Recognition method of multi-feature fusion based on D-S evidence theory in SAR image
TONG Tao1, YANG Guang1, LI Xin2, YE Yi1, WANG Shoubiao1
1. Department of Aerospace Intelligence, Aviation University of Air Force, Changchun 130022, China; 2. Department of Training, Aviation University of Air Force, Changchun 130022, China
Abstract:In view of the low accuracy of the single feature-based method for target recognition in SAR image, a multi-feature decision-making level fusion method based on SVM and D-S evidence theory was proposed.After a series of image processing, the texture feature, Hu invariant moments feature and peek feature were extracted from the target image. Then the targets were classified according to each type of features utilizing SVM, and the results were used as evidence to construct the basic probability assignment. Conclusively, D-S combination rule of evidence was used to achieve fusion, and final recognition results were given by classification thresholds. The method is used for recognizing three-class targets in MSTAR database, and the recognition rate arrives at 95.5%. Experimental result shows that the method is effective for SAR images target recognition.
童涛, 杨桄, 李昕, 叶怡, 王寿彪. 基于D-S证据理论的多特征融合SAR图像目标识别方法[J]. 国土资源遥感, 2013, 25(2): 37-41.
TONG Tao, YANG Guang, LI Xin, YE Yi, WANG Shoubiao. Recognition method of multi-feature fusion based on D-S evidence theory in SAR image. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(2): 37-41.
[1] 刘爱平,付琨,张利利,等.基于多尺度特征的高分辨率SAR图像机动目标识别[J].系统工程与电子技术,2010,32(6):1163-1165. Liu A P,Fu K,Zhang L L,et al.Maneuvering target recognition of high resolution SAR images based on multi-scale feature[J].Systems Engineering and Electronics,2010,32(6):1163-1165. [2] 张静,王国宏,梁发麦,等.基于证据理论的SAR图像融合识别方法[J].系统仿真学报,2007,19(9):2053-2056. Zhang J,Wang G H,Liang F M,et al.Study on fusion recognition method of target’s SAR images based on D-S evidence theory[J].Journal of System Simulation,2007,19(9):2053-2056. [3] Zhao Q,Principe J C.Support vector machines for SAR automatic target recognition[J].IEEE Trans on Aerospace and Electronic Systems,2001,37(2):643-654. [4] Vapnic V N.Statistical learning theory[M].New York:Wiley,1998. [5] 傅文杰,洪金益,朱谷昌.基于SVM遥感矿化蚀变信息提取研究[J].国土资源遥感,2006,18(2):17-19. Fu W J,Hong J Y,Zhu G C.The extraction of mineralized and altered rock information from remote sensing image based on SVM[J].Remote Sensing for Land and Resources,2006,18(2):17-19. [6] Yager R R.On the dempster shafer framework and new combination rules[J].Information System,1989,41(2):93-137. [7] 郝颖明,朱枫.2维Otsu自适应阈值的快速算法[J].中国图象图形学报,2005,10(4):484-488. Hao Y M,Zhu F.Fast algorithm for two-dimensional Ostu adaptive threshold algorithm[J].Journal of Image and Graphics,2005,10(4):484-488. [8] Hu M K.Visual pattern recognition by moment invariants[J].IEEE Trans on Information Theory,1962,12(6):170-179. [9] Platt J C.Probabilistic output for support vector machine and comparisons to regularized likelihood methods[G]//Smola A J.Advances in Large Margin Classifiers,Cambridge,MA:MIT Press,1999:1-11. [10] 付燕,詹新光.一种有效的SAR图像目标识别方法[J].计算机工程与应用,2010,46(15):156-157. Fu Y,Zhan X G.Efficient method of SAR image target recognition[J].Computer Engineering and Application,2010,46(15):156-157.