Abstract-This paper proposes a Synthetic Aperture Radar (SAR) vehicle target detection algorithm based on contextual knowledge. The proposed algorithm firstly obtains the general classification of SAR image with a Markov Random Field (MRF)-based segmentation algorithm; then modifies the prior target presence probability utilizing terrain types, distances to boundary and target aggregation degree; finally gains the detection results using improved Cell AveragingConstant False Alarm Rate (CA-CFAR). Detections with real SAR image data show that the proposed algorithm can effectively improve target detection rate and reduce false alarms compared with conventional CA-CFAR.

When the classical constant false-alarm rate (CFAR) combined with fuzzy C-means (FCM) algorithm is applied to target detection in synthetic aperture radar (SAR) images with complex background, CFAR requires block-by-block estimation of clutter models and FCM clustering converges to local optimum. To address these problems, this paper pro-poses a new detection algorithm: knowledge-based combined with improved genetic algorithm-fuzzy C-means (GA-FCM) algorithm. Firstly, the algorithm takes target region's maximum and average intensity, area, length of long axis and long-to-short axis ratio of the external ellipse as factors which influence the target appearing probability. The knowledge-based detection algorithm can produce preprocess results without the need of estimation of clutter models as CFAR does. Afterward the GA-FCM algorithm is improved to cluster pre-process results. It has advantages of incorporating global optimizing ability of GA and local optimizing ability of FCM, which will further eliminate false alarms and get better results. The effectiveness of the proposed technique is experimentally validated with real SAR images.