Change detection of multisource remote sensing images: a review

Change detection (CD) is essential in remote sensing (RS) for natural resource monitoring, territorial planning, and disaster assessment. With the abundance of data collected by satellite, aircraft, and unmanned aerial vehicles, the utilization of multisource RS image CD (RSICD) enables the efficient acquisition of ground object change information and timely updates to existing databases. Although CD techniques have been developed and successfully applied for approximately six decades, a systematic and comprehensive review that addresses emerging trends, including multisource, data-driven, and large-scale artificial intelligence (AI) models, is lacking. Therefore, first, the development process of RSICD was reviewed. Second, the characteristics of multisource RS images were analyzed, and all publicly available RSICD data that we could gather were collected and organized. Third, RSICD methods were systematically classified and summarized on the basis of the detection framework, detection granularity, and data sources. Fourth, the suitability of specific data and CD methods for diverse applications and tasks was assessed. Finally, challenges, opportunities, and future directions for RSICD were discussed within the context of high-resolution imagery, multisource data, and large-scale AI models. This review can help researchers better understand this field, shed light on this topic, and inspire further RSICD research efforts.

变化检测（Change Detection，CD）在遥感（Remote Sensing，RS）领域中是自然资源监测、国土空间规划与灾害评估的核心技术手段。随着卫星、航空器及无人机采集的数据量呈爆发式增长，多源遥感影像变化检测（Multisource Remote Sensing Image Change Detection，RSICD）技术的应用可高效获取地物变化信息，并实现现有数据库的及时更新。尽管变化检测技术已历经近六十年的发展并得到成功落地应用，但目前仍缺乏针对其新兴趋势展开系统性、全面性综述的研究，这些新兴趋势涵盖多源数据、数据驱动范式以及大规模人工智能（Artificial Intelligence，AI）模型等方向。有鉴于此，本文首先梳理了多源遥感影像变化检测的发展历程；其次分析了多源遥感影像的特征，并收集整理了当前可公开获取的全部多源遥感影像变化检测数据集；再次，基于检测框架、检测粒度与数据来源，对多源遥感影像变化检测方法进行了系统性分类与总结；第四，评估了特定数据集与变化检测方法针对不同应用场景与任务的适配性；最后，结合高分辨率影像、多源数据以及大规模人工智能模型的发展背景，探讨了多源遥感影像变化检测领域面临的挑战、机遇与未来发展方向。本综述能够帮助研究人员更好地理解该领域的发展全貌，明晰该研究主题的核心内涵，并为后续多源遥感影像变化检测领域的研究工作提供启发。