A method for automatic target recognition using shadow contour of SAR image

作者：Yin Kuiying^*; Jin Lin; Zhang Changchun; Guo Yufeng

来源：IETE Technical Review, 2013, 30(4): 313-323.

DOI：10.4103/0256-4602.116721

• ATR visit
• SAR de-noising
• SAR image segmentation
• SAR shadow contour

SAR image shadow is the geometric distortion caused by scene elevation and downs. Shadow contour of SAR image contains local spatial characteristic of target, the use of a targets shadow contour in synthetic aperture radar (SAR) imaging has garnered much attention for automated target recognition applications. Due to special imaging mechanism, shadow contour of SAR image is not as clear as that of optical image. Aiming at target recognition, this paper presents an SAR image segmentation method based on Partial Differential De-noising and Marker-controlled, and then the automatic target recognition can be carried out on the result of image segmentation. In the proposed method, the SAR image is first pre-processed for de-noising. After it, the shadow contour of SAR image is extracted through Marker-controlled based SAR image segmentation. And then, the characteristic quantity of target contour is represented by Fourier descriptor. Finally, the target recognition is implemented by maximum correlation. Experimental results show that the proposed method can achieve good segmentation result and the target in SAR image can be classified effectively.

• 出版日期2013-8
• 单位南京大学