Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process
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 fro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3239 |
| _version_ | 1797522154973036544 |
|---|---|
| author | Zhihao Shen Huawei Liang Linglong Lin Zhiling Wang Weixin Huang Jie Yu |
| author_facet | Zhihao Shen Huawei Liang Linglong Lin Zhiling Wang Weixin Huang Jie Yu |
| author_sort | Zhihao Shen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T08:25:28Z |
| format | Article |
| id | doaj.art-7eeb78092ffb48da8d4ce0c9212e5dbd |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:28Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7eeb78092ffb48da8d4ce0c9212e5dbd2023-11-22T09:34:20ZengMDPI AGRemote Sensing2072-42922021-08-011316323910.3390/rs13163239Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-ProcessZhihao Shen0Huawei Liang1Linglong Lin2Zhiling Wang3Weixin Huang4Jie Yu5School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaSchool of Information Science and Technology, University of Science and Technology of China, Hefei 230026, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaLiDAR 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.https://www.mdpi.com/2072-4292/13/16/3239autonomous vehiclesLiDARground segmentationconvolutionreal-time |
| spellingShingle | Zhihao Shen Huawei Liang Linglong Lin Zhiling Wang Weixin Huang Jie Yu Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process Remote Sensing autonomous vehicles LiDAR ground segmentation convolution real-time |
| title | Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process |
| title_full | Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process |
| title_fullStr | Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process |
| title_full_unstemmed | Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process |
| title_short | Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process |
| title_sort | fast ground segmentation for 3d lidar point cloud based on jump convolution process |
| topic | autonomous vehicles LiDAR ground segmentation convolution real-time |
| url | https://www.mdpi.com/2072-4292/13/16/3239 |
| work_keys_str_mv | AT zhihaoshen fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess AT huaweiliang fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess AT linglonglin fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess AT zhilingwang fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess AT weixinhuang fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess AT jieyu fastgroundsegmentationfor3dlidarpointcloudbasedonjumpconvolutionprocess |