遥感地学智能图解模型支持下的土地覆盖/土地利用分类

Land-cover and land-use classification based on remote sensing intelligent Geo-interpreting model

土地覆盖/土地利用 (LC/LU)调查已经成为开展土地利用动态变化预测、自然灾害防治及土地利用规划、土地管理和环境保护的一项关键的基础性工作 ,受到广泛注意和重视。随着遥感技术和各种地学分析模型的发展和深入 ,利用遥感技术获得的影像数据对区域的LC/LU情况及其动态变化进行定期或不定期的监测 ,成为一种最为迅速可靠和理想有效的手段。常规的LC/LU遥感分类方法主要包括基于常规数理统计分类方法、基于人工神经网络分类方法、基于知识逻辑推理的分类方法等。论文综合这些方法的特性 ,提出了遥感地学智能图解模型支持下的LC/LU分类体系 ,并以香港地区为试验对象 ,采用多平台遥感数据和辅助地理信息 ,进行了土地覆盖/土地利用遥感应用研究。

Land cover/land use has become one of the crucial but basic tasks in carrying out a series of important work,such as the prediction of land use change,prevention of natural disasters,management and planning of land use,protection of environment,etc.With the development of remote sensing techniques and Geo analysis model,using remotely sensed data to monitor the status and dynamical change of land cover/land use has become one of the most rapid,credible and effectual approaches.In this article,after we firstly present the RSIGIM model,the intelligent land cover/land use classification framework and system is built up.Based on remote sensing intelligent Geo interpretation model (RSIGIM),the characteristics of traditional RS classification models can be synthetically integrated so that the Geo decision knowledge can be structurally and parametrically fused into.The target aims to build a new systematic structure of land cover/land use classification with the experimental case in Hong Kong,with the support of the data fusion model between the multi platform remotely sensed data and ancillary geographic data.