基于深度学习的人体行为识别综述
Summary of Human Behavior Recognition Based on Deep Learning
吴婷 1刘瑞欣 1刘明甫 1刘海华1
作者信息
- 1. 中南民族大学,湖北 武汉 430074
- 折叠
摘要
近年来,人体行为识别是计算机视觉领域的研究热点,在诸多领域有着广泛的应用,例如视频监控、人机交互等.随着深度学习的发展,卷积神经网络作为其领域中表现能力优越的人工神经网络之一,在动作识别领域中发挥着不可或缺的作用.文章基于深度学习总结基于2D CNN和基于3D CNN的动作识别方法,根据不同算法搭建的模型进行性能对比,同时对基准数据集进行归纳总结.最后探讨了未来人体动作识别的研究重难点.
Abstract
In recent years,human behavior recognition is a research hotspot in the field of computer vision,and it has been widely used in many fields,such as video surveillance,human-computer interaction and so on.With the development of Deep Learning,as one of the artificial neural networks with superior performance capabilities in the field,Convolutional Neural Networks plays an indispensable role in the field of action recognition.Based on Deep Learning,this paper summarizes the action recognition methods based on 2D CNN and 3D CNN,compares the performance of models built according to different algorithms,and summarizes the benchmark data sets.Finally,the research key points and difficulties of human action recognition in the future are discussed.
关键词
动作识别/深度学习/卷积神经网络/图像分类Key words
action recognition/Deep Learning/Convolution Neural Networks/image classification引用本文复制引用
基金项目
国家自然科学基金项目资助项目(61773409)
出版年
2024
国家科技期刊平台
NSTL
万方数据