Precise Human Activity Recognition using Convolutional Neural Network and Deep Learning Models

Authors

  • Harshavardhan Patil Dept. of Artificial Intelligence and Data Science, PES’s Modern College of Engineering, India https://orcid.org/0009-0002-8807-9528
  • Priti Malkhede Dept. of Artificial Intelligence and Data Science, PES’s Modern College of Engineering, India
  • Shreyash Madake Dept. of Artificial Intelligence and Data Science, PES’s Modern College of Engineering, India
  • Ashutosh Kokate Dept. of Artificial Intelligence and Data Science, PES’s Modern College of Engineering, India
  • Yash Bhandure Dept. of Artificial Intelligence and Data Science, PES’s Modern College of Engineering, India

DOI:

https://doi.org/10.26438/ijcse/v12i7.2432

Keywords:

Convolutional Neural Network, Human Activity Recognition, UCF50 Dataset, Data Preprocessing, Frame Extraction, Model Architecture, Feature Extraction

Abstract

Human Activity Recognition (HAR) plays a pivotal role in various domains, ranging from healthcare to surveillance and robotics. This paper offers a comprehensive detail of Convolutional Neural Network (CNN)-based methodologies in HAR, emphasizing their efficiency in accurately recognizing human activities from video data. We used the UCF50 dataset, which contains videos of 50 different human activities, making it a suitable benchmark for evaluating CNN-based HAR models. The study investigates the utilization of CNNs for feature extraction and classification in HAR, focusing on techniques such as frame extraction, data preprocessing, and model architectures. Detailed analysis of convolutional layers, pooling layers, and activation functions within CNNs showcases their ability to capture intricate spatial and temporal features. The research also delves into the benefits of data augmentation and normalization in enhancing model performance and generalization. The findings highlight the significant advantages of CNNs in capturing spatial information and improving accuracy in HAR tasks, making them highly effective for real-world applications across various domains.

References

[1] X. Liang, H. -B. Zhang, Y. -X. Zhang and J. -L. Huang, "JTCR: Joint Trajectory Character Recognition for human action recognition," 2019 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), Yunlin, Taiwan, pp.350-353, 2019.

[2] R. R. Koli and T. I. Bagban, "Human Action Recognition Using Deep Neural Networks," 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4), London, UK, pp.376-380, 2020.

[3] W. Ma and S. Liang, "Human-Object Relation Network For Action Recognition In Still Images," 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK, pp.1-6, 2020.

[4] M. M. Hossain Shuvo, N. Ahmed, K. Nouduri and K. Palaniappan, "A Hybrid Approach for Human Activity Recognition with Support Vector Machine and 1D Convolutional Neural Network," 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington DC, DC, USA, pp.1-5, 2020.

[5] D. R. Beddiar and B. Nini, "Vision based abnormal human activities recognition: An overview," 2017 8th International Conference on Information Technology (ICIT), Amman, Jordan, pp.548-553, 2017.

[6] A. M. F and S. Singh, "Computer Vision-based Survey on Human Activity Recognition System, Challenges and Applications," 2021 3rd International Conference on Signal Processing and Communication (ICPSC), Coimbatore, India, pp.110-114, 2021.

[7] K. Raja, I. Laptev, P. Pérez and L. Oisel, "Joint pose estimation and action recognition in image graphs," 2011 18th IEEE International Conference on Image Processing, Brussels, Belgium, 2011.

[8] H. Nishimura, Y. Ozasa, Y. Ariki and M. Nakano, "Object Recognition by Integrated Information Using Web Images," 2013 2nd IAPR Asian Conference on Pattern Recognition, Naha, Japan, pp.657-661, 2013.

[9] C. Wang, "A learning-based human facial image quality evaluation method in video-based face recognition systems," 2017 3rd IEEE International Conference on Computer and Communications (ICCC), Chengdu, China, pp.1632-1636, 2017.

[10] D. Meng, X. Peng, K. Wang and Y. Qiao, "Frame Attention Networks for Facial Expression Recognition in Videos," 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, pp.3866-3870, 2019.

[11] Souradeep Ghosh, "Proposal of a Real-time American Sign Language Detector using MediaPipe and Recurrent Neural Network", International Journal of Computer Sciences and Engineering, Vol.9, Issue.7, pp.46-52, 2021.

[12] Chalavadi Sravanth, Gadde Harshavardhan, Kamineni. Kavya, Shaik Mohammad Akbar, Ch.M.H. Sai Baba, "Real-Time Human Detection in Video Surveillance", International Journal of Computer Sciences and Engineering, Vol.9, Issue.1, pp.44-50, 2021.

Downloads

Published

2024-07-31
CITATION
DOI: 10.26438/ijcse/v12i7.2432
Published: 2024-07-31

How to Cite

[1]
H. Patil, P. Malkhede, S. Madake, A. Kokate, and Y. Bhandure, “Precise Human Activity Recognition using Convolutional Neural Network and Deep Learning Models”, Int. J. Comp. Sci. Eng., vol. 12, no. 7, pp. 24–32, Jul. 2024.

Issue

Vol. 12 No. 7 (2024): IJCSE July Edition

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.