Design of High Spatial Resolution Remote Sensing Image Intelligent Interpretation System and Its Implementation

Dengkui Mo, Central South University of Forestry & Technology, China

The very high spatial resolution remote sensing images have been applied into many fields. However, researches on intelligent interpretation such kinds of images are rather insufficient partly due to the complexity and large size of such images. In this study, a high spatial resolution remote sensing image intelligent interpretation system (HSR—RSIIIs) was designed combining with image segmentation, geographical information system and data mining algorithm. Some key methods such as image segmentation, feature extraction, feature selection and classification algorithm for interpreting high spatial resolution remote sensing image had been studied. A land cover classification experiment is performed in the Zhuzhou area using Quickbird multi-spectral image. The classification result is consistent with the visual interpretation result. In additional, the proposed interpretation method is compared with traditional pixel-based method. The results indicate that the method proposed in the literature is more effectively and intelligently.

Keywords :  high spatial resolution, remote sensing, intelligent interpretation, land cover