Title :
Identification of Mangrove Using Decision Tree Method
Author_Institution :
Sch. of Remote Sensing, Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Abstract :
The classification accuracy of mangrove is always low due to the similarity of spectra between mangrove and water-vegetation mixed pixels. Greenness and wetness were extracted by K-T transformation based on Landsat5/TM imagery. The greenness and wetness can significantly improve the separability between mangrove and water-vegetation mixed pixels by comparison with NDVI, TM3/TM5,TM5/TM4, which always were employed by other researchers. The Kappa coefficient, commission error of mangrove class were 0.90, 7.9%, respectively, by using decision tree method.
Keywords :
decision trees; forestry; geophysical image processing; vegetation mapping; K-T transformation; Kappa coefficient; Landsat5-TM imagery; classification accuracy; commission error; decision tree method; greenness; mangrove; separability; water-vegetation mixed pixels; wetness; Decision trees; Earth; Green products; Pixel; Remote sensing; Satellites; Vegetation mapping; K-T transformation; TM; greennes; mangrove; wetness;
Conference_Titel :
Information and Computing (ICIC), 2011 Fourth International Conference on
Conference_Location :
Phuket Island
Print_ISBN :
978-1-61284-688-0
DOI :
10.1109/ICIC.2011.70
