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{178041,
        author = {Kalavala Thirumani and Battula Deepika and Sidhartha Reddy and M Adithya and Shalma H and Dr. M. Ramesh},
        title = {Vision-Based Real-Time Detection of Road Surface Damage and Lane Anomalies for Autonomous Driving Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {3715-3720},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178041},
        abstract = {Autonomous vehicles must perceive their environment accurately to ensure passenger and pedestrian safety. Road damages like potholes pose serious threats to vehicle stability, while clear lane markings are essential for proper navigation. This paper presents a simulated real-time system that integrates deep learning and computer vision techniques for detecting potholes, estimating their distance, detecting lane markings, and taking preventive actions such as autonomous lane switching and human presence alarm triggering. YOLOv8 is employed for object detection tasks, while OpenCV is utilized for lane marking extraction. Monocular depth estimation techniques predict object distance, ensuring that decisions like lane diversion and emergency alarms are executed accurately. Experimental results on recorded videos demonstrate the robustness and reliability of the system in enhancing autonomous driving safety.},
        keywords = {Autonomous vehicles, Deep learning, Computer vision, Monocular depth estimation, Object detection, Real-time road detection.},
        month = {May},
        }