Obstacle Circumnavigation System Based on Lidar Sensing

Yan, Dejun; Zeng, Chunnian; Shu, Yan

doi:10.1109/iccar55106.2022.9782601

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is widely used in point cloud processing, because it can obtain good detection results for various objects. Yan et al optimized the Euclidean clustering method, by the addition of a spatial distance threshold; however, the spatial distance threshold remained fixed [20]. Guo et al introduced a weight coefficient, to redefine the calculation method of the clustering threshold, and adopted the octree structure to accelerate detection; nevertheless, the accuracy of obstacle detection was still not high [21].…”

Section: Introductionmentioning

confidence: 99%

“…Current obstacle detection based on lidar mainly uses point cloud clustering methods. Setting clustering thresholds based on empirical values is a simple method, but it is difficult to accurately detect obstacles, such as pedestrians and vehicles with complex shapes [20,28]. Setting the point cloud clustering threshold based on the point cloud angle relationship is a method of determining the clustering threshold by considering the angle relationship between two adjacent points in the horizontal direction and the distance from the 3D point cloud to the lidar [22,23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Obstacle Detection by Autonomous Vehicles: An Adaptive Neighborhood Search Radius Clustering Approach

et al. 2023

View full text Add to dashboard Cite

For autonomous vehicles, obstacle detection results using 3D lidar are in the form of point clouds, and are unevenly distributed in space. Clustering is a common means for point cloud processing; however, improper selection of clustering thresholds can lead to under-segmentation or over-segmentation of point clouds, resulting in false detection or missed detection of obstacles. In order to solve these problems, a new obstacle detection method was required. Firstly, we applied a distance-based filter and a ground segmentation algorithm, to pre-process the original 3D point cloud. Secondly, we proposed an adaptive neighborhood search radius clustering algorithm, based on the analysis of the relationship between the clustering radius and point cloud spatial distribution, adopting the point cloud pitch angle and the horizontal angle resolution of the lidar, to determine the clustering threshold. Finally, an autonomous vehicle platform and the offline autonomous driving KITTI dataset were used to conduct multi-scene comparative experiments between the proposed method and a Euclidean clustering method. The multi-scene real vehicle experimental results showed that our method improved clustering accuracy by 6.94%, and the KITTI dataset experimental results showed that the F1 score increased by 0.0629.

show abstract

Section: Introductionmentioning

confidence: 99%