【作者】 薛笑荣； 赵荣椿； 张艳宁； 曾琪明；

【Author】 XUE Xiao-rong 1, ZhAO Rong-chun 2, ZHANG Yan-ning 2, ZENG Qi-ming 1(1.The Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871,China2. The Institute of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an 710072, china)

【机构】 北京大学遥感与地理信息研究所； 西北工业大学计算机学院；

【摘要】 提出了一种并行的SAR图像边缘检测方法,该方法根据SAR图像的特点,对图像中的每一点都计算相应的3个信息测度特征,并组成特征向量对SAR图像进行边缘检测,这样计算量较大,但由于采用并行计算,因此速度较快.实验结果证明该方法能取得较好的边缘检测效果,且速度较快.更多还原

【Abstract】 With the advantage of that parallel cluster calculation has high speed of data processing, and considering the characteristic of SAR image, a new method of parallel SAR image edge detection was proposed: for every pixel in an SAR image, three information measure features are calculated and compose a feature vector in parallel calculation environment, all feature vectors are clustered, and SAR image edge is detected. The experiments show that the edge detection can be gotten quickly.更多还原