《计算机应用研究》|Application Research of Computers

基于深度学习的视觉单目标跟踪综述

Survey on visual single object tracking based on deep learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张长弓,杨海涛,王晋宇,冯博迪,李高源,高宇歌
机构 航天工程大学 航天信息学院,北京 101400
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-002-2888-08
DOI 10.19734/j.issn.1001-3695.2021.03.0036
摘要 单目标跟踪是一种在视频中利用目标外观和上下文信息对单个目标分析运动状态、提供定位的技术,在智能监控、智能交互、导航制导等方面具有应用前景,但遮挡、背景干扰、目标变化等问题导致实际应用的进展缓慢。随着近年来深度学习的快速发展,研究使用深度学习技术优化单目标跟踪算法已成为计算机视觉领域的热点之一。围绕基于深度学习的单目标跟踪算法,在分析了单目标跟踪的基本原理基础上,从相关滤波、孪生网络、元学习、注意力、循环神经网络和生成对抗网络六个方面,根据核心算法的不同分别进行了概述和分析;此外,对研究现状进行了总结,提出了算法的发展趋势和优化思路。
关键词 单目标跟踪; 深度学习; 孪生网络; 相关滤波; 元学习; 注意力机制
基金项目
本文URL http://www.arocmag.com/article/01-2021-10-002.html
英文标题 Survey on visual single object tracking based on deep learning
作者英文名 Zhang Changgong, Yang Haitao, Wang Jinyu, Feng Bodi, Li Gaoyuan, Gao Yuge
机构英文名 School of Space Information,Space Engineering University,Beijing 101400,China
英文摘要 Single object tracking(SOT) is a technique to analyze the motion status and provide localization of the single target by using target appearance and context information in video. It has promising applications in intelligent surveillance, intelligent interaction, navigation and guidance, etc. However, problems such as occlusion, background interference and appearance variation led to slow progress in practical applications. With the rapid development of deep learning in recent years, the study of using deep learning techniques to optimize SOT algorithm has become one of the hot spots in computer vision. Around the SOT algorithm based on deep learning, this paper respectively provided outline and analysis of each of the six aspects of correlation filter, Siamese networks, meta-learning, attention, recurrent neural networks and generative adversarial networks according to the core algorithms, after analyzing the basic principles of SOT. In addition, this paper summarized the current state of research and proposed the development trend and optimization ideas of the algorithms.
英文关键词 single object tracking; deep learning; Siamese network; correlation filter; meta learning; attention mechanism
参考文献 查看稿件参考文献
 
收稿日期 2021/3/17
修回日期 2021/4/29
页码 2888-2895
中图分类号 TP391.41
文献标志码 A