Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (4): 775-790.DOI: 10.3778/j.issn.1673-9418.2108079

• Surveys and Frontiers • Previous Articles     Next Articles

Survey of Collective Activity Recognition Based on Deep Learning

PEI Lishen1, ZHAO Xuezhuan2,+()   

  1. 1. School of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450046, China
    2. School of Intelligent Engineering, Zhengzhou University of Aeronautics, Zhengzhou 450046, China
  • Received:2021-08-23 Revised:2021-11-03 Online:2022-04-01 Published:2021-11-08
  • About author:PEI Lishen, born in 1988, Ph.D., lecturer, M.S. supervisor, member of CCF. Her research interests include action recognition, image processing, computer vision and machine learning.
    ZHAO Xuezhuan, born in 1986, Ph.D., lecturer, member of CCF. His research interests include object detection, object tracking, saliency detection, abnormal behavior detection, computer vision, etc.
  • Supported by:
    National Natural Science Foundation of China(61806073);Key Research & Development and Promotion Project of Henan Province(192102210097);Key Research & Development and Promotion Project of Henan Province(192102210126);Key Research & Development and Promotion Project of Henan Province(212102210160)

群体行为识别深度学习方法研究综述

裴利沈1, 赵雪专2,+()   

  1. 1.河南财经政法大学 计算机与信息工程学院,郑州 450046
    2.郑州航空工业管理学院 智能工程学院,郑州 450046
  • 通讯作者: + E-mail: xuezhuansci@126.com
  • 作者简介:裴利沈(1988—),女,河南郑州人,博士,讲师,硕士生导师,CCF会员,主要研究方向为行为识别、图像处理、计算机视觉、机器学习。
    赵雪专(1986—),男,河南郑州人,博士,讲师,CCF会员,主要研究方向为目标检测、目标跟踪、显著性检测、异常行为检测、计算机视觉等。
  • 基金资助:
    国家自然科学基金(61806073);河南省重点研发与推广专项(科技攻关)基金(192102210097);河南省重点研发与推广专项(科技攻关)基金(192102210126);河南省重点研发与推广专项(科技攻关)基金(212102210160)

Abstract:

Collective activity recognition is an important issue in the field of computer vision, with wide application and urgently to be solved. With the development of deep neural network, the width and depth of collective activity recognition and understanding are expanding. Through investigating the research literature of collective activity recognition in recent ten years, the problem definition of the collective activity recognition is determined. The existing problems and challenges of collective activity recognition are pointed out. In the framework of deep neural network, this paper describes the development of the collective activity recognition algorithm from the early stage which only classifies and recognizes the collective activity categories to the current stage which focuses more on the understanding of the details of activities in the group behavior. Then, based on the network architectures such as CNN/3DCNN, Two-Stream Network, RNN/LSTM and Transformer, the core network architecture and the main research ideas of the mainstream collective activity recognition methods are mainly introduced. The recognition performance of these algorithms on common datasets is compared. The commonly used collective activity recognition datasets labeled with multilevel labels such as collective activity types and individual activity categories are combed and compared. Through objective and fair discussion and analysis of the advantages and disadvantages of various algorithms, it is expected to prompt readers to propose new solutions or new problems of collective activity recogni-tion. Finally, the future development of collective activity recognition is prospected, which is expected to stimulate new research directions.

Key words: collective activity recognition, deep learning, deep neural network architecture, convolutional neural network (CNN), long short-term memory (LSTM) neural network

摘要:

群体行为识别是计算机视觉领域应用广泛且亟待解决的重要研究问题。伴随着深度神经网络的发展,群体行为识别与理解的宽度与深度也在不断扩展。通过调研近十年来群体行为识别的研究文献,确定了目前群体行为识别研究的问题定义;指出了群体行为识别研究现存的问题与挑战;在深度学习网络架构下,描述了从早期仅仅对群体行为进行分类识别,到如今更加侧重于对行为群体中活动细节理解的群体行为识别算法的发展历程;重点介绍了以卷积神经网络CNN/3DCNN、双流网络Two-Stream Network、循环神经网络RNN/LSTM和Transformer等网络架构为基础的,主流群体行为识别算法的核心网络架构和主要研究思路,对各算法在常用公共数据集上的识别效果进行了对比;对标注了群体行为类型和个体行为类别等多级标签的常用的群体行为数据集进行了梳理和对比。期望通过客观的对各种算法优缺点的讨论分析,引发读者提出群体行为识别研究的新思路或新问题。最后,对群体行为分析的未来发展进行了展望,期待能够启发新的研究方向。

关键词: 群体行为识别, 深度学习, 深度神经网络架构, 卷积神经网络(CNN), 长短时记忆神经网络(LSTM)

CLC Number: