Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186967,
        author = {Divyadharshini V and Divya Sri J and Abinandhini KM and VijayaLakshmi.D.M},
        title = {Speed Breaker and Pothole Detection in Low-Light Conditions ( Deep Learning Approach)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4086-4090},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186967},
        abstract = {Road anomalies such as potholes and speed breakers pose significant risks to vehicle safety and driving comfort, particularly under low-light conditions where visibility is limited. Traditional vision-based detection methods often fail in such environments due to poor illumination and low contrast. This paper presents a deep learning-based approach for real-time detection of potholes and speed breakers using the YOLOv8 (You Only Look Once, version 8) object detection model. The dataset used for training and testing is curated and annotated through Rob flow to ensure compatibility with YOLO formats. To enhance robustness in low-light scenarios, data augmentation techniques from Augmentations, including brightness reduction and Gaussian noise addition, are applied. The trained model is evaluated using standard performance metrics such as precision, recall, and confusion matrices to assess classification accuracy. The proposed system can be deployed in smart vehicles, road-monitoring drones, and intelligent transportation systems to improve road safety and enable proactive infrastructure maintenance.},
        keywords = {Deep Learning, YOLOv8, Pothole Detection, Speed Breaker Detection, Low-Light Conditions.},
        month = {November},
        }