计算机与现代化 ›› 2023, Vol. 0 ›› Issue (09): 1-9.doi: 10.3969/j.issn.1006-2475.2023.09.001

• 人工智能 •    下一篇

基于深度学习的人体行为检测方法研究综述

  

  1. (1.苏州科技大学电子与信息工程学院,江苏 苏州 215009; 2.苏州科技大学天平学院,江苏 苏州 215009; 3.苏州科技大学苏州智慧城市研究院,江苏 苏州 215009; 4.苏州科技大学苏州市虚拟现实智能交互及应用技术重点实验室,江苏 苏州 215009)
  • 出版日期:2023-09-28 发布日期:2023-10-10
  • 作者简介:沈加炜(1998—),男,江苏兴化人,硕士研究生,研究方向:机器学习,建筑智能化,E-mail: 1968431836@qq.com; 陆一鸣(1990—),男,江苏苏州人,助理讲师,硕士,研究方向:人工智能,量化交易; 陈晓艺(1997—),女,山东泰安人,硕士研究生,研究方向:人工智能,机器学习; 钱美玲1999—),女,江苏泰州人,硕士研究生,研究方向:人工智能,机器学习; 陆卫忠(1964—),男,江苏苏州人,副教授,CCF会员,硕士,研究方向:人工智能,机器学习。
  • 基金资助:
    国家自然科学基金资助项目(61472267)

Review of Research on Human Behavior Detection Methods Based on Deep Learning

  1. (1. School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China;
    2. College of Tianping, Suzhou University of Science and Technology, Suzhou 215009, China; 
    3. Suzhou Smart City Research Institute, Suzhou University of Science and Technology, Suzhou 215009, China; 
    4. Suzhou Key Laboratory of Virtual Reality Intelligent Interaction and Application Technology, Suzhou University of Science and Technology, Suzhou 215009, China)
  • Online:2023-09-28 Published:2023-10-10

摘要: 当下结合计算机视觉和视频的特征提取对人体行为动作进行捕捉识别的研究炙手可热,并且其在智能视频监控和智能家居的人机交互等其他领域方向上的应用场景也十分丰富。基于传统方法的人体行为检测算法有着依赖数据样本过多、易受环境噪音影响从而降低精确率等缺点,而不断发展的深度学习技术逐渐展现出它的优势,可以很好地解决这些问题。本文基于此,首先介绍一些目前常用的行为识别数据集并在此基础上剖析当下基于深度学习的人体行为识别检测的研究现状;其次描述常见的人体行为识别检测方法及其识别的流程;最后对现存的各种行为识别检测方法性能、现存问题进行总结和未来发展方向进行展望。

关键词: 深度学习, 人体行为检测, 智能监控, 行为数据集

Abstract: Human behavior recognition has always been a hot topic of research in the field of computer vision and video understanding and is widely used in other areas such as intelligent video surveillance and human-computer interaction in smart homes. While traditional human behavior detection algorithms have the disadvantages of relying on too many data samples and being susceptible to environmental noise, evolving deep learning techniques are gradually showing their advantages and can be a good solution to these problems. Based on this, this paper firstly introduces some commonly used behavioral recognition datasets and analyses the current research status of human behavioral recognition based on deep learning, then describes the basic process of behavioral recognition and commonly used behavioral recognition methods, finally summarizes the performance, existing problems of various existing behavioral recognition methods, and outlooks the future development directions.

Key words: deep learning, human behavior recognition, smart surveillance, behavior dataset

中图分类号: