Computer vision for asphalt cracks detction using YOLOv5

Kenechukwu Sylvanus Anigbogu 1, *, Samuel Ochai Audu-war 2, Tochukwu Sunday Belonwu 1, Okwuchukwu Ejike Chukwuogo 1 and Emmanuel Chibogu Asogwa 1

1 Department of Computer Sciences, Nnamdi Azikiwe University, Awka, Anambra State, Nigeria.
2 Department of Computer Science, Benue State Polytechnic, Ugbokolo, Benue State, Nigeria.
 
Research Article
International Journal of Science and Research Archive, 2023, 10(01), 163–179.
Article DOI: 10.30574/ijsra.2023.10.1.0693
Publication history: 
Received on 16 July 2023; revised on 03 September 2023; accepted on 06 September 2023
 
Abstract: 
Recent studies have shown that researchers have proposed various techniques for Pothole detection using data collected from different parts of the world. Automating pothole detection will go a long way in providing safe driving for road users and intelligent transportation systems. This is not only necessary to guarantee safe and adequate performance, but also to adjust to the drivers’ needs, potentiate their acceptability, and ultimately meet drivers’ preferences in bad roads. This paper presents a computer vision model that assists drivers by detecting and predicting potholes while on the road to curb road accidents. The datasets used in this research were potholes images extracted from kaggle which were classified into two; potholes and normal roads. The object detection algorithm that was used to evaluate the model is YOLO 5. The results from the parallel testing provided good results in detecting and predicting normal roads and potholes. The predicted values were all positive. The two classifiers were all detected perfectly in while testing without being perverse. The system presents its predicted value in percentage, therefore showing the level of adherence to each of the classes detected.
 
Keywords: 
Safe driving; Object detection; YOLO 5; Asphalt cracks detection
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0