计算机科学 ›› 2016, Vol. 43 ›› Issue (Z11): 56-58.doi: 10.11896/j.issn.1002-137X.2016.11A.012

• 智能计算 • 上一篇    下一篇

一种基于卷积神经网络深度学习的人体行为识别方法

王忠民,曹洪江,范琳   

  1. 西安邮电大学计算机学院 西安710121,西安邮电大学计算机学院 西安710121,西安邮电大学计算机学院 西安710121
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(61373116),陕西省教育厅产业化培育项目(2012JC22),陕西省教育厅项目(15JK1653),西安邮电大学青年教师科研基金资助

Method on Human Activity Recognition Based on Convolutional Neural Networks

WANG Zhong-min, CAO Hong-jiang and FAN Lin   

  • Online:2018-12-01 Published:2018-12-01

摘要: 为提高基于智能终端的人体行为识别的准确率,提出一种基于卷积神经网络深度学习人体行为识别方法。该方法将原始数据进行简单处理,直接作为输入数据输入到卷积神经网络中,由卷积神经网络进行局部特征分析,得到特征输出项,直接输入到Softmax分类器中,可识别走路、跑步、上下楼梯、站立等5种动作。 对比实验结果表明,其对不同的实验者的识别率达到84.8%,证明了该方法的有效性。

关键词: 行为识别,深度学习,卷积神经网络

Abstract: In order to improve the accuracy of human activity recognition based on intelligent terminal,we proposed a recognition method based on convolution neural network.We pre-process the raw acceleration data,and input the processed data directly into the convolution neural network to do local feature analysis.After processing,we got the characteristic output items,which can be directly inputted into the Softmax classifier,which can recognize five activity,such as walking,running,going downstairs,going upstairs and standing.By comparing the experimental results,the recognition rate of different experimenters is 84.8%,which proved that the method is effective.

Key words: Human activity recognition,Deep learning,Convolutional neural networks

[1] Zeng M,Nguyen L T,et al.Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors[C]∥Moboi SCASE.2014:197-205
[2] Abdel-Hamid O,Mohamed A R,Jiang H,et al.Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2012:4277-4280
[3] Bagci U,Bai L.A comparison of daubechies and gabor wavelets for classification of mr images[C]∥IEEE International Confe-rence on Signal Processing and Communications,2007(ICSPC 2007).IEEE,2007:676-679
[4] Bengio Y.Learning deep architectures for ai[J].Foundationsand trends R in Machine Learning,2009,2(1):1-127
[5] Bhattacharya S,Nurmi P,Hammerla N,et al.Using unlabeled¨data in a sparse-coding framework for human activity recognition[J].arXiv preprint arXiv:1312.6995,2013
[6] 王喜昌,杨先军,徐强,等.基于三维加速度传感器的上肢动作识别系统[J].传感器学报,2010,6(23):816-819
[7] 王忠民,曹栋.基于蚁群算法的行为识别特征优选方法[J].西安邮电大学学报,2014,9(1):73-77
[8] 衡霞,王忠民.基于手机加速度传感器的人体行为识别[J].西安邮电大学学报,2014,9(6):76-79
[9] 徐姗姗.卷积神经网络的研究与应用[D].南京:南京林业大学,2013
[10] 陈先昌.基于卷积神经网络的深度学习算法和应用研究[D].杭州:浙江工商大学,2013
[11] 范琳,王忠民.穿戴位置无关的手机用户行为识别模型[J].计算机应用研究,2015,32(1):63-66
[12] 陈先昌.基于卷积神经网络的深度学习算法与应用研究[D].杭州:浙江工商大学,2014
[13] 杨心.基于卷积神经网络的交通标识识别研究与应用[D].大连:大连理工大学,2014
[14] 陆璐.卷积神经网络的研究及其在车牌识别系统中的应用[D].合肥:合肥工业大学,2006
[15] 赵志宏,杨绍普,马增强.基于卷积神经网络LeNet-5的车牌字符识别研究[J].系统仿真学报,2010(3):638-641

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!