Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points
The common statistical methods for supervised classification usually require a large amount of training data to achieve reasonable results, which is time consuming and inefficient. In many methods, only the features of each point are used, regardless of their spatial distribution within a certain ne...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/9/12/1216 |
| _version_ | 1819290641165713408 |
|---|---|
| author | Nan Li Norbert Pfeifer Chun Liu |
| author_facet | Nan Li Norbert Pfeifer Chun Liu |
| author_sort | Nan Li |
| collection | DOAJ |
| description | The common statistical methods for supervised classification usually require a large amount of training data to achieve reasonable results, which is time consuming and inefficient. In many methods, only the features of each point are used, regardless of their spatial distribution within a certain neighborhood. This paper proposes a tensor-based sparse representation classification (TSRC) method for airborne LiDAR (Light Detection and Ranging) points. To keep features arranged in their spatial arrangement, each LiDAR point is represented as a 4th-order tensor. Then, TSRC is performed for point classification based on the 4th-order tensors. Firstly, a structured and discriminative dictionary set is learned by using only a few training samples. Subsequently, for classifying a new point, the sparse tensor is calculated based on the tensor OMP (Orthogonal Matching Pursuit) algorithm. The test tensor data is approximated by sub-dictionary set and its corresponding subset of sparse tensor for each class. The point label is determined by the minimal reconstruction residuals. Experiments are carried out on eight real LiDAR point clouds whose result shows that objects can be distinguished by TSRC successfully. The overall accuracy of all the datasets is beyond 80% by TSRC. TSRC also shows a good improvement on LiDAR points classification when compared with other common classifiers. |
| first_indexed | 2024-12-24T03:25:58Z |
| format | Article |
| id | doaj.art-198c8b31dc5b4c3097a84cf7987956db |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T03:25:58Z |
| publishDate | 2017-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-198c8b31dc5b4c3097a84cf7987956db2022-12-21T17:17:20ZengMDPI AGRemote Sensing2072-42922017-11-01912121610.3390/rs9121216rs9121216Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR PointsNan Li0Norbert Pfeifer1Chun Liu2Department of Geodesy and Geoinformation, TU Wien, 1040 Vienna, AustriaDepartment of Geodesy and Geoinformation, TU Wien, 1040 Vienna, AustriaCollege of Survey and Geoinformation, Tongji University, 200092 Shanghai, ChinaThe common statistical methods for supervised classification usually require a large amount of training data to achieve reasonable results, which is time consuming and inefficient. In many methods, only the features of each point are used, regardless of their spatial distribution within a certain neighborhood. This paper proposes a tensor-based sparse representation classification (TSRC) method for airborne LiDAR (Light Detection and Ranging) points. To keep features arranged in their spatial arrangement, each LiDAR point is represented as a 4th-order tensor. Then, TSRC is performed for point classification based on the 4th-order tensors. Firstly, a structured and discriminative dictionary set is learned by using only a few training samples. Subsequently, for classifying a new point, the sparse tensor is calculated based on the tensor OMP (Orthogonal Matching Pursuit) algorithm. The test tensor data is approximated by sub-dictionary set and its corresponding subset of sparse tensor for each class. The point label is determined by the minimal reconstruction residuals. Experiments are carried out on eight real LiDAR point clouds whose result shows that objects can be distinguished by TSRC successfully. The overall accuracy of all the datasets is beyond 80% by TSRC. TSRC also shows a good improvement on LiDAR points classification when compared with other common classifiers.https://www.mdpi.com/2072-4292/9/12/1216tenor sparse codingstructured and discriminative dictionary learningfeature extraction |
| spellingShingle | Nan Li Norbert Pfeifer Chun Liu Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points Remote Sensing tenor sparse coding structured and discriminative dictionary learning feature extraction |
| title | Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points |
| title_full | Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points |
| title_fullStr | Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points |
| title_full_unstemmed | Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points |
| title_short | Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points |
| title_sort | tensor based sparse representation classification for urban airborne lidar points |
| topic | tenor sparse coding structured and discriminative dictionary learning feature extraction |
| url | https://www.mdpi.com/2072-4292/9/12/1216 |
| work_keys_str_mv | AT nanli tensorbasedsparserepresentationclassificationforurbanairbornelidarpoints AT norbertpfeifer tensorbasedsparserepresentationclassificationforurbanairbornelidarpoints AT chunliu tensorbasedsparserepresentationclassificationforurbanairbornelidarpoints |