Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (3): 447-459.doi: 10.23919/JSEE.2020.000027

• Electronics Technology •     Next Articles

A multi-source image fusion algorithm based on gradient regularized convolution sparse representation

Jian WANG1,2,*(), Chunxia QIN1(), Xiufei ZHANG1(), Ke YANG1(), Ping REN1()   

  1. 1 School of Electronics and Information Engineering, Northwestern Polytechnical University, Xi'an 710072, China
    2 No. 365 Institute, Northwestern Polytechnical University, Xi'an 710065, China
  • Received:2019-10-12 Online:2020-06-30 Published:2020-06-30
  • Contact: Jian WANG E-mail:jianwang@nwpu.edu.cn;chunxia_qin@163.com;921391314@qq.com;xgdms_yk@mail.nwpu.edu.cn;1403147639@mail.nwpu.edu.cn
  • About author:WANG Jian was born in 1972. He received his Ph.D. degree in signal and information processing from Northwestern Polytechnical University in 2005. Now he is an assistant professor at the School of Electronics and Information Engineering, Northwestern Polytechnical University, Xi'an, China. His current research interests include UAV intelligent processing technology, UAV ground observation video signal processing technology, and multi-source information intelligent processing technology. E-mail: jianwang@nwpu.edu.cn|QIN Chunxia was born in 1995. She received her B.S. degree in electronic and information engineering from Northwestern Normal University, Lanzhou, China in 2017. She is currently pursing her M.S. degree in the School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China. Her research interests include signal processing, target detection and recognition, etc. E-mail: chunxia_qin@163.com|ZHANG Xiufei was born in 1989. He received his M.S. degree from the School of Electronics and Information, Northwestern Polytechnical University in 2017. He is now pursing his Ph.D. degree in the School of Automation, Northwestern Polytechnical University, Xi'an, China. His research interests include signal processing, image fusion, etc. E-mail: 921391314@qq.com|YANG Ke was born in 1995. She received her B.S. degree in electronic and information engineering from Taiyuan University of Technology, Taiyuan, China in 2017. She is currently pursing her M.S. degree in the School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China. Her research interests include signal processing, image fusion, etc. E-mail: xgdms_yk@mail.nwpu.edu.cn|REN Ping was born in 1993. She received her B.S. degree in electronic and information engineering from Northwestern University in 2016. She is now pursing her M.S. degree in the School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China. Her research interests include signal processing, target recognition, etc. E-mail: 1403147639@mail.nwpu.edu.cn
  • Supported by:
    the National Natural Science Foundation of China(61671383);Shaanxi Key Industry Innovation Chain Project(2018ZDCXL-G-12-2);Shaanxi Key Industry Innovation Chain Project(2019ZDLGY14-02-02);Shaanxi Key Industry Innovation Chain Project(2019ZDLGY14-02-03);This work was supported by the National Natural Science Foundation of China (61671383), and Shaanxi Key Industry Innovation Chain Project (2018ZDCXL-G-12-2; 2019ZDLGY14-02-02; 2019ZDLGY14-02-03)

Abstract:

Image fusion based on the sparse representation (SR) has become the primary research direction of the transform domain method. However, the SR-based image fusion algorithm has the characteristics of high computational complexity and neglecting the local features of an image, resulting in limited image detail retention and a high registration misalignment sensitivity. In order to overcome these shortcomings and the noise existing in the image of the fusion process, this paper proposes a new signal decomposition model, namely the multi-source image fusion algorithm of the gradient regularization convolution SR (CSR). The main innovation of this work is using the sparse optimization function to perform two-scale decomposition of the source image to obtain high-frequency components and low-frequency components. The sparse coefficient is obtained by the gradient regularization CSR model, and the sparse coefficient is taken as the maximum value to get the optimal high frequency component of the fused image. The best low frequency component is obtained by using the fusion strategy of the extreme or the average value. The final fused image is obtained by adding two optimal components. Experimental results demonstrate that this method greatly improves the ability to maintain image details and reduces image registration sensitivity.

Key words: gradient regularization, convolution sparse representation (CSR), image fusion