RESUMEN
3D object-detection based on LiDAR point clouds can help driverless vehicles detect obstacles. However, the existing point-cloud-based object-detection methods are generally ineffective in detecting small objects such as pedestrians and cyclists. Therefore, a small-object-detection algorithm based on clustering is proposed. Firstly, a new segmented ground-point clouds segmentation algorithm is proposed, which filters out the object point clouds according to the heuristic rules and realizes the ground segmentation by multi-region plane-fitting. Then, the small-object point cloud is clustered using an improved DBSCAN clustering algorithm. The K-means++ algorithm for pre-clustering is used, the neighborhood radius is adaptively adjusted according to the distance, and the core point search method of the original algorithm is improved. Finally, the detection of small objects is completed using the directional wraparound box model. After extensive experiments, it was shown that the precision and recall of our proposed ground-segmentation algorithm reached 91.86% and 92.70%, respectively, and the improved DBSCAN clustering algorithm improved the recall of pedestrians and cyclists by 15.89% and 9.50%, respectively. In addition, visualization experiments confirmed that our proposed small-object-detection algorithm based on the point-cloud clustering method can realize the accurate detection of small objects.
RESUMEN
In order to improve the accuracy of structured road boundary detection and solve the problem of the poor robustness of single feature boundary extraction, this paper proposes a multi-feature road boundary detection algorithm based on HDL-32E LIDAR. According to the road environment and sensor information, the former scenic cloud data is extracted, and the primary and secondary search windows are set according to the road geometric features and the point cloud spatial distribution features. In the search process, we propose the concept of the largest and smallest cluster points set and a two-way search method. Finally, the quadratic curve model is used to fit the road boundary. In the actual road test in the campus road, the accuracy of the linear boundary detection is 97.54%, the accuracy of the curve boundary detection is 92.56%, and the average detection period is 41.8 ms. In addition, the algorithm is still robust in a typical complex road environment.