A target detection method and system based on vehicle-road collaboration

Abstract

The present invention relates to the field of vehicle-road collaboration technology, and specifically to a target detection method and system based on vehicle-road collaboration. The method includes the following steps: obtaining road point cloud data and vehicle point cloud data, wherein the road point cloud data includes historical road point cloud data and real-time road point cloud data; obtaining a background template point cloud using the historical road point cloud data, and obtaining a roadside foreground point cloud by combining the real-time road point cloud data and the background template point cloud; registering and fusing the vehicle point cloud data and the roadside foreground point cloud to obtain target detection point cloud data; and completing target detection and recognition based on the target detection point cloud data. The present invention reduces the amount of data transmission by optimizing the road point cloud data, which is beneficial to improving the target detection speed. At the same time, through the point cloud registration method, the point cloud data at both ends of the vehicle and road are effectively integrated, thereby improving the accuracy of target detection by intelligent connected vehicles and improving driving safety.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-road collaboration technology, and in particular to a target detection method and system based on vehicle-road collaboration. Background Art

[0002] With the continuous development and application of artificial intelligence, big data, and 5G technologies, autonomous driving technology has experienced rapid growth. Environmental perception, a key research topic in autonomous driving, is a crucial prerequisite for ensuring vehicle safety. Environmental perception performance impacts autonomous driving path planning, decision-making, and control. Researchers have historically focused on single-vehicle intelligent environmental perception, aiming to improve object detection performance by increasing onboard computing power and the number of sensors. However, single-vehicle intelligence suffers from issues such as blind spots and unstable mid- and long-range perception. The emergence of vehicle-infrastructure cooperative systems (VISs) offers a novel solution for autonomous driving environmental perception, effectively addressing these challenges. By communicating with road infrastructure, VISs can obtain real-time traffic status and road condition information. Leveraging the perspective and performance advantages of roadside sensors, VISs assist vehicles in obtaining more comprehensive object detection and perception results, ensuring safe driving.

[0003] Object detection is a key task in computer vision. It aims to accurately locate and identify objects in images by analyzing sensors such as lidar and cameras. Applying vehicle-infrastructure collaboration (VIS) to object detection will improve the performance of single-view object detection algorithms. In summary, VIS-based object detection is crucial for the safety of autonomous driving. The quality of VIS-based object detection algorithms plays a key role in whether intelligent connected vehicles can handle complex intersection scenarios. Therefore, research on VIS-based object detection algorithms is essential to promoting the development of intelligent connected vehicles. Summary of the Invention

[0004] In response to the shortcomings of existing methods and the needs of practical applications, in order to improve the target detection capabilities of intelligent connected vehicles in complex scenarios such as intersections and solve the blind spot and occlusion problems under a single perspective, the present invention provides a target detection method based on vehicle-road collaboration, including the following steps:

[0005] Obtain road point cloud data and vehicle point cloud data, the road point cloud data including historical road point cloud data and real-time road point cloud data; use the historical road point cloud data to obtain a background template point cloud, and combine the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud; perform registration and fusion on the vehicle point cloud data and the roadside foreground point cloud to obtain target detection point cloud data; and complete target detection and recognition based on the target detection point cloud data. The present invention optimizes the road point cloud data to reduce the amount of data transmission, which is conducive to improving the target detection speed. At the same time, through the point cloud registration method, the point cloud data of both ends of the road and the vehicle are effectively integrated for target detection, thereby improving the accuracy of target detection of intelligent connected vehicles, solving the blind spot and occlusion problems under a single perspective, and helping to improve driving safety.

[0006] Optionally, the target detection method based on vehicle-road collaboration further includes the following steps:

[0007] Construct a malicious node detection model; use the malicious node detection model to eliminate malicious base station information. The present invention uses the malicious node detection model to identify malicious base stations, effectively avoiding malicious node attacks, privacy leaks, and identity tampering, which is conducive to improving the applicability of the present invention.

[0008] Optionally, the malicious node detection model satisfies the following formula: ,in, Represents the trust value, Indicates the number of times a node successfully interacts with another node. Indicates the number of times a node fails to interact with another node. represents the trust threshold, , Represents the historical trust value between a node and another node, Represents the new trust value between a node and another node.

[0009] Optionally, combining the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud comprises the following steps:

[0010] Each point in the real-time roadside point cloud data is traversed to obtain the neighborhood corresponding to each point; a similarity model is constructed and used to determine the similarity between each point and the background template point cloud; a similarity threshold is set, and based on the similarity and the similarity threshold, a roadside foreground point cloud is obtained. By setting the background template point cloud once, the present invention reduces the amount of subsequent data matching and allows for rapid acquisition of point cloud data for areas of interest, thereby improving detection efficiency.

[0011] Optionally, the similarity model satisfies the following formula:

[0012]

[0013] in, Indicates the The similarity between the point cloud and the background template point cloud, represents the length of the neighborhood, represents the width of the neighborhood, represents the height of the neighborhood, Indicates the The coordinates of the point cloud on the X axis, Indicates the The coordinates of the point cloud on the Y axis, Indicates the The coordinates of the point cloud on the Z axis, Indicates the The number of point clouds in the neighborhood of a point cloud that also belong to the background template point cloud.

[0014] Optionally, registering and fusing the vehicle endpoint cloud data and the roadside foreground point cloud data to obtain target detection point cloud data includes the following steps:

[0015] The vehicle endpoint cloud data and the roadside foreground point cloud are subjected to voxel downsampling, and surface reconstruction is performed based on the voxel downsampling results to obtain vehicle endpoint cloud reconstruction data and roadside foreground reconstructed point cloud; a coarse registration transformation matrix is ​​obtained based on the vehicle endpoint cloud reconstruction data and the roadside foreground reconstructed point cloud; the roadside foreground reconstructed point cloud is subjected to rigid body transformation using the coarse registration transformation matrix, and based on an iterative closest point algorithm, the transformation result and the vehicle endpoint cloud reconstruction data are combined to obtain a fine registration transformation matrix; the fine registration transformation matrix, the vehicle endpoint cloud data, and the roadside foreground point cloud are combined to obtain the target detection point cloud data. The present invention uses the reconstructed point cloud data to perform two registrations to obtain a fine registration transformation matrix, and then completes the point cloud data fusion to obtain the target detection point cloud data.

[0016] Optionally, obtaining a coarse registration transformation matrix based on the vehicle end point cloud reconstruction data and the roadside foreground reconstructed point cloud comprises the following steps:

[0017] By using any two adjacent graphics in the surface graphics, a geometric relationship feature vector between the adjacent graphics is obtained; using the geometric relationship feature vector, a comprehensive feature vector of the surface graphics is obtained; based on the comprehensive feature vector, an initial matching graphic of the vehicle end point cloud reconstruction data and the roadside foreground reconstructed point cloud is obtained; the initial matching graphic is evaluated to obtain the optimal coarse matching graphic, and then the coarse registration transformation matrix is ​​obtained using the optimal coarse matching graphic. The present invention obtains all geometric relationship feature vectors of the surface graphics and then obtains a comprehensive feature vector, takes the one that meets the conditions as the initial matching graphic, and finally evaluates the optimal initial matching graphic to obtain the coarse registration transformation matrix, which is conducive to quickly completing the initial data screening and matching, and improves the detection efficiency of the present invention.

[0018] Optionally, the use of the geometric relationship feature vector to obtain the comprehensive feature vector of the surface graphic satisfies the following formula:

[0019] ,in, Represents the comprehensive feature vector of the graph within the feature calculation range, Represents the geometric relationship feature vector of the graphics within the feature calculation range, Indicates the number of adjacent graphics within the feature calculation range. Indicates the first graphic within the feature calculation range. The geometric relationship feature vectors of adjacent graphics, Indicates the first graphic within the feature calculation range. The area of ​​adjacent shapes.

[0020] Optionally, the evaluating the initial matching graph to obtain an optimal coarse matching graph satisfies the following formula:

[0021]

[0022] in, represents the initial matching error coefficient of the graphics, represents the number of initial matching graphs, Expressed as The distance difference between the initial matching graphics after conversion, Expressed as For the initial matching graph, Represents a pre-set distance difference. Through the model formula, the specific quantitative evaluation results are further facilitated to accurately and quickly match point clouds and complete target detection.

[0023] On the second aspect, in order to be able to efficiently execute the target detection method based on vehicle-road collaboration provided by the present invention, the present invention also provides a target detection system based on vehicle-road collaboration, including a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the target detection method based on vehicle-road collaboration as described in the first aspect of the present invention. The target detection system based on vehicle-road collaboration of the present invention has a compact structure and stable performance, and can stably execute the target detection method based on vehicle-road collaboration provided by the present invention, further improving the overall applicability and practical application capabilities of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flow chart of a target detection method based on vehicle-road collaboration provided by an embodiment of the present invention;

[0025] Figure 2 A framework diagram of a target detection system based on vehicle-road collaboration provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a target detection device based on vehicle-road collaboration provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the present invention. In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that these specific details are not necessarily required to practice the present invention. In other instances, well-known circuits, software, or methods are not specifically described to avoid obscuring the present invention.

[0028] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combinations and / or subcombinations in one or more embodiments or examples. Furthermore, those of ordinary skill in the art will appreciate that the figures provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0029] See also Figure 1In order to improve the target detection capability of intelligent connected vehicles in complex scenarios such as intersections and solve the blind spot and occlusion problems under a single perspective, the present invention provides a target detection method based on vehicle-road collaboration, such as Figure 1 As shown, the method includes the following steps:

[0030] S1. Obtain road endpoint cloud data and vehicle endpoint cloud data, wherein the road endpoint cloud data includes historical road endpoint cloud data and real-time road endpoint cloud data.

[0031] The roadside in vehicle-road collaboration refers to the road infrastructure, which is a crucial component of the vehicle-road collaboration system. Roadside equipment is primarily responsible for communicating with vehicle-side equipment and collecting information about the road and its surroundings to achieve comprehensive perception and collaborative control of the traffic environment. Specifically, roadside equipment typically includes intelligent roadside units (RSUs), cameras, millimeter-wave radars, lidars, and other sensing devices, as well as high-performance computing units required for data processing. These devices exchange and share information with vehicle-side equipment (such as intelligent on-board units (OBUs)) through wireless communication technology, enabling seamless collaboration between vehicles and road infrastructure.

[0032] The vehicle side is the part of the vehicle-road cooperative system that is responsible for real-time processing of massive amounts of data on the vehicle side and fusion of multi-sensor data. It uses various sensors and intelligent devices, such as lidar, cameras, millimeter-wave radar, etc., to perceive the information of the vehicle's surrounding environment in real time, and transmit this information to the roadside side or the cloud through the communication network for further processing and analysis.

[0033] Roadside point cloud data primarily comes from sensors installed on road infrastructure, such as LiDAR and cameras. These sensors capture three-dimensional information about the road and its surroundings in real time, generating point cloud data. LiDAR measures the distance between objects and the sensor by emitting laser pulses and receiving reflected signals, generating three-dimensional point cloud data. Commonly used equipment includes terrestrial laser scanners (such as Leica and Trimble), which are typically installed on both sides of roads or on overpasses to scan the road and its surroundings. Cameras capture images of the road and its surroundings and then use computer vision algorithms to synthesize these images into a complete three-dimensional model, generating point cloud data. Commonly used equipment includes high-definition cameras and stereo cameras, which can be installed on road infrastructure such as traffic lights and street lamps. In addition to LiDAR and cameras, other sensors such as ultrasonic sensors and infrared sensors can also be used to obtain roadside point cloud data. Each of these sensors has its own unique characteristics, and appropriate combinations can be selected based on actual needs.

[0034] Vehicle-to-point cloud data primarily comes from sensors installed on the vehicle, such as on-board LiDAR and cameras. These sensors can capture three-dimensional information about the vehicle's surroundings in real time, providing a basis for decision-making for autonomous vehicles. On-board LiDAR measures the distance between the vehicle and its surroundings by emitting laser pulses and receiving reflected signals, generating three-dimensional point cloud data. Commonly used devices include on-board LiDAR (such as Velodyne and Ouster), which are typically installed on the top or front of the vehicle to scan the vehicle's surroundings. On-board cameras capture images of the vehicle's surroundings and then process and analyze them using computer vision algorithms to generate point cloud data. Commonly used devices include high-definition cameras and stereo cameras, which can be installed on the front, side, and rear of the vehicle to obtain image information from different angles.

[0035] When acquiring point cloud data, it's important to consider its accuracy and resolution. The higher the accuracy and resolution, the better the point cloud data quality, and the more it can meet the requirements of applications like autonomous driving. In these applications, the real-time and reliability of point cloud data are crucial. Therefore, when selecting sensors and data processing algorithms, ensure they meet these real-time and reliability requirements. Furthermore, compliance with relevant privacy and security regulations is crucial to ensure the privacy and rights of others are not violated.

[0036] Furthermore, the road endpoint cloud data at the current detection moment is the real-time road endpoint cloud data, and the road endpoint cloud data stored in the database or cloud before the current detection moment is the historical road endpoint cloud data.

[0037] In other embodiments, after obtaining the road endpoint cloud data and the vehicle endpoint cloud data, the vehicle-road collaboration-based target detection method further includes the following steps:

[0038] S11. Build a malicious node detection model.

[0039] Specifically, the malicious node detection model satisfies the following formula:

[0040]

[0041] in, Represents the trust value, Indicates the number of times a node successfully interacts with another node. Indicates the number of times a node fails to interact with another node. represents the trust threshold, , Represents the historical trust value between a node and another node, Represents the new trust value between a node and another node. With each detection, the trust value between nodes is obtained based on the data exchange between each device as a port node. The current trust value is used as the new trust value, and the previous data is used as the historical trust value.

[0042] S12: Utilize the malicious node detection model to eliminate malicious base station information.

[0043] Specifically, the trust value and trust threshold between base stations are calculated by the malicious node detection model, and the corresponding base stations with trust values ​​less than the trust threshold are removed as malicious nodes.

[0044] S2. Utilize the historical road point cloud data to obtain a background template point cloud, and combine the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud.

[0045] There is a lot of redundancy between the point cloud frames collected by road-side equipment at the same location. The background parts such as buildings, trees, and ground in the surrounding environment show large-area overlap and highly similar statistical characteristics, while the differences between the point cloud frames happen to be the foreground point clouds of interest.

[0046] In this embodiment, the background template point cloud is obtained using the historical road point cloud data by removing all foreground target point clouds of interest. A single-frame point cloud is relatively sparse and may contain visual blind spots caused by target occlusion, making it impossible to fully describe the surrounding background environment. Therefore, multiple frames of point clouds can be spliced ​​together to construct a background template point cloud that provides a more comprehensive description of the surrounding environment. It should be understood that the template point cloud is collected during periods when foreground targets are sparse. If necessary, foreground points of targets of interest (including stationary foreground targets) are manually selected and removed to obtain a pure background template point cloud.

[0047] Furthermore, the step S2 combines the real-time road point cloud data and the background template point cloud to obtain the roadside foreground point cloud, including the following steps:

[0048] S21. Traverse each point in the real-time road endpoint cloud data to obtain a neighborhood corresponding to each point.

[0049] In this embodiment, the neighborhood is just centered on the point in the real-time road endpoint cloud data. For the long, For width, A high cube.

[0050] S22: construct a similarity model, and use the similarity model to obtain the similarity between each point and the background template point cloud.

[0051] Specifically, the similarity model satisfies the following formula: ,in, Indicates the The similarity between the point cloud and the background template point cloud, represents the length of the neighborhood, represents the width of the neighborhood, represents the height of the neighborhood, Indicates the The coordinates of the point cloud on the X axis, Indicates the The coordinates of the point cloud on the Y axis, Indicates the The coordinates of the point cloud on the Z axis, Indicates the The number of point clouds in the neighborhood of a point cloud that also belong to the background template point cloud.

[0052] S23 . Set a similarity threshold, and obtain a roadside foreground point cloud according to the similarity and the similarity threshold.

[0053] In an embodiment, the similarity threshold is set according to practical experience, and the similarity obtained by the similarity model is compared with the similarity threshold. The point cloud with a similarity greater than the similarity threshold is classified as a background template point cloud, otherwise it is classified as a roadside foreground point cloud.

[0054] It should be understood that the initial detection results still contain a small number of outliers. Outliers, also known as isolated points, are noise points that significantly deviate from the foreground point cloud cluster. These outliers mostly originate from the background point cloud or measurement noise, which not only affects the detection performance of subsequent algorithms but also consumes a certain amount of storage space. Therefore, it is necessary to perform outlier filtering based on the initial search results to obtain a smaller and purer roadside foreground point cloud.

[0055] S3. Register and fuse the vehicle endpoint cloud data and the roadside foreground point cloud data to obtain target detection point cloud data.

[0056] In an embodiment, the step S3 of registering and fusing the vehicle endpoint cloud data and the roadside foreground point cloud to obtain target detection point cloud data includes the following steps:

[0057] S31 . Perform voxel downsampling on the vehicle endpoint cloud data and the roadside foreground point cloud, and perform surface reconstruction based on the voxel downsampling result to obtain vehicle endpoint cloud reconstructed data and roadside foreground reconstructed point cloud.

[0058] The principle of voxel downsampling is to divide the three-dimensional space where the point cloud data is located into multiple cubes of fixed size (called voxels), and then retain only one point in each voxel as a representative to replace all the points in the voxel.

[0059] Specifically, the voxel downsampled three-dimensional point cloud is projected onto a two-dimensional plane using a greedy projection method, and then a polygonal mesh is established using a recursive growth method, a split-and-merge method, or a point-by-point insertion method. In this embodiment, a triangular mesh is used. After the establishment is completed, the two-dimensional polygonal mesh is restored to a three-dimensional space based on the three-dimensional topological relationship between the point clouds to complete the surface reconstruction.

[0060] S32. Obtain a coarse registration transformation matrix based on the vehicle end point cloud reconstruction data and the roadside foreground reconstructed point cloud.

[0061] In an embodiment, obtaining a coarse registration transformation matrix based on the vehicle end point cloud reconstruction data and the roadside foreground reconstructed point cloud includes the following steps:

[0062] S321. Obtain a geometric relationship feature vector between any two adjacent graphics in the surface graphics.

[0063] Taking any spatial polygon as the central figure and defining the local coordinate system, the geometric relationship feature vectors of other spatial polygons collinear with the central figure are obtained. Furthermore, the geometric relationship feature vectors include the normal vector of the spatial polygon and the unit vector of the local coordinate system. 、 、 The angle in radians between represents the unit normal vector of the central figure, Represents the unit vector from the center point of the central figure to the vertex, Represents 、 Perpendicular unit vector.

[0064] S322. Obtain a comprehensive feature vector of the surface graphic using the geometric relationship feature vector.

[0065] In an embodiment, the geometric relationship feature vector is used to obtain a comprehensive feature vector of the surface figure, which satisfies the following formula:

[0066] ,in, Represents the comprehensive feature vector of the graph within the feature calculation range, Represents the geometric relationship feature vector of the graphics within the feature calculation range, Indicates the number of adjacent graphics within the feature calculation range. Indicates the first graphic within the feature calculation range. The geometric relationship feature vectors of adjacent graphics, Indicates the first graphic within the feature calculation range. The area of ​​adjacent shapes.

[0067] S323. Obtain an initial matching graph of the vehicle endpoint cloud reconstruction data and the roadside foreground point cloud reconstruction data based on the comprehensive feature vector.

[0068] In this embodiment, the distance between the comprehensive feature vectors is calculated. When the distance between two feature vectors is less than or equal to a matching threshold, they are preliminarily identified as a matching feature pair, thereby obtaining an initial matching pattern between the vehicle endpoint cloud reconstructed data and the roadside foreground point cloud reconstructed data. Furthermore, the distance between the comprehensive feature vectors can be calculated using Euclidean distance, Manhattan distance, Minkowski distance, or Chebyshev distance.

[0069] S324 , evaluating the initial matching graph to obtain an optimal coarse matching graph, and then using the optimal coarse matching graph to obtain the coarse registration transformation matrix.

[0070] Specifically, the initial matching graph is evaluated to obtain an optimal coarse matching graph that satisfies the following formula:

[0071]

[0072] in, represents the initial matching error coefficient of the graphics, represents the number of initial matching graphs, Expressed as The distance difference between the initial matching graphics after conversion, Expressed as For the initial matching graph, Indicates the preset distance difference.

[0073] Furthermore, based on the obtained optimal coarse matching graph, a coarse registration transformation matrix is ​​obtained by the SAC-IA method.

[0074] S33. Use the coarse registration transformation matrix to perform a rigid body transformation on the roadside foreground reconstructed point cloud, and based on an iterative closest point algorithm, combine the transformation result and the vehicle end point cloud reconstruction data to obtain a fine registration transformation matrix.

[0075] Specifically, the coarse registration transformation matrix is ​​used to perform a rigid body transformation on the roadside foreground reconstructed point cloud to obtain a transformed point cloud; then, the transformed point cloud is used as the initial origin point cloud, and the vehicle end point cloud reconstructed data is used as the initial target point cloud, and the iterative closest point algorithm is used for calculation to obtain a fine registration transformation matrix.

[0076] S34. Combining the precise registration transformation matrix, the vehicle endpoint cloud data, and the roadside foreground point cloud, obtain the target detection point cloud data.

[0077] In an embodiment, the precise registration transformation matrix is ​​used to perform a rigid body transformation on the roadside foreground point cloud, and the transformed vehicle endpoint cloud data will be aligned with the roadside foreground point cloud data in a unified coordinate system; the transformed roadside foreground point cloud data and the vehicle endpoint cloud data are then fused to obtain the target detection point cloud data.

[0078] S4. Complete target detection and recognition based on the target detection point cloud data.

[0079] In an embodiment, a target detection model is constructed, and target detection and recognition are completed using the target detection model and the target detection point cloud data.

[0080] Furthermore, the target detection model includes PointNet, PointRCNN, and STD deep learning networks.

[0081] See also Figure 2 In an embodiment, in order to be able to efficiently execute the target detection method based on vehicle-road collaboration provided by the present invention, the present invention also provides a target detection system based on vehicle-road collaboration, including: an input device, an output device, a processor, and a memory, wherein the input device, output device, processor, and memory are interconnected, and the memory contains program instructions, and the program instructions are used for the steps of the target detection method based on vehicle-road collaboration. The target detection system based on vehicle-road collaboration of the present invention has a compact structure and stable performance, and can stably execute the target detection method based on vehicle-road collaboration of the present invention, further improving the overall applicability and practical application capabilities of the present invention.

[0082] In an embodiment, the processor may be a central processing unit (CPU), which may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The input device may be used to obtain data information. The output device may be used to output the results obtained by storing the program instructions contained in the computer program in the memory provided by the present invention. The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory.

[0083] In yet another alternative embodiment, see Figure 3 In order to efficiently execute the target detection method based on vehicle-road collaboration provided by the present invention, this embodiment also provides a target detection device based on vehicle-road collaboration, such as Figure 3 Shown, including:

[0084] The memory 10 is used to store computer programs; the processor 20 is used to execute the computer programs to implement the above-mentioned vehicle-road collaboration-based target detection method. The memory 10, processor 20, communication interface 31, and communication bus 32 are all interconnected via the communication bus 32.

[0085] In an embodiment, the memory 10 is used to store one or more program instructions. The memory 10 may store program instructions for implementing the following functions:

[0086] Obtain road point cloud data and vehicle point cloud data, wherein the road point cloud data includes historical road point cloud data and real-time road point cloud data; use the historical road point cloud data to obtain a background template point cloud, and combine the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud; align and fuse the vehicle point cloud data and the roadside foreground point cloud to obtain target detection point cloud data; and complete target detection and recognition based on the target detection point cloud data.

[0087] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function, etc.; the data storage area may store data created during use. In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0088] The processor 20 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array, or other programmable logic device. The processor 20 may be a microprocessor or any conventional processor. The processor 20 may call programs stored in the memory 10. The communication interface 31 may be an interface of a communication module for connecting to other devices or systems.

[0089] Of course, it needs to be explained that Figure 3 The structure shown does not constitute a limitation on the target detection device based on vehicle-road collaboration in this embodiment. In actual applications, the target detection device based on vehicle-road collaboration may include Figure 3 More or fewer components than shown, or combinations of certain components.

[0090] An embodiment further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned target detection method based on vehicle-road collaboration are implemented.

[0091] The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., which can store program codes.

[0092] In summary, the present invention optimizes the point cloud data at both ends of the road to reduce the amount of data transmission, which is beneficial to improving the target detection speed. At the same time, through the point cloud registration method, it effectively integrates the point cloud data at both ends of the vehicle and the road for target detection, thereby improving the accuracy of target detection of intelligent connected vehicles, solving the blind spot and occlusion problems under a single perspective, and helping to improve driving safety.

[0093] Therefore, the present invention effectively overcomes various shortcomings of the prior art and has high industrial utilization value.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope described in the present invention.

Claims

1. A target detection method based on vehicle-road collaboration, characterized in that: The target detection method based on vehicle-road collaboration includes the following steps: Acquire road endpoint cloud data and vehicle endpoint cloud data, wherein the road endpoint cloud data includes historical road endpoint cloud data and real-time road endpoint cloud data; Using the historical road point cloud data to obtain a background template point cloud, and combining the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud; Registering and fusing the vehicle endpoint cloud data and the roadside foreground point cloud data to obtain target detection point cloud data; Based on the target detection point cloud data, complete target detection and recognition; Build a malicious node detection model; Eliminate malicious base station information using the malicious node detection model; The malicious node detection model satisfies the following formula: in, Represents the trust value, Indicates the number of times a node successfully interacts with another node. Indicates the number of times a node fails to interact with another node. represents the trust threshold, , Represents the historical trust value between a node and another node, Represents the new trust value between a node and another node; The step of combining the real-time road point cloud data and the background template point cloud to obtain a roadside foreground point cloud comprises the following steps: Traversing each point in the real-time road endpoint cloud data to obtain a neighborhood corresponding to each point; Constructing a similarity model, and using the similarity model to obtain the similarity between each point and the background template point cloud; Setting a similarity threshold, and obtaining a roadside foreground point cloud according to the similarity and the similarity threshold; The similarity model satisfies the following formula: in, Indicates the The similarity between the point cloud and the background template point cloud, represents the length of the neighborhood, represents the width of the neighborhood, represents the height of the neighborhood, Indicates the The coordinates of the point cloud on the X axis, Indicates the The coordinates of the point cloud on the Y axis, Indicates the The coordinates of the point cloud on the Z axis, Indicates the The number of point clouds in the neighborhood of a point cloud that also belong to the background template point cloud.

2. The target detection method based on vehicle-road collaboration according to claim 1, characterized in that: The step of registering and fusing the vehicle endpoint cloud data and the roadside foreground point cloud data to obtain target detection point cloud data includes the following steps: Performing voxel downsampling on the vehicle endpoint cloud data and the roadside foreground point cloud, and performing surface reconstruction based on the voxel downsampling results to obtain vehicle endpoint cloud reconstructed data and roadside foreground reconstructed point cloud; Obtaining a coarse registration transformation matrix based on the vehicle endpoint cloud reconstruction data and the roadside foreground reconstructed point cloud; Using the coarse registration transformation matrix, the roadside foreground reconstructed point cloud is rigidly transformed, and based on an iterative closest point algorithm, the transformation result and the vehicle end point cloud reconstruction data are combined to obtain a fine registration transformation matrix; The target detection point cloud data is obtained by combining the fine registration transformation matrix, the vehicle endpoint cloud data and the roadside foreground point cloud.

3. The target detection method based on vehicle-road collaboration according to claim 2, characterized in that: The step of obtaining a coarse registration transformation matrix based on the vehicle end point cloud reconstruction data and the roadside foreground reconstructed point cloud comprises the following steps: Obtaining a geometric relationship feature vector between any two adjacent graphics in the surface graphics; Obtaining a comprehensive feature vector of the surface figure using the geometric relationship feature vector; Obtaining an initial matching graph of the vehicle endpoint cloud reconstruction data and the roadside foreground reconstructed point cloud according to the comprehensive feature vector; The initial matching graph is evaluated to obtain an optimal coarse matching graph, and then the coarse registration transformation matrix is ​​obtained using the optimal coarse matching graph.

4. The target detection method based on vehicle-road collaboration according to claim 3 is characterized in that: The geometric relationship feature vector is used to obtain the comprehensive feature vector of the surface figure, which satisfies the following formula: in, Represents the comprehensive feature vector of the graph within the feature calculation range, Represents the geometric relationship feature vector of the graphics within the feature calculation range, Indicates the number of adjacent graphics within the feature calculation range. Indicates the first graphic within the feature calculation range. The geometric relationship feature vectors of adjacent graphics, Indicates the first graphic within the feature calculation range. The area of ​​adjacent shapes.

5. The target detection method based on vehicle-road collaboration according to claim 3 is characterized in that: The initial matching graph is evaluated to obtain an optimal coarse matching graph that satisfies the following formula: in, represents the initial matching error coefficient of the graphics, represents the number of initial matching graphs, Expressed as The distance difference between the initial matching graphics after conversion, Expressed as For the initial matching graph, Indicates the preset distance difference.

6. A target detection system based on vehicle-road collaboration, characterized in that: The target detection system based on vehicle-road collaboration includes: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory includes program instructions, and the program instructions are used to execute the target detection method based on vehicle-road collaboration according to any one of claims 1-5.

Images