多时相遥感影像变化检测是指对同一地理区域、不同时间获取的遥感影像进行自动变化发现、识别与解释的遥感处理与分析技术。随着卫星遥感技术及人工智能理论方法的快速发展，基于多时相遥感影像数据驱动和模型驱动的传统变化检测方法正朝着数据-模型-知识联合驱动的方向转型和演变，以更加自动化、精细化和智能化的方式，解决多领域的地表时空变化检测问题。本文在总结多时相遥感数据源从同构到异构、变化检测模型从传统到智能、变化检测应用从理论到落地过程中存在问题的基础上，以光学遥感影像变化检测任务为例，梳理和分析了人工智能时代下变化检测技术的发展历程。从无监督、监督、弱监督三个方面探讨了遥感变化检测从传统到前沿技术的转型特点与趋势，并进一步提出了未来需重点突破模型的物理可解释性、泛化及迁移能力、跨数据-跨场景-跨领域应用水平等关键问题。

In the past decades, the effects of global climate change and the increase of human activities have significantly increased the demand for remote sensing monitoring. At the same time, with the accumulation of remote sensing data from multi-platforms and multi-sensors, the quantity and quality of multitemporal images are significantly improved. Multitemporal remote sensing images change detection (CD) is a processing and analysis technology that aims to automatically detect, identify and describe changes occurred in the same geographical area at different times. With the advancement of remote sensing and artificial intelligence (AI) technology, traditional data-driven and modal CD methods are evolving toward data-model-knowledge jointly driven direction, to solve the land surface spatio-temporal CD problem in a variety of application fields in a more automatic, refined, and intelligent way. This paper first summarizes existing problems in multitemporal remote sensing CD by analyzing the use of homogeneous and heterogenous data sources, developments from traditional to intelligent CD models, and challenges from theoretical to practical CD applications. We take optical images CD as an example, examines the evolution process of CD technology in the Era of AI, which can be summarized as data-driven CD, model-driven CD, and data-model-knowledge driven CD three periods. Then the characteristics and problems of each periods are discussed. Furthermore, for each of three aspects (unsupervised, supervised, and weakly supervised), characteristics and trends in the development of traditional to cutting-edge CD techniques are discussed. In the future, one can focus on breaking through key issues such as the physical interpretability, generalization and transferability of the CD models, as well as their successful implementation in cross-data, cross-scene and cross-domain applications.