Design of 3D Convolutional Neural Network for Action Recognition for Helping the Aged

LI Xiuzhi; ZHANG Ran; JIA Songmin

doi:10.11936/bjutxb2020040005

Journal of Beijing University of Technology > 2021 > 47(6): 589-597. > DOI: 10.11936/bjutxb2020040005

LI Xiuzhi, ZHANG Ran, JIA Songmin. Design of 3D Convolutional Neural Network for Action Recognition for Helping the Aged[J]. Journal of Beijing University of Technology, 2021, 47(6): 589-597. DOI: 10.11936/bjutxb2020040005

Citation:

PDF (8085 KB)

Design of 3D Convolutional Neural Network for Action Recognition for Helping the Aged

LI Xiuzhi^{1, 2,},
ZHANG Ran^{1, 2},
JIA Songmin¹

1.
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
2.
Engineering Research Center of Digital Community, Ministry of Education, Beijing 100124, China

More Information

Received Date: April 09, 2020
Available Online: August 03, 2022
Published Date: June 09, 2021

Graphical Abstract

Abstract

Abstract

To solve the problem of action recognition in indoor environment, a method for human falling recognition in indoor environment was proposed. First, a lightweight 3D network, which uses grouping convolution and factorization to lighten the network structure for action classification, was proposed. Then 2D subnetworks and lightweight 3D sub-networks were fused to improve behavior recognition network based on the 3D convolution. Finally, visual saliency detection was performed on video frames to improve the accuracy of real scene recognition by enhancing the correlation between background texture and human behavior. Results show that the network's parameter is reduced to 6.9×10⁶ and the floating point of operations is reduced to 6.9×10⁹. The algorithm achieves 81.5% accuracy in the task of indoor fall behavior recognition.
- action recognition,
- fall detection,
- 3D convolution neural network,
- visual saliency,
- factorization of convolution kernal,
- group convolution

FullText(HTML)

References (17)

References

[1]	何颖, 黄艳, 王腾, 等. 社区独居老人智能监控系统的手环设计[J]. 数字技术应用, 2019, 37(10): 163-164, 166. https://www.cnki.com.cn/Article/CJFDTOTAL-SZJT201910091.htm HE Y, HUANG Y, WANG T, et al. Bracelet design of intelligent monitoring system for the elderly living alone in the community[J]. Digital Technology & Application, 2019, 37(10): 163-164, 166. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SZJT201910091.htm
[2]	裴利然, 姜萍萍, 颜国正. 基于支持向量机的跌倒检测算法研究[J]. 光学精密工程, 2017, 25(1): 182-187. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201701024.htm PEI L R, JIANG P P, YAN G Z. Research on fall detection algorithm based on support vector machine[J]. Optics and Precision Engineering, 2017, 25(1): 182-187. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201701024.htm
[3]	米晓萍, 李雪梅. 基于物联网智能的独居老人自动监控方法研究[J]. 计算机仿真, 2014, 31(2): 378-381. doi: 10.3969/j.issn.1006-9348.2014.02.082 MI X P, LI X M. Old people who live alone automatic monitoring method based on IoT intelligence research[J]. Computer Simulation, 2014, 31(2): 378-381. (in Chinese) doi: 10.3969/j.issn.1006-9348.2014.02.082
[4]	张国梁, 贾松敏, 张祥银, 等. 采用自适应变异粒子群优化SVM的行为识别[J]. 光学精密工程, 2017, 25(6): 1669-1678. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201706032.htm ZHANG G L, JIA S M, ZHANG X Y, et al. Adaptive mu-tation particle swarm optimization for SVM behavior recognition[J]. Optics and Precision Engineering, 2017, 25(6): 1669-1678. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201706032.htm
[5]	WANG H, CORDELIA S. Action recognition with improved trajectories[C]//IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 3551-3558.
[6]	SIMONYAN K, ZISSERMAN A. Two-stream convolutional networks for action recognition in videos[J]. Advances in Neural Information Processing Systems, 2014, 27: 568-576 http://dl.acm.org/citation.cfm?id=2968890
[7]	FEICHTENHOFER C, PINZ A, ZISSERMAN A. Convolutional two-stream network fusion for video action recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1933-1941.
[8]	WANG L, XIONG Y, WANG Z, et al. Temporal segment networks: towards good practices for deep action recognition[C]//European Conference on Computer Vision. Berlin: Springer, 2016: 20-36.
[9]	JI S, XU W, YANG M, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 221-231. doi: 10.1109/TPAMI.2012.59
[10]	TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3d convolutional networks[C]//2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 4489-4497.
[11]	CARREIRA J, ZISSERMAN A, QUO V. Action recognition? a new model and the kinetics dataset[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 4724-4733.
[12]	TRAN D, WANG H, TORRESANI L, et al. A closer look at spatiotemporal convolutions for action recognition[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6450-6459.
[13]	XIE S, SUN C, HUANG J, et al. Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification[C]//European Conference on Computer Vision. Berlin: Springer, 2018: 305-321.
[14]	SOOMRO K, ZAMIR A R, SHAH M. UCF101: a dataset of 101 human actions classes from videos in the wild[J/OL]. [2012-01-03]. https://arxiv.org/abs/1212.0402.
[15]	AUVINET E, ROUGIER C, MEUNIER J, et al. Multiple cameras fall dataset[R]. Montreal: DIRO Université de Montréal, 2010.
[16]	WANG W, SHEN J, SHAO L. Video salient object detection via fully convolutional networks[J]. IEEE Transactions on Image Processing, 2017, 27(1): 38-49. http://ieeexplore.ieee.org/document/8047320
[17]	TRAN D, RAY J, SHOU Z, et al. Convnet architecture search for spatiotemporal feature learning[J/OL]. [2017-08-16]. https://arxiv.org/abs/1708.05038.

[1]	MIAO Yang, ZHANG Shuo, CHEN Jun, ZHANG Xiwei, AN Changming, HUANG Zehao, HAN Lei, RAN Dongsheng, LIU Haibin. Review of Medical Images Analysis of Hypopharyngeal Cancer Based on Convolutional Neural Network[J]. Journal of Beijing University of Technology, 2024, 50(7): 883-896. DOI: 10.11936/bjutxb2022110001
[2]	CHEN Shuangye, XU Leiheng, HUANG Chengyi, ZHANG Zhiwu, ZHANG Lin, HAN Mo. Audio Classification of Water Supply Pipeline Leakage Based on MobileNetV3 Convolutional Neural Network[J]. Journal of Beijing University of Technology, 2024, 50(7): 797-804. DOI: 10.11936/bjutxb2022090017
[3]	JI Junzhong, YU Le, LEI Minglong. Brain Disease Classification Method Based on 3D Attention Convolutional Neural Networks and Self-supervised Learning[J]. Journal of Beijing University of Technology, 2024, 50(3): 307-315. DOI: 10.11936/bjutxb2022040001
[4]	RUAN Xiaogang, LI Ang, HUANG Jing. Pose Estimation Method Based on Self-supervised Recurrent Convolutional Neural Networks[J]. Journal of Beijing University of Technology, 2021, 47(12): 1311-1320. DOI: 10.11936/bjutxb2020040001
[5]	HAN Honggui, ZHEN Qi, REN Keyan, WU Xiaolong, DU Yongping, QIAO Junfei. Mobile Phone Model Recognition Method Based on Siamese Convolutional Neural Network[J]. Journal of Beijing University of Technology, 2021, 47(2): 112-119. DOI: 10.11936/bjutxb2019100016
[6]	JI Junzhong, ZHANG Qi. Influence Function-based Convolutional Neural Network for Move Prediction in Go[J]. Journal of Beijing University of Technology, 2019, 45(1): 54-60. DOI: 10.11936/bjutxb2017060053
[7]	LI Jiangeng, LI Lijie, ZHANG Yan, WANG Pengfei, ZUO Guoyu. Method for Training Convolution Neural Network With Multiple Classifiers[J]. Journal of Beijing University of Technology, 2018, 44(10): 1291-1296. DOI: 10.11936/bjutxb2017040029
[8]	JIA Xibin, LI Ning, JIN Ya. Dynamic Convolutional Neural Network Extreme Learning Machine for Text Sentiment Classification[J]. Journal of Beijing University of Technology, 2017, 43(1): 28-35. DOI: 10.11936/bjutxb2016040093
[9]	LI Yujian, SHEN Chengkai, YANG Hongli, HU Haihe. PCA Shuffling Initialization of Convolutional Neural Networks[J]. Journal of Beijing University of Technology, 2017, 43(1): 22-27. DOI: 10.11936/bjutxb2016060070
[10]	SUN Yan-feng, QI Guang-lei, HU Yong-li, ZHAO Lu. Deep Convolution Neural Network Recognition Algorithm Based on Improved Fisher Criterion[J]. Journal of Beijing University of Technology, 2015, 41(6): 835-841. DOI: 10.11936/bjutxb2014110040

Cited By

Cited by

Periodical cited type(1)

王海桥. 未铺装桥面的钢箱拱桥架桥机携梁过桥受力分析. 铁道建筑技术. 2023(02): 148-151+194 .

Other cited types(0)

Get Citation

PDF

XML

Article views (237) PDF downloads (67) Cited by(1)

Turn off MathJax

Article Contents

Abstract

References

Design of 3D Convolutional Neural Network for Action Recognition for Helping the Aged