A spatial–spectral classification framework for multispectral LiDAR
ABSTRACTPrecise classification of Light Detection and Ranging (LiDAR) point cloud is a fundamental process in various applications, such as land cover mapping, forestry management, and autonomous driving. Due to the lack of spectral information, the existing research on single wavelength LiDAR class...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-06-01
|
| Series: | Geo-spatial Information Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10095020.2023.2208611 |
| _version_ | 1797814101914681344 |
|---|---|
| author | Shuo Shi Biwu Chen Sifu Bi Junkai Li Wei Gong Jia Sun Bowen Chen Lin Du Jian Yang Qian Xu Fei Wang Shalei Song |
| author_facet | Shuo Shi Biwu Chen Sifu Bi Junkai Li Wei Gong Jia Sun Bowen Chen Lin Du Jian Yang Qian Xu Fei Wang Shalei Song |
| author_sort | Shuo Shi |
| collection | DOAJ |
| description | ABSTRACTPrecise classification of Light Detection and Ranging (LiDAR) point cloud is a fundamental process in various applications, such as land cover mapping, forestry management, and autonomous driving. Due to the lack of spectral information, the existing research on single wavelength LiDAR classification is limited. Spectral information from images could address this limitation, but data fusion suffers from varying illumination conditions and the registration problem. A novel multispectral LiDAR successfully obtains spatial and spectral information as a brand-new data type, namely, multispectral point cloud, thereby improving classification performance. However, spatial and spectral information of multispectral LiDAR has been processed separately in previous studies, thereby possibly limiting the classification performance of multispectral LiDAR. To explore the potential of this new data type, the current spatial–spectral classification framework for multispectral LiDAR that includes four steps: (1) neighborhood selection, (2) feature extraction and selection, (3) classification, and (4) label smoothing. Three novel highlights were proposed in this spatial – spectral classification framework. (1) We improved the popular eigen entropy-based neighborhood selection by spectral angle match to extract a more precise neighborhood. (2) We evaluated the importance of geometric and spectral features to compare their contributions and selected the most important features to reduce feature redundancy. (3) We conducted spatial label smoothing by a conditional random field, accounting for the spatial and spectral information of the neighborhood points. The proposed method demonstrated by a multispectral LiDAR with three channels: 466 nm (blue), 527 nm (green), and 628 nm (red). Experimental results demonstrate the effectiveness of the proposed spatial – spectral classification framework. Moreover, this research takes advantages of the complementation of spatial and spectral information, which could benefit more precise neighborhood selection, more effective features, and satisfactory refinement of classification result. Finally, this study could serve as an inspiration for future efficient spatial–spectral process for multispectral point cloud. |
| first_indexed | 2024-03-13T08:02:35Z |
| format | Article |
| id | doaj.art-ce02f9c0e2c74cc286a61707e803688b |
| institution | Directory Open Access Journal |
| issn | 1009-5020 1993-5153 |
| language | English |
| last_indexed | 2024-03-13T08:02:35Z |
| publishDate | 2023-06-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geo-spatial Information Science |
| spelling | doaj.art-ce02f9c0e2c74cc286a61707e803688b2023-06-01T11:47:04ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532023-06-0111510.1080/10095020.2023.2208611A spatial–spectral classification framework for multispectral LiDARShuo Shi0Biwu Chen1Sifu Bi2Junkai Li3Wei Gong4Jia Sun5Bowen Chen6Lin Du7Jian Yang8Qian Xu9Fei Wang10Shalei Song11State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaScientific Laboratory, Shanghai Radio Equipment Research Institute, Shanghai, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaIndustry Development and Planning Institute, NFGA, Beijing, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaFaculty of Information Engineering, China University of Geosciences, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaFaculty of Information Engineering, China University of Geosciences, Wuhan, ChinaFaculty of Information Engineering, China University of Geosciences, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, ChinaInnovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuhan, ChinaABSTRACTPrecise classification of Light Detection and Ranging (LiDAR) point cloud is a fundamental process in various applications, such as land cover mapping, forestry management, and autonomous driving. Due to the lack of spectral information, the existing research on single wavelength LiDAR classification is limited. Spectral information from images could address this limitation, but data fusion suffers from varying illumination conditions and the registration problem. A novel multispectral LiDAR successfully obtains spatial and spectral information as a brand-new data type, namely, multispectral point cloud, thereby improving classification performance. However, spatial and spectral information of multispectral LiDAR has been processed separately in previous studies, thereby possibly limiting the classification performance of multispectral LiDAR. To explore the potential of this new data type, the current spatial–spectral classification framework for multispectral LiDAR that includes four steps: (1) neighborhood selection, (2) feature extraction and selection, (3) classification, and (4) label smoothing. Three novel highlights were proposed in this spatial – spectral classification framework. (1) We improved the popular eigen entropy-based neighborhood selection by spectral angle match to extract a more precise neighborhood. (2) We evaluated the importance of geometric and spectral features to compare their contributions and selected the most important features to reduce feature redundancy. (3) We conducted spatial label smoothing by a conditional random field, accounting for the spatial and spectral information of the neighborhood points. The proposed method demonstrated by a multispectral LiDAR with three channels: 466 nm (blue), 527 nm (green), and 628 nm (red). Experimental results demonstrate the effectiveness of the proposed spatial – spectral classification framework. Moreover, this research takes advantages of the complementation of spatial and spectral information, which could benefit more precise neighborhood selection, more effective features, and satisfactory refinement of classification result. Finally, this study could serve as an inspiration for future efficient spatial–spectral process for multispectral point cloud.https://www.tandfonline.com/doi/10.1080/10095020.2023.2208611multispectral Light Detection and Ranging (LiDAR)point cloud classificationneighborhood selectionfeature selectioncondition random field |
| spellingShingle | Shuo Shi Biwu Chen Sifu Bi Junkai Li Wei Gong Jia Sun Bowen Chen Lin Du Jian Yang Qian Xu Fei Wang Shalei Song A spatial–spectral classification framework for multispectral LiDAR Geo-spatial Information Science multispectral Light Detection and Ranging (LiDAR) point cloud classification neighborhood selection feature selection condition random field |
| title | A spatial–spectral classification framework for multispectral LiDAR |
| title_full | A spatial–spectral classification framework for multispectral LiDAR |
| title_fullStr | A spatial–spectral classification framework for multispectral LiDAR |
| title_full_unstemmed | A spatial–spectral classification framework for multispectral LiDAR |
| title_short | A spatial–spectral classification framework for multispectral LiDAR |
| title_sort | spatial spectral classification framework for multispectral lidar |
| topic | multispectral Light Detection and Ranging (LiDAR) point cloud classification neighborhood selection feature selection condition random field |
| url | https://www.tandfonline.com/doi/10.1080/10095020.2023.2208611 |
| work_keys_str_mv | AT shuoshi aspatialspectralclassificationframeworkformultispectrallidar AT biwuchen aspatialspectralclassificationframeworkformultispectrallidar AT sifubi aspatialspectralclassificationframeworkformultispectrallidar AT junkaili aspatialspectralclassificationframeworkformultispectrallidar AT weigong aspatialspectralclassificationframeworkformultispectrallidar AT jiasun aspatialspectralclassificationframeworkformultispectrallidar AT bowenchen aspatialspectralclassificationframeworkformultispectrallidar AT lindu aspatialspectralclassificationframeworkformultispectrallidar AT jianyang aspatialspectralclassificationframeworkformultispectrallidar AT qianxu aspatialspectralclassificationframeworkformultispectrallidar AT feiwang aspatialspectralclassificationframeworkformultispectrallidar AT shaleisong aspatialspectralclassificationframeworkformultispectrallidar AT shuoshi spatialspectralclassificationframeworkformultispectrallidar AT biwuchen spatialspectralclassificationframeworkformultispectrallidar AT sifubi spatialspectralclassificationframeworkformultispectrallidar AT junkaili spatialspectralclassificationframeworkformultispectrallidar AT weigong spatialspectralclassificationframeworkformultispectrallidar AT jiasun spatialspectralclassificationframeworkformultispectrallidar AT bowenchen spatialspectralclassificationframeworkformultispectrallidar AT lindu spatialspectralclassificationframeworkformultispectrallidar AT jianyang spatialspectralclassificationframeworkformultispectrallidar AT qianxu spatialspectralclassificationframeworkformultispectrallidar AT feiwang spatialspectralclassificationframeworkformultispectrallidar AT shaleisong spatialspectralclassificationframeworkformultispectrallidar |