A YOLO-Driven Pedestrian Detection Framework for Vehicle-to-Everything Networks with Enhanced Accuracy
Received: 20 February 2026 | Revised: 13 March 2026, 2 April 2026, 5 April 2026, and 6 April 2026 and | Accepted: 10 April 2026 | Online: 3 June 2026
Corresponding author: Raad Hmmood Afiet
Abstract
Accurate pedestrian detection is a critical requirement for autonomous vehicles to enhance road safety and support intelligent transportation systems. This study presents a pedestrian detection framework designed for Vehicle-to-Everything (V2X) environments, where real-time perception and reliable decision-making are essential. The proposed framework integrates a YOLOv8-based deep learning model with temporal behavior modeling to improve detection performance in dynamic urban scenarios. The model is evaluated using the CityPersons benchmark dataset and standard object detection metrics, including precision, recall, Intersection over Union (IoU), and mean Average Precision (mAP). The experimental results demonstrate that the proposed approach achieves an mAP@0.5 of 0.838, indicating a strong balance between detection accuracy and reliability. Further analysis using precision-confidence and recall-confidence curves shows that the model maintains stable detection performance while reducing false-positive predictions. In addition, a comparative evaluation with established object detection models confirms the effectiveness of the proposed framework for pedestrian detection tasks. The results indicate that the proposed approach improves real-time pedestrian recognition in V2X environments and contributes to enhancing road safety and traffic management in autonomous driving systems.
Keywords:
Vehicle-to-Everything (V2X), autonomous vehicles, pedestrian detection, deep learning, YOLOv8, precision-confidence, recall-confidenceReferences
S. Pang, J. Xue, Q. Tian, and N. Zheng, "Exploiting local linear geometric structure for identifying correct matches," Computer Vision and Image Understanding, vol. 128, pp. 51–64, Nov. 2014.
X. Cao, S. Guo, J. Lin, W. Zhang, and M. Liao, "Online tracking of ants based on deep association metrics: method, dataset and evaluation," Pattern Recognition, vol. 103, July 2020, Art. no. 107233.
Y. Zhang, Y. Jin, J. Chen, S. Kan, Y. Cen, and Q. Cao, "PGAN: Part-Based Nondirect Coupling Embedded GAN for Person Reidentification," IEEE MultiMedia, vol. 27, no. 3, pp. 23–33, July 2020.
C. Han et al., "Re-ID Driven Localization Refinement for Person Search," in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2019, pp. 9813–9822.
S. Anbalagan, P. Srividya, B. Thilaksurya, S. G. Senthivel, G. Suganeshwari, and G. Raja, "Vision-Based Ingenious Lane Departure Warning System for Autonomous Vehicles," Sustainability, vol. 15, no. 4, Feb. 2023.
J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement." arXiv, 2018.
D. R. Kumar and A. Rammohan, "Revolutionizing Intelligent Transportation Systems with Cellular Vehicle-to-Everything (C-V2X) technology: Current trends, use cases, emerging technologies, standardization bodies, industry analytics and future directions," Vehicular Communications, vol. 43, Oct. 2023, Art. no. 100638.
R. Zhang, D. Meng, S. Shen, Z. Zou, H. Li, and H. X. Liu, "MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles." arXiv, 2023.
L. Huang, W. Huang, H. Gong, C. Yu, and Z. You, "PEFNet: Position Enhancement Faster Network for Object Detection in Roadside Perception System," IEEE Access, vol. 11, pp. 73007–73023, 2023.
B. Ghari, A. Tourani, A. Shahbahrami, and G. Gaydadjiev, "Pedestrian detection in low-light conditions: A comprehensive survey," Image and Vision Computing, vol. 148, Aug. 2024, Art. no. 105106.
W. Farhat, O. B. Rhaiem, H. Faiedh, and C. Souani, "Optimized deep learning for pedestrian safety in autonomous vehicles," International Journal of Transportation Science and Technology, Apr. 2025, Art. no. S204604302500053X.
K. L. Masita, A. N. Hasan, and S. Paul, "Pedestrian Detection Using R-CNN Object Detector," in 2018 IEEE Latin American Conference on Computational Intelligence (LA-CCI), Nov. 2018, pp. 1–6.
G. Shariha, M. Elmogy, E. El-Daydamony, and A. Atwan, "Multiple Pedestrian Detection Depending on Faster Region-based Convolutional Neural Network (RCNN)," Mansoura Journal for Computer and Information Sciences, vol. 15, no. 1, pp. 13–20, June 2019.
M. Saeidi and A. Arabsorkhi, "A novel backbone architecture for pedestrian detection based on the human visual system," The Visual Computer, vol. 38, no. 6, pp. 2223–2237, June 2022.
F. Sultana, A. Sufian, and P. Dutta, "A Review of Object Detection Models Based on Convolutional Neural Network," in Intelligent Computing: Image Processing Based Applications, vol. 1157, J. K. Mandal and S. Banerjee, Eds. Springer Singapore, 2020, pp. 1–16.
V. Teju, K. V. Sowmya, S. R. Kandula, A. Stan, and O. P. Stan, "A Hybrid Retina Net Classifier for Thermal Imaging," Applied Sciences, vol. 13, no. 14, July 2023, Art. no. 8525.
K. Wang and W. Zhou, "Pedestrian and cyclist detection based on deep neural network fast R-CNN," International Journal of Advanced Robotic Systems, vol. 16, no. 2, Mar. 2019, Art. no. 1729881419829651.
Y. Xue, Z. Ju, Y. Li, and W. Zhang, "MAF-YOLO: Multi-modal attention fusion based YOLO for pedestrian detection," Infrared Physics & Technology, vol. 118, Nov. 2021, Art. no. 103906.
S. Zhang, R. Benenson, and B. Schiele, "CityPersons: A Diverse Dataset for Pedestrian Detection," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, pp. 4457–4465.
B. Paranjape, A. Naik, and S. P. Sankar, "A Performance Comparison of Object Detection Algorithms on Traffic Scenes in Indian Roads," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25492–25498, Aug. 2025.
"Cityscapes Dataset – Semantic Understanding of Urban Street Scenes," Oct. 17, 2020. https://www.cityscapes-dataset.com/.
Downloads
How to Cite
License
Copyright (c) 2026 Syahid Anuar, Raad Hmmood Afiet
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
