文献类型：会议论文

英文题名：Pedestrian Detection Method Based on Fusion of LIDAR and Camera

作者：Fan, Yangyang[1,2]; Liu, Yuansheng[1,2]

第一作者：Fan, Yangyang

机构：[1] Beijing Union University, Beijing Key Laboratory of Information Service Engineering, Beijing, 100101, China; [2] College of Robotics, Beijing Union University, Beijing, 100101, China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]Beijing Union University, Beijing Key Laboratory of Information Service Engineering, Beijing, 100101, China|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

会议论文集：Proceedings - 2024 IEEE 24th International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

会议日期：July 1, 2024 - July 5, 2024

会议地点：Cambridge, United kingdom

语种：英文

外文关键词：Autonomous driving perception; Camera; Decision level fusion; M1 solid-state LIDAR; Pedestrian detection

摘要：As two important sensors in the perception process of autonomous driving, LIDAR is weak in judging target details, and camera typically have more demanding requirements regarding light conditions. In order to overcome the limitations of single sensor in pedestrian detection, a pedestrian detection method based on the fusion of laser radar and camera is proposed. Firstly, the M1 solid-state LIDAR is temporally and spatially synchronised with the camera, and then the point cloud is processed to achieve point cloud downsampling and ground point cloud removal and the processed point cloud is clustered using the density-based DBSCAN clustering algorithm. Concurrently, the camera image is used to detect pedestrians using the YOLOv5 visual target detection algorithm. Finally, the detection results of the two sensors are fused by decision level fusion to obtain the final detection information. The experiments carried out in the campus scene confirm that the accuracy of the proposed method for pedestrian fusion detection is 85.7%, and it solves the problem of missed detection of visual detection caused by light factors of camera sensors. ? 2024 IEEE.