Factorization-based Active Contour for Water-Land SAR image segmentation via the Fusion of Features

Qingxia Meng, Xianbin Wen, Liming Yuan, Haixia Xu
2019 IEEE Access  
The segmentation of synthetic aperture radar (SAR) water-land images is a very difficult task not only because of strong multiplicative noise but also due to the blurred boundary, irregular shape, and together with diminished contrast. In this paper, we propose a matrix factorization active contour model based on fused features for SAR image segmentation. First, to enhance the robustness, multiple features are utilized. For each pixel location, feature maps (matrix) are constructed by combining
more » ... wavelet textual features, Gaussian (DoG) filter features, and Gabor filter features via local spectral histogram, which improves spatial pattern and express image structure. Second, the energy function is constructed based on region information and edge information of SAR image. Region information is obtained via matrix factorization theory on the feature matrix. Edge information is obtained by modified the ratio of exponentially weighted averages operator. Then, a convex energy function is proposed to avoid the local minima. A fast dual formulation is introduced for the evolution of the contour. Finally, synthetic and real SAR data are used for verification. The experimental results demonstrate the proposed algorithm is effective for water/land segmentation in SAR images. INDEX TERMS Synthetic aperture radar (SAR), remote sensing, image segmentation, active contour, edge detector, matrix decomposition techniques, texture feature. The associate editor coordinating the review of this manuscript and approving it for publication was Xiang Huang. is blurred due to the shadow. All those hinder SAR data segmentation with optical image analysis methods. Generally, the SAR image segmentation method can be divided into four categories: the edge detection [2], [3], hierarchical split-merge methods [4], clustering methods [5], and model-based methods [6]-[8]. Among these methods, the variational active contour models (ACM) attract the increasing attention in SAR image segment, since ACM show many advantages, such as sub-pixel precision segmentation, smooth closed contours and accuracy object boundary. Generally, ACM are mainly divided into two categories: edge-based [9], [10] and region-based [11] ACM. The edge-based active contour model, proposed by Kass et al. [12] moves the explicit parametric curves to extract objects in images. However, the edge-based ACM stop its evolution relying on the gradient of the image, which may not be achieved when the boundary is weak. Therefore, the region-based active contour model can handle various
doi:10.1109/access.2019.2905847 fatcat:z3xyzzgajbgtllfvsvezxogj5u