Vehicle Detection and Shape Refinement Based on LiDAR
Nowadays, the vehicle detection technology based on lidar has been widely used in the field of intelligent connected vehicles. Accurate vehicle detection and shape estimation can provide accurate static information for follow-up tracking and prediction. Although the existing vehicle detection algori...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2022-12-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.06.011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849224979395117056 |
|---|---|
| author | YU An HU Dongfang WANG Xuepeng ZHANG Jin ZHOU Yan XIE Guotao QIN Xiaohui HU Manjiang |
| author_facet | YU An HU Dongfang WANG Xuepeng ZHANG Jin ZHOU Yan XIE Guotao QIN Xiaohui HU Manjiang |
| author_sort | YU An |
| collection | DOAJ |
| description | Nowadays, the vehicle detection technology based on lidar has been widely used in the field of intelligent connected vehicles. Accurate vehicle detection and shape estimation can provide accurate static information for follow-up tracking and prediction. Although the existing vehicle detection algorithm based on lidar can accurately detect and classify each target vehicle, there is a problem of unstable estimation when the vehicle point cloud contour is partially obscured in an "L" shape. In order to solve this problem, this paper proposes a vehicle shape optimization algorithm based on point cloud cluster features, the proposed algorithm outputs vehicle detection results with PointPillars target detection algorithm. Vehicle shape refinement module based on point cloud cluster features is adopted to further estimate the shape and heading of vehicle detection results. The experimental results in multiple scenes show that the vehicle shape refinement algorithm proposed in this paper can effectively improve the stability of vehicle shape and heading estimation to a certain extent compared with the existing vehicle detection algorithms, and the average consuming-time per frame of all algorithm module is 88.93 ms, which can meet the real-time requirement of vehicles. |
| format | Article |
| id | doaj-art-be02711e1bbd41e4aaf0c5a0ebdc3fd2 |
| institution | Kabale University |
| issn | 2096-5427 |
| language | zho |
| publishDate | 2022-12-01 |
| publisher | Editorial Office of Control and Information Technology |
| record_format | Article |
| series | Kongzhi Yu Xinxi Jishu |
| spelling | doaj-art-be02711e1bbd41e4aaf0c5a0ebdc3fd22025-08-25T06:49:22ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272022-12-01697633243586Vehicle Detection and Shape Refinement Based on LiDARYU AnHU DongfangWANG XuepengZHANG JinZHOU YanXIE GuotaoQIN XiaohuiHU ManjiangNowadays, the vehicle detection technology based on lidar has been widely used in the field of intelligent connected vehicles. Accurate vehicle detection and shape estimation can provide accurate static information for follow-up tracking and prediction. Although the existing vehicle detection algorithm based on lidar can accurately detect and classify each target vehicle, there is a problem of unstable estimation when the vehicle point cloud contour is partially obscured in an "L" shape. In order to solve this problem, this paper proposes a vehicle shape optimization algorithm based on point cloud cluster features, the proposed algorithm outputs vehicle detection results with PointPillars target detection algorithm. Vehicle shape refinement module based on point cloud cluster features is adopted to further estimate the shape and heading of vehicle detection results. The experimental results in multiple scenes show that the vehicle shape refinement algorithm proposed in this paper can effectively improve the stability of vehicle shape and heading estimation to a certain extent compared with the existing vehicle detection algorithms, and the average consuming-time per frame of all algorithm module is 88.93 ms, which can meet the real-time requirement of vehicles.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.06.011intelligent connected vehicleenvironmental perceptionLiDARvehicle detectionshape refinement |
| spellingShingle | YU An HU Dongfang WANG Xuepeng ZHANG Jin ZHOU Yan XIE Guotao QIN Xiaohui HU Manjiang Vehicle Detection and Shape Refinement Based on LiDAR Kongzhi Yu Xinxi Jishu intelligent connected vehicle environmental perception LiDAR vehicle detection shape refinement |
| title | Vehicle Detection and Shape Refinement Based on LiDAR |
| title_full | Vehicle Detection and Shape Refinement Based on LiDAR |
| title_fullStr | Vehicle Detection and Shape Refinement Based on LiDAR |
| title_full_unstemmed | Vehicle Detection and Shape Refinement Based on LiDAR |
| title_short | Vehicle Detection and Shape Refinement Based on LiDAR |
| title_sort | vehicle detection and shape refinement based on lidar |
| topic | intelligent connected vehicle environmental perception LiDAR vehicle detection shape refinement |
| url | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.06.011 |
| work_keys_str_mv | AT yuan vehicledetectionandshaperefinementbasedonlidar AT hudongfang vehicledetectionandshaperefinementbasedonlidar AT wangxuepeng vehicledetectionandshaperefinementbasedonlidar AT zhangjin vehicledetectionandshaperefinementbasedonlidar AT zhouyan vehicledetectionandshaperefinementbasedonlidar AT xieguotao vehicledetectionandshaperefinementbasedonlidar AT qinxiaohui vehicledetectionandshaperefinementbasedonlidar AT humanjiang vehicledetectionandshaperefinementbasedonlidar |