IEEE Access | |
A Novel Hybrid Edge Detection Method for Polarimetric SAR Images | |
Junfei Shi1  Haiyan Jin2  Zhaolin Xiao3  | |
[1] School of Computer Science and Technology, Xi&x2019;an University of Technology, Xi&x2019;an, China; | |
关键词: Hybrid edge detection method; improved polarimetric CFAR detector; weighted gradient-based detector; wavelet fusion; | |
DOI : 10.1109/ACCESS.2020.2963989 | |
来源: DOAJ |
【 摘 要 】
The edge detection plays an important role in post-processing of PolSAR images. It is still a great challenge for extracting all the edge features and suppress speckle noises, especially when weak/strong edges appear simultaneously outside and within heterogenous areas. In this paper, a novel hybrid edge detection framework is proposed to address this problem. The proposed method is designed by fusing two initial edge detectors, which can detect complementary edge information. One is an improved polarimetric constant false alarm rate (IP_CFAR) edge detector, which can detect weak edges well, but fail to detect the edges in the heterogeneous regions. The other is the proposed weighted gradient-based (WG) detector which can detect edges in heterogeneous areas well, but loses some weak edges and produces some false edges due to the speckle noises. Secondly, based on the two detectors above, a wavelet-based hybrid edge detection method is proposed by combining their merits and suppress their shortcomings. To fuse them effectively, wavelet transformation is utilized and semantic rules are defined to extract their advantages. Moreover, a despeckling scheme is designed to suppress the false edges in the wavelet domain. Experimental results demonstrate that the proposed method outperforms the state-of-art methods in extracting both weak edges and strong edges within heterogeneous regions.
【 授权许可】
Unknown