Statistical analysis of LiDAR-derived structure and intensity variables for tree species identification
Paper
Paper/Presentation Title | Statistical analysis of LiDAR-derived structure and intensity variables for tree species identification |
---|---|
Presentation Type | Paper |
Authors | Zhang, Zhenyu (Author), Liu, Xiaoye (Author) and Wright, Wendy (Author) |
Editors | Denys, P., Strack, M., Moore, A. B. and Whingham, P. |
Journal or Proceedings Title | Proceedings of the 125th NZIS Annual Conference, and SIRC NZ 2013: GIS and Remote Sensing Research Conference |
Number of Pages | 4 |
Year | 2013 |
Place of Publication | Wellington, New Zealand |
ISBN | 9780473247560 |
9780473247577 | |
Web Address (URL) of Paper | https://www.otago.ac.nz/surveying/news/seminars/otago043532.html |
Conference/Event | 2013 GIS and Remote Sensing Research Conference (SIRC NZ 2013) |
Event Details | 2013 GIS and Remote Sensing Research Conference (SIRC NZ 2013) Event Date 29 to end of 30 Aug 2013 Event Location Otago, New Zealand |
Abstract | Tree species identification is critical for sustainable forest management and native forest conservation. It has been recognised that airborne LiDAR (light detection and ranging) offers advantages over the interpretation of aerial photographs and processing of multi-spectral and/or hyper-spectral remote sensing data in forest classification. However, as shown by our previous studies of forest communities of the Strzelecki Ranges, Victoria, Australia, the only use of LiDAR-derived structure variables may not offer unequivocal distinction between all forest types, such as cool temperate rainforest dominated by the Myrtle Beech (Nothofagus cunninghamii) and adjacent Silver Wattle (Acacia dealbata) forest. This paper reports the results of deploying both structure and intensity variables derived from small-footprint, high-density discrete airborne LiDAR data for the classification of the Myrtle Beech and the Silver Wattle at individual tree level in the Strzeleckis. The tree species classification was achieved via linear discriminant analysis with cross-validation, the accuracy having been assessed by an error matrix. The results showed that the inclusion of LiDAR-derived intensity variables improved the accuracy of the classification of the Myrtle Beech and the Silver Wattle species in the study area. An overall classification accuracy of 86.4% was achieved using both structure and intensity variables. |
Keywords | cool temperate rainforest, LiDAR, LiDAR intensity, statistical analysis, Strzelecki Ranges, tree species identification |
ANZSRC Field of Research 2020 | 401304. Photogrammetry and remote sensing |
Public Notes | No evidence of copyright restrictions preventing deposit of Accepted Version. |
Byline Affiliations | School of Civil Engineering and Surveying |
Monash University | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q5479/statistical-analysis-of-lidar-derived-structure-and-intensity-variables-for-tree-species-identification
Download files
168
total views55
total downloads0
views this month1
downloads this month