Journal of Systems Engineering and Electronics ›› 2018, Vol. 29 ›› Issue (3): 483-490.doi: 10.21629/JSEE.2018.03.05

• Electronics Technology • Previous Articles     Next Articles

Saliency detection of infrared image based on region covariance and global feature

Songtao LIU*(), Ning JIANG(), Zhenxing LIU(), Kanghui JIANG()   

  • Received:2017-03-02 Online:2018-06-28 Published:2018-07-02
  • Contact: Songtao LIU;;;
  • About author:LIU Songtao was born in 1978. He received his B.S. degree in aviation radar, M.S. degree and Ph.D. degree in signal and information processing from Naval Aeronautical Engineering Institute, in 2000, 2003 and 2006, respectively. He joined the Dalian Naval Academy in 2006 where he is now an associate professor in the Department of Information Operation. From 2010 to 2012, he was a postdoctoral researcher at the Postdoctoral Station of Information and Communication Engineering, Dalian University of Technology. He has published over 70 papers on journals and conference proceedings. His research interests include image processing, optoelectronic engineering, and electronic countermeasures. E-mail:|JIANG Ning was born in 1964. He has been with the Dalian Naval Academy since 1989. He received his B.S. degree in electronic countermeasure engineering from Naval Electronic Engineering Academy in 1987, and M.S. degree and Ph.D. degree in computer application and system engineering from Dalian University of Technology in 1996 and 2000, respectively. From 2000 to 2002, he was a postdoctoral researcher at the Postdoctoral Station of Control Science and Engineering, Nanjing University of Technology. He became an associate professor in 2002 and has been a professor since 2007. His research interests include electronic countermeasure and information operation. E-mail:|LIU Zhenxing was born in 1980. He received his B.S., M.S. and Ph.D. degrees in operation command from Dalian Naval Academy (DNA) in 2002, 2007 and 2010, respectively. Since 2010, he has been a lecturer at the Department of Information Operation, DNA. His research interests include optoelectronic engineering and electronic countermeasures. E-mail:|JIANG Kanghui was born in 1991. He received his B.S. degree in information engineering from Hohai University in 2015. Now he is a postgraduate in information and communication engineering from Dalian Naval Academy. His research interest includes image processing. E-mail:
  • Supported by:
    the National Natural Science Foundation of China(61303192);the China Postdoctoral Science Foundation(2015M572694);the China Postdoctoral Science Foundation(2016T90979);This work was supported by the National Natural Science Foundation of China (61303192) and the China Postdoctoral Science Foundation (2015M572694; 2016T90979)


In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on different scale spaces and different image regions are extracted and transformed into sigma features, then combined with central position feature, the local salient map is generated. Next, a global salient map is generated by gray contrast and density estimation. Finally, the saliency detection result of infrared images is obtained by fusing the local and global salient maps. The experimental results show that the salient map of the proposed method has complete target features and obvious edges, and the proposed method is better than the state of art method both qualitatively and quantitatively.

Key words: saliency detection, region covariance, gray contrast, density estimation