An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions
This paper proposes an efficient approach for the plane segmentation of indoor and corridor scenes. Specifically, the proposed method first uses voxels to pre-segment the scene and establishes the topological relationship between neighboring voxels. The voxel normal vectors are projected onto the su...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/4/247 |
| _version_ | 1827619699879313408 |
|---|---|
| author | Xuming Ge Jingyuan Zhang Bo Xu Hao Shu Min Chen |
| author_facet | Xuming Ge Jingyuan Zhang Bo Xu Hao Shu Min Chen |
| author_sort | Xuming Ge |
| collection | DOAJ |
| description | This paper proposes an efficient approach for the plane segmentation of indoor and corridor scenes. Specifically, the proposed method first uses voxels to pre-segment the scene and establishes the topological relationship between neighboring voxels. The voxel normal vectors are projected onto the surface of a Gaussian sphere based on the corresponding directions to achieve fast plane grouping using a variant of the K-means approach. To improve the segmentation integration, we propose releasing the points from the specified voxels and establishing second-order relationships between different primitives. We then introduce a global energy-optimization strategy that considers the unity and pairwise potentials while including high-order sequences to improve the over-segmentation problem. Three benchmark methods are introduced to evaluate the properties of the proposed approach by using the ISPRS benchmark datasets and self-collected in-house. The results of our experiments and the comparisons indicate that the proposed method can return reliable segmentation with precision over 72% even with the low-cost sensor, and provide the best performances in terms of the precision and recall rate compared to the benchmark methods. |
| first_indexed | 2024-03-09T10:33:49Z |
| format | Article |
| id | doaj.art-21e289fe7c0947cba2572d8c98f385d4 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T10:33:49Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-21e289fe7c0947cba2572d8c98f385d42023-12-01T21:01:23ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-04-0111424710.3390/ijgi11040247An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency DirectionsXuming Ge0Jingyuan Zhang1Bo Xu2Hao Shu3Min Chen4Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610000, ChinaFaculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610000, ChinaFaculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610000, ChinaChina Railway Eryuan Engineering Group Co., Ltd., Chengdu 610000, ChinaFaculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 610000, ChinaThis paper proposes an efficient approach for the plane segmentation of indoor and corridor scenes. Specifically, the proposed method first uses voxels to pre-segment the scene and establishes the topological relationship between neighboring voxels. The voxel normal vectors are projected onto the surface of a Gaussian sphere based on the corresponding directions to achieve fast plane grouping using a variant of the K-means approach. To improve the segmentation integration, we propose releasing the points from the specified voxels and establishing second-order relationships between different primitives. We then introduce a global energy-optimization strategy that considers the unity and pairwise potentials while including high-order sequences to improve the over-segmentation problem. Three benchmark methods are introduced to evaluate the properties of the proposed approach by using the ISPRS benchmark datasets and self-collected in-house. The results of our experiments and the comparisons indicate that the proposed method can return reliable segmentation with precision over 72% even with the low-cost sensor, and provide the best performances in terms of the precision and recall rate compared to the benchmark methods.https://www.mdpi.com/2220-9964/11/4/247indoor scenesnormal directionsplane segmentationpoint clouds |
| spellingShingle | Xuming Ge Jingyuan Zhang Bo Xu Hao Shu Min Chen An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions ISPRS International Journal of Geo-Information indoor scenes normal directions plane segmentation point clouds |
| title | An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions |
| title_full | An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions |
| title_fullStr | An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions |
| title_full_unstemmed | An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions |
| title_short | An Efficient Plane-Segmentation Method for Indoor Point Clouds Based on Countability of Saliency Directions |
| title_sort | efficient plane segmentation method for indoor point clouds based on countability of saliency directions |
| topic | indoor scenes normal directions plane segmentation point clouds |
| url | https://www.mdpi.com/2220-9964/11/4/247 |
| work_keys_str_mv | AT xumingge anefficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT jingyuanzhang anefficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT boxu anefficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT haoshu anefficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT minchen anefficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT xumingge efficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT jingyuanzhang efficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT boxu efficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT haoshu efficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections AT minchen efficientplanesegmentationmethodforindoorpointcloudsbasedoncountabilityofsaliencydirections |