Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 16; p. 3239
• Main Authors: Shen, Zhihao, Liang, Huawei, Lin, Linglong, Wang, Zhiling, Huang, Weixin, Yu, Jie
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 15.08.2021
• Subjects: Accuracy; Adaptability; Algorithms; autonomous vehicles; Clouds; Convolution; data collection; Deep learning; Driving ability; Environmental information; Feature extraction; ground segmentation; Image segmentation; landscapes; LiDAR; memory; Methods; Neural networks; Propagation; real-time; Roads & highways; Three dimensional models; Vehicle safety
• DOI: 10.3390/rs13163239
• ISSN: 2072-4292

LiDAR occupies a vital position in self-driving as the advanced detection technology enables autonomous vehicles (AVs) to obtain much environmental information. Ground segmentation for LiDAR point cloud is a crucial procedure to ensure AVs’ driving safety. However, some current algorithms suffer from embarrassments such as unavailability on complex terrains, excessive time and memory usage, and additional pre-training requirements. The Jump-Convolution-Process (JCP) is proposed to solve these issues. JCP converts the segmentation problem of the 3D point cloud into the smoothing problem of the 2D image and takes little time to improve the segmentation effect significantly. First, the point cloud marked by an improved local feature extraction algorithm is projected onto an RGB image. Then, the pixel value is initialized with the points’ label and continuously updated according to image convolution. Finally, a jump operation is introduced in the convolution process to perform calculations only on the low-confidence points filtered by the credibility propagation algorithm, reducing the time cost. Experiments on three datasets show that our approach has a better segmentation accuracy and terrain adaptability than those of the three existing methods. Meanwhile, the average time for the proposed method to deal with one scan data of 64-beam and 128-beam LiDAR is only 8.61 ms and 15.62 ms, which fully meets the AVs’ requirement for real-time performance.