1(School of Computer Science,Fudan University,Shanghai 200433,China)
2(School of Computer Science and Technology,Shandong Institute of Business and Technology,Yantai 264005,China)
Abstract:Video object tracking is an important research topic of computer vision which has been widely used in many applications,such as surveillance,robotics,humancomputer interface and so on.This paper aims to review the stateoftheart online tracking methods.Firstly,we summarize the main framework of modern tracking algorithms.Then we introduce and analyze the important components for modern trackers including the appearance models as well as the motion models.In addition,new characters and trends for the tracking research in the big data era are described and the application of deeplearning method on video object tracking is introduced.Finally,we have a discussion and provide insights for future.