Fuzzy Active Contour Model With Markov Random Field for Change Detection

Abstract

The traditional active contour models are sensitive to the speckle noise in the synthetic aperture radar (SAR) images. In this paper, the Markov random field (MRF) theory is incorporated into the fuzzy active contour model to detect the changes of multitemporal SAR images. In the proposed method, neighboring information is considered to modify the pointwise prior probability for exploiting the mutual and spatial information. In addition, we incorporate MRF into the fuzzy active contour model and get the resulting MRF-based energy function. Finally, we drive the associated first variation of the energy function to compute the fuzzy membership. Due to the introduction of MRF, the proposed MRF-based fuzzy active contour model is robust to the speckle noise in the SAR images and can achieve accurate change detection results. Experiments on four SAR image datasets demonstrate that the proposed MRF-based fuzzy active contour model is able to accurately segment the difference image and has better performance in comparison with other change detection techniques. INDEX TERMS fuzzy active contour model, Markov random field, change detection, synthetic aperture radar

Active contour model based on hybrid signed pressure force function

“…The C-V model makes full use of the global statistical information of the image to define the energy functional, which gets rid of the constraint of image gradient information, enabling it to deal with the weak edge images and the images with hollow regions [35,36]. Moreover, the algorithm omits the smoothing operation on the image and is relatively immune to image noise [24].…”