Synergistic use of multi-temporal ALOS/PALSAR with SPOT multispectral satellite imagery for land cover mapping in the Ho Chi Minh city area, Vietnam

This paper discusses the synergistic use of multi-temporal ALOS/PALSAR and SPOT multi-spectral images for land cover classification in the Ho Chi Minh city area in Vietnam. Five PALSAR images and SPOT 2 multispectral image were used for classification. Integration of additional information such as interferometric coherence, textural data was also studied. Different combinations of multi-temporal SAR backscatter images, coherence data, SPOT multi-spectral bands, texture measures were generated and tested in order to determine the best combination, which gives the highest classification accuracy. Results indicate that the combination of SAR and optical images gives significantly higher classification accuracy than using a single type of data, and that the Support Vector Machine (SVM) classifier could outperform the Maximum Likelihood (ML) classifier in cases of classification of the combined datasets.