Roadside sensing control system and method based on Leiyu fusion

Abstract

The invention relates to the technical field of roadside sensing, in particular to a roadside sensing control system and method based on Leiyu fusion. Comprising a sensor unit, a data processing unit and an early warning control unit, according to the method, more comprehensive and accurate perception of traffic participants is realized by integrating laser radar data and video data, and meanwhile, a conversion relation between a laser radar coordinate system and a visual coordinate system is determined based on space matching of a calibration object, so that the same target detected by different sensors can be accurately corresponding in space, and the accuracy of target detection is improved. The accuracy of judging the traffic condition by the whole roadside sensing system is greatly improved, and in addition, when the control threshold value is compared with the pre-stored control threshold value, whether early warning is sent out or not can be judged more scientifically and reasonably.

Description

Technical Field

[0001] The present invention relates to the field of roadside perception technology, and specifically to a roadside perception control system and method based on radar and vision fusion. Background Art

[0002] The purpose of roadside perception is to achieve instantaneous intelligent perception of traffic participants, road conditions, etc. on the road section. Roadside perception can expand the perception range of driving vehicles and drivers.

[0003] When a vehicle implements autonomous driving or assisted autonomous driving functions, it not only needs its own sensors to obtain surrounding information, but also relies on the roadside perception system to provide more macro and comprehensive traffic scene data as a supplement and reference. Although radar can accurately measure the motion parameters of the target, it is difficult to accurately judge the specific type of the target, because radar mainly analyzes based on the physical characteristics of the reflected signal and lacks visual feature information such as the appearance and shape of the target. It is difficult to accurately obtain the motion parameters of the target from video images, and the accuracy is relatively low and the error is large. Due to the above limitations, the traditional single sensor perception method is difficult to fully and accurately capture these abnormal behaviors and issue timely warnings, and cannot meet the growing demand for traffic safety assurance.

[0004] Based on this, the present invention provides a roadside perception control system and method based on radar and vision fusion to solve the technical problems mentioned above. Summary of the invention

[0005] The purpose of the present invention is to provide a roadside perception control system and method based on radar and vision fusion, which realizes a more comprehensive and accurate perception of traffic participants by integrating lidar data and video data. At the same time, based on the spatial matching of calibration objects, the conversion relationship between the lidar coordinate system and the visual coordinate system is determined, so that the same target detected by different sensors can be accurately matched in space, which greatly improves the accuracy of the entire roadside perception system in judging traffic conditions. In addition, when compared with the pre-stored control threshold, it can more scientifically and reasonably determine whether to issue an early warning.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The first aspect of the present invention provides a roadside perception control system based on radar and vision fusion, comprising a sensor unit, a data processing unit and an early warning control unit, wherein:

[0008] The sensor unit is used to obtain data information of the target, and the data information includes laser radar data, video data and positioning information data;

[0009] The data processing unit is used to spatially match the laser radar data and the video data, respectively extract first feature data and second feature data based on the laser radar data and the video data, and fuse the feature data extracted by the laser radar and the vision, and the data processing unit is connected to the sensor unit;

[0010] The early warning control unit is used to upload the preset control threshold, receive the early warning instruction, and issue the early warning information according to the received early warning instruction. The early warning control unit is connected to the data processing unit.

[0011] The present invention is further configured as follows: the sensor unit includes a laser radar module, a position positioning module, a video acquisition module and a first communication module, wherein:

[0012] The data processing unit is used for real-time laser radar data of the target;

[0013] The position positioning module is used to obtain real-time positioning information of the target;

[0014] The video acquisition module is used to acquire real-time video information of the target;

[0015] The first communication module is used to realize information interaction between the sensor unit and the data processing unit.

[0016] The present invention is further configured as follows: the data processing unit includes a second communication module, a coordinate conversion module and a feature extraction module, wherein:

[0017] The second communication module is used to realize information interaction between the data processing unit and the sensor unit and the early warning control unit;

[0018] The coordinate conversion module, based on the calibration object obtained under the laser radar and the calibration object obtained under the vision, makes a one-to-one correspondence between the coordinates of the calibration object obtained under the laser radar coordinate system and the coordinates under the vision coordinate system, determines the conversion relationship between the laser radar coordinate system and the vision coordinate system, and realizes the conversion between the laser radar coordinates and the vision coordinates. The coordinate conversion module is connected to the second communication module, and the coordinate conversion module is connected to the second communication module;

[0019] The feature extraction module extracts first feature data based on the laser radar data and extracts second feature data based on the video data. The feature extraction module is connected to the coordinate conversion module.

[0020] The present invention is further configured as follows: the data processing unit further includes a feature fusion module, a threshold comparison module and a database module, wherein:

[0021] The feature fusion module is used to fuse the feature data extracted by the laser radar and the visual system to obtain a matching target having the first feature data and the second feature data, and the feature fusion module is connected to the feature extraction module;

[0022] The threshold comparison module is used to compare the fused target feature data with the pre-stored control threshold to determine whether to issue a corresponding warning instruction. The threshold comparison module is connected to the feature fusion module.

[0023] The database module is used to store the acquired sensor data and preset control threshold information, and the database module is connected to both the second communication module and the threshold comparison module.

[0024] The present invention is further configured as follows: the warning control unit includes a third communication module, a warning issuing module and a threshold setting module, wherein:

[0025] The third communication module is used to realize information interaction between the early warning control unit and the data processing unit;

[0026] The warning issuing module is used to receive the warning instruction and issue the warning information according to the received warning instruction, and the warning issuing module is connected to the third communication module;

[0027] The threshold setting module is used for uploading a preset control threshold, and the threshold setting module is connected to the third communication module.

[0028] The second aspect of the present invention: A roadside perception control method based on radar and visual fusion is also provided, which is applied to the above-mentioned roadside perception control system based on radar and visual fusion, and comprises the following steps:

[0029] Acquire sensor data, wherein the sensor data includes lidar data and video data;

[0030] Spatially aligning lidar data and video data;

[0031] Extracting first feature data based on the laser radar data;

[0032] Extracting second feature data based on the video data;

[0033] Fuse feature data extracted from LiDAR and vision;

[0034] According to the characteristic data of the fused target, it is compared with the pre-stored control threshold and an early warning instruction is issued.

[0035] The present invention is further configured as follows: the matching process is as follows:

[0036] Based on the calibration objects obtained under the laser radar and the calibration objects obtained under the vision, the coordinates of the calibration objects obtained in the laser radar coordinate system are matched one by one with the coordinates in the vision coordinate system;

[0037] According to the coordinates of the calibration object, determine the conversion relationship between the laser radar coordinate system and the visual coordinate system, (x v ,y v ,z v )=T×(x r ,y r ,z r ), where (x v ,y v ,z v ) is the coordinate of the target in the laser radar coordinate system, (x r ,y r ,z r ) is the coordinate of the target in the visual coordinate system, and T is the transformation matrix.

[0038] The present invention is further configured as follows: the process of extracting the first characteristic data is as follows:

[0039] Speed ​​feature extraction: Obtain the laser radar's transmitted signal frequency f1, received signal frequency f2 and laser radar propagation speed c to calculate the target's speed

[0040] Acceleration feature extraction: Get the target's velocity data for several consecutive moments and calculate the target's acceleration at moment i: In the formula, v i+1 is the speed at time i+1, v i-1 is the speed at time i-1, Δt is the laser radar update period; then the average value of several continuous accelerations in the i+n period is obtained, which is the acceleration in this period.

[0041] The present invention is further configured as follows: the process of extracting the second characteristic data is as follows:

[0042] Extract the target contour shape from the video data; identify the extracted target contour shape to obtain the classification information of the target.

[0043] The present invention is further configured as follows: the process of fusing the feature data extracted by the laser radar and the vision is as follows:

[0044] Matching the target coordinates of the acquired first feature data to the visual coordinate system to obtain the target coordinates having the first feature data in the visual coordinate system, that is, converting the target coordinates;

[0045] calculating the distance between the converted target coordinates and the target coordinates having the second feature data;

[0046] The target with the smallest distance is selected for matching to obtain a matching target, which has first feature data and second feature data.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention obtains sensor data, matches the laser radar data and the video data in space, extracts the first feature data based on the laser radar data, and extracts the second feature data based on the video data, then fuses the feature data extracted by the laser radar and the visual, and compares the feature data of the fused target with the pre-stored control threshold to issue a warning instruction; the present invention can not only obtain the target's distance, speed, acceleration and other motion-related information by integrating the laser radar data and the video data, but also know the target's appearance contour and specific classification. The fusion of the two realizes a more comprehensive and accurate perception of traffic participants. At the same time, based on the spatial matching of the calibration object, the conversion relationship between the laser radar coordinate system and the visual coordinate system is determined, so that the same target detected by different sensors can be accurately corresponded in space, avoiding the problem of target information mismatch in the process of fusion data, and greatly improving the accuracy of the entire roadside perception system in judging the traffic conditions. In addition, the fused feature data covers many key features of the target. When compared with the pre-stored control threshold, it can more scientifically and reasonably determine whether to issue a warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a system diagram of the roadside perception control system based on radar and vision fusion of the present invention;

[0050] Figure 2 It is a system diagram of the sensor unit in the roadside perception control system based on radar and vision fusion of the present invention;

[0051] Figure 3 It is a system diagram of a data processing unit in a roadside perception control system based on radar-vision fusion according to the present invention;

[0052] Figure 4 It is a system diagram of the early warning control unit in the roadside perception control system based on radar and vision fusion of the present invention.

[0053] Description of Figure Numbers:

[0054] 10. Sensor unit; 11. LiDAR module; 12. Positioning module; 13. Video acquisition module; 14. First communication module; 20. Data processing unit; 21. Second communication module; 22. Coordinate conversion module; 23. Feature extraction module; 24. Feature fusion module; 25. Threshold comparison module; 26. Database module; 30. Warning control unit; 31. Third communication module; 32. Warning release module; 33. Threshold setting module. DETAILED DESCRIPTION

[0055] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example:

[0057] like Figure 1-Figure 4 As shown, the present embodiment provides a roadside perception control system based on radar and vision fusion, including a sensor unit 10, a data processing unit 20 and an early warning control unit 30, wherein: the sensor unit 10 is used to obtain data information of the target, the data information includes lidar data, video data and positioning information data; the data processing unit 20 is used to spatially match the lidar data and the video data, and respectively extract the first feature data and the second feature data based on the lidar data and the video data, and fuse the feature data extracted by the lidar and the vision, and the data processing unit 20 is connected to the sensor unit 10; the early warning control unit 30 is used to upload a preset control threshold, and receive early warning instructions, and issue early warning information according to the received early warning instructions, and the early warning control unit 30 is connected to the data processing unit 20.

[0058] In the present embodiment, it should be noted that the sensor unit 10 acquires the laser radar data, video data and positioning information data of different targets in real time, and transmits the above-acquired information to the data processing unit 20. The data processing unit 20 first matches the coordinates of the calibration objects acquired in the laser radar coordinate system with the coordinates in the visual coordinate system based on the calibration objects acquired under the laser radar and the calibration objects acquired under the vision, and determines the conversion relationship between the laser radar coordinate system and the visual coordinate system for subsequent target matching. Then, the laser radar data and the video data are used respectively to obtain the first feature data and the second feature data. Finally, the obtained first feature data and the second feature data are fused to obtain the matching target with the first feature data and the second feature data. The data processing unit 20 retrieves the pre-stored threshold control information, and determines whether to issue a warning instruction by comparison. When the warning instruction is issued, it is uploaded to the warning control unit 30, and the warning control unit 30 issues the warning.

[0059] In the present invention, the sensor unit 10 includes a laser radar module 11, a position positioning module 12, a video acquisition module 13 and a first communication module 14, wherein: the data processing unit 20 is used for real-time laser radar data of the target; the position positioning module 12 is used to obtain real-time positioning information of the target; the video acquisition module 13 is used to obtain real-time video information of the target; the first communication module 14 is used to realize information interaction between the sensor unit 10 and the data processing unit 20.

[0060] In this embodiment, it should be noted that the laser radar module 11, the position positioning module 12 and the video acquisition module 13 respectively obtain the laser radar data, real-time video information and real-time positioning information, and upload the above information to the data processing unit 20 through the first communication module 14. The laser radar continuously emits laser pulses to the monitoring area and receives the laser signal reflected by the target. The road scene image is collected by a high-definition camera installed at a suitable position on the roadside, and then the image data is transmitted to the data processing unit 20 for storage and subsequent processing through wired (Ethernet, etc.) or wireless (5G network, etc.) communication methods.

[0061] In the present invention, the data processing unit 20 includes a second communication module 21, a coordinate conversion module 22 and a feature extraction module 23, wherein: the second communication module 21 is used to realize information interaction between the data processing unit 20 and the sensor unit 10 and the warning control unit 30; the coordinate conversion module 22, based on the calibration objects obtained under the laser radar and the calibration objects obtained under the vision, matches the coordinates of the calibration objects obtained under the laser radar coordinate system with the coordinates under the visual coordinate system one by one, determines the conversion relationship between the laser radar coordinate system and the visual coordinate system, and realizes the conversion between the laser radar coordinates and the visual coordinates. The coordinate conversion module 22 is connected to the second communication module 21, and the coordinate conversion module 22 is connected to the second communication module 21; the feature extraction module 23 extracts the first feature data based on the laser radar data, and extracts the second feature data based on the video data, and the feature extraction module 23 is connected to the coordinate conversion module 22.

[0062] In addition, the data processing unit 20 also includes a feature fusion module 24, a threshold comparison module 25 and a database module 26, wherein: the feature fusion module 24 is used to fuse the feature data extracted by the laser radar and the vision to obtain a matching target with the first feature data and the second feature data, and the feature fusion module 24 is connected to the feature extraction module 23; the threshold comparison module 25 is used to compare the feature data of the fused target with the pre-stored control threshold to determine whether to issue a corresponding early warning instruction, the threshold comparison module 25 is connected to the feature fusion module 24, and the database module 26 is used to store the acquired sensor data and the preset control threshold information, and the database module 26 is connected to both the second communication module 21 and the threshold comparison module 25.

[0063] In this embodiment, it should be noted that the information uploaded by the sensor unit 10 is received by the second communication module 21, and the conversion relationship between the laser radar coordinates and the visual coordinates is determined by the coordinate conversion module 22. Then, the feature extraction module 23 extracts the first feature data based on the laser radar data, and extracts the second feature data based on the video data, and uploads the first feature data and the second feature data to the feature fusion module 24, and the feature fusion module 24 fuses the first feature data and the second feature data. The specific process is: matching the target coordinates of the first feature data to the visual coordinate system to obtain the target coordinates with the first feature data in the visual coordinate system, that is, the converted target coordinates; calculating the distance between the converted target coordinates and the target coordinates with the second feature data; selecting the target with the smallest distance for matching to obtain a matching target, which has the first feature data and the second feature data, and comparing the matching target with the preset control threshold information through the threshold comparison module 25 to determine whether to issue an early warning. After fusion, each target contains multi-dimensional features, which avoids the one-sidedness of judging the target based on the laser radar or video data alone, and can more accurately grasp the overall situation of the target, thereby improving the accuracy of traffic condition analysis and decision-making.

[0064] In the present invention, the warning control unit 30 includes a third communication module 31, a warning issuing module 32 and a threshold setting module 33, wherein: the third communication module 31 is used to realize information interaction between the warning control unit 30 and the data processing unit 20; the warning issuing module 32 is used to receive warning instructions and issue warning information according to the received warning instructions, and the warning issuing module 32 is connected to the third communication module 31; the threshold setting module 33 is used to upload the preset control threshold, and the threshold setting module 33 is connected to the third communication module 31.

[0065] In the embodiment, it should be noted that the warning issuing instruction is received by the set third communication module 31, and the warning issuing module 32 will issue corresponding warning information after receiving the instruction. At the same time, the control threshold can be preset by the threshold setting module 33 and uploaded to the data processing unit 20 for storage through the third communication module 31.

[0066] In addition, this embodiment also provides a roadside perception control method based on radar and vision fusion, which is applied to the above-mentioned roadside perception control system based on radar and vision fusion, and includes the following steps:

[0067] Acquire sensor data, wherein the sensor data includes lidar data and video data;

[0068] Spatially match the lidar data and the video data; the matching process is as follows:

[0069] Based on the calibration objects obtained under the laser radar and the calibration objects obtained under the vision, the coordinates of the calibration objects obtained in the laser radar coordinate system are matched one by one with the coordinates in the vision coordinate system;

[0070] According to the coordinates of the calibration object, determine the conversion relationship between the laser radar coordinate system and the visual coordinate system, (x v ,y v ,z v )=T×(x r ,y r ,z r ), where (x v ,y v ,z v ) is the coordinate of the target in the laser radar coordinate system, (x r ,y r ,z r ) is the coordinate of the target in the visual coordinate system, and T is the transformation matrix.

[0071] Based on the laser radar data, first feature data is extracted; wherein the process of extracting the first feature data is as follows:

[0072] Speed ​​feature extraction: Obtain the laser radar's transmitted signal frequency f1, received signal frequency f2 and laser radar propagation speed c to calculate the target's speed

[0073] Acceleration feature extraction: Get the target's velocity data for several consecutive moments and calculate the target's acceleration at moment i: In the formula, v i+1 is the speed at time i+1, v i-1 is the speed at time i-1, Δt is the laser radar update period; then the average value of several continuous accelerations in the i+n period is obtained, which is the acceleration in this period.

[0074] Based on the video data, second feature data is extracted; wherein the process of extracting the second feature data is as follows:

[0075] Extract the target contour shape from the video data; identify the extracted target contour shape to obtain the classification information of the target.

[0076] The feature data extracted by the laser radar and the vision are integrated; wherein the process of integrating the feature data extracted by the laser radar and the vision is as follows:

[0077] Matching the target coordinates of the acquired first feature data to the visual coordinate system to obtain the target coordinates having the first feature data in the visual coordinate system, that is, converting the target coordinates;

[0078] calculating the distance between the converted target coordinates and the target coordinates having the second feature data;

[0079] The target with the smallest distance is selected for matching to obtain a matching target, which has first feature data and second feature data.

[0080] According to the characteristic data of the fused target, it is compared with the pre-stored control threshold and an early warning instruction is issued.

[0081] In this embodiment, it should be noted that as a method of extracting the target contour shape, including but not limited to using the Canny edge detection algorithm for extraction, obtaining the target's speed information is very critical for analyzing the target's motion state, determining whether it is speeding, and the dynamic evaluation of subsequent traffic flow. It is one of the important indicators for describing the dynamic characteristics of the target. Extracting the target contour shape helps to intuitively distinguish different types of targets. By comparing the fused target feature data with the preset control threshold, it is determined whether there is an abnormal situation in the traffic scene (such as speeding, abnormal acceleration and deceleration, etc.), and then decide whether to issue a warning information, thereby realizing real-time monitoring of traffic order and timely prompting of potential dangers, and ensuring road traffic safety.

[0082] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0083] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The roadside perception control system based on radar and vision fusion is characterized by: The system comprises a sensor unit (10), a data processing unit (20) and an early warning control unit (30), wherein: The sensor unit (10) is used to obtain data information of a target, wherein the data information includes laser radar data, video data and positioning information data; The data processing unit (20) is used to spatially match the laser radar data and the video data, respectively extract first feature data and second feature data based on the laser radar data and the video data, and fuse the feature data extracted by the laser radar and the vision, and the data processing unit (20) is connected to the sensor unit (10); The early warning control unit (30) is used to upload a preset control threshold value, receive an early warning instruction, and issue early warning information according to the received early warning instruction. The early warning control unit (30) is connected to the data processing unit (20).

2. The roadside perception control system based on radar and vision fusion according to claim 1 is characterized in that: The sensor unit (10) comprises a laser radar module (11), a position positioning module (12), a video acquisition module (13) and a first communication module (14), wherein: The data processing unit (20) is used for real-time laser radar data of the target; The position positioning module (12) is used to obtain real-time positioning information of the target; The video acquisition module (13) is used to acquire real-time video information of the target; The first communication module (14) is used to realize information interaction between the sensor unit (10) and the data processing unit (20).

3. The roadside perception control system based on radar and visual fusion according to claim 1 is characterized in that: The data processing unit (20) comprises a second communication module (21), a coordinate conversion module (22) and a feature extraction module (23), wherein: The second communication module (21) is used to realize information interaction between the data processing unit (20) and the sensor unit (10) and the early warning control unit (30); The coordinate conversion module (22) makes one-to-one correspondence between the coordinates of the calibration object obtained in the laser radar coordinate system and the coordinates in the visual coordinate system based on the calibration object obtained under the laser radar and the calibration object obtained under the visual system, determines the conversion relationship between the laser radar coordinate system and the visual coordinate system, and realizes the conversion between the laser radar coordinates and the visual coordinates. The coordinate conversion module (22) is connected to the second communication module (21), and the coordinate conversion module (22) is connected to the second communication module (21); The feature extraction module (23) extracts first feature data based on the laser radar data and extracts second feature data based on the video data. The feature extraction module (23) is connected to the coordinate conversion module (22).

4. The roadside perception control system based on radar and visual fusion according to claim 3 is characterized in that: The data processing unit (20) further comprises a feature fusion module (24), a threshold comparison module (25) and a database module (26), wherein: The feature fusion module (24) is used to fuse the feature data extracted by the laser radar and the visual system to obtain a matching target having the first feature data and the second feature data, and the feature fusion module (24) is connected to the feature extraction module (23); The threshold comparison module (25) is used to compare the fused target feature data with the pre-stored control threshold to determine whether to issue a corresponding warning instruction. The threshold comparison module (25) is connected to the feature fusion module (24). The database module (26) is used to store the acquired sensor data and preset control threshold information, and the database module (26) is connected to both the second communication module (21) and the threshold comparison module (25).

5. The roadside perception control system based on radar and visual fusion according to claim 1 is characterized in that: The warning control unit (30) comprises a third communication module (31), a warning issuing module (32) and a threshold setting module (33), wherein: The third communication module (31) is used to realize information interaction between the early warning control unit (30) and the data processing unit (20); The warning issuing module (32) is used to receive the warning instruction and issue the warning information according to the received warning instruction, and the warning issuing module (32) is connected to the third communication module (31); The threshold setting module (33) is used for uploading a preset control threshold, and the threshold setting module (33) is connected to the third communication module (31).

6. A roadside perception control method based on radar and visual fusion, applied to a roadside perception control system based on radar and visual fusion as claimed in any one of claims 1 to 5, characterized in that: The following steps are involved: Acquire sensor data, wherein the sensor data includes lidar data and video data; Spatially aligning lidar data and video data; Extracting first feature data based on the laser radar data; Extracting second feature data based on the video data; Fuse feature data extracted from LiDAR and vision; According to the characteristic data of the fused target, it is compared with the pre-stored control threshold and an early warning instruction is issued.

7. The roadside perception control method based on radar and visual fusion according to claim 6 is characterized in that: The matching process is as follows: Based on the calibration objects obtained under the laser radar and the calibration objects obtained under the vision, the coordinates of the calibration objects obtained in the laser radar coordinate system are matched one by one with the coordinates in the vision coordinate system; According to the coordinates of the calibration object, determine the conversion relationship between the laser radar coordinate system and the visual coordinate system, (x v ,y v ,z v )=T×(x r ,y r ,z r ), where (x v ,y v ,z v ) is the coordinate of the target in the laser radar coordinate system, (x r ,y r ,z r ) is the coordinate of the target in the visual coordinate system, and T is the transformation matrix.

8. The roadside perception control method based on radar and visual fusion according to claim 10 is characterized in that: The process of extracting the first feature data is as follows: Speed ​​feature extraction: Obtain the laser radar's transmitted signal frequency f1, received signal frequency f2 and laser radar propagation speed c to calculate the target's speed Acceleration feature extraction: Get the target's velocity data for several consecutive moments and calculate the target's acceleration at moment i: In the formula, v i+1 is the speed at time i+1, v i-1 is the speed at time i-1, Δt is the laser radar update period; then the average value of several continuous accelerations in the i+n period is obtained, which is the acceleration in this period.

9. The roadside perception control method based on radar and visual fusion according to claim 6 is characterized in that: The process of extracting the second characteristic data is as follows: Extract the target contour shape from the video data; identify the extracted target contour shape to obtain the classification information of the target.

10. The roadside perception control method based on radar and visual fusion according to claim 6, characterized in that: The process of fusing the feature data extracted by LiDAR and vision is as follows: Matching the target coordinates of the acquired first feature data to the visual coordinate system to obtain the target coordinates having the first feature data in the visual coordinate system, that is, converting the target coordinates; calculating the distance between the converted target coordinates and the target coordinates having the second feature data; The target with the smallest distance is selected for matching to obtain a matching target, which has first feature data and second feature data.

Images