AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA
The study deals with the automatic supervised classification of urban objects from point clouds collected by the vehicle-based Mobile Laser Scanning (MLS) system. A benchmark dataset representing the Technical University of Munich (TUM) City Campus was used. The main contribution of this article is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-12-01
|
| 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/XLVIII-4-W3-2022/171/2022/isprs-archives-XLVIII-4-W3-2022-171-2022.pdf |
| _version_ | 1811316187645083648 |
|---|---|
| author | S. Seyfeli S. Seyfeli A. O. Ok |
| author_facet | S. Seyfeli S. Seyfeli A. O. Ok |
| author_sort | S. Seyfeli |
| collection | DOAJ |
| description | The study deals with the automatic supervised classification of urban objects from point clouds collected by the vehicle-based Mobile Laser Scanning (MLS) system. A benchmark dataset representing the Technical University of Munich (TUM) City Campus was used. The main contribution of this article is evaluating the performance difference between kNN, cylindrical and spherical local neighborhood relations in point-based classification of an MLS system using local geometric and shape-based features. The Random Forest (RF) classifier was performed for 8 manually marked classes in the benchmark set: artificial terrain, natural terrain, high vegetation, low vegetation, building, hardscape, artifact and vehicle. We reveal that the cylindrical neighborhood with 13 attributes provides an improvement of 5.2% compared to the spherical neighborhood, while the kNN gave almost the same result as the cylindrical neighborhood (0.8% improvement) in the shortest time. Finally, a new feature set was created by combining the most important features obtained from different neighborhood types. As a result, we achieved 96.9% overall accuracy by using 19 significant features obtained from all neighborhood types for the TUM-MLS1 point cloud. |
| first_indexed | 2024-04-13T11:44:21Z |
| format | Article |
| id | doaj.art-c7cab9f69d374554a1d844e6e7267dba |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-04-13T11:44:21Z |
| publishDate | 2022-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-c7cab9f69d374554a1d844e6e7267dba2022-12-22T02:48:13ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342022-12-01XLVIII-4-W3-202217117710.5194/isprs-archives-XLVIII-4-W3-2022-171-2022AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATAS. Seyfeli0S. Seyfeli1A. O. Ok2Hacettepe University, Graduate School of Science and Engineering, Ankara, TürkiyeHacettepe University, Department of Geomatics Engineering, Ankara, TürkiyeHacettepe University, Department of Geomatics Engineering, Ankara, TürkiyeThe study deals with the automatic supervised classification of urban objects from point clouds collected by the vehicle-based Mobile Laser Scanning (MLS) system. A benchmark dataset representing the Technical University of Munich (TUM) City Campus was used. The main contribution of this article is evaluating the performance difference between kNN, cylindrical and spherical local neighborhood relations in point-based classification of an MLS system using local geometric and shape-based features. The Random Forest (RF) classifier was performed for 8 manually marked classes in the benchmark set: artificial terrain, natural terrain, high vegetation, low vegetation, building, hardscape, artifact and vehicle. We reveal that the cylindrical neighborhood with 13 attributes provides an improvement of 5.2% compared to the spherical neighborhood, while the kNN gave almost the same result as the cylindrical neighborhood (0.8% improvement) in the shortest time. Finally, a new feature set was created by combining the most important features obtained from different neighborhood types. As a result, we achieved 96.9% overall accuracy by using 19 significant features obtained from all neighborhood types for the TUM-MLS1 point cloud.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVIII-4-W3-2022/171/2022/isprs-archives-XLVIII-4-W3-2022-171-2022.pdf |
| spellingShingle | S. Seyfeli S. Seyfeli A. O. Ok AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA |
| title_full | AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA |
| title_fullStr | AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA |
| title_full_unstemmed | AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA |
| title_short | AUTOMATIC CLASSIFICATION OF URBAN OBJECTS FROM MOBILE LASER SCANNING DATA |
| title_sort | automatic classification of urban objects from mobile laser scanning data |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVIII-4-W3-2022/171/2022/isprs-archives-XLVIII-4-W3-2022-171-2022.pdf |
| work_keys_str_mv | AT sseyfeli automaticclassificationofurbanobjectsfrommobilelaserscanningdata AT sseyfeli automaticclassificationofurbanobjectsfrommobilelaserscanningdata AT aook automaticclassificationofurbanobjectsfrommobilelaserscanningdata |