作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2021, Vol. 47 ›› Issue (10): 260-268. doi: 10.19678/j.issn.1000-3428.0060938

• 开发研究与工程应用 • 上一篇    下一篇

基于卷积长短时记忆网络的人体行为识别研究

孙彦玺1, 赵婉婉1, 武东辉1, 陈继斌1, 仇森2   

  1. 1. 郑州轻工业大学 建筑环境工程学院, 郑州 450002;
    2. 大连理工大学 控制科学与工程学院, 辽宁 大连 116024
  • 收稿日期:2021-02-25 修回日期:2021-04-27 发布日期:2021-05-06
  • 作者简介:孙彦玺(1996-),男,硕士研究生,主研方向为深度学习、人体行为识别;赵婉婉,助理实验师;武东辉,讲师、博士;陈继斌,教授、硕士;仇森,讲师、博士。
  • 基金资助:
    国家自然科学基金青年科学基金项目(61803072);河南省科技攻关项目(182102210622);河南省高等学校重点科研项目(19A413013);郑州轻工业大学青年骨干项目(13501050002);郑州轻工业大学博士科研项目(13501050009)。

Research of Human Activity Recognition Based on Convolutional Long Short-Term Memory Network

SUN Yanxi1, ZHAO Wanwan1, WU Donghui1, CHEN Jibin1, QIU Sen2   

  1. 1. College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China;
    2. School of Control Science and Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China
  • Received:2021-02-25 Revised:2021-04-27 Published:2021-05-06

摘要: 人体行为识别利用深度学习网络模型自动提取数据的深层特征,但传统机器学习算法存在依赖手工特征提取、模型泛化能力差等问题。提出基于空时特征融合的深度学习模型(CLT-net)用于人体行为识别。采用卷积神经网络(CNN)自动提取人体行为数据的深层次隐含特征,利用长短时记忆(LSTM)网络构建时间序列模型,学习人体行为特征在时间序列上的长期依赖关系。在此基础上,通过softmax分类器实现对不同人体行为分类。在DaLiAc数据集的实验结果表明,相比CNN、LSTM、BP模型,CLT-net模型对13种人体行为的总体识别率达到了97.6%,具有较优的人体行为识别分类性能。

关键词: 人体行为识别, 深度学习, 卷积神经网络, 长短时记忆网络, 模式识别, 可穿戴传感器

Abstract: Human activity recognition is a deep learning-based technology, which uses deep learning network models to automatically extract deep features of data.The traditional machine learning algorithms rely heavily on manual intervention during feature extraction, and exhibit a poor generalization ability.To address the problem, a deep learning model, CLT-net, is proposed based on space-time feature fusion for human activity recognition.CLT-net employs Convolution Neural Network (CNN) to extract the deep hidden features of human activity data automatically.Also, Long Short-Term Memory (LSTM) network is used to construct the time series model to learn the long-term dependence of human activity features on the time series.Finally, the softmax classifier is used to classify different human activities.The experimental results based on the public dataset, DaLiAc, show that CLT-net achieves an accuracy of 97.6% in the recognition of 13 kinds of human activities, outperforming the traditional models based on CNN, LSTM and BP.CLT-net has better classification performance of human activity recognition.

Key words: human activity recognition, Deep Learning(DL), Convolutional Neural Network(CNN), Long Short-Term Memory(LSTM) network, pattern recognition, wearable sensors

中图分类号: