计算技术与自动化2018，Vol.37Issue(1)：73-82,10.DOI:10.16339/j.cnki.jsjsyzdh.201801016
在线多目标视频跟踪算法综述
Survey of Online Multi-object Video Tracking Algorithms
摘要
Abstract
Video multi-object tracking is one of the important research topics in the field of computer vision,which is widely used in military and civil areas.At present,the research of single object tracking algorithm has quite mature,but for multi-object tracking of the research is still ongoing.This paper focuses on four important stages in the multi-object tracking process:feature extraction,detector,data association and the tracker.The feature extraction part introduces the current meth-ods of feature extraction,as well as the merits and demerits of each method;In the stage of detection,the tracking effect of the object appearance model in specific applications is described,and then we analyze the multi-object tracking algorithm based on detection and tracking as well as the multi-object tracking algorithm based on deep learning;In the tracking phase, the establishment of object motion model and multi-object tracking with different tracker hybrid algorithm are introduced;During the stage of data correlation,we introduce the multi-object tracking based on energy minimization and commonly used data association algorithm,respectively.Then we introduce the current mainstream datasets and evaluation methods.Finally, the future development of the multi-object tracking is discussed and forecasted.关键词
视频分析/计算机视觉/多目标跟踪/深度学习Key words
video analysis/computer vision/multi-object tracking/deep learning分类
信息技术与安全科学引用本文复制引用
李月峰,周书仁..在线多目标视频跟踪算法综述[J].计算技术与自动化,2018,37(1):73-82,10.基金项目
国家自然科学基金资助项目(61402053,61602059) （61402053,61602059）
湖南省教育厅科学研究资助项目(16C0046,16A008,17A007) （16C0046,16A008,17A007）
