Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation
Segmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classif...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2013-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/5/4/1624 |
| _version_ | 1819003058764382208 |
|---|---|
| author | Laurent Trassoudaine Paul Checchin Ahmad Kamal Aijazi |
| author_facet | Laurent Trassoudaine Paul Checchin Ahmad Kamal Aijazi |
| author_sort | Laurent Trassoudaine |
| collection | DOAJ |
| description | Segmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classify urban scenes based on a super-voxel segmentation of sparse 3D data obtained from LiDAR sensors is presented. The 3D point cloud is first segmented into voxels, which are then characterized by several attributes transforming them into super-voxels. These are joined together by using a link-chain method rather than the usual region growing algorithm to create objects. These objects are then classified using geometrical models and local descriptors. In order to evaluate the results, a new metric that combines both segmentation and classification results simultaneously is presented. The effects of voxel size and incorporation of RGB color and laser reflectance intensity on the classification results are also discussed. The method is evaluated on standard data sets using different metrics to demonstrate its efficacy. |
| first_indexed | 2024-12-20T23:14:58Z |
| format | Article |
| id | doaj.art-7e7036ee01f0472f91977052aeb5a180 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T23:14:58Z |
| publishDate | 2013-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7e7036ee01f0472f91977052aeb5a1802022-12-21T19:23:39ZengMDPI AGRemote Sensing2072-42922013-03-01541624165010.3390/rs5041624Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with EvaluationLaurent TrassoudainePaul ChecchinAhmad Kamal AijaziSegmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classify urban scenes based on a super-voxel segmentation of sparse 3D data obtained from LiDAR sensors is presented. The 3D point cloud is first segmented into voxels, which are then characterized by several attributes transforming them into super-voxels. These are joined together by using a link-chain method rather than the usual region growing algorithm to create objects. These objects are then classified using geometrical models and local descriptors. In order to evaluate the results, a new metric that combines both segmentation and classification results simultaneously is presented. The effects of voxel size and incorporation of RGB color and laser reflectance intensity on the classification results are also discussed. The method is evaluated on standard data sets using different metrics to demonstrate its efficacy.http://www.mdpi.com/2072-4292/5/4/1624segmentation3D point cloudsuper-voxelclassificationurban scene3D objects |
| spellingShingle | Laurent Trassoudaine Paul Checchin Ahmad Kamal Aijazi Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation Remote Sensing segmentation 3D point cloud super-voxel classification urban scene 3D objects |
| title | Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation |
| title_full | Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation |
| title_fullStr | Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation |
| title_full_unstemmed | Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation |
| title_short | Segmentation Based Classification of 3D Urban Point Clouds: A Super-Voxel Based Approach with Evaluation |
| title_sort | segmentation based classification of 3d urban point clouds a super voxel based approach with evaluation |
| topic | segmentation 3D point cloud super-voxel classification urban scene 3D objects |
| url | http://www.mdpi.com/2072-4292/5/4/1624 |
| work_keys_str_mv | AT laurenttrassoudaine segmentationbasedclassificationof3durbanpointcloudsasupervoxelbasedapproachwithevaluation AT paulchecchin segmentationbasedclassificationof3durbanpointcloudsasupervoxelbasedapproachwithevaluation AT ahmadkamalaijazi segmentationbasedclassificationof3durbanpointcloudsasupervoxelbasedapproachwithevaluation |