基于混合像元分类的城市地表覆盖时空演变格局研究

Spatio-temporal Pattern of Urban Land Cover Evolvement Based on Mixed-pixel Classification for Remote Sensing Imagery

基于可能性理论和中心点聚类方法的原理,提出可能性C中心点(PCRMDD)聚类方法。运用该法对上海市中心城区Landsat ETM+遥感影像进行混合像元分类,并自动获取地物端元盖度分布图及影像端元光谱,解混精度的检验结果表明该方法能在噪声环境下获得精度较高的分类结果和端元光谱信息。根据各时期研究区域的地表覆盖分类结果,应用GIS空间分析功能,进一步探讨在城市化过程中上海中心城区土地利用时空演变格局,揭示城市用地空间扩展模式。

In this paper, we propose a Possibilistic C Repulsive Medoids （PCRMDD） clustering algorithm, based on possibility theory and principle of c-medoids clustering method. The PCRMDD algorithm is applied to mixed-pixel classification on Landsat ETM＋ images of Shanghai central city, and endmember fraction images and spectral reflectance of endmembers on images are automatically acquired. Accuracy analysis of pixels unmixing demonstrates that PCRMDD represents a robust and efficient tool for mixed-pixel classification on remote sensing imagery to obtain reliable soft classification results and endmember spectral information in noisy environment. Furthermore, according to the obtained multi-temporal land cover classification of the study area, the pattern of spatio-temporal land use evolvement and urban land spatial sprawl with urbanization in Shanghai central city are explored with the application of spatial analytical function of GIS. Results show that the urban land use structure is optimizing during vigorous urban renewal and large-scale development of the whole Pudong District, which will have an active influence to improve urban space landscape and enhance quality of ecological environment.