| 融合多特征的遥感影像变化检测 |
| |
| 引用本文： | 杜培军,柳思聪.融合多特征的遥感影像变化检测[J].遥感学报,2012,16(4):663-677. |
| |
| 作者姓名： | 杜培军 柳思聪 |
| |
| 作者单位： | 南京大学地理信息科学系, 江苏 南京 210093;国土环境与灾害监测国家测绘局重点实验室(中国矿业大学), 江苏 徐州 221116;国土环境与灾害监测国家测绘局重点实验室(中国矿业大学), 江苏 徐州 221116 |
| |
| 基金项目： | 国家自然科学基金(编号:40871195);对地观测技术国家测绘局重点实验室开放基金(编号:K201007);江苏省自然科学基金(编号:BK2010182);江苏省“333”工程科研项目(编号:2009-32) |
| |
| 摘 要： | 常规多时相遥感影像变化检测主要基于光谱信息,没有充分利用纹理、几何、形状等多种特征信息,不足以体现检测目标的完整性和准确性。本文针对不同特征在变化检测中应用的优势,在提取影像多种特征的基础上,构建了1维和多维两种基于信息融合策略的变化检测方法,即利用1维特征空间加权距离相似度运算、多维特征空间的模糊集融合和支持向量机融合策略进行变化检测。利用多时相QuickBird高分辨率遥感影像进行城市土地覆盖变化检测试验,结果表明,本文方法可以有效集成不同特征的优势与表征变化信息的能力,提高变化检测过程的稳定性和适用性,同时能够更好地保持变化地物的结构和形状,突出主要变化目标。
|
| 关 键 词： | 变化检测 信息融合 多源特征 模糊集理论 支持向量机 |
| 收稿时间： | 2011/6/28 0:00:00 |
| 修稿时间： | 2011/10/9 0:00:00 |
Change detection from multi-temporal remote sensing images byintegrating multiple features |
| |
| DU Peijun and LIU Sicong.Change detection from multi-temporal remote sensing images byintegrating multiple features[J].Journal of Remote Sensing,2012,16(4):663-677. |
| |
| Authors: | DU Peijun and LIU Sicong |
| |
| Institution: | Department of Geographic Information Science, Nanjing University, Nanjing 210093, China;Key Laboratory for Land Environment and Disaster Monitoring, State Bureau of Surveying and Mapping of China, China University of Mining and Technology, Xuzhou 221116, China;Key Laboratory for Land Environment and Disaster Monitoring, State Bureau of Surveying and Mapping of China, China University of Mining and Technology, Xuzhou 221116, China |
| |
| Abstract: | Traditional change detection approaches from multi-temporal remote sensing images are mainly based on spectralinformation in original images, without utilizing other derived features, such as texture, geometrical structure and shape. With theincreasing spatial resolution in remote sensing imagery, change detection only relying on spectral information cannot guaranteethe completeness and accuracy of change targets, suggesting the importance to integrate the merits of different features. Afterextracting multiple features from original images, two change detection procedures based on information fusion strategies areproposed in this paper:weighted similarity distance in one-dimensional feature space, and fuzzy set theory and support vectormachines in n-dimensional feature space, respectively. Multi-temporal QuickBird high-resolution images are used as experimentaldata for land cover change detection over urban areas, and the results demonstrate the effectiveness of the proposed method.By integrating the merits of different features, the stability and applicability can be improved, and the structure and shape can bewell preserved to highlight the important change targets at the same time. |
| |
| Keywords: | change detection information fusion multiple features fuzzy set theory support vector machine |
| 本文献已被 CNKI 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 |
|
