基于SAM和多源信息的土地利用／覆盖自动分类  

Land use/cover classification using multi-source data with SAM

作　　者：刘璞[1] 张远[1] 周斌[1] 吴嘉平[1] 

机构地区：[1]浙江大学环境与资源学院,浙江省农业遥感与信息技术研究重点实验室,浙江杭州310029

出　　处：《浙江大学学报（工学版）》2009年第9期1574-1579,共6页Journal of Zhejiang University：Engineering Science

基　　金：浙江省重点科技资助项目(2006C22026);浙江大学引进人才启动基金

摘　　要：将多源信息与光谱角制图(SAM)自动分类相结合,探求多源信息在TM图像自动分类中的作用.以具有代表性的浙江富阳市和义乌市为研究区,进行试验验证.结果表明,与其他多源信息如海拔高程、坡向、归一化植被指数(NDVI)、归一化水体指数(NDWI)、归一化建筑指数(NDBI)和归一化裸土指数(NDBaI)相比,坡度信息的辅助作用最为突出.复合坡度信息后的TM图像SAM分类总精度比单独TM图像SAM分类提高10%左右.融合坡度辅助信息运用SAM方法,适用于地形地貌复杂、土地利用细碎地区的TM图像土地利用/覆盖自动分类.The effectiveness of multi-source data was analyzed by using TM imagery and multi-source data with spectral angle mapper （SAM） algorithm. Fuyang City, Zhejiang Province was selected as the study site, while Yiwu City of the Province was as a verification site. Results showed that slope information provided the best assistance in land use/cover classification, compared with other source data such as eleva- tion, aspect, normalized difference vegetation index（NDVI）, normalized difference water index（NDWI）, normalized difference build-up index（NDBI） and normalized difference bareness index（NDBaI）. The classification accuracy with the slope information added increased by about 10% compared with the result from TM data only. The SAM method by integrating TM imagery and slope data is applicable for the area with complex physiography and finelybroken land use/cover.

关 键 词：土地利用/覆盖分类 光谱角制图 TM 辅助信息 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]