Object Oriented Information Extraction from High Resolution Remote Sensing Imagery

Abstract

With the wide use of high-resolution remote sensing image, the technology of object-oriented information extraction from high resolution imagery has been developed rapidly. In this paper, mainly used eCognition software and selected image of HuShiTai in ShenYang as study area, made use of object-oriented technology to extract features information. Finally the information result is compared with traditional schemes. The contrastive result shows that object-oriented technology can overcome the phenomenon of "salt and pepper" which happened in traditional classification, the accuracy of extraction has been greatly improved relative to traditional method and object-oriented technology provides an effective way for the utilization of high-resolution image.