多时相遥感影像变化检测综述

Review on Change Detection Using Multi-temporal Remotely Sensed Imagery

近几十年来,多时相影像处理和变化检测是遥感领域一个较为活跃的研究方向。虽然在环境变化监测和检测方面成功的应用有很多,但是从多时相影像及时提取地球环境和人类活动的动态信息仍面临很多挑战。近年来,随着新型遥感平台和传感器的发展,在克服技术障碍方面取得了很大进步。历史影像档案提供范围的扩大也使得长期变化检测和建模成为可能。这些发展推动了更先进的影像处理方法的开发和处理时间维度影像数据新方法的研究工作。本文回顾了多时相数据处理和变化检测的发展现状。作者首先对地球表面环境变化的性质进行了分析,从四个方面总结了遥感变化检测技术的发展,包括变化检测影像预处理、变化检测方法和途径分类、遥感变化检测方法和多时相影像处理的准确度评估。文章试图在先验知识的基础上从多源数据、集成处理和智能方法角度提出综合解决方案。为促进遥感影像变化检测技术的深入研究,本文还指出了变化检测所面临的挑战和可能的对策。

Processing of multi-temporal images and change detection has been an active research field in remote sensing for decades. Although plenty successful applications have been reported on the monitoring and detecting of environmental change, there are enormous challenges in applying multi-temporal imagery to derive timely information on the Earth＇s environment and human activities. In recent years, great progress has been observed to overcome technological obstacles by the development of new platforms and sensors. The wider availability of large archives of historical images also makes long-term change detection and modelling possible. Such a development stimulates further investigations to develop more advanced image processing methods and new approaches to handling image data in the time dimension. This paper reviews the current progress in the processing of multi-temporal data and change detection. The nature of the environmental change on the Earth＇s surface is analysed first, followed by a review of the development of remote sensing change detection technology in the following four aspects： image preprocessing for change detection, the classification of change detection methods and approaches, methods of remote sensing change detection, and accuracy assessment in muhi-temporal image processing. This paper tries to find the comprehensive solution from muhi-source data, integrated processes and intelligent methods with the assistance of prior knowledge. It also points out the challenges that change detection is facing and possible countermeasures, in the hope of deepening the research into change detection technology for remote sensing image.