中文摘要：

随着摄像头安装数量的日益增多,以及智慧城市和公共安全需求的日益增长,采用人工的视频监控方式已经远远不能满足需要,因此智能视频监控技术应运而生并迅速成为一个研究热点.智能视频监控技术是一个跨领域的研究方向,它的研究内容丰富,应用领域广泛多样.文中对智能视频监控技术的发展历史、研究现状以及典型算法的现状给了比较全面的综述.首先从底层、中层、高层对智能视频监控技术进行分类,分别对目标检测、目标跟踪、分类识别以及行为分析算法进行归纳总结;然后对典型算法的优缺点进行分析,给出了典型算法在现有研究数据库上的性能对比,并对待解决问题和难点进行了总结;最后对智能视频监控技术在物联网背景下存在的挑战以及未来发展趋势进行了探讨.

英文摘要：

Due to the rapid increase of the number of cameras used in the video surveillance and the huge needs of the smart city and public security, video surveillance by human beings is no longer suitable. Hence, intelligent video surveillance emerges and becomes one of the hottest research points. Intelligent video surveillance is an interdisciplinary research area that has abundant research interests and diverse applications. This paper summarizes the history, the state-of-the-art, and various applications of the intelligent videosurveillance. Firstly, this paper classifies the algorithms by low level, middle level and high level, then analyses their advantages and disadvantages, and compares the performances on diflerent datasets, as well as presents the outstanding issues; finally, we discuss the future research trends of intelligent video surveillance in the context of Internet of Things.