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{158581,
        author = {Anand Upadhyay and Bhavana Mishra and Aditi Singh and Aradhana Pal},
        title = {Comparative Study of Pothole Recognition Using CNN and YOLOV5},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {10},
        pages = {244-250},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=158581},
        abstract = {Methods for recognizing potholes on roadsides goal is to evolve plans for real-time or else offline proof of identity potholes, to support real-time resistor of a vehicle (for driver help or independent driving) or else offline data gathering for road preservation. [1]It causes accidents in very high numbers. Therefore, it is a need to carry out timely inspection and maintenance to avoid the problem for road users. This paper projected a deep learning-based model that can perceive potholes initially using images, which can decrease the probability of a fortune. This model is mostly based on Convolutional Neural Network(CNN) and YOLOV5 [2]. The project can reduce the manpower for the maintenance of the roads. This project will be useful for the government for better road maintenance with less manpower in a small period. The Accuracy for the same with image processing techniques such as CNN and YOLO. using this approach, it was possible to detect potholes with an accuracy of 88% and 95% respectively.},
        keywords = {Deep learning, Pothole Detection, CNN YOLO, Image processing, TensorFlow.},
        month = {},
        }