摘要
单目标跟踪是计算机视觉领域重要的分支,旨在对视频序列中的指定目标进行连续跟踪。近年来,基于深度学习的单目标跟踪方法发展迅猛,其中基于孪生网络的双流跟踪方法和基于Transformer的单流跟踪方法是两种基础架构。本文从原理、组成结构、局限性及未来发展方向等角度对这两种架构进行了全面介绍与分析。另外,数据集是方法训练及评测的基石,本文汇总了当前主流的深度学习单目标跟踪数据集,详细阐述了跟踪方法在数据集上的评测方式及评测指标,并总结了多种方法在数据集上的表现。最后,从宏观角度分析了深度学习目标跟踪方法的未来发展趋势,以期为相关研究人员提供参考。
Significance Single object tracking(SOT)is one of the fundamental problems in computer vision,which has received extensive attention from scholars and industry professionals worldwide due to its important applications in intelligent video surveillance,human-computer interaction,autonomous driving,military target analysis,and other fields.For a given video sequence,a SOT method needs to predict the real-time and accurate location and size of the target in subsequent frames based on the initial state of the target(usually represented by the target bounding box)in the first frame.Unlike object detection,the tracking target in the tracking task is not specified by any specific category,and the tracking scene is always complex and diverse,involving many challenges such as changes in target scales,target occlusion,motion blur,and target disappearance.Therefore,tracking targets in real-time,accurately,and robustly is an extremely challenging task.The mainstream object tracking methods can be divided into three categories:discriminative correlation filters-based tracking methods,Siamese network-based tracking methods,and Transformer-based tracking methods.Among them,the accuracy and robustness of discirminative correlation filter(DCF)are far below the actual requirements.Meanwhile,with the advancement of deep learning hardware,the advantage of DCF methods being able to run in real time on mobile devices no longer exists.On the contrary,deep learning techniques have rapidly developed in recent years with the continuous improvement of computer performance and dataset capacity.Among them,deep learning theory,deep backbone networks,attention mechanisms,and self-supervised learning techniques have played a powerful role in the development of object tracking methods.Deep learning-based SOT methods can make full use of large-scale datasets for end-to-end offline training to achieve real-time,accurate,and robust tracking.Therefore,we provide an overview of deep learning-based object tracking methods.Some review works on tracking
作者
许廷发
王颖
史国凯
李天昊
李佳男
Xu Tingfa;Wang Ying;Shi Guokai;Li Tianhao;Li Jianan(Key Laboratory of Photoelectronic Imaging Technology and System,Ministry of Education,School of Optics and Photonics,Beijing Institute of Technology,Beijing 100081,China;Chongqing Innovation Center,Beijing Institute of Technology,Chongqing 401120,China;North Automatic Control Technology Institute,Taiyuan 030006,Shanxi,China)
出处
《光学学报》
EI
CAS
CSCD
北大核心
2023年第15期166-178,共13页
Acta Optica Sinica
基金
国家自然科学基金青年科学基金(62101032)。
