Open Access iconOpen Access

ARTICLE

crossmark

Human Gait Recognition Based on Sequential Deep Learning and Best Features Selection

Ch Avais Hanif1, Muhammad Ali Mughal1,*, Muhammad Attique Khan2, Usman Tariq3, Ye Jin Kim4, Jae-Hyuk Cha4

1 Department of Electrical Engineering, HITEC University, Taxila, Pakistan
2 Department of Computer Science, HITEC University, Taxila, Pakistan
3 College of Computer Engineering and Science, Prince Sattam Bin Abdulaziz University, Al-Kharaj, 11942, Saudi Arabia
4 Department of Computer Science, Hanyang University, Seoul, 04763, Korea

* Corresponding Author: Muhammad Ali Mughal. Email: email

Computers, Materials & Continua 2023, 75(3), 5123-5140. https://doi.org/10.32604/cmc.2023.038120

Abstract

Gait recognition is an active research area that uses a walking theme to identify the subject correctly. Human Gait Recognition (HGR) is performed without any cooperation from the individual. However, in practice, it remains a challenging task under diverse walking sequences due to the covariant factors such as normal walking and walking with wearing a coat. Researchers, over the years, have worked on successfully identifying subjects using different techniques, but there is still room for improvement in accuracy due to these covariant factors. This paper proposes an automated model-free framework for human gait recognition in this article. There are a few critical steps in the proposed method. Firstly, optical flow-based motion region estimation and dynamic coordinates-based cropping are performed. The second step involves training a fine-tuned pre-trained MobileNetV2 model on both original and optical flow cropped frames; the training has been conducted using static hyperparameters. The third step proposed a fusion technique known as normal distribution serially fusion. In the fourth step, a better optimization algorithm is applied to select the best features, which are then classified using a Bi-Layered neural network. Three publicly available datasets, CASIA A, CASIA B, and CASIA C, were used in the experimental process and obtained average accuracies of 99.6%, 91.6%, and 95.02%, respectively. The proposed framework has achieved improved accuracy compared to the other methods.

Keywords


Cite This Article

APA Style
Hanif, C.A., Mughal, M.A., Khan, M.A., Tariq, U., Kim, Y.J. et al. (2023). Human gait recognition based on sequential deep learning and best features selection. Computers, Materials & Continua, 75(3), 5123-5140. https://doi.org/10.32604/cmc.2023.038120
Vancouver Style
Hanif CA, Mughal MA, Khan MA, Tariq U, Kim YJ, Cha J. Human gait recognition based on sequential deep learning and best features selection. Comput Mater Contin. 2023;75(3):5123-5140 https://doi.org/10.32604/cmc.2023.038120
IEEE Style
C.A. Hanif, M.A. Mughal, M.A. Khan, U. Tariq, Y.J. Kim, and J. Cha "Human Gait Recognition Based on Sequential Deep Learning and Best Features Selection," Comput. Mater. Contin., vol. 75, no. 3, pp. 5123-5140. 2023. https://doi.org/10.32604/cmc.2023.038120



cc 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.
  • 608

    View

  • 361

    Download

  • 0

    Like

Share Link