计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (7): 1504-1515.DOI: 10.3778/j.issn.1673-9418.2111105

• 综述·探索 • 上一篇    下一篇

视频目标跟踪算法综述

刘艺1,+(), 李蒙蒙1, 郑奇斌2, 秦伟1, 任小广1   

  1. 1.国防科技创新研究院,北京 100071
    2.军事科学院,北京 100091
  • 收稿日期:2021-11-22 修回日期:2022-01-20 出版日期:2022-07-01 发布日期:2022-07-25
  • 作者简介:刘艺(1990—),男,安徽蚌埠人,博士,助理研究员,主要研究方向为机器人操作系统、数据质量、演化算法。
    LIU Yi, born in 1990, Ph.D., assistant researcher. His research interests include robot operating system, data quality and evolutionary algorithms.
    李蒙蒙(1992—),女,河北邯郸人,硕士研究生,主要研究方向为演化算法、数据质量、目标跟踪等。
    LI Mengmeng, born in 1992, M.S. candidate. Her research interests include evolutionary algorithms, data quality, object tracking, etc.
    郑奇斌(1990—),男,甘肃兰州人,博士,助理研究员,主要研究方向为数据工程、数据挖掘、机器学习等。
    ZHENG Qibin, born in 1990, Ph.D., assistant researcher. His research interests include data engineering, data mining, machine learning, etc.
    秦伟(1983—),男,安徽阜阳人,硕士,助理研究员,主要研究方向为智能信息系统管理。
    QIN Wei, born in 1983, M.S., assistant researcher. His research interest is intelligent information system management.
    任小广(1986—),男,湖北随州人,博士,副研究员,主要研究方向为高性能计算、数值计算和模拟、机器人操作系统等。
    REN Xiaoguang, born in 1986, Ph.D., associate research fellow. His research interests include high performance computing, numerical computation and simulation, robot operation systems, etc.
  • 基金资助:
    国家自然科学基金青年基金项目(61802426)

Survey on Video Object Tracking Algorithms

LIU Yi1,+(), LI Mengmeng1, ZHENG Qibin2, QIN Wei1, REN Xiaoguang1   

  1. 1. Defense Innovation Institute, Beijing 100071, China
    2. Academy of Military Science, Beijing 100091, China
  • Received:2021-11-22 Revised:2022-01-20 Online:2022-07-01 Published:2022-07-25
  • Supported by:
    the National Natural Science Foundation for Young Scientists of China(61802426)

摘要:

视频目标跟踪是计算机视觉领域重要的研究内容,主要研究在视频流或者图像序列中定位其中感兴趣的物体。视频目标跟踪在视频监控、无人驾驶、精确制导等领域中具有广泛的应用,因此,全面地综述视频目标跟踪算法具有重要的意义。首先根据挑战来源不同,将视频目标跟踪技术面临的挑战分为目标自身因素和背景因素两方面,并分别进行总结;其次将近些年典型的视频目标跟踪算法分为基于相关滤波的视频目标跟踪算法和基于深度学习的视频目标跟踪算法,并进一步将基于相关滤波的视频目标跟踪算法分为核相关滤波算法、尺度自适应相关滤波算法和多特征融合相关滤波算法三类,将基于深度学习的视频目标跟踪算法分为基于孪生网络的视频目标跟踪算法和基于卷积神经网络的视频目标跟踪算法两类,并对各类算法从研究动机、算法思想、优缺点等方面进行分析;然后介绍了视频目标跟踪算法中常用的数据集和评价指标;最后总结了全文,并指出视频目标跟踪领域未来的发展趋势。

关键词: 计算机视觉, 视频目标跟踪, 相关滤波, 深度学习

Abstract:

Video object tracking is an important research content in the field of computer vision, mainly studying the tracking of objects with interest in video streams or image sequences. Video object tracking has been widely used in cameras and surveillance, driverless, precision guidance and other fields. Therefore, a comprehensive review on video object tracking algorithms is of great significance. Firstly, according to different sources of challenges, the challenges faced by video object tracking are classified into two aspects, the objects’ factors and the backgrounds’ factors, and summed up respectively. Secondly, the typical video object tracking algorithms in recent years are classified into correlation filtering video object tracking algorithms and deep learning video object tracking algorithms. And further the correlation filtering video object tracking algorithms are classified into three categories: kernel correlation filtering algorithms, scale adaptive correlation filtering algorithms and multi-feature fusion corre-lation filtering algorithms. The deep learning video object tracking algorithms are classified into two categories: video object tracking algorithms based on siamese network and based on convolutional neural network. This paper analyzes various algorithms from the aspects of research motivation, algorithm ideas, advantages and disadvantages. Then, the widely used datasets and evaluation indicators are introduced. Finally, this paper sums up the research and looks forward to the development trends of video object tracking in the future.

Key words: computer vision, video object tracking, correlation filtering, deep learning

中图分类号: