Education, Science, Technology, Innovation and Life
Open Access
Sign In

Action Recognition Based on Kinect Deep Learning

Download as PDF

DOI: 10.23977/jeis.2022.070107 | Downloads: 18 | Views: 614


Wenlu Yang 1, Ying Peng 1, Hong Xie 1


1 College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China

Corresponding Author

Wenlu Yang


With the development of science and technology, human motion recognition technology is widely used in rehabilitation medicine, artificial intelligence, somatosensory games and many other fields. More and more scholars have carried out in-depth research on how to improve the accuracy of human motion recognition.This paper systematically reviews the methods of human motion recognition based on Kinect, summarizes the accuracy of these methods, compares the advantages and disadvantages, summarizes the performance of each method, and provides reasonable suggestions for researchers with different needs.


Action recognition, Kinect, Deep learning


Wenlu Yang, Ying Peng, Hong Xie, Action Recognition Based on Kinect Deep Learning. Journal of Electronics and Information Science (2022) Vol. 7: 43-47. DOI:


[1] Pichao Wang,Wanqing Li,Chuankun Li,et al. Action recognition based on joint trajectory maps with convolutional neural networks[J]. Knowledge-Based Systems,2018.
[2] Yang Zhengyuan,Li Yuncheng,Yang Jianchao,et al. Action recognition with visual attention on skeleton images[C]/ /Proc of the 24th Interna- tional Conference on Pattern Recognition Piscataway,NJ: IEEE Press,2018: 3309-3314.
[3] Wasenmüller O,Stricker D. Comparison of kinect v1 and v2 depth ima- ges in terms of accuracy and precision[C]/ /Proc of Asian Conference on Computer Vision.Berlin: Springer,2016: 34-45.
[4] Anonymous. New All-in-One Mount for Xbox 360 Kinect Sensor,[J]. Multimedia Publisher,2011,22(7).
[5] Tsai Jen Kai,Hsu Chen Chien,Wang Wei Yen,Huang Shao Kang. Deep Learning-Based Real-Time Multiple-Person Action Recognition System.[J].Sensors (Basel, Switzerland),2020,20(17).
[6] Nesrine Grati,Achraf Ben-Hamadou,Mohamed Hammami. Learning local representations for scalable RGB-D face recognition[J]. Expert Systems With Applications,2020,150.
[7] Saranya Rajan,Poongodi Chenniappan,Somasundaram Devaraj, et al. Novel deep learning model for facial expression recognition based on maximum boosted CNN and LSTM[J]. IET Image Processing,2020,14(7).
[8] Lei Wang;Xu Zhao;Yuncai Liu. Skeleton Feature Fusion Based on Multi-Stream LSTM for Action Recognition[J]. IEEE ACCESS, 2018, Vol.6(0):50788-50800.
[9] Wu Qian, Wu Fei, Luo Lizhi. Motion recognition algorithm based on geometric features combined with LSTM network [ J ]. Sensors and microsystems, 2020,39 ( 10 ) : 111-114.
[10] Ji Shuiwang,Yang Ming,Yu Kai. 3D convolutional neural networks for human action recognition.[J]. IEEE transactions on pattern analysis and machine intelligence,2013,35(1).
[11] Shen Xiting, Yu Sheng, Dong Yao, etc. Human action recognition method based on deep learning [ J ]. Computer engineering and design, 2020,41 ( 04 ) : 1153-1157.
[12] Liu Yabin,Yu Jun,Hu Zhiyi. Improved Faster R-CNN Algorithm for Sea Object Detection Under Complex Sea Conditions[J]. International Journal of Advanced Network, Monitoring and Controls,2020,5(2).
[13] Wang Qian, Sun Xiankun, Fan Dongyan. Spatiotemporal feature fusion based on deep learning for human action recognition [ J ]. Sensors and microsystems, 2020,39 ( 10 ) : 35-38.
[14] A. Jeyanthi Suresh;J. Visumathi. Inception ResNet deep transfer learning model for human action recognition using LSTM[J]. Materials Today: Proceedings, 2020, (0)
[15] Varol Gul,Laptev Ivan,Schmid,et al.Long-Term Temporal Convolutions for Action Recognition.[J].IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018, Vol.40(6):1510-1517.
[16] Liu Jun,Shahroudy, Amir, et al. Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition[J]. COMPUTER VISION - ECCV 2016, PT III, 2016, Vol.9907(0):816-833. 
[17] LIU J,WANG G,HU P,et al.Global context-aware attention LSTM networks for 3D action recognition[C]∥2017 IEEE Con- ference on Computer Vision and Pattern Recognition (CVPR),IEEE Computer Society,2017.
[18] Mahshid Majd, Reza Safabakhsh. Correlational Convolutional LSTM for human action recognition[J]. Neurocomputing, 2020, 396.

Downloads: 3253
Visits: 172282

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.