Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas
Point clouds are a very detailed and accurate vector data model of 3D geographic information. In contrast to other data models, no standard has been defined for visualization and management of point clouds based on levels of detail (LOD). This paper proposes the application of the concept of LODs to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2018-01-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/22797254.2018.1522934 |
| _version_ | 1818672387396206592 |
|---|---|
| author | J. Balado L. Díaz-Vilariño P. Arias L. M. González-Desantos |
| author_facet | J. Balado L. Díaz-Vilariño P. Arias L. M. González-Desantos |
| author_sort | J. Balado |
| collection | DOAJ |
| description | Point clouds are a very detailed and accurate vector data model of 3D geographic information. In contrast to other data models, no standard has been defined for visualization and management of point clouds based on levels of detail (LOD). This paper proposes the application of the concept of LODs to point clouds and defines the LOD0 for point cloud classification (the lowest possible level of detail) as urban and non-urban. A methodology based on the use of machine learning techniques is developed to perform LOD0 classification to airborne LiDAR data. Point clouds acquired with airborne laser scanner (ALS) are structured in grid maps and geometric features related with Z distribution and roughness are extracted from each cell. Six machine learning classifiers have been trained with datasets including urban (cities) and non-urban samples (farmlands and forests). The influence of grid size, point density, number of features and classifier type are analysed in detail. The classifiers have been tested in three case studies. The best results correspond to a grid size of 100 m and the use of 12 geometric features. The accuracy is around 90% in all tests and Cohen’s Kappa index reaches 81% in the best of cases. |
| first_indexed | 2024-12-17T07:39:05Z |
| format | Article |
| id | doaj.art-a3dd11f5677c4ab5bce1815547045b03 |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-12-17T07:39:05Z |
| publishDate | 2018-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-a3dd11f5677c4ab5bce1815547045b032022-12-21T21:58:12ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542018-01-0151197899010.1080/22797254.2018.15229341522934Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areasJ. Balado0L. Díaz-Vilariño1P. Arias2L. M. González-Desantos3University of VigoUniversity of VigoUniversity of VigoUniversity of VigoPoint clouds are a very detailed and accurate vector data model of 3D geographic information. In contrast to other data models, no standard has been defined for visualization and management of point clouds based on levels of detail (LOD). This paper proposes the application of the concept of LODs to point clouds and defines the LOD0 for point cloud classification (the lowest possible level of detail) as urban and non-urban. A methodology based on the use of machine learning techniques is developed to perform LOD0 classification to airborne LiDAR data. Point clouds acquired with airborne laser scanner (ALS) are structured in grid maps and geometric features related with Z distribution and roughness are extracted from each cell. Six machine learning classifiers have been trained with datasets including urban (cities) and non-urban samples (farmlands and forests). The influence of grid size, point density, number of features and classifier type are analysed in detail. The classifiers have been tested in three case studies. The best results correspond to a grid size of 100 m and the use of 12 geometric features. The accuracy is around 90% in all tests and Cohen’s Kappa index reaches 81% in the best of cases.http://dx.doi.org/10.1080/22797254.2018.1522934Supervised classificationmachine learningpoint cloudbig datalaser scanner |
| spellingShingle | J. Balado L. Díaz-Vilariño P. Arias L. M. González-Desantos Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas European Journal of Remote Sensing Supervised classification machine learning point cloud big data laser scanner |
| title | Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas |
| title_full | Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas |
| title_fullStr | Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas |
| title_full_unstemmed | Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas |
| title_short | Automatic LOD0 classification of airborne LiDAR data in urban and non-urban areas |
| title_sort | automatic lod0 classification of airborne lidar data in urban and non urban areas |
| topic | Supervised classification machine learning point cloud big data laser scanner |
| url | http://dx.doi.org/10.1080/22797254.2018.1522934 |
| work_keys_str_mv | AT jbalado automaticlod0classificationofairbornelidardatainurbanandnonurbanareas AT ldiazvilarino automaticlod0classificationofairbornelidardatainurbanandnonurbanareas AT parias automaticlod0classificationofairbornelidardatainurbanandnonurbanareas AT lmgonzalezdesantos automaticlod0classificationofairbornelidardatainurbanandnonurbanareas |