monitoring device is adjusted.

9. The method according to any one of claims 1 to 6, characterized in that: Also includes: For each selected group of target monitoring systems, a layout evaluation is performed based on the area of ​​the monitoring coverage area of ​​each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result.

10. The method according to claim 9, characterized in that For each selected group of target monitoring systems, a layout evaluation is performed based on the area of ​​the monitoring coverage area of ​​each monitoring device in the monitoring system and the total area of ​​the required monitoring area to obtain a layout evaluation result, including: Acquire at least one of a first area, a second area, a third area, and a fourth area, wherein the first area is an area covered by at least one monitoring device, the second area is an area covered by at least two monitoring devices, the third area is an area not covered by the monitoring device or not reaching the required DORI level, and the fourth area is an area covered by two opposite monitoring devices; Obtaining a ratio of at least one of the first area, the second area, the third area, and the fourth area to the total area of ​​the required monitoring area; Based on the ratio, a layout evaluation result of the monitoring system is determined.

11. A monitoring equipment layout device, characterized in that: include: A system definition module, used to define one or more monitoring systems each including one to N monitoring devices, wherein the number of monitoring devices included in different monitoring systems is different, and N is a preset positive integer; The area acquisition module is used to obtain the monitoring coverage area of ​​each monitoring device; An optimization and adjustment module, used to adjust the installation parameters of each monitoring device based on the monitoring coverage area of ​​each monitoring device until a preset optimization target is met; A system determination module, used to select a target monitoring system from one or more groups of monitoring systems that meet a preset optimization target based on a preset target requirement; The monitoring layout module is used to recommend the monitoring device layout based on the number of monitoring devices in the selected target monitoring system and the adjusted installation parameters of each monitoring device.

12. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 10 when executed by a processor.

14. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 10 when being executed by a processor.

Images