The final, formatted version of the article will be published soon.
ORIGINAL RESEARCH article
Front. Neurorobot.
Volume 18 - 2024 |
doi: 10.3389/fnbot.2024.1443678
This article is part of the Research Topic Advancing Neural Network-Based Intelligent Algorithms in Robotics: Challenges, Solutions, and Future Perspectives View all 13 articles
Unmanned Aerial Vehicles for Human detection and Recognition using Neural-Network Model
Provisionally accepted
Yawar Abbas
1
Naif Al Mudawi
2
Bayan Alabdullah
3
Touseef Sadiq
4*
Asaad Algarni
5
Hameedur Rahman
1*
Ahmad Jalal
1*- 1 Air University, Islamabad, Pakistan
- 2 Najran University, Najran, Saudi Arabia
- 3 Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
- 4 University of Agder, Kristiansand, Vest-Agder, Norway
- 5 Northern Border University, Arar, Northern Borders, Saudi Arabia
Recognizing human actions is crucial for allowing machines to understand and recognize human behavior, with applications spanning video based surveillance systems, human-robot collaboration, sports analysis systems, and entertainment. The immense diversity in human movement and appearance poses a significant challenge in this field, especially when dealing with drone-recorded (RGB) videos. Factors such as dynamic backgrounds, motion blur, occlusions, varying video capture angles, and exposure issues greatly complicate recognition tasks. In this study, we suggest a method that addresses these challenges in RGB videos captured by drones. Our approach begins by segmenting the video into individual frames, followed by preprocessing steps applied to these RGB frames. The preprocessing aims to reduce computational costs, optimize image quality, and enhance foreground objects while removing the background. This results in improved visibility of foreground objects while eliminating background noise. Next, we employ the YOLOv9 detection algorithm to identify human bodies within the images. From the grayscale silhouette, we extract the human skeleton and identify 15 important locations, such as the head, neck, shoulders (left and right), elbows, wrists, hips, knees, ankles, and hips (left and right), and belly button. By using all these points, we extract specific positions, angular and distance relationships between them, as well as 3D point clouds and fiducial points. Subsequently, we optimize this data using the kernel discriminant analysis (KDA) optimizer, followed by classification using a deep neural network (CNN). To validate our system, we conducted experiments on three benchmark datasets: UAV-Human, UCF, and Drone-Action. On these datasets, our suggested model produced corresponding action recognition accuracies of 0.68, 0.75, and 0.83.
Keywords: Neural Network, Sequential data processing, Convolutional neural network (CNNs), decision-making processes, unmanned aerial vehicles Neural network, unmanned aerial vehicles
Received: 04 Jun 2024; Accepted: 18 Nov 2024.
Copyright: © 2024 Abbas, Al Mudawi, Alabdullah, Sadiq, Algarni, Rahman and Jalal. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Touseef Sadiq, University of Agder, Kristiansand, 4604, Vest-Agder, Norway
Hameedur Rahman, Air University, Islamabad, Pakistan
Ahmad Jalal, Air University, Islamabad, Pakistan
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.