CN-116977970-B - Road drivable area detection method based on fusion of laser radar and millimeter wave radar

CN116977970BCN 116977970 BCN116977970 BCN 116977970BCN-116977970-B

Abstract

The invention relates to a road drivable area detection method based on fusion of a laser radar and a millimeter wave radar, and belongs to the fields of vehicle-road cooperation and intelligent traffic. The method processes point cloud data of the laser radar through a self-adaptive DBSCAN clustering algorithm, can improve intra-class consistency and inter-class difference of clustering results, can solve the problem that a traditional fixed global threshold segmentation method cannot give consideration to all conditions of a point cloud image so that segmentation effect is poor by constructing a drivable region electronic fence of a road through a self-adaptive threshold segmentation method based on a large law method, can solve the problem that sparseness degree is different under different distances by converting a sector code into a point cloud coordinate system to express position and direction information of the point, and can improve environmental adaptability through selecting a radius and using a attention mechanism to fuse dynamic adjustment weights in a pseudo-image fusion mode.

Inventors

JIANG JIANCHUN
WANG ZHANGQI
ZENG SUHUA
SU YUNLONG
YU HAO
SUN YUCHEN
XIA YUNJUN

Assignees

重庆邮电大学

Dates

Publication Date: 20260508
Application Date: 20230814

Claims (4)

1. A road drivable area detection method based on fusion of a laser radar and a millimeter wave radar is characterized by comprising the following steps: s1, extracting and clustering point cloud data of a laser radar, and then dividing lane lines and pavements in the point cloud data by adopting an improved local self-adaptive threshold segmentation method based on a law method, so as to construct and obtain an electronic fence; the method for extracting and clustering comprises the steps of firstly filtering laser radar original point cloud data to extract effective point cloud data, and then selecting an interested region through a self-adaptive DBSCAN clustering algorithm, wherein the growth radius of a clustering cluster in the clustering algorithm is corrected through a sigmoid function, and the correction relation is as follows: in the formula, Indicating the radius parameter after the correction, Representing an initial radius parameter; in the formula, 、b r 、 And All are algorithm model parameters, and the optimal value is obtained by enumerating different values of the parameters ; Representing seed points searching for the same cluster point; the improved local self-adaptive threshold segmentation method based on the discipline method comprises the steps of classifying point cloud data obtained after extraction and clustering according to scanning lines, carrying out gray level conversion on reflection intensity data in each scanning line, calculating global average values of gray level values in all scanning lines, finding out gray level values larger than the global average value, calculating average values of the gray level values to obtain intra-class secondary gray level average values, defining a threshold selection interval by taking the intra-class secondary gray level average values as an initial threshold value, defining a threshold value th in the threshold selection interval, dividing an image into a foreground image and a background image by the threshold value th, combining probability and average gray level values of the foreground image and the background image, and calculating global gray level average values with gray level values larger than the intra-class secondary gray level average value, marking a threshold value th corresponding to the maximum inter-class variance as an optimal threshold value, marking data with gray level values larger than the optimal threshold value as lane line point cloud data, and marking data with gray level values smaller than the optimal threshold value as road point cloud data; s2, respectively carrying out sector coding on millimeter wave Lei Dadian cloud data and the laser radar point cloud data processed in the step S1, dividing a space into grids through the sector coding, generating polar coordinate cylinder elements in a three-dimensional space, then converting the point cloud cylinders into pseudo images and extracting feature images; and S3, carrying out weighted fusion on the feature images of the laser radar and the millimeter wave radar by adopting a pointpillar feature layer-based attention fusion model, multiplying the fusion result by a proportion coefficient, and then adding the result with the laser radar feature image to obtain a detection result of the road drivable region.
2. The method for detecting a road drivable region according to claim 1, characterized in that in step S1, in the modified local adaptive threshold segmentation method based on the discriminant method, the calculation formula of the inter-class variance is: in the formula, The variance between the classes is represented as, The probability of representing the background image is indicated, The probability of representing the foreground image is indicated, Represents an average gray value representing the background image, Represents the average gray value of the foreground image, The global gray average value representing the gray value greater than the intra-class secondary gray average value.
3. The method for detecting the road drivable area according to claim 1, characterized in that in the step S2, the sector coding is completed under a polar coordinate system, the method comprises the steps of setting a circular ring detection area in the point cloud data, dividing the circular ring detection area into a plurality of sector ring areas, dividing the sector ring areas into a plurality of grids along the radial direction, converting the coordinate system of the points in the point cloud data into the polar coordinate system, dividing the points falling in the grid intervals into the grids, thereby generating polar cylindrical elements in the three-dimensional space, and the length of the grids along the radial direction is equal to the inner arc length of the grids.
4. The method for detecting a road drivable area according to claim 1, wherein in step S3, after the feature map of the lidar and the millimeter wave radar is input into the feature layer attention fusion model, convolution and normalization processing are performed respectively, and then attention fusion is performed: in the formula, W v respectively represents a weight matrix obtained by convolving and learning a laser radar feature map X 1 , W k represents a weight matrix obtained by convolving and learning a millimeter wave radar feature map X r , Q, V respectively represents a laser radar matrix, K represents a millimeter wave radar matrix, and a fusion result O is obtained by multiplying a laser radar matrix V and a millimeter wave radar matrix K by each other and multiplying the result by a laser radar matrix Q by each other.

Description

Road drivable area detection method based on fusion of laser radar and millimeter wave radar Technical Field The invention belongs to the field of vehicle-road coordination and intelligent traffic, and relates to a road drivable area detection method based on laser radar and millimeter wave radar fusion. Background In recent years, with the rapid development of automobile related fields such as new energy technology and computer communication technology, the development of traditional automobiles towards intelligentization, electric and networking is promoted. Along with the improvement of the living standard of people and the continuous improvement of the requirements on the performance of automobiles, people pay more and more attention to the safety and smoothness of the vehicles, and the perception of road environment is one of the keys for ensuring the safety and smoothness of the vehicles. The road environment perception is a key link of the mature development of the vehicle-road cooperative technology, and the environment perception layer mainly utilizes various sensors to provide traffic environment information for vehicles, including lane marks, signal lamps, identification plates and the like, and information such as barrier profile information, positions and relative distances of vehicles and barriers. The intelligent vehicle road cooperation control method is a primary challenge of vehicle road cooperation, provides basis for global path planning, driving behavior decision and motion planning of the intelligent vehicle, and realizes control of the vehicle by combining with a bottom-layer executing mechanism. The intelligent automobile perception hardware system is based on biological sensory products, whether a camera or a radar is adopted, and the intelligent automobile perception hardware system is mounted at the automobile end, so that a 'blind zone' phenomenon is necessarily generated, even if the system is re-intelligent, a fast and accurate decision can be made only in a visual range, and the phenomenon that a human driver such as a 'ghost probe' is difficult to avoid is caused, and the phenomenon is also difficult to avoid for single-car intelligence. In severe weather and lane changing scenes, traffic accidents are easy to occur due to insufficient perception of the bicycle on the environment. The road side camera can well complete the functions of part object recognition, classification, detection and the like, but because of the lack of depth information, the position and distance of a vehicle or an obstacle cannot be accurately mastered, and a more accurate road drivable area cannot be established. Therefore, a strategy of fusion of the laser radar and the millimeter wave radar is used in the establishment of the road side drivable region, and the data of the laser radar and the millimeter wave radar can be mutually complemented, so that the detection accuracy is improved. The lidar may provide high-precision point cloud data for detecting the shape and position of an object, while the millimeter wave radar may provide high-precision speed and distance measurements for detecting the motion state of an object. By combining the two data, obstacles, pedestrians and the like on the road can be detected more accurately, the robustness of the road side drivable region in different environments can be improved, for example, in rainy and snowy weather, a laser radar can be interfered to lose precision, and a millimeter wave radar can be better adapted to the environment. Road environment perception is taken as a general basic technology, and plays an important role in the directions of automatic driving, vehicle-road coordination and the like. However, the perception of the vehicle-mounted intelligent road drivable area has remained the mainstream solution so far. In the future, the automatic driving vehicle needs to sense and acquire the road drivable area in real time, and the limitation of bicycle sensing causes that the drivable area cannot be accurately acquired, so that the vehicle cannot effectively generate a local path. In addition, in bad weather and lane changing scenes, traffic accidents are easy to happen due to insufficient perception of the bicycle on the environment. Therefore, in order to solve the insufficient needs of single vehicle and the needs of vehicle-road cooperation, provide road environment perception service free from environmental constraint, ensure travel safety and advance cooperative development, a road exercisable area detection technology based on laser radar and millimeter wave radar fusion is needed, and accurate drivable area information is provided for a vehicle-network intelligent traffic scene, so that vehicle-road cooperation and subsequent unmanned driving are realized. Disclosure of Invention In view of the above, the present invention aims to provide a method for detecting a road drivable region based on fusion of a laser radar and a millimeter wave