PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION
The common method of LiDAR classifications is Markov random fields (MRF). Based on construction of MRF energy function, spectral and directional features are extracted for on-board urban point clouds. The MRF energy function is consisted of unary and pairwise potentials. The unary terms are computed...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2016-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/109/2016/isprs-archives-XLI-B1-109-2016.pdf |
| _version_ | 1828742291198574592 |
|---|---|
| author | Z. Shu K. Sun K. Qiu K. Ding |
| author_facet | Z. Shu K. Sun K. Qiu K. Ding |
| author_sort | Z. Shu |
| collection | DOAJ |
| description | The common method of LiDAR classifications is Markov random fields (MRF). Based on construction of MRF energy function, spectral and directional features are extracted for on-board urban point clouds. The MRF energy function is consisted of unary and pairwise potentials. The unary terms are computed by SVM classifictaion. The initial labeling is mainly processed through geometrical shapes. The pairwise potential is estimated by Naïve Bayes. From training data, the probability of adjacent objects is computed by prior knowledge. The final labeling method is reweighted message-passing to minimization the energy function. The MRF model is difficult to process the large-scale misclassification. We propose a super-voxel clustering method for over-segment and grouping segment for large objects. Trees, poles ground, and building are classified in this paper. The experimental results show that this method improves the accuracy of classification and speed of computation. |
| first_indexed | 2024-04-13T01:16:53Z |
| format | Article |
| id | doaj.art-c759545086cf4fadb6ee781d14046c25 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-04-13T01:16:53Z |
| publishDate | 2016-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-c759545086cf4fadb6ee781d14046c252022-12-22T03:08:54ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342016-06-01XLI-B110911310.5194/isprs-archives-XLI-B1-109-2016PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATIONZ. Shu0K. Sun1K. Qiu2K. Ding3Leador Spatial Information Technology Co., Ltd. Building No. 12, Huazhong University Sci. & Tec. Park, East Lake Hi-Tech Zone, Wuhan, ChinaLeador Spatial Information Technology Co., Ltd. Building No. 12, Huazhong University Sci. & Tec. Park, East Lake Hi-Tech Zone, Wuhan, ChinaLeador Spatial Information Technology Co., Ltd. Building No. 12, Huazhong University Sci. & Tec. Park, East Lake Hi-Tech Zone, Wuhan, ChinaLeador Spatial Information Technology Co., Ltd. Building No. 12, Huazhong University Sci. & Tec. Park, East Lake Hi-Tech Zone, Wuhan, ChinaThe common method of LiDAR classifications is Markov random fields (MRF). Based on construction of MRF energy function, spectral and directional features are extracted for on-board urban point clouds. The MRF energy function is consisted of unary and pairwise potentials. The unary terms are computed by SVM classifictaion. The initial labeling is mainly processed through geometrical shapes. The pairwise potential is estimated by Naïve Bayes. From training data, the probability of adjacent objects is computed by prior knowledge. The final labeling method is reweighted message-passing to minimization the energy function. The MRF model is difficult to process the large-scale misclassification. We propose a super-voxel clustering method for over-segment and grouping segment for large objects. Trees, poles ground, and building are classified in this paper. The experimental results show that this method improves the accuracy of classification and speed of computation.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/109/2016/isprs-archives-XLI-B1-109-2016.pdf |
| spellingShingle | Z. Shu K. Sun K. Qiu K. Ding PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION |
| title_full | PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION |
| title_fullStr | PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION |
| title_full_unstemmed | PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION |
| title_short | PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION |
| title_sort | pairwise svm for on board urban road lidar classification |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/109/2016/isprs-archives-XLI-B1-109-2016.pdf |
| work_keys_str_mv | AT zshu pairwisesvmforonboardurbanroadlidarclassification AT ksun pairwisesvmforonboardurbanroadlidarclassification AT kqiu pairwisesvmforonboardurbanroadlidarclassification AT kding pairwisesvmforonboardurbanroadlidarclassification |