PAVE: Pothole Avoidance and Vision Engine
DOI:
https://doi.org/10.61779/jasetm.v4i1.4Keywords:
pothole detection, traffic signal recognition, YOLOv8, computer vision, deep learning, ADASAbstract
The rapid growth of transportation systems has increased the demand for safer and smarter road infrastructure. Road defects such as potholes and improper recognition of traffic signals are major causes of accidents and traffic inefficiencies. This paper presents PAVE (Pothole Avoidance and Vision Engine), an intelligent system that integrates pothole detection and traffic signal recognition using computer vision and deep learning techniques. The proposed system utilizes a YOLOv8-based model to detect potholes and identify traffic signals such as red and green lights from images and real-time video streams. A dataset consisting of road images is used to train the model for accurate classification and detection. The system enables efficient processing and real-time performance. The integrated approach improves driver awareness by providing timely alerts for road hazards and traffic signals. This enhances road safety, reduces accidents, and supports advanced driver assistance systems (ADAS). Experimental results demonstrate that the system achieves high accuracy and performs effectively in real-time environments.
References
Z. Zhang, B. Shao, L. Yang, and A. Qin, “Improved YOLOv8-CBAM enhanced pothole road recognition-based model,” in Proc. 2024 IEEE 4th Int. Conf. Data Science and Computer Application (ICDSCA), 2024.
Y. Liu, Y. Shi, and X. Yuan, “RCW-YOLO: Improved traffic sign detection model based on YOLOv8 for complex scenes,” in Proc. 2024 9th Int. Conf. Intelligent Informatics and Biomedical Sciences (ICIIBMS), 2024.
“What is YOLOv8: An in-depth exploration of the internal features of the next-generation object detector,” arXiv preprint arXiv:2408.15857v1, 2024.
S. Biswas, S. Acharjee, A. Ali, and S. S. Chaudhari, “YOLOv8 based traffic signal detection in Indian road,” in Proc. 2023 7th Int. Conf. Electronics, Materials Engineering & Nano-Technology (IEMENTech), 2023.
J. Wijaya, I. K. D. W. Kusuma, M. A. Ammaar, and A. A. S. Gunawan, “Enhancing infrastructure monitoring: Pothole detection in road images using YOLOv8 and open datasets,” IEEE, 2024.
“Introduction to convolutional neural networks in deep learning,” Analytics Vidhya, 2022. [Online]. Available: https://www.analyticsvidhya.com/blog/2022/03/basic-introduction-to-convolutional-neural-network-in-deep-learning/
“Potholes-detection-YOLOv8,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/anggadwisunarto/potholes-detection-yolov8
“Traffic signs detection using YOLOv8,” Kaggle. [Online]. Available: https://www.kaggle.com/code/pkdarabi/traffic-signs-detection-using-yolov8
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Bhadra M.U. , Harikrishna K.S., Harikrishnan M.A., Jerin V . Brijesh, Rejusha T.R.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal 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 permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after the acceptance, with an acknowledgement of its initial publication in this journal, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
