Statistical analysis of LiDAR-derived structure and intensity variables for tree species identification

Zhang, Zhenyu and Liu, Xiaoye and Wright, Wendy (2013) Statistical analysis of LiDAR-derived structure and intensity variables for tree species identification. In: 2013 GIS and Remote Sensing Research Conference (SIRC NZ 2013) , 29-30 Aug 2013, Otago, Dunedin, New Zealand.

[img]
Preview
Text (Accepted Version)
sircnz2013_submission_o0901zhang.pdf

Download (33Kb) | Preview

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.


Statistics for USQ ePrint 36581
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Additional Information: No evidence of copyright restrictions preventing deposit of Accepted Version.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 July 2013 -)
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 July 2013 -)
Date Deposited: 14 Aug 2019 03:02
Last Modified: 14 Aug 2019 03:02
Uncontrolled Keywords: cool temperate rainforest, LiDAR, LiDAR intensity, statistical analysis, Strzelecki Ranges, tree species identification
Fields of Research : 09 Engineering > 0909 Geomatic Engineering > 090905 Photogrammetry and Remote Sensing
Socio-Economic Objective: D Environment > 96 Environment > 9606 Environmental and Natural Resource Evaluation > 960604 Environmental Management Systems
URI: http://eprints.usq.edu.au/id/eprint/36581

Actions (login required)

View Item Archive Repository Staff Only