Study Of Extracting The Forest Area Based On The ETM+ Remote Sensing Image

Forest resource is the rare, renewable resources in the economic construction and ecological environment construction, having the ecological function of water and soil conserving, wind-defending, sand-binding, air purifying and weather regulating and so on. The forest resource status of growth and decline influence not only the sustainable development of the regional economy, but also the changes of region and even global environment. Therefore, it is important to master the status of forest resource in time.The first earth resources satellite was launched in 1972, and the remote sensing technology is developing quickly. The remote sensing technology has greatly improved resolving power in recent years and provides the new method for the research of forest resource.People pay more attention to usage of remote sensing images extracting the forest area. In this paper, Nanjing is the region of study, and the basic theory and methods of image fusion and classification are adopted. Finish forest land extraction from ETM+ image, and study image preprocessing, spectrum character analysis, multi-spectrum transformation during the paper.The primary work in the paper as followed:(l)According to image spectrum character, correlation coefficients and so on, choose the band combination and image fusion.(2)Different merge methods such as HIS, PCA, Brovey, and Wavelet have been discussed. Based on correlation coefficient quantitative analysis, conclusion was given that Brovey transformation is a kind of fine merge method.(3)Based on the characteristic of TM, improve the transform of Brovey.(4)In image classification, gain the sample by ISODATA unsupervised classification, and verify the sample in reality.(5) In view of the TM database with a normal distribution, choose the method of maximum likelihood as the supervised classification to classify the images.