Remote Sensing Image Registration Based on Fuzzy Shape Context Feature and Local Space Vector Similarity Constraint

Abstract

Remote sensing image registration is a fundamental and challenging problem, and it is a critical prerequisite in a wide range of applications including environment monitoring, change detection, image fusion, image mosaic, and map updating. Remote sensing image registration is a key technology for dynamic monitoring of a city. In order to promote remote sensing image registration precision, we propose a remote sensing image registration method based on fuzzy shape context feature and local space vector similarity constraint. There are two main contributions: (1) Fuzzy shape context feature (2) Local spatial vector similarity constraints based on local vector feature. Meanwhile, we evaluated the performances of the proposed method and compared with four state-of-the-art methods (SIFTCPDR-SOCGLMDTPS) where our method shows the best alignments in most cases.