Next Article in Journal
Graphs from Features: Tree-Based Graph Layout for Feature Analysis
Next Article in Special Issue
Experimenting the Automatic Recognition of Non-Conventionalized Units in Sign Language
Previous Article in Journal
Groundwater Prediction Using Machine-Learning Tools
Article

I3D-Shufflenet Based Human Action Recognition

1
School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, China
2
Mechanical & Electrical Engineering Department, Weihai Vocational College, Weihai 264210, China
*
Author to whom correspondence should be addressed.
Algorithms 2020, 13(11), 301; https://doi.org/10.3390/a13110301
Received: 7 October 2020 / Revised: 28 October 2020 / Accepted: 13 November 2020 / Published: 18 November 2020
(This article belongs to the Special Issue Algorithms for Human Gesture, Activity and Mobility Analysis)
In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel of I3D is replaced by a double 3 × 3 convolution kernels, which reduces the amount of calculations. The shuffle layer is adopted to achieve feature exchange. The recognition and classification of human action is performed based on trained I3D-shufflenet model. The experimental results show that the shuffle layer improves the composition of features in each channel which can promote the utilization of useful information. The Histogram of Oriented Gradients (HOG) spatial-temporal features of the object are extracted for training, which can significantly improve the ability of human action expression and reduce the calculation of feature extraction. The I3D-shufflenet is testified on the UCF101 dataset, and compared with other models. The final result shows that the I3D-shufflenet has higher accuracy than the original I3D with an accuracy of 96.4%. View Full-Text
Keywords: action recognition; 3D convolution; I3D neural network; shufflenet action recognition; 3D convolution; I3D neural network; shufflenet
Show Figures

Figure 1

MDPI and ACS Style

Liu, G.; Zhang, C.; Xu, Q.; Cheng, R.; Song, Y.; Yuan, X.; Sun, J. I3D-Shufflenet Based Human Action Recognition. Algorithms 2020, 13, 301. https://doi.org/10.3390/a13110301

AMA Style

Liu G, Zhang C, Xu Q, Cheng R, Song Y, Yuan X, Sun J. I3D-Shufflenet Based Human Action Recognition. Algorithms. 2020; 13(11):301. https://doi.org/10.3390/a13110301

Chicago/Turabian Style

Liu, Guocheng, Caixia Zhang, Qingyang Xu, Ruoshi Cheng, Yong Song, Xianfeng Yuan, and Jie Sun. 2020. "I3D-Shufflenet Based Human Action Recognition" Algorithms 13, no. 11: 301. https://doi.org/10.3390/a13110301

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop