Gesture Recognition using FastDTW and Deep Learning Methods in the MSRC-12 and the NTU RGB+D Databases

Authors

Keywords:

Deep learning, convolutional neural networks, long short-term memory, gated recurrent unit, gesture recognition, FastDTW

Abstract

This work explores the use of three deep learning methods for gesture recognition: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) using Fast Dynamic Time Warping (FastDTW). The gestures were captured by Kinect sensors, two skeleton-based databases are used: Microsoft Research Cambridge-12 (MSRC-12) and NTU RGB+D. Also, the FastDTW technique was also employed to standardize the input size of the data. The MSRC-12 database achieved an accuracy rate of 82,36% in the test set with the CNN, the LSTM achieved an accuracy rate of 87,30% also in the test set, and in GRU the accuracy achieved in the test set was 89,34%. With the NTU RGB+D database, two evaluation methods were used: Cross-View and Cross-Subject. In the test set with Cross-View evaluation was obtained an accuracy rate of 63,53%, 55,14%, and 61,00%, with CNN, LSTM, and GRU respectively; and with the Cross-Subject evaluation method, it was achieved an accuracy rate of 66,19%, 64,43% and 60,17% in the test set on CNN, LSTM and GRU, respectively.

Downloads

Download data is not yet available.

Author Biographies

Júlia Schubert Peixoto, Universidade Federal de Santa Maria, Brazil

Julia Schubert Peixoto has a degree in Control and Automation Engineering from the Universidade Federal de Santa Maria in Brazil (2021). She is currently a Data Scientist at Luizalabs. Her current research interests include robotics, deep learning, computer vision and natural language processing.

Anselmo Rafael Cukla, Universidade Federal de Santa Maria, Brazil

Anselmo Rafael Cukla has a degree in Electrical Engineering from the Universidad Nacional de Misiones in Argentina (2010). He completed Master and PhD in Mechanical Engineering in the Federal University of Rio Grande do Sul
(UFRGS), Brazil (2012 and 2016). He also is PhD in Electrical and Computers Engineering in the FCT (Faculty of Science and Technology) of the UNINOVA (Portugal). He is currently a professor in the Electrical Engineering course
at the Federal University of Santa Maria, RS, Brazil. His research interests include automations, industrial robotics, robotics mobile, optimization algorithms and evolutionary systems.

Marco Antonio de Souza Leite Cuadros, Instituto Federal de Educacao, Ciencia e Tecnologia do Espirito Santo

Marco Antonio de Souza Leite Cuadros received his BSc. Degree in electrical engineering from Universidad Nacional del Centro del Peru (UNCP) in 1998, , and his MSc in electrical Engineering from Universidade Federal do Espirito Santo (UFES) in 2004, and PhD degree in electrical engineering from Universidade Federal do Espírito Santo in 2011.Currently, he is professor of the Instituto Federal do Espeirito Santo (IFES) in Vitoria-Espirito Santo- Brazil.

Daniel Welfer, Universidade Federal de Santa Maria, Brazil

Daniel Welfer Professor at the Department of Applied Computing at Federal University of Santa Maria (UFSM). Currently, he is also a permanent professor at the Graduate Program in Computer Science (PPGC). He works with medical image processing and analysis, software engineering, deep learning and mobile programming.

Daniel Fernando Tello Gamarra, Universidade Federal de Santa Maria (UFSM)

Daniel Fernando Tello Gamarra received his BSc. Degree in mechanical engineering from Universidad Nacional del Centro del Peru (UNCP), in Huancayo, Peru (1999), and his MSc in electrical Engineering from Universidade Federal do Espirito Santo (UFES), in Vitoria, Espirito Santo, Brazil(2004) and PhD degree in Biomedical Robotics from Scuola Superiore Santa Anna, Pisa, Italy (2009). He is Professor at the Universidade Federal de Santa Maria(UFSM), in the Department of Control and Automation in Santa Maria, Rio Grande do Sul, Brazil. His current research interest
centers on robotics, computational vision and machine learning.

References

S. Fothergill, H. M. Mentis, P. Kohli, and S. Nowozin, “Instructing

people for training gestural interactive systems,” Proceedings of the

SIGCHI Conference on Human Factors in Computing Systems, 2012.

A. Shahroudy, J. Liu, T.-T. Ng, and G. Wang, “Ntu rgb+d: A large

scale dataset for 3d human activity analysis,” in 2016 IEEE Conference

on Computer Vision and Pattern Recognition (CVPR), pp. 1010–1019,

S. Salvador and P. Chan, “Fastdtw: Toward accurate dynamic time

warping in linear time and space,” 2004.

K. Simonyan and A. Zisserman, “Very deep convolutional networks

for large-scale image recognition,” in 3rd International Conference on

Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9,

, Conference Track Proceedings (Y. Bengio and Y. LeCun, eds.),

C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov,

D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,”

in 2015 IEEE Conference on Computer Vision and Pattern

Recognition (CVPR), pp. 1–9, June 2015.

M. Pfitscher, D. Welfer, E. J. D. Nascimento, M. A. D. S. L. Cuadros,

and D. F. T. Gamarra, “Article users activity gesture recognition on

kinect sensor using convolutional neural networks and fastdtw for

controlling movements of a mobile robot,” Inteligencia Artif., vol. 22,

no. 63, pp. 121–134, 2019.

J. S. Peixoto, M. Pfitscher, M. A. de Souza Leite Cuadros, D. Welfer,

and D. F. T. Gamarra, “Comparison of different processing methods of

joint coordinates features for gesture recognition with a cnn in the msrc-

database,” in Intelligent Systems Design and Applications, (Cham),

pp. 590–599, Springer International Publishing, 2021.

F. Meng, H. Liu, Y. Liang, M. Liu, and W. Liu, “Hierarchical dropped

convolutional neural network for speed insensitive human action recognition,”

in 2018 IEEE International Conference on Multimedia and Expo

(ICME), pp. 1–6, 2018.

J. Tu, M. Liu, and H. Liu, “Skeleton-based human action recognition

using spatial temporal 3d convolutional neural networks,” in 2018 IEEE

International Conference on Multimedia and Expo (ICME), pp. 1–6,

K. Lai and S. N. Yanushkevich, “Cnn+rnn depth and skeleton based dynamic

hand gesture recognition,” in 2018 24th International Conference

on Pattern Recognition (ICPR), pp. 3451–3456, 2018.

D.-W. Lee, K. Jun, S. Lee, J.-K. Ko, and M. S. Kim, “Abnormal gait

recognition using 3d joint information of multiple kinects system and

rnn-lstm,” in 2019 41st Annual International Conference of the IEEE

Engineering in Medicine and Biology Society (EMBC), pp. 542–545,

P. Molchanov, X. Yang, S. Gupta, K. Kim, S. Tyree, and J. Kautz,

“Online detection and classification of dynamic hand gestures with

recurrent 3d convolutional neural networks,” in 2016 IEEE Conference

on Computer Vision and Pattern Recognition (CVPR), pp. 4207–4215,

Y.-F. Song, Z. Zhang, and L. Wang, “Richly activated graph convolutional

network for action recognition with incomplete skeletons,” in 2019

IEEE International Conference on Image Processing (ICIP), pp. 1–5,

M.-H. Ha and O. T.-C. Chen, “Deep neural networks using capsule

networks and skeleton-based attentions for action recognition,” IEEE

Access, vol. 9, pp. 6164–6178, 2021.

X. Hao, J. Li, Y. Guo, T. Jiang, and M. Yu, “Hypergraph neural network

for skeleton-based action recognition,” IEEE Transactions on Image

Processing, vol. 30, pp. 2263–2275, 2021.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification

with deep convolutional neural networks,” in Advances in Neural Information

Processing Systems (F. Pereira, C. J. C. Burges, L. Bottou, and

K. Q. Weinberger, eds.), vol. 25, Curran Associates, Inc., 2012.

D. Reis, D. Welfer, M. Cuadros, and D. F. Gamarra, “Mobile robot

navigation using an object recognition software with rgbd images and

the yolo algorithm,” Applied Artificial Intelligence, vol. 33, pp. 1–16,

2019.

J. C. Jesus, J. A. Bottega, M. A. S. L. Cuadros, and D. F. T. Gamarra,

“Deep deterministic policy gradient for navigation of mobile robots

in simulated environments,” in 2019 19th International Conference on

Advanced Robotics (ICAR), pp. 362–367, 2019.

V. Phung and E. Rhee, “A deep learning approach for classification of

cloud image patches on small datasets,” Journal of Information and

Communication Convergence Engineering, vol. 16, pp. 173–178, 01

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural

Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

X. Yuan, L. Li, and Y. Wang, “Nonlinear dynamic soft sensor modeling

with supervised long short-term memory network,” IEEE Transactions

on Industrial Informatics, vol. PP, pp. 1–1, 02 2019.

K. Cho, B. van Merriënboer, C. Gulcehre, F. Bougares, H. Schwenk, and

Y. Bengio, “Learning phrase representations using rnn encoder-decoder

for statistical machine translation,” 06 2014.

H. Zhao, Z. Chen, H. Jiang,W. Jing, L. Sun, and M. Feng, “Evaluation of

three deep learning models for early crop classification using sentinel-1a

imagery time series-a case study in zhanjiang, china,” Remote Sensing,

vol. 11, p. 2673, 11 2019.

S. Fothergill, H. Mentis, P. Kohli, and S. Nowozin, “Instructing people

for training gestural interactive systems,” Conference on Human Factors

in Computing Systems - Proceedings, 05 2012

Published

2022-08-22

How to Cite

Peixoto, J. S., Cukla, A. R. ., de Souza Leite Cuadros, M. A. ., Welfer, D., & Tello Gamarra, D. F. (2022). Gesture Recognition using FastDTW and Deep Learning Methods in the MSRC-12 and the NTU RGB+D Databases. IEEE Latin America Transactions, 20(9), 2189–2195. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/6504