The Research Of Sample Extraction And Image Sample Database For High Resolution Remote Sensing Image

With the progress of RS technology and improve of image resolution,the high resolution remote sensing image has been put into wide application by different fields of the society. The high resolution remote sensing image has many characteristics like its detailed information capacity and obvious geography structure, so the process method of remote sensing image emerged. The image segmentation is the main and important process of remote sensing image. The image patterns was obtained by image segmentation. These image samples saved into database and comparison with new remote sensing image. It represent the shape content of an image. the image segmentation method influences the identification and analysis of new remote sensing image, and the image sample database influences convenience using too. Because of the complexity of remote sensing image and the uncertainty of image segmentation, great attention has been paid to the remote sensing image segmentation.A remote sensing image processing system named ELU is designed and developde by Remote Sensing Laboratory of Shanghai Jiao Tong University, supported by the research project of Content-based Search in Image and Change Detection and Auto-updating of Special Target, which is administered by Shanghai Science and Technology Committee. The remote sensing image extraction of image sample and management of image sample dababase is relatively deeply studied in this thesis supported by the project. There are three important parts in this thesis. The first part of this paper, the extraction of remote sensing iamge sample is described. In the second part, image segmentation method with extraction of remote sensing image samples are described. In the third part, the design and implementation management system of the remote sensing image sample database is detailed described development.