P‐2.21: Research on multi‐lidar detection technology for autonomous driving

Abstract

Nowadays autonomous driving has become a hot topic, many people pay attention to the field. Target detection through sensors is the basis of autonomous driving and plays an important role in high-level autonomous driving. The effective environmental information obtained by using a single sensor is less, and the visual sensor is easily affected by the weather and the algorithm is complex, so there are problems in real-time detection and accuracy. Multi-lidar detection is also a popular research in this field and has important research value and application prospect.This paper mainly describes the key steps of multi-lidar detection and proposes a fully automatic point cloud registration scheme. The fully automatic calibration method does not require manual initialization and does not rely on additional sensors at all, which can play a good role in multi-lidar detection. After that, the fused point cloud data is filtered to remove interference points and reduce the number of point clouds. In view of the under-segmentation of ground point cloud, the point cloud is mapped to the raster graph, and the ground point and non-ground point are separated by Random sample consensus algorithm and least square method. Then, distance-based clustering is used for obstacle detection on non-ground points.