The use of decision tree and multiscale texture for classification of JERS-1 SAR data over tropical forest
- 1 January 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 38 (5) , 2310-2321
- https://doi.org/10.1109/36.868888
Abstract
The objective of this paper is to study the use of a de- cision tree classifier and multiscale texture measures to extract the- matic information on the tropical vegetation cover from the Global Rain Forest Mapping (GRFM) JERS-1 SAR mosaics. We focus our study on a coastal region of Gabon, which has a variety of land cover types common to most tropical regions. A decision tree clas- sifier does not assume a particular probability density distribution of the input data, and is thus well adapted for SAR image classifica- tion. A total of seven features, including wavelet-based multiscale texture measures (at scales of 200, 400, and 800 m) and multiscale multitemporal amplitude data (two dates at scales 100 and 400 m), are used to discriminate the land cover classes of interest. Among these layers, the best features for separating classes are found by constructing exploratory decision trees from various feature com- binations. The decision tree structure stability is then investigated by interchanging the role of the training samples for decision tree growth and testing. We show that the construction of exploratory decision trees can improve the classification results. The analysis also proves that the radar backscatter amplitude is important for separating basic land cover categories such as savannas, forests, and flooded vegetation. Texture is found to be useful for refining flooded vegetation classes. Temporal information from SAR im- ages of two different dates is explicitly used in the decision tree structure to identify swamps and temporarily flooded vegetation.Keywords
This publication has 25 references indexed in Scilit:
- Compilation of a bi-temporal JERS SAR mosaic over the African rain forest belt in the GRFM projectPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The Global Rain Forest Mapping Project JERS-1 radar mosaic of tropical Africa: development and product characterization aspectsIEEE Transactions on Geoscience and Remote Sensing, 2000
- The Global Rain Forest Mapping project - A reviewInternational Journal of Remote Sensing, 2000
- A vegetation map of Central Africa derived from satellite imageryJournal of Biogeography, 1999
- The Amazon Floodplain through Radar Eyes: Lago Grande de Monte Alegre Case StudyCanadian Journal of Remote Sensing, 1998
- Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiersInternational Journal of Remote Sensing, 1998
- Classification trees: an alternative to traditional land cover classifiersInternational Journal of Remote Sensing, 1996
- Regression Tree Analysis of satellite and terrain data to guide vegetation sampling and surveysJournal of Vegetation Science, 1994
- A comparison of supervised maximum likelihood and decision tree classification for crop cover estimation from multitemporal LANDSAT MSS dataInternational Journal of Remote Sensing, 1987
- Textural Infornation in SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 1986