Study of Classification with SPOT Images: Feng-Shan Upper Stream Watershed
Track: Remote Sensing Imagery
Author(s): Chen WEN Fu
There were many developed cases in the Feng-Shan upper stream watershed during 1988-1994. This study analyzed the land use changes. It appears that the agricultural use tends to ward planting highly economical crops. After traffic transportation was constructed and immigration has grown, Lung-Tan County of the study area has urbanized significantly. The result of classification is that Unsupervised classification is the worst, Supervised is better than Unsupervised, and Neural Network classification is the best. Particularly, the more the complex pixels are included in an image, the better effect Neural Network classification will be.
Chen WEN Fu
National Chung-Hsing University
No.250, Guoguang Rd., Taichung, Taiwan 402, R.O.C.
Taichung, Taiwan 402