• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2023, Volume: 16, Issue: 29, Pages: 2190-2197

Original Article

An Enhancement of Deep Positional Attention-Based Human Action Recognition by Using Geometric Positional Features

Received Date:20 February 2023, Accepted Date:20 June 2023, Published Date:03 August 2023


Objective: To learn different geometric features of body joints from video frames, as well as trajectory point coordinates, for Human Activity Recognition (HAR). Methods: Joints and Trajectory-pooled 3D-Deep Geometric Positional Attention-based Hierarchical Bidirectional Recurrent convolutional Descriptors (JTDGPAHBRD)-based HAR framework is proposed. This framework considers the skeleton graph to extract geometric features such as joints, edges, and surfaces, along with the trajectory point coordinates. A new 3D-deep convolutional network with View Conversion (VC) and Temporal Dropout (TD) layers is designed that uses a Positional Attention-based Hierarchical Bidirectional Recurrent Neural Network (PAHBRNN) to learn more discriminatory high-level features. Then, a Fully Connected Layer (FCL) is applied to get the Video Descriptor (VD) of a particular frame. Moreover, the obtained VD is classified by the Support Vector Machine (SVM) classifier to recognize various kinds of human activities. Findings: The test findings show that the JTDGPAHBRD framework using the Penn Action database achieves a recognition rate of 99.7% compared to the existing HAR frameworks. Novelty: This framework has significantly improved the recognition of human activities. Thus, it represents a promising framework for the HAR.

Keywords: Human activity recognition; JTDPAHBRD; Geometric features; View conversion; Temporal dropout; SVM


  1. Weiyao X, Muqing W, Min Z, Ting XZ. Fusion of Skeleton and RGB Features for RGB-D Human Action Recognition. IEEE Sensors Journal. 2021;21(17):19157–19164. Available from: https://doi.10.1109/JSEN.2021.3089705
  2. Muhammad K, Mustaqeem, Ullah A, Imran AS, Sajjad M, Kiran MS, et al. Human action recognition using attention based LSTM network with dilated CNN features. Future Generation Computer Systems. 2021;125:820–830. Available from: https://doi.org/10.1016/j.future.2021.06.045
  3. Khan S, Khan MA, Alhaisoni M, Tariq U, Yong HSS, Armghan A, et al. Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion. Sensors. 2021;21(23):7941. Available from: https://doi.org/10.3390/s21237941
  4. Wang H, Yu B, Xia K, Li J, Zuo X. Skeleton edge motion networks for human action recognition. Neurocomputing. 2021;423:1–12. Available from: https://doi.org/10.1016/j.neucom.2020.10.037
  5. Saleem R, Ahmad T, Aslam M, Martinez-Enriquez AM. An Intelligent Human Activity Recognizer for Visually Impaired People Using VGG-SVM Model. In: Advances in Computational Intelligence. (Vol. 13613, pp. 356-368) Springer Nature Switzerland. 2022.
  6. Yadav SK, Tiwari K, Pandey HM, Akbar SA. Skeleton-based human activity recognition using ConvLSTM and guided feature learning. Soft Computing. 2022;26(2):877–890. Available from: https://doi.10.1007/s00500-021-06238-7
  7. Putra PU, Shima K, Shimatani K. A deep neural network model for multi-view human activity recognition. PLOS ONE. 2022;17(1):e0262181. Available from: https://doi.org/10.1371/journal.pone.0262181
  8. Li J, Xie Z, Wang Z, Lin Z, Lu C, Zhao Z, et al. A triboelectric gait sensor system for human activity recognition and user identification. Nano Energy. 2023;112. Available from: https://doi.org/10.1016/j.nanoen.2023.108473
  9. Nagarathinam S, Narayanan R. Deep Positional Attention-Based Hierarchical Bidirectional RNN with CNN-Based Video Descriptors for Human Action Recognition. International Journal of Intelligent Engineering & Systems. 2022;15(3):406–415. Available from: https://doi:10.22266/ijies2022.0630.34
  10. Srilakshmi N, Radha N. Body Joints and Trajectory Guided 3D Deep Convolutional Descriptors for Human Activity Identification. International Journal of Innovative Technology and Exploring Engineering. 2019;8(12):1016–1021. Available from: https://doi.10.35940/ijitee.K1985.1081219
  11. Srilakshmi N, Radha N. Deep Positional Attention-based Bidirectional RNN with 3D Convolutional Video Descriptors for Human Action Recognition. IOP Conference Series: Materials Science and Engineering. 2021;1022(1):1–10. Available from: https://doi.10.1088/1757-899X/1022/1/012017


© 2023 Srilakshmi & Radha. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.