Current situation and needs of change detection techniques

作者：Dengsheng Lu, Guiying Li, Emilio Federico Moran · 发表于：International Journal of Image and Data Fusion · 年份：2014 · DOI：10.1080/19479832.2013.868372 · 被引用次数：175 · 研究领域：Remote Sensing and Land Use、Remote-Sensing Image Classification、Environmental Changes in China

Research on change detection techniques has long been an active topic and many techniques have been developed. In reality, change detection is a comprehensive procedure that requires careful consideration of many factors such as the nature of change detection problems, image preprocessing, selection of suitable variables and algorithms. This paper briefly overviews the major steps involved in a change detection, summarises major change detection methods, discusses the impacts of scales and complexity of study areas on the selection of remote-sensing data and change detection algorithms and finally discusses the needs of developing new change detection methods. As high spatial resolution images are easily available in the past decade, texture- and object-based methods become valuable to improve change detection performance. At national and global scales, coarse spatial resolution satellite images such as MODIS become important data sources for rapidly detecting land-cover change, but results have high uncertainty. More research is needed to develop new techniques to solve the mixed pixel problem. At regional scale, it is necessary to explore integration of multi-sensor data and multiple algorithms to improve change detection results.