Analysis of the importance of five new spectral indices from WorldView-2 in tree species classification. Issue 3 (1st September 2020)

• Record Type: Journal Article
• Authors: Liu, Huaipeng; An, Huijun
• Is Part Of: Journal of spatial science. Volume 65:Issue 3(2020)
• Page Start: 455
• Page End: 466
• Publication Date: 2020-09-01
• Subjects: WorldView-2 -- tree species classification -- spectral index mining -- importance measure -- MLC-RFI; Geographic information systems -- Periodicals; Cartography -- Periodicals; Surveying -- Periodicals; Geodesy -- Periodicals; Photogrammetry -- Periodicals; Cartography; Geodesy; Geographic information systems; Photogrammetry; Surveying; Periodicals; 526.05
• DOI: 10.1080/14498596.2018.1521754
• Languages: English
• ISSNs: 1449-8596

Abstract

ABSTRACT: Spectral information mining plays a significant role in tree species classification using remote sensing images but a measure of the importance of the mined features is also necessary. We created five new spectral indices and used MLC-RFI to determine their importance. The results showed that these spectral indices had a positive effect on tree species classification, and their importance was ranked as follows: PAI578 > PAI678 > TAI578 > TAI678 > SI57 . The experimental results showed that important spectral indices for tree species classification can be created and that it is beneficial to mine spectral information from remote sensing images.