Target detection region planning method and device, electronic equipment and storage medium

Abstract

This application discloses a target detection region planning method, apparatus, electronic device, and storage medium. The method includes: acquiring road images of a target road captured by multiple roadside cameras, and obtaining an initial ground sensing region for each roadside camera based on the road images; visualizing the target road and the initial ground sensing regions of the multiple roadside cameras to obtain a visualization result; acquiring sensing range adjustment information generated based on the visualization result, and obtaining an adjusted ground sensing region for each roadside camera based on the sensing range adjustment information; and obtaining the adjusted target detection region for each roadside camera based on the adjusted ground sensing region. The technical solution of this application can improve the computational efficiency of roadside cameras and save computational resources.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a target detection area planning method, device, electronic equipment, and storage medium. Background Technology

[0002] The development of intelligent transportation roadside monitoring systems is becoming increasingly mature. The most important aspect of the system's application is the use of roadside cameras and other equipment to detect vehicles and pedestrians on the road, which can then be sent to the vehicle as a basis for traffic accident detection and early warning, as well as route planning.

[0003] Currently, single poles are typically erected every 200-300 meters or even longer along the road, with multiple cameras mounted on each pole facing different directions. For example, if five cameras are mounted on a single pole on a north-facing road, the two north-facing cameras each include a telephoto camera and a short-focus camera to monitor oncoming vehicles and pedestrians. The telephoto camera is used for long-range monitoring, while the short-focus camera is used for close-range monitoring. The two south-facing cameras also include a telephoto camera and a short-focus camera, with a fisheye camera mounted downwards to supplement the blind spots of the two close-range cameras. In actual installation, the fields of view of these five cameras need to be complementary while also maximizing the range of vision.

[0004] In this situation, the image data collected by the roadside camera not only includes a large amount of useless information outside the section monitored by the camera, but also has significant overlap with other roadside cameras, especially at intersections where there may be more than 16 cameras covering the area, making the overlap between image data even more complex. (Reference) Figure 2 , Figure 2 This is a schematic diagram illustrating the field of view coverage of two roadside cameras in a real-world scenario. Figure 2 As can be seen, the ground perception area of ​​the telephoto camera includes not only the road section it monitors, but also a large amount of perception information from other road sections. These other road sections are generally perceived by corresponding roadside cameras. Therefore, when the roadside cameras perform target detection and tracking based on the image data of the roadside cameras, these overlapping fields of view will not only consume a lot of computing resources, but also affect the computing efficiency of the roadside cameras. Summary of the Invention

[0005] This application provides a target detection area planning method, device, electronic device, and storage medium, which improves the computational efficiency of roadside cameras and saves computational resources by replanning the target detection area of ​​roadside cameras.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, embodiments of this application provide a target detection region planning method, the method comprising:

[0008] Acquire road images of the target road captured by multiple roadside cameras, and obtain the initial ground sensing area of ​​each roadside camera based on the road images;

[0009] The target road and the initial ground perception area of ​​multiple roadside cameras are visualized to obtain visualization results;

[0010] Obtain the perception range adjustment information generated based on the visualization results, and obtain the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information;

[0011] The adjusted target detection area of ​​each roadside camera is obtained based on the adjusted ground sensing area of ​​each roadside camera.

[0012] Optionally, obtaining the initial ground perception area for each roadside camera based on the road image includes:

[0013] Perform ground detection on the road images of each roadside camera to obtain the ground detection results corresponding to each roadside camera;

[0014] Based on the calibration parameters of each roadside camera and the ground detection results corresponding to each roadside camera, the initial ground perception area of ​​each roadside camera is obtained.

[0015] Optionally, the visualization process of the target road and the initial ground perception area of ​​multiple roadside cameras to obtain a visualization result includes:

[0016] A visual interface for obtaining the target road;

[0017] Based on the initial ground perception area of ​​each roadside camera, obtain the visualization result of the initial ground perception area of ​​each roadside camera on the visualization interface of the target road.

[0018] Optionally, the visualization interface for obtaining the target road includes:

[0019] Obtain a visual interface of the target road through a digital twin platform or cloud visualization platform.

[0020] Optionally, obtaining the visualization result of the initial ground perception area of ​​each roadside camera on the visualization interface of the target road based on the initial ground perception area of ​​each roadside camera includes:

[0021] Obtain visualization parameters for each roadside camera, including visualization colors;

[0022] Based on the visualization parameters of each roadside camera, the initial ground perception area of ​​each roadside camera is visualized on the visualization interface of the target road.

[0023] Optionally, the sensing range adjustment information includes new boundary point information for each roadside camera, and the step of obtaining the adjusted ground sensing area for each roadside camera based on the sensing range adjustment information includes:

[0024] The adjusted ground sensing area of ​​each roadside camera is obtained based on the new boundary point information of each roadside camera.

[0025] Optionally, obtaining the adjusted target detection area of ​​the roadside camera based on the adjusted ground sensing area of ​​each roadside camera includes:

[0026] The adjusted target detection area of ​​the roadside camera is obtained based on the calibration parameters of each roadside camera and the adjusted ground sensing area of ​​each roadside camera.

[0027] Secondly, embodiments of this application also provide a target detection area planning device, the device comprising:

[0028] The first computing unit is used to acquire road images of the target road captured by multiple roadside cameras, and to obtain the initial ground perception area of ​​each roadside camera based on the road images.

[0029] The visualization unit is used to visualize the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results;

[0030] The area adjustment unit is used to acquire the perception range adjustment information generated based on the visualization results, and to acquire the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information.

[0031] The second calculation unit is used to obtain the adjusted target detection area of ​​the roadside camera based on the adjusted ground perception area of ​​each roadside camera.

[0032] Thirdly, embodiments of this application also provide an electronic device, including:

[0033] Processor; and

[0034] A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform a target detection region planning method.

[0035] Fourthly, embodiments of this application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform a target detection region planning method.

[0036] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0037] This application embodiment first acquires road images of the target road captured by multiple roadside cameras, and obtains the initial ground perception area of ​​each roadside camera based on the road images; then, it performs visualization processing on the target road and the initial ground perception areas of the multiple roadside cameras to obtain visualization results; next, it acquires perception range adjustment information generated based on the visualization results, and obtains the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information; finally, it obtains the adjusted target detection area of ​​the roadside cameras based on the adjusted ground perception areas of each roadside camera.

[0038] This application embodiment obtains and visualizes the initial ground perception area of ​​each roadside camera based on road images. From a global top-down view of the target road, the initial ground perception area of ​​each roadside camera is adjusted based on the positional relationship between the initial ground perception area and the target road. The planned target detection area is then determined by reverse engineering using the adjusted ground perception area. This reduces the difficulty of adjusting the target detection area, and region planning based on the aforementioned positional relationship ensures the compliance of the planned target detection area. Thus, the replanned target detection area of ​​each roadside camera has a reasonable overlap of field of view, improving the computational efficiency of the roadside cameras and saving computational resources. Attached Figure Description

[0039] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0040] Figure 1 This is a flowchart illustrating a target detection region planning method in an embodiment of this application;

[0041] Figure 2 This is a schematic diagram showing the field of view coverage of two roadside cameras in a real-world scenario.

[0042] Figure 3 for Figure 2 A schematic diagram of the ground sensing area after the adjustment of the two roadside cameras;

[0043] Figure 4 This is a schematic diagram of the structure of a target detection area planning device according to an embodiment of this application;

[0044] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0047] This application provides a target detection region planning method, such as... Figure 1 The diagram shows a flowchart of a target detection region planning method according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0048] Step S110: Obtain road images of the target road captured by multiple roadside cameras, and obtain the initial ground perception area of ​​each roadside camera based on the road images.

[0049] The target detection area planning method in this application embodiment can be executed by the roadside. The roadside includes, for example, roadside units deployed at intersections or road sections. Here, the road where the intersection or road section is located is generally equipped with multiple single poles, and each single pole is equipped with multiple roadside cameras facing different directions.

[0050] In this embodiment, road images are first acquired from each roadside camera on the target road. The "target road" is, for example, the road area where the intersection or road segment is located. Each roadside camera acquires images of the target road from different angles. Considering that the compliance of the ground perception area of ​​different roadside cameras is not only measured by the size of the overlapping area of ​​the field of view, it is generally necessary to ensure that the target can be detected in the overlapping area of ​​the field of view and that the targets can be successfully correlated. Based on this, if the target detection area is directly replanned at the image level from the road image, it is difficult to determine whether the replanned target detection area is compliant.

[0051] To address the above situation, this application embodiment obtains and visualizes the initial ground perception area of ​​each roadside camera based on road images, adjusts the initial ground perception area of ​​each roadside camera from a global top-down view of the target road, and determines the corresponding target detection area in reverse through the adjusted ground perception area. This reduces the difficulty of adjusting the target detection area, and the compliance of the planned target detection area can be guaranteed based on geographical location information.

[0052] refer to Figure 2As shown, the initial ground sensing area in this embodiment refers to the ground area within the field of view of the roadside camera. The road images acquired by the roadside camera generally include ground areas and non-ground areas (e.g., aerial areas). Ground detection can be performed on the road images to obtain the initial ground sensing area of ​​each roadside camera.

[0053] Step S120: Visualize the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results.

[0054] After obtaining the initial ground perception area of ​​each roadside camera, this area can be visualized on a map of the target road (e.g., a high-resolution map). This allows maintenance personnel to understand the field of view (including occlusion) of each roadside camera and the positional relationship between the initial ground perception areas of all roadside cameras, enabling them to adjust the initial ground perception area of ​​each camera and generate corresponding perception range adjustment information.

[0055] Step S130: Obtain the perception range adjustment information generated based on the visualization results, and obtain the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information.

[0056] Step S140: Obtain the adjusted target detection area of ​​the roadside camera based on the adjusted ground sensing area of ​​each roadside camera.

[0057] like Figure 1 As illustrated in the target detection region planning method, this embodiment of the application obtains and visualizes the initial ground perception region of each roadside camera based on road images. From a global top-down view of the target road, the initial ground perception region of each roadside camera is adjusted based on the positional relationship between the initial ground perception region and the target road. The planned target detection region is then determined by reverse engineering using the adjusted ground perception region. This reduces the difficulty of adjusting the target detection region, and region planning based on the aforementioned positional relationship ensures the compliance of the planned target detection region. Thus, the replanned target detection region of each roadside camera has a reasonable overlap area in its field of view, improving the computational efficiency of the roadside camera and saving computational resources.

[0058] In some embodiments of this application, the step S110 above, which obtains the initial ground perception area of ​​each roadside camera based on the road image, specifically includes:

[0059] Ground detection is performed on the road image of each roadside camera to obtain the ground detection result corresponding to each roadside camera. This embodiment can combine the ground detection algorithm in the prior art to perform ground detection on the road image, such as the detection principle of lane line intersection, road vanishing point or ground plane.

[0060] Based on the calibration parameters of each roadside camera and the ground detection results corresponding to each roadside camera, the initial ground perception area of ​​each roadside camera is obtained.

[0061] The calibration parameters of the roadside camera are used to calibrate the transformation relationship between the image coordinate system and the world coordinate system of the roadside camera. When the ground detection results in the road image are obtained, the ground detection results can be transformed into the world coordinate system according to the above calibration parameters. In order to facilitate the subsequent positioning of the initial ground perception area and the visualization of the target road, the world coordinate system in this embodiment can be the ground coordinate system.

[0062] In some embodiments of this application, step S120 above involves visualizing the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results, specifically including:

[0063] A visual interface for the target road is obtained, which displays the road's own attribute information such as road surface traffic lines, traffic lights, and road control posts. In some implementation schemes, the visual interface of the target road can be obtained through a digital twin platform or a cloud-based visualization platform. Of course, those skilled in the art can also obtain the visual interface of the target road through other visualization platforms. It should be understood that the visual interface of the target road can be a two-dimensional visualization or a three-dimensional visualization.

[0064] Based on the initial ground perception area of ​​each roadside camera, a visualization result of the initial ground perception area of ​​each roadside camera is obtained on the visualization interface of the target road. Preferably, visualization parameters for each roadside camera are obtained, and the initial ground perception area of ​​each roadside camera is visualized on the visualization interface of the target road based on these parameters. These visualization parameters may include, for example, visualization colors, so that the initial ground perception areas of different roadside cameras are displayed using different colors, facilitating accurate location of the boundaries of the initial ground perception area of ​​each roadside camera by maintenance personnel and reducing confusion.

[0065] In some scenarios, when the visualization platform supports mouse control, maintenance personnel can select the target roadside camera with the mouse and generate multiple new boundary points within the initial ground perception area of ​​the target roadside camera. The adjusted ground perception area of ​​the target roadside camera can be generated according to the order in which the new boundary points are generated.

[0066] It should be noted that maintenance personnel can generate new boundary points based on the interactive methods supported by the visualization platform, and are not limited to the mouse control method mentioned above. For example, they can also use touch control, command-triggered control, and other interactive methods. Furthermore, during the generation of new boundary points, it should be ensured that the adjusted ground sensing area generated based on the new boundary points meets the compliance requirements of the roadside cameras. In some embodiments, while ensuring compliance requirements, maintenance personnel can also generate new boundary points by referring to indicators such as the optimal sensing range of the roadside cameras and the multi-camera field of view coverage of key road sections (e.g., accident-prone road sections). That is, in practical applications, the generation rules for new boundary points can be set according to specific requirements, providing a reference for maintenance personnel to generate new boundary points. In addition, maintenance personnel can also generate multiple sets of new boundary points according to different needs, with each set corresponding to an adjusted ground sensing area under a specific requirement. Thus, during application, the corresponding target detection area of ​​the roadside camera can be selected according to specific needs. The compliance requirements described in this application are mainly defined based on the shooting requirements of the roadside camera itself and the actual road scene. For example, it is required that the target detection area of ​​a telephoto camera should cover its monitored road section.

[0067] In light of the above scenario, the sensing range adjustment information in this embodiment includes new boundary point information for each roadside camera. This new boundary point information includes, for example, the location of the new boundary points and the generation order of the boundary points. Therefore, step S130, which involves obtaining the adjusted ground sensing area for each roadside camera based on the sensing range adjustment information, specifically includes:

[0068] The adjusted ground sensing area of ​​each roadside camera is obtained based on the new boundary point information of each roadside camera.

[0069] Combination Figure 2 and Figure 3 As shown, the adjusted ground sensing areas of the telephoto and short-focus cameras can cover their respective monitored road sections, and they have a reasonable overlap in their fields of view. Therefore, the adjusted ground sensing areas of both cameras meet their respective compliance requirements. Compared to their initial ground sensing areas, the adjusted ground sensing areas of the telephoto and short-focus cameras are significantly smaller. Correspondingly, the area of ​​the target detection area planned by the telephoto and short-focus cameras is much smaller than the area of ​​their respective road images. This reduces the amount of image data that the roadside needs to compute during target detection and tracking, thereby improving the roadside's computational efficiency and saving computational resources.

[0070] After obtaining the adjusted ground sensing area of ​​each roadside camera, in some embodiments of this application, step S140 above, which involves obtaining the adjusted target detection area of ​​the roadside camera based on the adjusted ground sensing area of ​​each roadside camera, specifically includes:

[0071] The adjusted target detection area of ​​the roadside camera is obtained based on the calibration parameters of each roadside camera and the adjusted ground sensing area of ​​each roadside camera.

[0072] As mentioned earlier, the calibration parameters of the roadside camera are used to calibrate the transformation relationship between the image coordinate system and the world coordinate system of the roadside camera. When the adjusted ground perception area of ​​each roadside camera is obtained, the adjusted ground perception area can be transformed into the image coordinate system according to the above calibration parameters to obtain the adjusted target detection area of ​​the roadside camera.

[0073] This application embodiment also provides a target detection area planning device 400, such as Figure 4 As shown, a schematic diagram of a target detection region planning device according to an embodiment of this application is provided. The target detection region planning device 400 includes: a first calculation unit 410, a visualization unit 420, a region adjustment unit 430, and a second calculation unit 440, wherein:

[0074] The first computing unit 410 is used to acquire road images of the target road captured by multiple roadside cameras, and to obtain the initial ground perception area of ​​each roadside camera based on the road images.

[0075] The visualization unit 420 is used to visualize the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results.

[0076] The area adjustment unit 430 is used to acquire the perception range adjustment information generated based on the visualization results, and to acquire the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information.

[0077] The second calculation unit 440 is used to obtain the adjusted target detection area of ​​the roadside camera based on the adjusted ground perception area of ​​each roadside camera.

[0078] In some embodiments of this application, the first computing unit 410 is specifically used to perform ground detection on the road image of each roadside camera to obtain the ground detection result corresponding to each roadside camera; and to obtain the initial ground perception area of ​​each roadside camera based on the calibration parameters of each roadside camera and the ground detection result corresponding to each roadside camera.

[0079] In some embodiments of this application, the visualization unit 420 is specifically used to acquire the visualization interface of the target road; based on the initial ground perception area of ​​each roadside camera, the visualization result of the initial ground perception area of ​​each roadside camera is obtained on the visualization interface of the target road.

[0080] In some embodiments of this application, the visualization unit 420 is specifically used to obtain a visualization interface of the target road through a digital twin platform or a cloud visualization platform.

[0081] In some embodiments of this application, the visualization unit 420 is specifically used to acquire visualization parameters of each roadside camera, the visualization parameters including visualization color; and to visualize the initial ground perception area of ​​each roadside camera on the visualization interface of the target road according to the visualization parameters of each roadside camera.

[0082] In some embodiments of this application, the sensing range adjustment information includes new boundary point information for each roadside camera. The area adjustment unit 430 is specifically used to obtain the adjusted ground sensing area of ​​each roadside camera based on the new boundary point information of each roadside camera.

[0083] In some embodiments of this application, the second calculation unit 440 is specifically used to obtain the adjusted target detection area of ​​the roadside camera based on the calibration parameters of each roadside camera and the adjusted ground sensing area of ​​each roadside camera.

[0084] It is understood that the above-described target detection region planning device can implement each step of the target detection region planning method provided in the foregoing embodiments. The relevant explanations of the target detection region planning method are applicable to the target detection region planning device, and will not be repeated here.

[0085] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 5 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0086] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0087] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0088] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a target detection region planning device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0089] Acquire road images of the target road captured by multiple roadside cameras, and obtain the initial ground sensing area of ​​each roadside camera based on the road images;

[0090] The target road and the initial ground perception area of ​​multiple roadside cameras are visualized to obtain visualization results;

[0091] Obtain the perception range adjustment information generated based on the visualization results, and obtain the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information;

[0092] The adjusted target detection area of ​​each roadside camera is obtained based on the adjusted ground sensing area of ​​each roadside camera.

[0093] The above is as stated in this application. Figure 1The method executed by the target detection region planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads the information from the memory and, in conjunction with its hardware, completes the steps of the aforementioned target detection region planning method.

[0094] The electronic device can also perform Figure 1 A method for implementing a target detection area planning device, and realizing the target detection area planning device in... Figure 1 The functions of the embodiments shown are not described in detail here.

[0095] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the target detection region planning device in the illustrated embodiment is specifically used to perform:

[0096] Acquire road images of the target road captured by multiple roadside cameras, and obtain the initial ground sensing area of ​​each roadside camera based on the road images;

[0097] The target road and the initial ground perception area of ​​multiple roadside cameras are visualized to obtain visualization results;

[0098] Obtain the perception range adjustment information generated based on the visualization results, and obtain the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information;

[0099] The adjusted target detection area of ​​each roadside camera is obtained based on the adjusted ground sensing area of ​​each roadside camera.

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0106] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0108] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A target detection region planning method, characterized in that, The method includes: Acquire road images of the target road captured by multiple roadside cameras, and obtain the initial ground sensing area of ​​each roadside camera based on the road images; The target road and the initial ground perception area of ​​multiple roadside cameras are visualized to obtain visualization results; Obtain the perception range adjustment information generated based on the visualization results, and obtain the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information; The adjusted target detection area of ​​each roadside camera is obtained based on the adjusted ground sensing area of ​​each roadside camera; The sensing range adjustment information includes new boundary point information for each roadside camera. The step of obtaining the adjusted ground sensing area for each roadside camera based on the sensing range adjustment information includes: The adjusted ground sensing area of ​​each roadside camera is obtained based on the new boundary point information of each roadside camera; The new boundary point information is generated according to the interaction method supported by the visualization platform, and the new boundary point information includes the position of the new boundary points and the generation order of the new boundary points; The new boundary point information is generated in the following manner: The rules for generating new boundary points are set according to the demand indicators, which include at least one of the optimal sensing range of the roadside camera and the multi-camera field of view coverage of key road sections. New boundary point information for each roadside camera is generated according to the new boundary point generation rules.

2. The method as described in claim 1, characterized in that, The step of obtaining the initial ground perception area for each roadside camera based on the road image includes: Perform ground detection on the road images of each roadside camera to obtain the ground detection results corresponding to each roadside camera; Based on the calibration parameters of each roadside camera and the ground detection results corresponding to each roadside camera, the initial ground perception area of ​​each roadside camera is obtained.

3. The method as described in claim 1, characterized in that, The process of visualizing the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results includes: A visual interface for obtaining the target road; Based on the initial ground perception area of ​​each roadside camera, obtain the visualization result of the initial ground perception area of ​​each roadside camera on the visualization interface of the target road.

4. The method as described in claim 3, characterized in that, The visualization interface for obtaining the target road includes: Obtain a visual interface of the target road through a digital twin platform or cloud visualization platform.

5. The method as described in claim 3, characterized in that, The step of obtaining the visualization result of the initial ground perception area of ​​each roadside camera on the visualization interface of the target road based on the initial ground perception area of ​​each roadside camera includes: Obtain visualization parameters for each roadside camera, including visualization colors; Based on the visualization parameters of each roadside camera, the initial ground perception area of ​​each roadside camera is visualized on the visualization interface of the target road.

6. The method as described in claim 1, characterized in that, The step of obtaining the adjusted target detection area of ​​each roadside camera based on the adjusted ground sensing area includes: The adjusted target detection area of ​​the roadside camera is obtained based on the calibration parameters of each roadside camera and the adjusted ground sensing area of ​​each roadside camera.

7. A target detection area planning device, characterized in that, The device includes: The first computing unit is used to acquire road images of the target road captured by multiple roadside cameras, and to obtain the initial ground perception area of ​​each roadside camera based on the road images. The visualization unit is used to visualize the target road and the initial ground perception area of ​​multiple roadside cameras to obtain visualization results; The area adjustment unit is used to acquire the perception range adjustment information generated based on the visualization results, and to acquire the adjusted ground perception area of ​​each roadside camera based on the perception range adjustment information. The second calculation unit is used to obtain the adjusted target detection area of ​​the roadside camera based on the adjusted ground perception area of ​​each roadside camera; The sensing range adjustment information includes new boundary point information for each roadside camera, and the region adjustment unit is specifically used for: The adjusted ground sensing area of ​​each roadside camera is obtained based on the new boundary point information of each roadside camera; The new boundary point information is generated according to the interaction method supported by the visualization platform, and the new boundary point information includes the position of the new boundary points and the generation order of the new boundary points; The new boundary point information is generated in the following manner: The rules for generating new boundary points are set according to the demand indicators, which include at least one of the optimal sensing range of the roadside camera and the multi-camera field of view coverage of key road sections. New boundary point information for each roadside camera is generated according to the new boundary point generation rules.

8. An electronic device, characterized in that, include: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the target detection region planning method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the target detection region planning method as described in any one of claims 1 to 6.

Images