SAR图像直线提取

Line Extraction for SAR Image

针对合成孔径雷达 (SAR)图像中相干斑的统计特性 ,设计了对应的直线提取算法 .首先组合运用Canny算子和Ratio算子得到边缘点及其边缘方向 ,然后根据边缘方向一致性原理得到初始直线图 ;最后 ,通过高层编组方法连接由于噪声引起的直线缺损 .本文提出的边缘检测方法克服了边缘方向量化带来的直线断裂 ,并且具有恒虚警的特性 .高层编组过程通过对初始直线图的分析确定可能扩展的直线区域 ,之后在原始图像中进行统计证实 ,得到完整的直线图 .直线提取算法在X波段机载SAR图像上进行了试验 ,得到了满意的效果 .提取的直线图可以用于遥感图像矢量化、自动目标识别等方面 .

A line extraction algorithm for synthetic aperture radar (SAR) image is presented. The algorithm is designed for the statistical characteristics of the speckle in SAR image. Three steps are involved. Firstly, a new edge detector, which combines the Canny operator and Ratio operator, is used to get the edge points and their directions, then the edge points are grouped based on the edge direction consistency to form the initial lines. Finally, the broken lines due to speckle noise are connected by the high level grouping. The proposed new edge operator is CFAR and prevents the line from cleaving. The high level grouping step analyses the initial lines, finds out the possible areas for expanding lines, and verifies the possible areas by statistical hypothesis determination. The line extraction algorithm is tested on the X-band airborne SAR images. The extracted line graph can be used for SAR image vectorization and comprehension etc.