| 多特征证据融合的遥感图像变化检测 |
| |
| 引用本文： | 汪闽,张星月.多特征证据融合的遥感图像变化检测[J].遥感学报,2010,14(3):564-577. |
| |
| 作者姓名： | 汪闽 张星月 |
| |
| 作者单位： | 1. 南京师范大学虚拟地理环境教育部重点实验室,江苏南京210046;北京师范大学遥感科学国家重点实验室,北京100875
2. 南京师范大学虚拟地理环境教育部重点实验室,江苏南京,210046 |
| |
| 基金项目： | 国家自然科学基金(编号: 40871189), 国家863课题(编号: 2007AA12Z224, 编号: 2009AA12Z148)和遥感科学国家重点实验室(北师大)开放基金。 |
| |
| 摘 要： | 提出了一种以证据理论综合利用图像多种特征的变化检测方法。方法利用滑动窗口计算两时相图像3种特征的结构相似度, 以之构建D-S证据理论的基本概率赋值函数并进行证据合成, 通过规则判定得到图像变化区域。通过对不同试验区、不同证据组合方式以及方法间的比较实验表明, 相对单一特征检测方法有效地提高了检测的精度。此外, 由于采用统计而非原始图像特征度量特征相似性, 方法具有对辐射、几何配准精度要求较低等优点。
|
| 关 键 词： | 证据理论 变化检测 高空间分辨率遥感 多特征 结构相似性 |
| 收稿时间： | 2009/4/12 0:00:00 |
| 修稿时间： | 7/4/2009 12:00:00 AM |
Change detection using high spatial resolution remotely sensed im-agery by combining evidence theory and structural similarity |
| |
| WANG Min and ZHANG Xingyue.Change detection using high spatial resolution remotely sensed im-agery by combining evidence theory and structural similarity[J].Journal of Remote Sensing,2010,14(3):564-577. |
| |
| Authors: | WANG Min and ZHANG Xingyue |
| |
| Institution: | 1. Key Laboratory of Virtual Geographic Environment, Nanjing Normal University, Ministry of Education, Jiangsu Nanjing 210046, China;2. State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China;1. Key Laboratory of Virtual Geographic Environment, Nanjing Normal University, Ministry of Education, Jiangsu Nanjing 210046, China |
| |
| Abstract: | This paper presents an evidence theory based change detection method capable of utilizing multiple image features. With a moving window, we first get the structural similarities of both time phase image visual features and construct the basic probability assignment function (BPAF) of D-S evidence theory. We then fuse all the evidence and get the changed image areas with decision rules. Comparative work on different experimental areas, combinations of change evidence and with other meth-ods has been carried out. It shows that our method prevents effectively the detection errors from only utilizing single feature and thus improves the detection precision. Furthermore, since the image similarity is derived from image statistical features rather than original grey, texture and gradient features, this method is robust to low calibration precision. |
| |
| Keywords: | evidence theory change detection high spatial resolution image multi-feature structural similarity |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《遥感学报》浏览原始摘要信息 |
| 点击此处可从《遥感学报》下载免费的PDF全文 |
|
