An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation
Point cloud data segmentation, filtering, classification, and feature extraction are the main focus of point cloud data processing. DBSCAN (density-based spatial clustering of applications with noise) is capable of detecting arbitrary shapes of clusters in spaces of any dimension, and this method is...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/1/172 |
| _version_ | 1798034036350779392 |
|---|---|
| author | Chunxiao Wang Min Ji Jian Wang Wei Wen Ting Li Yong Sun |
| author_facet | Chunxiao Wang Min Ji Jian Wang Wei Wen Ting Li Yong Sun |
| author_sort | Chunxiao Wang |
| collection | DOAJ |
| description | Point cloud data segmentation, filtering, classification, and feature extraction are the main focus of point cloud data processing. DBSCAN (density-based spatial clustering of applications with noise) is capable of detecting arbitrary shapes of clusters in spaces of any dimension, and this method is very suitable for LiDAR (Light Detection and Ranging) data segmentation. The DBSCAN method needs at least two parameters: The minimum number of points minPts, and the searching radius ε. However, the parameter ε is often harder to determine, which hinders the application of the DBSCAN method in point cloud segmentation. Therefore, a segmentation algorithm based on DBSCAN is proposed with a novel automatic parameter ε estimation method—Estimation Method based on the average of k nearest neighbors’ maximum distance—with which parameter ε can be calculated on the intrinsic properties of the point cloud data. The method is based on the fitting curve of k and the mean maximum distance. The method was evaluated on different types of point cloud data: Airborne, and mobile point cloud data with and without color information. The results show that the accuracy values using ε estimated by the proposed method are 75%, 74%, and 71%, which are higher than those using parameters that are smaller or greater than the estimated one. The results demonstrate that the proposed algorithm can segment different types of LiDAR point clouds with higher accuracy in a robust manner. The algorithm can be applied to airborne and mobile LiDAR point cloud data processing systems, which can reduce manual work and improve the automation of data processing. |
| first_indexed | 2024-04-11T20:38:38Z |
| format | Article |
| id | doaj.art-2ce4b2d6f4f24f4b9251778fba15aef3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T20:38:38Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2ce4b2d6f4f24f4b9251778fba15aef32022-12-22T04:04:18ZengMDPI AGSensors1424-82202019-01-0119117210.3390/s19010172s19010172An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps EstimationChunxiao Wang0Min Ji1Jian Wang2Wei Wen3Ting Li4Yong Sun5Geomatics College, Shandong University of Science and Technology, Qingdao 266590, ChinaGeomatics College, Shandong University of Science and Technology, Qingdao 266590, ChinaGeomatics College, Shandong University of Science and Technology, Qingdao 266590, ChinaHainan Geomatics Centre, National Administration of Surveying, Mapping and Geoinformation of China, Haikou 570203, ChinaGeomatics College, Shandong University of Science and Technology, Qingdao 266590, ChinaGeomatics College, Shandong University of Science and Technology, Qingdao 266590, ChinaPoint cloud data segmentation, filtering, classification, and feature extraction are the main focus of point cloud data processing. DBSCAN (density-based spatial clustering of applications with noise) is capable of detecting arbitrary shapes of clusters in spaces of any dimension, and this method is very suitable for LiDAR (Light Detection and Ranging) data segmentation. The DBSCAN method needs at least two parameters: The minimum number of points minPts, and the searching radius ε. However, the parameter ε is often harder to determine, which hinders the application of the DBSCAN method in point cloud segmentation. Therefore, a segmentation algorithm based on DBSCAN is proposed with a novel automatic parameter ε estimation method—Estimation Method based on the average of k nearest neighbors’ maximum distance—with which parameter ε can be calculated on the intrinsic properties of the point cloud data. The method is based on the fitting curve of k and the mean maximum distance. The method was evaluated on different types of point cloud data: Airborne, and mobile point cloud data with and without color information. The results show that the accuracy values using ε estimated by the proposed method are 75%, 74%, and 71%, which are higher than those using parameters that are smaller or greater than the estimated one. The results demonstrate that the proposed algorithm can segment different types of LiDAR point clouds with higher accuracy in a robust manner. The algorithm can be applied to airborne and mobile LiDAR point cloud data processing systems, which can reduce manual work and improve the automation of data processing.http://www.mdpi.com/1424-8220/19/1/172LiDARsegmentationDBSCANparameter estimation |
| spellingShingle | Chunxiao Wang Min Ji Jian Wang Wei Wen Ting Li Yong Sun An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation Sensors LiDAR segmentation DBSCAN parameter estimation |
| title | An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation |
| title_full | An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation |
| title_fullStr | An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation |
| title_full_unstemmed | An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation |
| title_short | An Improved DBSCAN Method for LiDAR Data Segmentation with Automatic Eps Estimation |
| title_sort | improved dbscan method for lidar data segmentation with automatic eps estimation |
| topic | LiDAR segmentation DBSCAN parameter estimation |
| url | http://www.mdpi.com/1424-8220/19/1/172 |
| work_keys_str_mv | AT chunxiaowang animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT minji animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT jianwang animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT weiwen animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT tingli animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT yongsun animproveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT chunxiaowang improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT minji improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT jianwang improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT weiwen improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT tingli improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation AT yongsun improveddbscanmethodforlidardatasegmentationwithautomaticepsestimation |