引用本文: | 朱晓林,王冬丽,欧阳万里,李抱朴,周彦,刘金富.基于深度学习的群体行为识别: 综述与展望[J].控制理论与应用,2024,41(12):2207~2223.[点击复制] |
ZHU Xiao-lin,WANG Dong-li,OUYANG Wan-li,LI Bao-pu,ZHOU Yan,LIU Jin-fu.Group activity recognition based on deep learning: Overview and outlook[J].Control Theory and Technology,2024,41(12):2207~2223.[点击复制] |
|
基于深度学习的群体行为识别: 综述与展望 |
Group activity recognition based on deep learning: Overview and outlook |
摘要点击 4062 全文点击 61 投稿时间:2022-05-10 修订日期:2022-12-09 |
查看全文 查看/发表评论 下载PDF阅读器 |
DOI编号 10.7641/CTA.2023.20375 |
2024,41(12):2207-2223 |
中文关键词 群体行为识别 深度学习 层级时序建模 交互关系推理 Transformer |
英文关键词 group activity recognition deep learning hierarchical temporal modeling interaction relationship reasoning Transformer |
基金项目 国家重点研发计划项目(2020YFA0713503), 国家自然科学基金项目(61773330), 国家航空科学基金项目(20200020114004), 湖南省科技创新计划 项目(2020GK2036), 湖南省自然科学基金项目(2023JJ30598), 湖南省研究生科研创新项目(CX20220652)资助. |
|
中文摘要 |
群体行为识别是计算机视觉领域中备受关注的研究方向, 在智能监控系统和体育运动分析等领域中具有广泛的应用推广价值. 本文对过去七年来基于深度学习的群体行为识别方法进行了全面综述, 有助于更好推动群体行为识别的发展. 首先, 介绍群体行为的定义、通用识别流程以及主要的挑战; 其次, 从群体行为识别的建模方法和内在机理进行划分, 并进一步细分类、讨论和分析这些方法的优缺点; 然后, 给出群体行为识别的常用数据集, 列举了相关的开源代码库和评估指标; 最后, 对该领域未来的研究方向进行了展望. |
英文摘要 |
Group activity recognition has attracted much attention in the computer vision community, and it is widely applied in intelligent monitoring systems and sports video analysis. This paper provides a comprehensive review of the group activity recognition methods based on deep learning over the past seven years, which will help to promote the development of group activity recognition. First, the definition, the general recognition process, and the main challenges of group activity are introduced; Secondly, we classify the group activity recognition methods in modeling and internal mechanism, subdivide them, and further discuss the advantages and disadvantages of these methods; Thirdly, we present the common datasets of group activity recognition, the relevant open-source code libraries, and the evaluation index; Finally, we analyze the future research directions in group activity recognition. |
|
|
|
|
|