分区分类法——针对山区遥感图象的一种有效的分类方法

SUB REGION CLASSIFICATION METHOD ——AN NEW CLASSIFICATION METHOD TO REMOTE SENSING IMAGE IN MOUNTAIN AREAS

高原山区山高坡陡、地形复杂、地块零碎 ,形成大量的阴影区及混合象元 ,被认为是遥感分类的难点地区。笔者在多年的山区遥感研究的基础上 ,通过对地形地貌、地物生态环境、地物分布特点的分析 ,提出分区分类法 ,对光照区与阴影区、地形陡峻区与地形平缓区、不同地物组合、地物生境区分别分类 。

In mountain areas, with high elevation and steep slope, their topography is varied.There are a lot of shadows and mixed pixels on the remote sensing images in mountain areas, it is considered that the remote sensing image in these areas is difficult to classify.In this paper, a new method, sub region classification,is proposed to deal with the remote sensing image classification in moutain areas. Different region, for example, sunshiny or shadowy, steep slope and gentle slope, and with different ecologic environment and land cover patterns, were classified, respectively. It is an efficient classification method to classify remote sensing images in mountain areas.