Font Size: a A A

Feature Extraction And Matching In Environmental Disaster Mitigation Satellite Image Based On Affince Invariant Feature

Posted on:2012-02-27Degree:MasterType:Thesis
Country:ChinaCandidate:S GeFull Text:PDF
GTID:2178330332499046Subject:Cartography and Geographic Information Engineering
Abstract/Summary:PDF Full Text Request
Feature extraction and description is one of the most important technologies of image pattern recognition, which can be used in object recognition, image matching, image stitching, content searching, and so on. According to the feature matching performance, feature descriptor plays an important role in image matching. Remote sensing image and common digital photos have distinguished differences in image formation model. In this context, the key character of image geometry and spectral characteristics is demonstrated, which is also one of the most important technologies to do high precision registration of multi-source remote sensing images.This paper promoted a new method to do visual information expression of image formalization and systematization base on visual information representation theory, and analyzed the characteristics of HJ remote sensing image from the aspect of remote sensing imaging mechanism, and expatiates some pivotal rules about visual information during image capturing,description and reconstruction.The paper proposes a new method (MSER+LBP) to deal with visual information expression of image formation and systematization based on visual information representation theory,and analyzes the characteristics of HJ remote sensing image from the perspective of remote sensing imaging mechanism, and expatiates some pivotal rules regarding visual information during image capturing, description and reconstruction. Results of this study show that the proposed matching approach performs well, and the matching accuracy is stable and reliable.
Keywords/Search Tags:Maximally Stable Extremal Region, Image Scale-space, Affine Invariant Feature, Local Binary Pattern
PDF Full Text Request
Related items