Advancing Real-Time Pedestrian Behavior Analysis at Zebra Crossings with Transfer Learning and Pre-trained Model
Advancing Real-Time Pedestrian Behavior Analysis at Zebra Crossings with Transfer Learning and Pre-trained Model |
||
 |
 |
|
| © 2024 by IJETT Journal | ||
| Volume-72 Issue-6 |
||
| Year of Publication : 2024 | ||
| Author : Pannalal Boda, Y. Ramadevi |
||
| DOI : 10.14445/22315381/IJETT-V72I6P105 | ||
How to Cite?
Pannalal Boda, Y. Ramadevi, "Advancing Real-Time Pedestrian Behavior Analysis at Zebra Crossings with Transfer Learning and Pre-trained Model," International Journal of Engineering Trends and Technology, vol. 72, no. 6, pp. 39-56, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I6P105
Abstract
This paper introduces the Predictive Pedestrian Analytics for Safety Enhancement (PPASE) framework, aimed at enhancing real-time pedestrian behavior analysis at zebra crossings to improve urban traffic safety and facilitate the integration of autonomous vehicles. Addressing limitations in real-time applicability, accuracy under diverse conditions, and scalability of current methodologies, the PPASE utilizes transfer learning and pre-trained models tailored for pedestrian behavior. Leveraging the Pedestrian Intention Estimation (PIE) dataset, enriched with real-time urban traffic data, the framework offers refined predictions of pedestrian movements. Performance is rigorously evaluated using accuracy, precision, recall, and F1 score, with the PPASE demonstrating commendable overall accuracy of 92.5% in pedestrian crossing predictions, 89.4% in movement pattern identification, and 93.7% in group dynamics analysis. These quantitative results highlight the framework’s potential to significantly mitigate incidents at zebra crossings and improve crowd management in urban settings, affirming its efficacy as an advanced tool for enhancing pedestrian safety within intelligent urban traffic systems.
Keywords
Pedestrian Behavior Analysis, Urban Traffic Safety, Autonomous vehicles, Real-Time Prediction, Group dynamics.
References
[1] Mohan Manubhai Trivedi, Tarak Gandhi, and Joel McCall, “Looking-in and Looking-Out of a Vehicle: Computer-Vision-Based Enhanced Vehicle Safety,” IEEE Transactions on Intelligent Transportation Systems, vol. 8, no. 1, pp. 108-120, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Antonio Brunett et al., “Computer Vision and Deep Learning Techniques for Pedestrian Detection and Tracking: A Survey,” Neurocomputing, vol. 300, pp. 17-33, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[3] M. Bhavsingh, and B. Pannalal, “Review: Pedestrian Behavior Analysis and Trajectory Prediction with Deep Learning,” International Journal of Computer Engineering in Research Trends, vol. 9, no. 12, pp. 263-268, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Sushma Jaiswal et al., “Exploring a Spectrum of Deep Learning Models for Automated Image Captioning: A Comprehensive Survey," International Journal of Computer Engineering in Research Trends, vol. 10, no. 12, pp. 1-11, 2023.
[CrossRef] [Publisher Link]
[5] Sushma Jaiswal et al., “Stylistic Image Captioning with Adversarial Learning: A Novel Approach,” International Journal of Computer Engineering in Research Trends, vol. 11, no. 1, pp. 1-8, 2024.
[CrossRef] [Publisher Link]
[6] J. Lampkins, Z. Huang, and Radwan, “Multimodal Perception for Dynamic Traffic Sign Understanding in Autonomous Driving,” Frontiers in Collaborative Research, vol. 1, no. 1, pp. 22-34, 2023.
[Publisher Link]
[7] Daniel Parra-Ovalle, Carme Miralles-Guasch, and Oriol Marquet, “Pedestrian Street Behavior Mapping using Unmanned Aerial Vehicles. A Case Study in Santiago De Chile,” PLoS ONE, vol. 18, no. 3, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Taylor Li et al., “Pedestrian Behavior Study to Advance Pedestrian Safety in Smart Transportation Systems Using Innovative LiDAR Sensors,” 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Pannalal Boda, Y. Ramadevi, and M. Bhavsingh, “Leveraging Pre-Trained Vision for Enhanced Real Time Pedestrian Behavior Prediction at Zebra Crossings,” Frontiers in Collaborative Research, vol. 1, no. 2, pp. 10–21, 2023.
[Publisher Link]
[10] Christian Brynning, A. Schirrer, and S. Jakubek, “Transfer Learning for Agile Pedestrian Dynamics Analysis: Enabling Real-Time Safety at Zebra Crossings,” Synthesis: A Multidisciplinary Research Journal, vol. 1, no. 1, pp. 22-31, 2023.
[Publisher Link]
[11] Jun Yang et al., “Pedestrian Behavior Interpretation from Pose Estimation,” IEEE International Intelligent Transportation Systems Conference, Indianapolis, IN, USA, pp. 3110-3115, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Amir Rasouli, and Iuliia Kotseruba, “Pedformer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning,” IEEE International Conference on Robotics and Automation, London, United Kingdom, pp. 9844-9851, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Chi Zhang, and Christian Berger, “Pedestrian Behavior Prediction Using Deep Learning Methods for Urban Scenarios: A Review,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 10, pp. 10279-10301, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Shrutika Deokar, and Shridhar Khandekar, “Identification of Pedestrian Movement and Classification Using Deep Learning for Advanced Driver Assistance System,” International Conference on Augmented Intelligence and Sustainable Systems, pp. 374-381, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ahmed Alhomoud et al., “Augmenting Real-Time Surveillance with EfficientDet a Leap Towards Scalable and Accurate Object Detection,” International Journal of Computer Engineering in Research Trends, vol. 11, no. 2, pp. 9-17, 2024.
[CrossRef] [Publisher Link]
[16] Sheng-Chih Ho et al., “A Traffic Crash Warning Model for BOT E-Tolling Operations Based on Predictions Using a Data Association Framework,” Applied Science, vol. 13, no. 10, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Amirhossein Abdi, Seyedehsan Seyedabrishami, and Steve O’Hern, “A Two-Stage Sequential Framework for Traffic Accident Post-Impact Prediction Utilizing Real-Time Traffic, Weather, and Accident Data,” Journal of Advanced Transportation, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] B. Pannalal, M. Bhavsingh, and Y. Ramadevi, “Enhancing Zebra Crossing Safety with Edge-Enabled Deep Learning for Pedestrian Dynamics Prediction,” International Journal of Computer Engineering in Research Trends, vol. 10, no. 10, pp. 71-79, Oct. 2023.
[CrossRef] [Publisher Link]
[19] Liping Bao et al., “Learning Transferable Pedestrian Representation from Multimodal Information Supervision,” arXiv preprint arXiv:2304.05554, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Qi Zhang et al., “An Integrated Framework for Real-Time Intelligent Traffic Management of Smart Highways,” Journal of Transportation Engineering, Part A: Systems, vol. 149, no. 7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jia Huang, Alvika Gautam, and Srikanth Saripalli, “Learning Pedestrian Actions to Ensure Safe Autonomous Driving,” IEEE Intelligent Vehicles Symposium (IV), Anchorage, AK, USA, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Yuxuan Wu et al., “Multi-Stream Representation Learning for Pedestrian Trajectory Prediction,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 3, pp. 2875-2882, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Ling Zhao et al., “T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 9, pp. 3848-3858, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Hao Xue, Du Q. Huynh, Mark Reynolds, “Bi-Prediction: Pedestrian Trajectory Prediction Based on Bidirectional LSTM Classification,” International Conference on Digital Image Computing: Techniques and Applications, pp. 1-8, 2017.
[CrossRef] [Google Scholar] [Publisher Link]