INVENTARISASI TUTUPAN LAHAN MENGGUNAKAN SATELIT PENGINDERAAN JAUH ALOS DENGAN METODE KLASIFIKASI TETANGGA TERDEKAT STUDY KASUS: JAWA BARAT

Abstract

In the concept of conventional remote sensing supervised classification, the relationship between the trained information and the classification result is one pixel belongs to one class. The existence of mixed class can not be accepted due to the it assumption that had been taken during the classification and during the determination of pixel membership. The algorithm of classification using definiens software with based on nearest neighborhood method consist of: 1) image segmentation; 2) defined of class/objects, 3). trainning area; 4) classification using the decision of nearest neighborhood. One of the limitation of the training area process is the decrease of the image accuracy. So that, the classification analisis using ALOS Image at May 10st, 2007 in West Java Province stands for : man made object area is 38.077,46 ha, the open field is about 29,23.,06 ha, water body is 13,985.47 ha, while the sparsely and dense vegetation are 42988.47 ha and 70821.76 Ha respectively.