Vol.63, No.3, 2020, pp.1081-1091, doi:10.32604/cmc.2020.09648
OPEN ACCESS
ARTICLE
3-Dimensional Bag of Visual Words Framework on Action Recognition
  • Shiqi Wang1, Yimin Yang1, *, Ruizhong Wei1, Qingming Jonathan Wu2
1 Department of Computer Science, Lakehead University, Thunder Bay, Canada.
2 Department of Electrical and Computer Engineering, University of Windsor, Windsor, Canada.
* Corresponding Author: Yimin Yang. Email: .
Received 13 January 2020; Accepted 26 March 2020; Issue published 30 April 2020
Abstract
Human motion recognition plays a crucial role in the video analysis framework. However, a given video may contain a variety of noises, such as an unstable background and redundant actions, that are completely different from the key actions. These noises pose a great challenge to human motion recognition. To solve this problem, we propose a new method based on the 3-Dimensional (3D) Bag of Visual Words (BoVW) framework. Our method includes two parts: The first part is the video action feature extractor, which can identify key actions by analyzing action features. In the video action encoder, by analyzing the action characteristics of a given video, we use the deep 3D CNN pre-trained model to obtain expressive coding information. A classifier with subnetwork nodes is used for the final classification. The extensive experiments demonstrate that our method leads to an impressive effect on complex video analysis. Our approach achieves state-of-the-art performance on the datasets of UCF101 (85.3%) and HMDB51 (54.5%).
Keywords
Action recognition, 3D CNNs, recurrent neural networks, residual networks, subnetwork nodes.
Cite This Article
. , "3-dimensional bag of visual words framework on action recognition," Computers, Materials & Continua, vol. 63, no.3, pp. 1081–1091, 2020.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.