Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations
3D laser scanning is widely used in modeling industrial scenes, involving crucial steps like point cloud (PC) data preprocessing and extracting modeling targets from scattered points. Extracting target PC data from larger scenes is more challenging than from smaller settings. To efficiently obtain h...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-02-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157824000521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849387162252869632 |
|---|---|
| author | Ruiheng Li Lu Gan Yi Di Hao Tian Qiankun Zuo Yiming Luo Xuan Wu Haiyang Wang |
| author_facet | Ruiheng Li Lu Gan Yi Di Hao Tian Qiankun Zuo Yiming Luo Xuan Wu Haiyang Wang |
| author_sort | Ruiheng Li |
| collection | DOAJ |
| description | 3D laser scanning is widely used in modeling industrial scenes, involving crucial steps like point cloud (PC) data preprocessing and extracting modeling targets from scattered points. Extracting target PC data from larger scenes is more challenging than from smaller settings. To efficiently obtain high-quality scene data and modeling targets, we introduce an innovative approach with the adaptive density-based voxel grid filtering algorithm and a probability statistics histogram method during preprocessing. We also propose a novel method for automatic extraction of target PC data using the adjacent feature plane constraint (AFPC) clustering technique. Initially, we capture height characteristics of the target object's PC through experiential and statistical height attributes. Points corresponding to each height are then clustered based on the PC's density distribution using the density-based spatial clustering of applications with noise algorithm. The intersection of these results optimizes the position of the target object's extraction bounding box, achieving seamless automatic object extraction. Experimental results validate the effectiveness of our preprocessing methodology, with F1 scores of 97.7 % and 97.3 % for the 220 kV and 500 kV areas, respectively. Furthermore, our novel extraction method demonstrates the ability to autonomously and directly extract electrical equipment from substation PC data. |
| format | Article |
| id | doaj-art-330f92ff13014cd88bf8465ccd398e29 |
| institution | Kabale University |
| issn | 1319-1578 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | Springer |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj-art-330f92ff13014cd88bf8465ccd398e292025-08-20T03:55:17ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782024-02-0136210196310.1016/j.jksuci.2024.101963Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substationsRuiheng Li0Lu Gan1Yi Di2Hao Tian3Qiankun Zuo4Yiming Luo5Xuan Wu6Haiyang Wang7School of Information Engineering, Hubei University of Economics, Wuhan 430205, China; Hubei Key Laboratory of Digital Finance Innovation, Wuhan 430205, China; Hubei Internet Finance Information Engineering Technology Research Center, Hubei University of Economics, Wuhan 430205, China; The State Key Laboratory of Power Transmission Equipment and System Security and New Technology, Chongqing University, Chongqing 400044, ChinaSchool of Information Engineering, Hubei University of Economics, Wuhan 430205, ChinaSchool of Information Engineering, Hubei University of Economics, Wuhan 430205, China; Hubei Key Laboratory of Digital Finance Innovation, Wuhan 430205, China; Hubei Internet Finance Information Engineering Technology Research Center, Hubei University of Economics, Wuhan 430205, China; Corresponding authors at: School of Information Engineering, Hubei University of Economics, Wuhan 430205, China; Hubei Key Laboratory of Digital Finance Innovation, Wuhan 430205, China; Hubei Internet Finance Information Engineering Technology Research Center, Wuhan 430205, China.School of Information Engineering, Hubei University of Economics, Wuhan 430205, China; Hubei Key Laboratory of Digital Finance Innovation, Wuhan 430205, China; Corresponding authors at: School of Information Engineering, Hubei University of Economics, Wuhan 430205, China; Hubei Key Laboratory of Digital Finance Innovation, Wuhan 430205, China; Hubei Internet Finance Information Engineering Technology Research Center, Wuhan 430205, China.School of Information Engineering, Hubei University of Economics, Wuhan 430205, ChinaSchool of Information Engineering, Hubei University of Economics, Wuhan 430205, ChinaSchool of Information Engineering, Hubei University of Economics, Wuhan 430205, ChinaSchool of Information Engineering, Hubei University of Economics, Wuhan 430205, China3D laser scanning is widely used in modeling industrial scenes, involving crucial steps like point cloud (PC) data preprocessing and extracting modeling targets from scattered points. Extracting target PC data from larger scenes is more challenging than from smaller settings. To efficiently obtain high-quality scene data and modeling targets, we introduce an innovative approach with the adaptive density-based voxel grid filtering algorithm and a probability statistics histogram method during preprocessing. We also propose a novel method for automatic extraction of target PC data using the adjacent feature plane constraint (AFPC) clustering technique. Initially, we capture height characteristics of the target object's PC through experiential and statistical height attributes. Points corresponding to each height are then clustered based on the PC's density distribution using the density-based spatial clustering of applications with noise algorithm. The intersection of these results optimizes the position of the target object's extraction bounding box, achieving seamless automatic object extraction. Experimental results validate the effectiveness of our preprocessing methodology, with F1 scores of 97.7 % and 97.3 % for the 220 kV and 500 kV areas, respectively. Furthermore, our novel extraction method demonstrates the ability to autonomously and directly extract electrical equipment from substation PC data.http://www.sciencedirect.com/science/article/pii/S1319157824000521Point clouds dataVoxel grid filtering algorithmDensity-based spatial clusteringObject extraction3D laser scanning |
| spellingShingle | Ruiheng Li Lu Gan Yi Di Hao Tian Qiankun Zuo Yiming Luo Xuan Wu Haiyang Wang Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations Journal of King Saud University: Computer and Information Sciences Point clouds data Voxel grid filtering algorithm Density-based spatial clustering Object extraction 3D laser scanning |
| title | Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations |
| title_full | Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations |
| title_fullStr | Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations |
| title_full_unstemmed | Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations |
| title_short | Neighborhood constraint extraction for rapid modeling of point cloud scenes in large-scale power grid substations |
| title_sort | neighborhood constraint extraction for rapid modeling of point cloud scenes in large scale power grid substations |
| topic | Point clouds data Voxel grid filtering algorithm Density-based spatial clustering Object extraction 3D laser scanning |
| url | http://www.sciencedirect.com/science/article/pii/S1319157824000521 |
| work_keys_str_mv | AT ruihengli neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT lugan neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT yidi neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT haotian neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT qiankunzuo neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT yimingluo neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT xuanwu neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations AT haiyangwang neighborhoodconstraintextractionforrapidmodelingofpointcloudscenesinlargescalepowergridsubstations |