现代信息科技2024，Vol.8Issue(21)：78-82,5.DOI:10.19850/j.cnki.2096-4706.2024.21.016
基于FlowNet2.0改进的运动人体识别研究
Research on Improved Moving Human Body Recognition Based on FlowNet2.0
摘要
Abstract
Aiming at the problem that the existing Two-Stream Convolutional Neural Networks cannot quickly and accurately identify human body information because the human body moves fast in motion,an improved human recognition detection method based on FlowNet2.0 network is proposed,which can effectively enhance the network's ability to extract appearance information and posture features by introducing Self-Attention into the input channels of each video frame of FlowNet2.0 network,so as to better describe moving targets.Finally,the model is trained on the HDBM51 dataset,and the experimental results show that the improved FlowNet2.0 network has achieved significant improvement results.This study provides an effective solution to solve the problems of human recognition during action.关键词
双流卷积神经网络/视频理解/运动目标/多注意力网络Key words
Two-Stream Convolutional Neural Networks/video understanding/moving target/Multi-Attention Networks分类
信息技术与安全科学引用本文复制引用
沈英杰,付江龙,王剑雄,魏士磊,任一帅..基于FlowNet2.0改进的运动人体识别研究[J].现代信息科技,2024,8(21):78-82,5.基金项目
河北省体育科技研究课题资助项目(2024QT01) （2024QT01）
河北省研究生创新资助项目(XY2024038,XY2023080) （XY2024038,XY2023080）
