A target detection method based on CBR in high resolution SAR images
Bo Jiang, Bin Zou, Lamei Zhang, Chengyi Wang · 2014
With the improvement of SAR image resolution, more accurate detection method fit for complicated scenes should be developed to satisfy most commercial and military customers' interests. In this paper, a novel case based reasoning (CBR) method is investigated and well exploited to rule out a mathematical model which performs high detection accuracy in very high resolution SAR images. The cordial innovation of the proposed method is a feature based case library which is established through empirical knowledge as well as existing interpretational results. Each target to be detected will be matched with the most likely case in the case library and its detection result can be determined according to the description of the matched case. The experimental results from several real SAR images with resolution of 0.1m×0.1m show that the satisfactory performance of interpretation can be obtained by the proposed method.