基于加权Hausdorff距离矩阵测度的SAR图像与光学图像匹配研究  

Research on Matching SAR Image to Optical Image Based on Weight Hausdorff Distance Matrix Metric

作　　者：李晴[1,2] 赵欣[2] 曲广洲[2] 袁健全[2] 于秋则[3] 

机构地区：[1]海军航空工程学院,山东烟台264001 [2]北京机电工程研究所,北京100074 [3]上海交通大学电子信息与电气工程学院,上海200240

出　　处：《战术导弹技术》2012年第4期89-95,共7页Tactical Missile Technology

摘　　要：针对多传感器图像匹配问题,提出一种基于加权Hausdorff距离矩阵(Weight Hausdorff Distance Matrix,WHDM)测度的合成孔径雷达(SAR)图像与光学图像匹配算法。该算法采用边缘特征作为SAR图像与光学特征的共性特征,克服了两种不同图像的灰度不一致性。算法中提出了基于边缘连续性密度加权的Hausdorff距离矩阵范数测度的相似性准则,该测度相对经典的Hausdorff距离与改进的距离测度相比,具有更高抗噪声水平与大比例遮挡能力。试验结果表明,这种算法匹配精度高,适合并行计算,该算法可应用于无人飞行器的自主导航中。As to multi-sensor image matching, a novel algorithm is proposed for matching synthetic aperture radar （SAR） image to optical image based on weight hausdorff distance matrix （WHDM） metric. In the proposed method, edge feature is used for common feature, which can solve the key problem brought by different senor. WHDM is designed as a similarity measure. It is demonstrated that the proposed WHDM metric outperforms most existed Hausdorff Distance based （HD-based） match methods, especially in higher level noise and higher ratio of occlusion. Experimental results using synthetic and real images demonstrate that the proposed algorithm is robust, and can achieve high matching accuracy. This algorithm can be used in automatic navigation of Unmanned Automatic Vehicle.

关 键 词：合成孔径雷达图像 图像匹配 HD-M距离测度 

分 类 号：TJ765.4[兵器科学与技术—武器系统与运用工程]