Research on human activity recognition based on two-stream network

TANG Ruize; WANG Beibei; XIA Hongtao; YE Runfeng; GAO Ruizhen

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on human activity recognition based on two-stream network

Research & Approach | 更新时间：2026-07-20

- Research on human activity recognition based on two-stream network
- Vol. 45, Issue 7, Pages: 47-51(2026)
- 作者机构：
  
  1. 河北工程大学机械与装备工程学院,河北,邯郸,056000
  2. 河北工程大学医学院,河北,邯郸,056000
  3. 河北工程大学生命科学与食品工程学院,河北,邯郸,056000
  4. 河北工程大学研究生部,河北,邯郸,056000
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP242;TP212
- Published：2026
- 稿件说明：
移动端阅览
TANG Ruize, WANG Beibei, XIA Hongtao, et al. Research on human activity recognition based on two-stream network[J]. 2026, 45(7): 47-51.
DOI：

TANG Ruize, WANG Beibei, XIA Hongtao, et al. Research on human activity recognition based on two-stream network[J]. 2026, 45(7): 47-51. DOI：

摘要

针对外骨骼机器人使用中的人机协同问题，在外骨骼机器人上搭载传感器

采集人体行走、蹲起、上楼梯、下楼梯以及站立五种行为数据。基于传感器数据中不同的数据特征，提出一种基于双流网络的人体行为识别（HAR）方法。通过双流网络捕捉学习传感器的时序特征，采用门控循环单元(GRU)融合特征，对人体上述五种行为状态进行行为识别，实现外骨骼机器人助力功能。实验结果表明：所提出的方法识别准确率为96.11%，可有效解决外骨骼机器人使用中的人机协同问题。

Abstract

Aiming at the problem of human-machine collaboration in the use of exoskeleton robots

sensors are mounted on the exoskeleton robot to collect data of five human behaviors:walking

squatting

ascending stairs

descending stairs and standing.Based on different data features of sensor data

a two-stream network-based human activity recognition(HAR) algorithm is proposed.The two-stream network is adopted to extract and learn temporal features of sensors

and the gated recurrent unit (GRU) is used for feature fusion to recognize the above five behavioral states.This enables the assistive function of the exoskeleton robot.Experimental results show that the proposed method achieves a recognition accuracy of 96.11%

which can effectively solve the human-machine collaboration issue in the use of exoskeleton robots.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lower limb exoskeleton gait detection based on IGAO-SVM

Research on navigation error correction method for trans-media aircraft

Preparation and performance study of 3D flexible pressure sensor based on MWCNTs

Research on angle sensor and its linear compensation technology based on image recognition

Cardiac MRI image segmentation based on parallel receptive fields and attention

Related Author

HUANG Binhao

L Jian

QIANG Ligang

Related Institution

Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education,Guizhou University

Guizhou Aerospace Control Technology Co Ltd

⁰