Copyright © 2025 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{167591,
        author = {Miss. Vidya Ambi and Prof.V.M.Chandode and Prof. S.V.Kulkarni},
        title = {AFFORDABLE POTHOLE DETECTION AND REPORTING SYSTEM FOR LOCAL ROAD SAFETY USING MACHINE LEARNING AND ANDROID INTEGRATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {1645-1653},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167591},
        abstract = {The deterioration of road quality due to potholes poses significant challenges to road safety, particularly in developing countries like India. Existing solutions for pothole detection often require expensive equipment or sophisticated smartphones, making them inaccessible to local cab drivers and other low-income road users. This paper presents an affordable, portable system that integrates machine learning and Android technology to automatically detect and report potholes in real-time. The proposed system utilizes DenseNet121, a convolutional neural network (CNN) model, to analyze images captured by a simple camera mounted on a moving vehicle. The system processes these images to detect potholes with high accuracy and promptly reports the location of detected potholes to a centralized server. This data is then used to suggest safer and more comfortable routes for drivers. Our solution is designed to be cost-effective, making it accessible to a broader user base. Field tests on real roads demonstrate the system’s efficacy in enhancing road safety and providing actionable insights for infrastructure maintenance.},
        keywords = {Pothole Detection, Road Safety, Machine Learning, DenseNet121, Android Integration, Image Processing, Affordable Technology, Real-time Reporting, Infrastructure Maintenance, CNN (Convolutional Neural Network).},
        month = {September},
        }