In this article, a method based on a non-parametric estimation of the Kullback-Leibler divergence using a local feature space is proposed for synthetic aperture radar (SAR) image change detection. First, local features based on a set of Gabor filters are extracted from both preand post-event images. The distribution of these local features from a local neighbourhood is considered as a statistical representation of the local image information. The Kullback-Leibler divergence as a probabilistic distance is used for measuring the similarity of the two distributions. Nevertheless, it is not trivial to estimate the distribution of a high-dimensional random vector, let alone the comparison of two distributions. Thus, a non-parametric method based on k-nearest neighbour search is proposed to compute the Kullback-Leibler divergence between the two distributions. Through experiments, this method is compared with other state-of-the-art methods and the effectiveness of the proposed method for SAR image change detection is demonstrated.
ABSTRACT:Stereo positioning is a important content for Spaceborne SAR imagery mapping, which is still lack of investigation depend on exterior orientation elements. In this paper, we firstly introduced the Range-Coplanarity (R-Cp) geometric imaging equation and its character for radar imagery, compared the difference and relationship between R-Cp and R-D model, and build stereo positioning rigorous model for spaceborne SAR imagery based on the R-Cp equation, satellite orbit, and pose refinement model. Then separate taking TerraSAR-X images in mountainous terrain observed from same and opposite side-looking direction as test data, we presented the initial attitude value acquirement method for TerraSAR-X image after moving compensation, analyzed stereo positioning precision according to amounts and spatial distributions of GCPs and lengths of baseline between SAR antennas, and also compared the precision with R-D model. the proposed stereo positioning model avoids SAR signal imaging parameters during the geometric processing, with one GCP it could improved the plan and height precision from (17.9m,29.2m) to (10.3m,6.1m) in the test of opposite side-looking direction images, and even had a better accuracy than R-D model when more GCPs were used, which indicate that R-Cp model have a potential application in spaceborne SAR image stereo positioning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.