CAJ | 학술논문

由于SAR（Synthetic Aperture Radar）图像纹理丰富且存在大量的噪声，使得传统SURF（Speed Up Robust Fea-tures）算子对SAR图像的目标兴趣点检测并不理想，存在兴趣点检测适应性不强和出现大量无用特征点，致使目标匹配的成功率下降。提出了融合恒虚警率（ CFAR，Constant False-Alarm Rate）和SURF的SAR图像目标匹配新算法。采用适应性较强的混合高斯模型拟合杂波的CFAR进行目标兴趣区域检测，运用SURF算子对检测的目标进行特征提取，使用改进的多层剔除方法匹配特征点。通过仿真分析了算法对SAR图像目标匹配的有效性，并在此方面与传统算法进行了比较。仿真实验表明该方法在目标尺度、旋转、噪声变化的情况下，依然可以达到较高的匹配率，具有优越的适应性、鲁棒性。
유우SAR（Synthetic Aperture Radar）도상문리봉부차존재대량적조성，사득전통SURF（Speed Up Robust Fea-tures）산자대SAR도상적목표흥취점검측병불이상，존재흥취점검측괄응성불강화출현대량무용특정점，치사목표필배적성공솔하강。제출료융합항허경솔（ CFAR，Constant False-Alarm Rate）화SURF적SAR도상목표필배신산법。채용괄응성교강적혼합고사모형의합잡파적CFAR진행목표흥취구역검측，운용SURF산자대검측적목표진행특정제취，사용개진적다층척제방법필배특정점。통과방진분석료산법대SAR도상목표필배적유효성，병재차방면여전통산법진행료비교。방진실험표명해방법재목표척도、선전、조성변화적정황하，의연가이체도교고적필배솔，구유우월적괄응성、로봉성。
Because the SAR image has rich texture and a lot of noise , the traditional SURF operator is not ideal for the detection of target interest points on the SAR ( Synthetic Aperture Radar ) image, and it has poor adaptability to interest point detection and a large number of useless feature points , so that the target matching success rate decreases , It proposes a new SAR image matching algorithm which integrates CFAR with SURF .The mixed Gauss model CFAR was used for the detection of target interest regions , and the SURF operator was used to detect feature extraction .Finally, the improved multilayer elimination method was used for matching feature points .The simulation results show that the proposed method has a high matching rate and good robustness when the scale , rotation and noise vary .