A method and system for radar target queue maintenance and trajectory correlation at intersections

Abstract

This invention discloses a radar target queuing maintenance and trajectory association method and system at intersections, relating to the field of intelligent traffic management. The method includes: acquiring target states by comprehensively considering intersection topology information such as lane number, lane width, and stop line position, along with detection data; combining target detection results such as position, vehicle type, and reflection intensity; and using a bipartite graph matching algorithm to associate the motion state information of moving targets and queuing targets in a vehicle-to-vehicle transition scenario, ensuring the accuracy of trajectory association between moving targets and queuing targets. Simultaneously, short-term predictions are performed on stationary targets, and these predictions are retained based on stop line position and preceding vehicle data to prevent distortion caused by long-term predictions of low-speed and stationary targets, and to avoid false targets formed by setting fixed retention times, further improving the accuracy of trajectory association between moving targets and queuing targets.

Description

Technical Field

[0001] This invention relates to the field of intelligent traffic management, and in particular to a radar target intersection queue maintenance and trajectory association method and system. Background Technology

[0002] In intelligent transportation systems, intersections are crucial nodes in traffic flow and accident-prone areas. Therefore, monitoring and controlling traffic flow at intersections is of significant practical importance. Currently, traffic flow monitoring systems based on millimeter-wave radar are widely used, enabling rapid and accurate detection and tracking of moving vehicles within intersections.

[0003] Currently, radar sensors have poor tracking capabilities for stationary targets, making it difficult to effectively address the issues of maintaining vehicle queue lengths and trajectory correlation at intersections. Radar measures range and velocity of targets through electromagnetic wave reflection and the Doppler effect. The echoes from stationary targets and the background do not undergo Doppler frequency shift in the frequency domain and are generally referred to as background clutter. Because a large amount of background clutter severely interferes with radar's detection and measurement of moving targets, although radar can detect stationary targets, it typically filters out low-speed targets to eliminate the influence of background clutter. Therefore, radar's identification of low-speed and stationary vehicles is relatively poor. Furthermore, since vehicles at intersections are often in complex states such as waiting, changing lanes, and turning, traditional target tracking methods struggle to accurately identify and track vehicle trajectories, leading to significant challenges in using radar for vehicle queue length detection and subsequent traffic monitoring and flow control.

[0004] Given the above background, some solutions exist for the problems of intersection queue maintenance and trajectory association. For example, target tracking and intersection queue maintenance based on Kalman filtering is a common technical solution. However, when dealing with radar target intersection queue maintenance and trajectory association, using only Kalman filtering for tracking still has some problems, the specific reasons of which are as follows:

[0005] (1) Long-term prediction of low-speed and stationary targets leads to distortion. The time window length of traffic lights at different intersections varies, as does the degree of congestion. Setting a simple fixed time retention for queuing targets can easily create false targets, while long-term Kalman filtering can easily lead to distortion.

[0006] (2) The road topology structure, such as road stop lines and lane lines, was not fully utilized, resulting in inaccurate calculation of the queuing start position and queuing length.

[0007] (3) The motion trajectories in the intersection area are complex, and target matching based on Euclidean distance is prone to producing incorrect associated trajectories. Vehicles in the intersection are usually in complex states such as waiting, changing lanes, and turning. When multiple targets move near the intersection, their trajectories may intersect, which will cause the Kalman filter to fail to accurately track the position and speed of the targets, thus affecting the trajectory association results. Summary of the Invention

[0008] To address the aforementioned technical problems, this invention provides a radar target intersection queue maintenance and trajectory association method and system, which can solve the problem of low accuracy in existing radar target intersection queue maintenance and trajectory association methods.

[0009] To achieve the above objectives, in one aspect, the present invention provides a radar target intersection queue maintenance and trajectory association method, the method comprising:

[0010] Obtain the intersection topology information and configure the radar sensor parameters of the intersection based on the topology information;

[0011] The system collects target status information at the intersection based on the configured radar sensors and updates the target status information according to a preset filtering algorithm.

[0012] Based on the updated target state information, the target is classified into motion types and the state information of stationary targets is obtained.

[0013] Trajectory association matching of targets with different motion types is performed using a pre-set bipartite graph matching algorithm;

[0014] Traffic management at intersections is carried out based on the state information of the stationary target and the trajectory information after trajectory association and matching.

[0015] Furthermore, the step of configuring the radar sensor parameters of the intersection based on the topology information includes:

[0016] Configure the target intensity threshold of the radar sensor based on the empirical value of the target reflection intensity in the topology information, and configure the clustering range of the radar sensor for the target based on the road width and number of lanes in the topology information.

[0017] Furthermore, the step of collecting intersection target state information based on the configured radar sensors and updating the target state information according to a preset filtering algorithm includes:

[0018] Based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector, the target state information at the intersection is measured and updated using a preset Kalman filter algorithm.

[0019] Based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimate of the current frame, the radar sensor's observed position vector, the observation matrix, the identity matrix, the measurement error matrix, and the Kalman gain, the target state information at the intersection is predicted and updated using a preset Kalman filtering algorithm.

[0020] Furthermore, the step of classifying the motion type of the target based on the updated target state information and obtaining the state information of the stationary target includes:

[0021] Based on the updated target speed, the targets in the intersection area are divided into stationary targets and moving targets, and the status information of the stationary targets is obtained.

[0022] Furthermore, the step of performing trajectory association matching for targets of different motion types using a preset bipartite graph matching algorithm includes:

[0023] Construct a bipartite graph G = (X, Y, E) between moving targets and stationary targets, where X represents the set of moving targets, Y represents the set of stationary targets, E represents the set of edges connecting moving targets and stationary targets, and the weight of each edge represents the degree of matching between moving targets and stationary targets.

[0024] Construct an n1*n2 matrix M based on the number of nodes in the bipartite graph, where w ij This represents the weight between the i-th moving target and the j-th stationary target;

[0025] Based on the target state information and environmental state information in the intersection topology information, obtain each element w in matrix M. ij The matching index between the corresponding moving target and the stationary target;

[0026] Based on each element w in matrix M ij The matching index between the corresponding moving and stationary targets associates the trajectory information of the stationary targets with the trajectory of the moving targets that have started.

[0027] On the other hand, the present invention provides a radar target intersection queue maintenance and trajectory association system, the system comprising: an acquisition unit, used to acquire intersection topology information and configure radar sensor parameters of the intersection according to the topology information;

[0028] The update unit is used to collect the target status information at the intersection based on the configured radar sensors, and update the target status information according to a preset filtering algorithm.

[0029] The classification unit is used to classify the motion type of the target based on the updated target state information and to obtain the state information of stationary targets.

[0030] The matching unit is used to perform trajectory association matching for targets with different motion types using a preset bipartite graph matching algorithm;

[0031] The management unit is used to perform intersection traffic management based on the state information of the stationary target and the trajectory information after trajectory association and matching.

[0032] Furthermore, the acquisition unit is specifically configured to configure the target intensity threshold of the radar sensor based on the empirical value of the target reflection intensity in the topology information, and to configure the clustering range of the radar sensor for the target based on the road width and number of lanes in the topology information.

[0033] Furthermore, the updating unit is specifically used to measure and update the intersection target state information based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector using a preset Kalman filter algorithm;

[0034] Based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimate of the current frame, the radar sensor's observed position vector, the observation matrix, the identity matrix, the measurement error matrix, and the Kalman gain, the target state information at the intersection is predicted and updated using a preset Kalman filtering algorithm.

[0035] Furthermore, the classification unit is specifically used to divide the targets in the intersection area into stationary targets and moving targets according to the updated target speed, and to obtain the state information of the stationary targets.

[0036] Further, the matching unit is specifically used to establish a bipartite graph G = (X, Y, E) between moving targets and stationary targets, where X represents the set of moving targets, Y represents the set of stationary targets, E represents the set of edges connecting moving targets and stationary targets, and the weight of each edge represents the degree of matching between moving targets and stationary targets; and to establish an n1*n2 matrix M based on the number of nodes in the bipartite graph, where w ij This represents the weight between the i-th moving target and the j-th stationary target; each element w in matrix M is obtained based on the target state information and environmental state information in the intersection topology information. ij The matching index between the corresponding moving target and the stationary target; based on each element w in matrix M ij The matching index between the corresponding moving and stationary targets associates the trajectory information of the stationary targets with the trajectory of the moving targets that have started.

[0037] This invention provides a radar target queuing maintenance and trajectory association method and system at intersections. By comprehensively considering intersection topology information such as the number of lanes, lane width, and stop line position, as well as detection data, the system acquires the target state. Combined with target detection results such as position, vehicle type, and reflection intensity, a bipartite graph matching algorithm is used to associate the motion state information of moving targets and queuing targets in the vehicle stationary-to-start transition scenario. This ensures the accuracy of trajectory association between moving targets and queuing targets. Simultaneously, short-term prediction is performed on stationary targets, and the prediction is retained in conjunction with stop line position and preceding vehicle data. This prevents distortion caused by long-term prediction of low-speed and stationary targets and avoids false targets formed by setting a fixed retention time, further improving the accuracy of trajectory association between moving targets and queuing targets. Attached Figure Description

[0038] Figure 1 This is a flowchart of a radar target intersection queue maintenance and trajectory association method provided by the present invention;

[0039] Figure 2 This is a schematic diagram of the structure of a radar target intersection queue maintenance and trajectory association system provided by the present invention. Detailed Implementation

[0040] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0041] like Figure 1 As shown in the figure, an embodiment of the present invention provides a radar target intersection queue maintenance and trajectory association method, which includes the following steps:

[0042] 101. Obtain the intersection topology information and configure the radar sensor parameters of the intersection according to the topology information.

[0043] In this embodiment of the invention, step 101 may specifically include: configuring the target intensity threshold of the radar sensor according to the empirical value of the target reflection intensity in the topology information, and configuring the clustering range of the radar sensor for the target according to the road width and number of lanes in the topology information.

[0044] For example, firstly, the intersection's topological structure information, including the number of lanes, lane width, and green belt width, is obtained through surveying or high-precision mapping. The intersection area is then divided and marked, and the radar installation location, intersection area, stop line location, and detection range are recorded. The millimeter-wave radar parameters are set using the road topology, outputting the detection and clustering results for road traffic targets. Currently, radar chips provided by manufacturers have built-in filtering and clustering algorithms. The radar's target detection intensity threshold can be set using empirical values ​​of target reflection intensity, and the target clustering range can be set using road width and number, grouping targets in the same location and with similar speeds into the same cluster. Combining the radar installation location, stop line location, and detection range, the position, speed, and other status information of moving targets can finally be obtained.

[0045] 102. Collect target status information at the intersection based on the configured radar sensors, and update the target status information according to the preset filtering algorithm.

[0046] In this embodiment of the invention, step 102 may specifically include: measuring and updating the intersection target state information using a preset Kalman filter algorithm based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector; and predicting and updating the intersection target state information using a preset Kalman filter algorithm based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimated value of the current frame, the radar sensor observation position vector, observation matrix, identity matrix, measurement error matrix, and Kalman gain.

[0047] For example, according to the formula Perform measurement updates according to the formula. The prediction is updated, where x is the target's velocity and position state vector, "^" represents the predicted value for the current frame, and "~" represents the optimal estimate for the current frame. z is the observation position vector, and u is the input vector. A is the state transition matrix, B is the input control matrix, P is the prediction error matrix, Q is the process noise matrix, K is the Kalman gain, R is the measurement error matrix, H is the observation matrix, and I is the identity matrix.

[0048] 103. Classify the motion type of the target based on the updated target state information and obtain the state information of the stationary target.

[0049] In this embodiment of the invention, step 103 may specifically include: dividing the targets in the intersection area into stationary targets and moving targets according to the updated target speed, and obtaining the state information of the stationary targets.

[0050] For example, target speeds are classified based on Kalman filtering results, creating a database of moving targets and a database of stationary, queued targets. A speed threshold, such as 1 m / s, is set; if the target speed is below this threshold, it is considered to be in a queue; if the target speed is greater than or equal to the threshold, it is considered to be moving. Queued targets undergo only short-duration Kalman filtering to prevent prediction distortion. Using the stop line defined in the intersection topology information as a reference, queued targets and the vehicle in front are aligned within the lane, and the IDs and queue times of stationary targets are maintained.

[0051] 104. Use a pre-set bipartite graph matching algorithm to perform trajectory association matching for targets with different motion types.

[0052] In this embodiment of the invention, step 104 may specifically include: when the queuing target starts to move and there is a target with a speed exceeding a preset speed threshold, the moving target in the intersection area is associated with the trajectory of the original queuing target through the KM bipartite graph matching algorithm.

[0053] For example, a matching area is defined at an intersection. The KM bipartite graph matching algorithm is used to match the stationary queuing targets in step four with the moving targets in the intersection area, thereby establishing trajectory association. When the traffic light changes from red to green, the queuing targets will gradually resume their movement, and their speed will exceed the preset speed threshold, thus associating the trajectories of the moving targets in the intersection area with the original queuing targets. In this invention, we can consider the moving targets and stationary targets as the left and right parts of a bipartite graph, and match them to achieve target tracking and association for both starting and stopping targets. Specific details are as follows:

[0054] a) Construct a bipartite graph:

[0055] The matching between moving and stationary targets can be viewed as a bipartite graph G = (X, Y, E), where X represents the set of moving targets, Y represents the set of stationary targets, and E represents the set of edges connecting the moving and stationary targets. The weight of each edge represents the degree of matching between the moving and stationary targets.

[0056] b) Initialize the matching matrix:

[0057] Based on the number of nodes in the bipartite graph, construct an n1*n2 matrix M, and use w ij This represents the weight between the i-th moving target (i = 1, 2, 3, ..., n1) and the j-th stationary target (j = 1, 2, 3, ..., n2), which is the matching score between the i-th moving target and the j-th stationary target. All initial values ​​are set to 0.

[0058] c) Calculate the matching score:

[0059] For each element w in matrix M ijThe matching score is calculated based on information such as location, vehicle type, and reflection intensity, where w ij =k1a ij +k2b ij +k3c ij a ij b ij and c ij The values ​​represent the differences in position, vehicle type, and reflection intensity between the i-th moving target and the j-th stationary target, with k1, k2, and k3 being their corresponding coefficients.

[0060] d) Matching of movement goals and queuing goals:

[0061] Use algorithms such as DFS or BFS to find augmenting paths. For each x... i ∈X and y j Assign a label α to each of ∈Y i =0 and β j =0. Before finding a complete match, each time from x... i ∈X and begin finding augmenting paths: if x i It has already been matched, so from x i The matching y-vertex begins the search for an augmenting path; if x i There is no match yet, so from x i The y-vertex connected to the path begins the search for an augmenting path. To avoid redundant searches, an auxiliary array T is used to record whether a y-vertex has already been visited. j =1, t not visited j =0. For the found augmenting path, remove the unmatched points x. i With y j Match. For the original match, take the y... j0 With x k Cancel the match, then change x i With y j0 match.

[0062] Define a matching E0 that satisfies Initially empty. For each x... i ∈X and y j For ∈Y, update the label according to the following formula: Where: α i Indicates with x i The maximum weight of the match minus y j The tag value, β j Indicates with y j Maximum matching weight minus x i The marker value. Repeat the above steps until a complete match is found, that is, a set of edges is found. Maximize their total weight. Update the queuing time for unmatched stationary targets.

[0063] (e) Output the matching results:

[0064] After obtaining the matching relationship between moving and stationary targets, the trajectory information of the original queued targets is associated with the initiated moving targets. For stationary targets that have not completed matching, when the queuing area enters the passage state, their retention time is checked, and they are deleted if the time limit is exceeded to prevent the formation of false targets.

[0065] 105. Based on the state information of the stationary target and the trajectory information after trajectory association and matching, perform traffic management at the intersection.

[0066] Specifically, the state information of the stationary target and the trajectory information after trajectory association and matching are sent to the edge traffic control device. By analyzing and predicting vehicle trajectories, traffic congestion, accidents, and other problems can be detected in a timely manner, and effective intersection traffic control strategies can be provided, thereby reducing traffic accidents and improving intersection traffic efficiency.

[0067] This invention provides a radar target queuing and trajectory association method at intersections. By comprehensively considering intersection topology information such as location, vehicle type, and reflection intensity, the method acquires the target state information at the intersection. It then uses a bipartite graph matching algorithm to associate the motion state information of moving targets and queuing targets in the vehicle stationary-to-start transition scenario, ensuring the accuracy of trajectory association between moving targets and queuing targets. Simultaneously, it performs short-term prediction of stationary targets and retains them in conjunction with stop line position and preceding vehicle data to prevent distortion caused by long-term prediction of low-speed and stationary targets and avoids false targets formed by setting a fixed retention time, further improving the accuracy of trajectory association between moving targets and queuing targets.

[0068] To implement the method provided in the embodiments of the present invention, the embodiments of the present invention provide a radar target intersection queue maintenance and trajectory association system, such as... Figure 2 As shown, the system includes: an acquisition unit 21, an update unit 22, a classification unit 23, a matching unit 24, and a management unit 25.

[0069] Acquisition unit 21 is used to acquire intersection topology information and configure the radar sensor parameters of the intersection according to the topology information;

[0070] The updating unit 22 is used to collect the target status information at the intersection according to the configured radar sensor, and update the target status information according to the preset filtering algorithm;

[0071] Classification unit 23 is used to classify the motion type of the target based on the updated target state information and obtain the state information of the stationary target;

[0072] Matching unit 24 is used to perform trajectory association matching for targets with different motion types using a preset bipartite graph matching algorithm;

[0073] The management unit 25 is used to perform intersection traffic management based on the state information of the stationary target and the trajectory information after trajectory association matching.

[0074] Furthermore, the acquisition unit 21 is specifically used to configure the target intensity threshold of the radar sensor according to the empirical value of the target reflection intensity in the topology information, and to configure the clustering range of the radar sensor for the target according to the road width and number of lanes in the topology information.

[0075] Furthermore, the updating unit 22 is specifically used to measure and update the intersection target state information based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector using a preset Kalman filter algorithm;

[0076] Based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimate of the current frame, the radar sensor's observed position vector, the observation matrix, the identity matrix, the measurement error matrix, and the Kalman gain, the target state information at the intersection is predicted and updated using a preset Kalman filtering algorithm.

[0077] Furthermore, the classification unit 23 is specifically used to divide the targets in the intersection area into stationary targets and moving targets according to the updated target speed, and to obtain the state information of the stationary targets.

[0078] Further, the matching unit 24 is specifically used to establish a bipartite graph G = (X, Y, E) between moving targets and stationary targets, where X represents the set of moving targets, Y represents the set of stationary targets, E represents the set of edges connecting moving targets and stationary targets, and the weight of each edge represents the degree of matching between moving targets and stationary targets; and to establish an n1×n2 matrix M based on the number of nodes in the bipartite graph, where w ij This represents the weight between the i-th moving target and the j-th stationary target; each element w in matrix M is obtained based on the target state information and environmental state information in the intersection topology information. ij The matching index between the corresponding moving target and the stationary target; based on each element w in matrix M ij The matching index between the corresponding moving and stationary targets associates the trajectory information of the stationary targets with the trajectory of the moving targets that have started.

[0079] This invention provides a radar target intersection queue maintenance and trajectory association system. By comprehensively considering intersection topology information such as location, vehicle type, and reflection intensity, the system acquires intersection target state information and uses a bipartite graph matching algorithm to associate the motion state information of moving targets and queued targets in the vehicle stationary-to-start transition scenario. This ensures the accuracy of trajectory association between moving targets and queued targets. Simultaneously, the system performs short-term prediction of stationary targets and retains the data by combining stop line position and preceding vehicle data. This prevents distortion caused by long-term prediction of low-speed and stationary targets and avoids false targets formed by setting a fixed retention time, further improving the accuracy of trajectory association between moving targets and queued targets.

[0080] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0081] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features of the single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, wherein each claim stands alone as a preferred embodiment of the invention.

[0082] The disclosed embodiments have been described above to enable any person skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit and scope of this disclosure. Therefore, this disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0083] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

[0084] Those skilled in the art will also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention can be implemented by electronic hardware, computer software, or a combination of both. To clearly demonstrate the interchangeability of hardware and software, the functions of the various illustrative components, units, and steps described above have been generally described. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functions using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present invention.

[0085] The various illustrative logic blocks or units described in the embodiments of this invention can be implemented or operate the described functions using a general-purpose processor, digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array or other programmable logic system, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor; alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented using a combination of computing systems, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0086] The steps of the methods or algorithms described in the embodiments of this invention can be directly embedded in hardware, a software module executed by a processor, or a combination of both. The software module can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be housed in an ASIC, which can be housed in a user terminal. Optionally, the processor and storage medium can also be housed in different components of the user terminal.

[0087] In one or more exemplary designs, the functions described in the embodiments of the present invention can be implemented in hardware, software, firmware, or any combination of these three. If implemented in software, these functions can be stored on a computer-readable medium or transmitted on a computer-readable medium in the form of one or more instructions or code. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. Storage media can be any available media that can be accessed by a general-purpose or special-purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage systems, or any other medium that can be used to carry or store program code in the form of instructions or data structures and other forms that can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Furthermore, any connection can be suitably defined as a computer-readable medium, for example, if the software is transmitted from a website, server, or other remote resource via a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wirelessly, such as infrared, wireless, and microwave, it is also included in the defined computer-readable medium. The disks and discs mentioned include compressed disks, laser discs, optical discs, DVDs, floppy disks, and Blu-ray discs. Disks typically copy data magnetically, while disks typically copy data optically using lasers. Combinations of the above can also be contained in computer-readable media.

[0088] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for radar target queuing and trajectory correlation at intersections, characterized in that, The method includes: Obtain the intersection topology information and configure the radar sensor parameters of the intersection based on the topology information; The system collects target status information at the intersection based on the configured radar sensors and updates the target status information according to a preset filtering algorithm. Based on the updated target state information, the target is classified into motion types and the state information of stationary targets is obtained. Trajectory association matching of targets with different motion types is performed using a pre-set bipartite graph matching algorithm; Traffic management at intersections is carried out based on the state information of the stationary target and the trajectory information after trajectory association and matching. The step of performing trajectory association matching for targets of different motion types using a preset bipartite graph matching algorithm includes: Construct a bipartite graph G = (X, Y, E) between moving targets and stationary targets, where X represents the set of moving targets, Y represents the set of stationary targets, E represents the set of edges connecting moving targets and stationary targets, and the weight of each edge represents the degree of matching between moving targets and stationary targets. Construct an n1*n2 matrix M based on the number of nodes in the bipartite graph, where w ij This represents the weight between the i-th moving target and the j-th stationary target; Each element w in matrix M is obtained based on the target state information and environmental state information in the intersection topology information. ij The matching index between the corresponding moving target and the stationary target; Based on each element w in matrix M ij The matching index between the corresponding moving and stationary targets associates the trajectory information of the stationary targets with the trajectory of the moving targets that have started.

2. The radar target intersection queue maintenance and trajectory association method according to claim 1, characterized in that, The step of configuring the radar sensor parameters of the intersection based on the topology information includes: Configure the target intensity threshold of the radar sensor based on the empirical value of the target reflection intensity in the topology information, and configure the clustering range of the radar sensor for the target based on the road width and number of lanes in the topology information.

3. The radar target intersection queue maintenance and trajectory association method according to claim 1, characterized in that, The step of collecting intersection target status information based on the configured radar sensors and updating the target status information according to a preset filtering algorithm includes: Based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector, the target state information at the intersection is measured and updated using a preset Kalman filter algorithm. Based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimate of the current frame, the radar sensor's observed position vector, the observation matrix, the identity matrix, the measurement error matrix, and the Kalman gain, the target state information at the intersection is predicted and updated using a preset Kalman filtering algorithm.

4. A radar target intersection queue maintenance and trajectory association method according to claim 1 or 3, characterized in that, The step of classifying the motion type of the target based on the updated target state information and obtaining the state information of the stationary target includes: Based on the updated target speed, the targets in the intersection area are divided into stationary targets and moving targets, and the status information of the stationary targets is obtained.

5. A radar target intersection queue maintenance and trajectory association system, characterized in that, The system includes: An acquisition unit is used to acquire intersection topology information and configure the radar sensor parameters of the intersection according to the topology information; The update unit is used to collect the target status information at the intersection based on the configured radar sensors, and update the target status information according to a preset filtering algorithm. The classification unit is used to classify the motion type of the target based on the updated target state information and to obtain the state information of stationary targets. The matching unit is used to perform trajectory association matching for targets with different motion types using a preset bipartite graph matching algorithm; The management unit is used to perform intersection traffic management based on the state information of the stationary target and the trajectory information after trajectory association and matching. The matching unit is specifically used to establish a bipartite graph G = (X, Y, E) between moving targets and stationary targets, where X represents the set of moving targets, Y represents the set of stationary targets, E represents the set of edges connecting moving targets and stationary targets, and the weight of each edge represents the degree of matching between moving targets and stationary targets; and to establish an n1*n2 matrix M based on the number of nodes in the bipartite graph, where w ij This represents the weight between the i-th moving target and the j-th stationary target; each element w in matrix M is obtained based on the target state information and environmental state information in the intersection topology information. ij The matching index between the corresponding moving target and the stationary target; based on each element w in matrix M ij The matching index between the corresponding moving and stationary targets associates the trajectory information of the stationary targets with the trajectory of the moving targets that have started.

6. A radar target intersection queue maintenance and trajectory association system according to claim 5, characterized in that, The acquisition unit is specifically used to configure the target intensity threshold of the radar sensor according to the empirical value of the target reflection intensity in the topology information, and to configure the clustering range of the radar sensor for the target according to the road width and number of lanes in the topology information.

7. A radar target intersection queue maintenance and trajectory association system according to claim 5, characterized in that, The updating unit is specifically used to measure and update the intersection target state information based on the target's velocity and position state vector, state transition matrix, input control matrix, prediction error matrix, process noise matrix, and input vector using a preset Kalman filter algorithm. Based on the target's velocity and position state vector, the predicted value of the current frame, the optimal estimate of the current frame, the radar sensor's observed position vector, the observation matrix, the identity matrix, the measurement error matrix, and the Kalman gain, the target state information at the intersection is predicted and updated using a preset Kalman filtering algorithm.

8. A radar target intersection queue maintenance and trajectory association system according to claim 5 or 7, characterized in that, The classification unit is specifically used to divide the targets in the intersection area into stationary targets and moving targets according to the updated target speed, and to obtain the state information of the stationary targets.

Images