基于敏感特征向量的SAR图像灾害变化检测技术.pdf.pdfVIP

24 2012 ，48 （3） Computer Engineering and Applications 计算机工程与应用 基于敏感特征向量的SAR 图像灾害变化检测技术 1 1 2 1 1 李 坤 ，杨 然 ，王雷光 ，林立宇 ，秦前清 1 1 2 1 1 LI Kun , YANG Ran , WANG Leiguang , LIN Liyu , QIN Qianqing 1.武汉大学 测绘遥感信息工程国家重点实验室，武汉 430079 2.西南林业大学 资环学院，昆明 650224 1.State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China 2.School of Environmental Science and Engineering, Southwest Forestry University, Kunming 650224, China LI Kun, YANG Ran, WANG Leiguang, et al. Sensitive feature vector-based disaster change detection using SAR images. Com- puter Engineering and Applications, 2012, 48 （3 ）：24-28. Abstract ：In order to overcome the problem of the limited application of optical image during bad weather condition, this paper analyz- es the sensitivity of SAR image gray features and texture features for the four land cover changes （lake, landslide debris flow, part of collapsed buildings and serious collapsed buildings ）which usually happen in the natural disasters, and put forward the concept of sensi- tive feature vector. Taking sensitive feature vector which is comprehensive utilization of the gray scale difference and texture difference as evaluation factor, a new disaster change detection method of SAR image is carried out, and verifying on two groups of ALOS SAR images prove the better performance than the method only using gray scale difference. Key words ：Synthetic Aperture Radar（SAR）; texture difference; gray difference; change detection; disaster assessment 摘 要：为了解决阴雨云雾条件下光学遥感图像的应用局限性问题，针对典型的四类地表变化（堰塞湖、滑坡泥石流、部分倒塌建 筑和严重倒塌建筑）分析SAR 图像灰度和纹理特征的敏感程度，并提出敏感特征向量的概念；以综合利用了灰度差值和纹理差值 的敏感特征向量作为评判因子，结合主成分分析技术和K 均值聚类技术，提出了新的SAR 图像灾害变化检测算法。该方法算法 简单，检测效果好，并用两组ALOS SAR 实验数据进行了证实。 关键词：合成孔径雷达；纹理差值；灰度差值；变化检测；灾害评估 DOI ：10.3778/j.issn. 1002-8331.2012.03.007 文章编号：1002-8331（2012 ）03-0024-05 文献标识码：A