Adaptive High-frequency Information Fusion Algorithm of Radar and Optical Images
An adaptive High-frequency Information Fusion Algorithm of Radar and Optical Images is proposed in this paper, in order to improve the resolution of the radar image and reserve more radar information. Firstly, Hough Transform is adopted in the process of low-resolution radar image and high-resolution optical image registration. The implicit linear information is extracted from two different heterogeneous images for better result. Then NSCT transform is used for decomposition and fusion. In different decomposition layers or in the same layer with different directions, fusion rules are adaptive for the high-frequency information of images. The ratio values of high frequency information entropy, variance, gradient and edge strength are calculated after NSCT decomposition. High frequency information entropy, variance, gradient or edge strength, which has the smallest ratio value, is selected as an optimal rule for regional fusion. High-frequency information of radar image could be better retained, at the same time the low-frequency information of optical image also could be remained. Experimental results showed that our approach performs better than those methods with single fusion rule.
Image Fusion NSCT Transform Hough Transform Adaptive Rule
Wang Yiding Qin Shuai
College of Information Engineering, North China University of Technology, Beijing, China College of Information Engineering, North China University of Technology,Beijing, China
国际会议
桂林
英文
1-5
2011-11-01（万方平台首次上网日期，不代表论文的发表时间）