利用SPOT-6影像提取新增建设用地的方法研究

Extraction Method for Increasing Construction Land with SPOT-6 image

随着我国城镇化进程的推进,新增建设用地占用耕地不可避免,特别是在城市郊区/近郊区。为加强土地管理,国土部门对土地利用进行年度变更调查监测与核查工作,重点监测各类新增建设用地。SPOT-6影像是一种投入使用时间不长的全新遥感数据源。本文基于SPOT-6影像,结合基期土地利用图,利用SEaTH算法,采用面向对象的方法,研究新增建设用地自动提取算法。首先提取基期的非建设用地图斑,在其约束下对SPOT-6影像进行多尺度分割,以分割得到的新图斑为基本单元,利用光谱、纹理等特征构建土地类型识别知识库,基于SEaTH算法来实现特征优选和特征阈值自动确定,并构建了模糊分类规则,最后将分类结果与基期土地利用数据叠加分析,获取新增建设用地。实验结果表明,应用SPOT-6影像与基期土地利用图,提取新增建设用地的精度达到88%,满足土地利用年度变更调查监测与核查的基本要求。

Along with economic development and urbanization accelerating, the phenomenon of land occupied by construction is more and more noticeable, especially in the suburbs of the city. To strengthen the land management, land department have to monitor the land use every year by remote sensing imges. SPOT-6 images is a new kind of remote sensing data source. This article is based onSPOT-6, combining with the base land use map, using the method of object-oriented to extractthe increasing construction land in Beijing suburb. First, using the characteristics such as spectral, texture, shape, features semantic build a knowledge base for various land cover types, using SEaTH algorithm achieves feature selection and threshold determination, then construct the rules of fuzzy classification, finally the classification results are analyzed by overlaid with the base period data of land use. Experimental results show that the combination of SPOT-6 imaging with the land use base map, can effectively extract the increasing construction land information, the image can be used as a data source of dynamic remote sensing monitoring of land use.