FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS
Terrestrial Laser scanner has been widely used in the field of forestry. Wood-leaf separation is the fundamental step to most applications of forestry. This paper presented a robust supervised learning method for wood and leaf classification by developing four new feature vectors. Fractal dimension...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2020-08-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-1-2020/95/2020/isprs-annals-V-1-2020-95-2020.pdf |
| _version_ | 1819119682157805568 |
|---|---|
| author | Z. Hui Y. Xia Y. Nie Y. Chang H. Hu N. Li Y. He |
| author_facet | Z. Hui Y. Xia Y. Nie Y. Chang H. Hu N. Li Y. He |
| author_sort | Z. Hui |
| collection | DOAJ |
| description | Terrestrial Laser scanner has been widely used in the field of forestry. Wood-leaf separation is the fundamental step to most applications of forestry. This paper presented a robust supervised learning method for wood and leaf classification by developing four new feature vectors. Fractal dimension is first calculated to indicate the difference of regularity or roughness between wood and leaf. Zenith angle and variation are presented to distinguish trunks or branches from leaves. The adaptive axis direction of cylinder is adopted to calculate the local point density precisely. Experimental results show that the supervised learning method using the four feature vectors presented in this paper can achieve a good classification performance. Both accuracy and <i>F</i>1 score are higher than the ones of the method using eigen value based feature vectors. |
| first_indexed | 2024-12-22T06:08:39Z |
| format | Article |
| id | doaj.art-fa4129b5f7854d7db78b6fa42815db33 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-22T06:08:39Z |
| publishDate | 2020-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-fa4129b5f7854d7db78b6fa42815db332022-12-21T18:36:18ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502020-08-01V-1-2020959910.5194/isprs-annals-V-1-2020-95-2020FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDSZ. Hui0Y. Xia1Y. Nie2Y. Chang3H. Hu4N. Li5Y. He6Faculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaFaculty of Geomatics, East China University of Technology, Nanchang, ChinaTerrestrial Laser scanner has been widely used in the field of forestry. Wood-leaf separation is the fundamental step to most applications of forestry. This paper presented a robust supervised learning method for wood and leaf classification by developing four new feature vectors. Fractal dimension is first calculated to indicate the difference of regularity or roughness between wood and leaf. Zenith angle and variation are presented to distinguish trunks or branches from leaves. The adaptive axis direction of cylinder is adopted to calculate the local point density precisely. Experimental results show that the supervised learning method using the four feature vectors presented in this paper can achieve a good classification performance. Both accuracy and <i>F</i>1 score are higher than the ones of the method using eigen value based feature vectors.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-1-2020/95/2020/isprs-annals-V-1-2020-95-2020.pdf |
| spellingShingle | Z. Hui Y. Xia Y. Nie Y. Chang H. Hu N. Li Y. He FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS |
| title_full | FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS |
| title_fullStr | FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS |
| title_full_unstemmed | FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS |
| title_short | FRACTAL DIMENSION BASED SUPERVISED LEARNING FOR WOOD AND LEAF CLASSIFICATION FROM TERRESTRIAL LIDAR POINT CLOUDS |
| title_sort | fractal dimension based supervised learning for wood and leaf classification from terrestrial lidar point clouds |
| url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-1-2020/95/2020/isprs-annals-V-1-2020-95-2020.pdf |
| work_keys_str_mv | AT zhui fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT yxia fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT ynie fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT ychang fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT hhu fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT nli fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds AT yhe fractaldimensionbasedsupervisedlearningforwoodandleafclassificationfromterrestriallidarpointclouds |