电子与信息学报
電子與信息學報
전자여신식학보
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY
2013年
5期
1120-1127
,共8页
刘帅奇*%胡绍海%肖扬%安永丽
劉帥奇*%鬍紹海%肖颺%安永麗
류수기*%호소해%초양%안영려
SAR图像边缘检测%指数加权均值比%局部混合滤波%非下采样滤波
SAR圖像邊緣檢測%指數加權均值比%跼部混閤濾波%非下採樣濾波
SAR도상변연검측%지수가권균치비%국부혼합려파%비하채양려파
SAR Image edge detecting%Ratio Of Exponentially Weighted Averages (ROEWA)%Local hybrid filter%Nonsubsampled filter
该文结合基于非下采样方向滤波-双树复小波变换(NonSubsampled Direction Filter Bank-Dual-Tree Complex Wavelet Transform, NSDFB-DTCWT)的局部混合滤波算法和Dempster-Shafet (DS)证据理论提出一种基于局部混合滤波的 SAR 图像边缘检测算法.该算法首先对 SAR 图像进行局部混合滤波,然后对不同尺度滤波图像使用指数加权均值比(Ratio Of Exponentially Weighted Averages, ROEWA)算子检测边缘的强度,再使用Canny算子检测边缘的方向,从而得到SAR图像各尺度上的边缘,最后使用DS证据理论融合各尺度的边缘形成原始 SAR 图像的边缘.实验结果表明:该文所提出的算法具有很好的边缘检测效果,检测到的 SAR 图像的边缘定位准确和完整,且伪边缘较少.
該文結閤基于非下採樣方嚮濾波-雙樹複小波變換(NonSubsampled Direction Filter Bank-Dual-Tree Complex Wavelet Transform, NSDFB-DTCWT)的跼部混閤濾波算法和Dempster-Shafet (DS)證據理論提齣一種基于跼部混閤濾波的 SAR 圖像邊緣檢測算法.該算法首先對 SAR 圖像進行跼部混閤濾波,然後對不同呎度濾波圖像使用指數加權均值比(Ratio Of Exponentially Weighted Averages, ROEWA)算子檢測邊緣的彊度,再使用Canny算子檢測邊緣的方嚮,從而得到SAR圖像各呎度上的邊緣,最後使用DS證據理論融閤各呎度的邊緣形成原始 SAR 圖像的邊緣.實驗結果錶明:該文所提齣的算法具有很好的邊緣檢測效果,檢測到的 SAR 圖像的邊緣定位準確和完整,且偽邊緣較少.
해문결합기우비하채양방향려파-쌍수복소파변환(NonSubsampled Direction Filter Bank-Dual-Tree Complex Wavelet Transform, NSDFB-DTCWT)적국부혼합려파산법화Dempster-Shafet (DS)증거이론제출일충기우국부혼합려파적 SAR 도상변연검측산법.해산법수선대 SAR 도상진행국부혼합려파,연후대불동척도려파도상사용지수가권균치비(Ratio Of Exponentially Weighted Averages, ROEWA)산자검측변연적강도,재사용Canny산자검측변연적방향,종이득도SAR도상각척도상적변연,최후사용DS증거이론융합각척도적변연형성원시 SAR 도상적변연.실험결과표명:해문소제출적산법구유흔호적변연검측효과,검측도적 SAR 도상적변연정위준학화완정,차위변연교소.
@@@@A SAR image detection method is proposed based on local hybrid filter. This method combines the advantages of both local hybrid filter based NonSubsampled Direction Filter Bank-Dual-Tree Complex Wavelet Transform (NSDFB-DTCWT) and Dempster-Shafet (DS) evidence theory. First, local hybrid filter is applied to SAR image. Then edge strength is got by using Ratio Of Exponentially Weighted Averages (ROEWA) operator and edge direction is got by using Canny operator at every scale from NSDFB-DTCWT. Finally, DS theory is used to fuse the edge in all scales to get the whole edge of the original SAR image. The experimental results demonstrate its effectiveness and superiority in terms of edge positioning accuracy and integrity, and it also has a fewer false edge points.