A SVD-Based Visual Attention Detection Algorithm of SAR Image
This paper proposes a new method based on visual attention and singular value decompositions (SVD) for target detection in SAR image. SAR image is confronted with many difficulties such as complicated environment and scarcity of target information. To solve these problems, we proposed the method that combined the pyramid model with singular value decomposition to simulate human retina. The human retina collected information in Non-uniform way. Experimental results validate a effect performance of the method in improving both the efficiency and the accuracy of target detection in complicated environment and weak target condition.
KeywordsSingular value decomposition (SVD) Visual attention Target detection SAR image
This work is supported by the National Natural Science Foundation of China (Grant No. 61271287).
- 1.Dirk B. Walther, Christof Koch (2007) Attention in hierarchical models of object recognition, DB Walther, C Koch: Progress in brain researchGoogle Scholar
- 3.Dirk Walther (2006) Interactions of visual attention and object recognition: computational modeling, algorithms, and psychophysics. PhD thesis, California Institute of Technology, Pasadena, CA, 23 Feb 2006Google Scholar
- 4.Rigas I, Economou G, Fotopoulos S (2013) Low-level visual saliency with application on aerial imagery, geoscience and remote sensing letters, IEEEGoogle Scholar
- 5.Navalpakkam V,Itti L (2006) An integrated model of top-down and bottom-upattention for optimal object detection. Proc. IEEE conference on computer vision and pattern recognition (CVPR). New York, NY, p 2049–2056Google Scholar
- 6.Jilan Feng, Zognjie Cao, Yiming Pi (2013) Multiphase SAR image segmentation with G0 statistical model based active contours. IEEE Trans GRS 51(7)Google Scholar