WorldView-2 satellite imagery and airborne LiDAR data for object-based forest species classification in a cool temperate rainforest environment

Zhang, Zhenyu and Liu, Xiaoye (2013) WorldView-2 satellite imagery and airborne LiDAR data for object-based forest species classification in a cool temperate rainforest environment. In: Developments in multidimensional spatial data models. Lecture Notes in Geoinformation and Cartography. Springer, Heidelberg, Germany, pp. 103-122. ISBN 978-3-642-36378-8

Abstract

High resolution spatial data including airborne LiDAR data and newly available WorldView-2 satellite imagery provide opportunities to develop new efficient ways of solving conventional problems in forestry. Those responsible for monitoring forest changes over time relevant to timber harvesting and native forest conservation realize the potential for improved documentation from using such data. Proper use of high spatial resolution data with object-based image analysis approach and nonparametric classification method such as decision trees offer an alternative to aerial photograph interpretation in support of forest classification and mapping. This study explored ways of processing airborne Li-DAR data and WorldView-2 satellite imagery for object-based forest species classification using decision trees in the Strzelecki Ranges, one of the four major Victorian areas of cool temperate rainforest in Australia. The effectiveness of variables derived from different data sets, in particular, the four new bands of WorldView-2 imagery was examined. The results showed that using LiDAR data alone or four conventional bands only, the overall accuracies achieved were 61.39% and 61.42% respectively, but the overall accuracy increased to 82.35% when all eight bands and the LiDAR data were used. This study demonstrated that the integration of airborne LiDAR and eight WorldView-2 bands significantly improved the classification accuracy.


Statistics for USQ ePrint 24494
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Additional Information: Copyright Springer-Verlag Berlin Heidelberg 2013. Permanent restricted access to published version due to publisher copyright policy. Originally presented at: GeoAdvances 2012 workshop, 7-8 Nov, at the Universiti Teknologi Malaysia. All the submitted full papers (42 of them) were blind peer reviewed by the Scientific Program Committee members, and the 16 accepted papers are published in this Springer book of the Lecture Notes on Geoinformation and Cartography (LNG&C) series.
Faculty / Department / School: Historic - Faculty of Engineering and Surveying - Department of Surveying and Land Information
Date Deposited: 01 Feb 2014 07:47
Last Modified: 03 May 2017 02:13
Uncontrolled Keywords: WorldView-2; LiDAR; object-based image analysis; forest classification; decision tree; cool temperate rainforest
Fields of Research : 09 Engineering > 0909 Geomatic Engineering > 090905 Photogrammetry and Remote Sensing
05 Environmental Sciences > 0502 Environmental Science and Management > 050206 Environmental Monitoring
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing
Socio-Economic Objective: D Environment > 96 Environment > 9613 Remnant Vegetation and Protected Conservation Areas > 961306 Remnant Vegetation and Protected Conservation Areas in Forest and Woodlands Environments
Identification Number or DOI: 10.1007/978-3-642-36379-5_7
URI: http://eprints.usq.edu.au/id/eprint/24494

Actions (login required)

View Item Archive Repository Staff Only