计算机应用 ›› 2018, Vol. 38 ›› Issue (6): 1568-1574.DOI: 10.11772/j.issn.1001-9081.2017112831

• 人工智能 • 上一篇    下一篇

基于长短时记忆网络的人体姿态检测方法

郑毅, 李凤, 张丽, 刘守印   

  1. 华中师范大学 物理科学与技术学院, 武汉 430079
  • 收稿日期:2017-12-01 修回日期:2018-02-05 出版日期:2018-06-10 发布日期:2018-06-13
  • 通讯作者: 刘守印
  • 作者简介:郑毅(1993-),男,湖北武汉人,硕士研究生,主要研究方向:机器学习、深度神经网络;李凤(1993-),女,四川成都人,硕士研究生,主要研究方向:无线传感器网络、物联网;张丽(1993-),女,四川成都人,硕士研究生,主要研究方向:Web前端、数据可视化;刘守印(1964-),男,河南周口人,教授,博士,主要研究方向:无线通信、物联网、机器学习。

Human posture detection method based on long short term memory network

ZHENG Yi, LI Feng, ZHANG Li, LIU Shouyin   

  1. College of Physical Science and Technology, Central China Normal University, Wuhan Hubei 430079
  • Received:2017-12-01 Revised:2018-02-05 Online:2018-06-10 Published:2018-06-13

摘要: 针对在循环神经网络(RNN)网络结构下较为遥远的历史信号无法传递至当前时刻的问题,长短时记忆(LSTM)网络作为RNN的一种变体被提出,在继承RNN对时间序列优秀的记忆能力的前提下,LSTM克服了这种时间序列的长期依赖问题,并在自然语言处理与语音识别领域有较好的表现。对于人体行为动作中也存在作为时间序列的长期依赖问题与使用传统滑窗算法采集数据时造成的无法实时检测的问题,将LSTM扩展应用到人体姿态检测,提出了基于LSTM的人体姿态检测方法。通过目前智能手机中一般都带有的加速度传感器、陀螺仪、气压计和方向传感器实时采集的时序数据,制作了包含3336条带有人工标注数据的人体姿态数据集,对行走、奔跑、上楼梯、下楼梯和平静五种日常持续性行为姿态与跌倒、起立、坐下和跳跃这四个突发行为姿态进行预测分类。对比LSTM网络与该研究领域内常用的浅层学习算法、深度学习全连接神经网络与卷积神经网络,实验结果表明,所提方法使用端对端的深度学习的方法相比基于所制作数据集的人体姿态检测算法模型的正确率提高了4.49个百分点,验证了该网络结构的泛化能力且更适合姿态检测。

关键词: 长短时记忆网络, 人体姿态, 多传感器, 时序数据, 深度学习

Abstract: Concerning the problem that distant historical signals cannot be transmitted to the current time under the network structure of Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) network was proposed as a variant of RNN. On the premise of inheriting RNN's excellent memory ability for time series, LSTM overcomes the long-term dependence problem of time series and has a remarkable performance in natural language processing and speech recognition. For the long-term dependence problem of human behavior data as a time series and the problem of not real-time detection caused by using the traditional sliding window algorithm to collect data, the LSTM was extended and applied to the human posture detection, and then a human posture detection method based on LSTM was proposed. By using the real-time data collected by the accelerometers, gyroscopes, barometers and direction sensors in the smartphones, a human posture dataset with a total of 3336 manual annotation data was produced. The five kinds of daily behavior postures such as walking, running, going upstairs, going downstairs, calmness as well as the four kinds of sudden behavior postures of fallling, standing, sitting, jumping, were predicted and classified. The LSTM network was compared with the commonly used methods such as shallow learning algorithm, deep learning fully connected neural network and convolution neural network. The experimental results show that, by using the end-to-end deep learning method, the proposed method has improved the accuracy by 4.49 percentage points compared to the model of human posture detection algorithm trained on the produced dataset. The generalization ability of the proposed network structure is verified and it is more suitable for posture detection.

Key words: Long Short Term Memory (LSTM) network, human posture, multi-sensor, time series data, deep learning

中图分类号: