Pothole Detection System
Shylee Veronica, Poojashree C, Himangshu Das, Mangesh Thakur Guided by Dr. Mallikarjun K. Director of School of Computing and Information Technology
REVA University
Bengaluru, India
Abstract— The maintenance of the road for daily commute is necessary in order to avoid traffic congestions and accidents.. One of the major causes for road accidents in Indian roads is due to the potholes and humps. Potholes are bowl-shaped openings on the road that can be up to 10 inches in depth and are caused by the wear-and-tear and weathering of the road Hence there is a need for an automated system that is quick, scalable and cost effective for gathering information about road defects. Human intervention checks are performed manually, resulting in poor road maintenance, particularly in villages. In this digital era, it becomes essential to identify and report these potholes to the corresponding authorities in an automated version. We propose a system for road pothole detection using computer vision and deep learning. We make use of YOLO v5 algorithm to identify and detect the potholes from the provided data set. It is a novel convolutional neural network (CNN) that detects objects in real-time with great accuracy. This approach uses a single neural network to process the entire picture, then separates it into parts and predicts bounding boxes and probabilities for each component. These bounding boxes are weighted by the expected probability. The method “just looks once” at the image in the sense that it makes predictions after only one forward propagation run through the neural network. It then delivers detected items after non-max suppression (which ensures that the object detection algorithm only identifies each object once).
Keywords—potholes, intervention, automation, condition, monitoring
I. INTRODUCTION
Road damage not only causes accidents but also affects the drive quality. Frequent encounters with potholes causes vehicle damage as well. Autonomous vehicles have gradually received stronger attention due to its commercial value, but they still have some safety issues, such as hitting potholes . Hitting Potholes can affect driving comfort and increases maintenance costs of vehicles. If the depth of the Potholes is large the rate of accidents is also high. Once the pothole is formed its depth can grow several inches it may cause increase in traffic. Potholes on roads are especially dangerous for drivers when cruising in high speed. Because the driver can hardly see potholes on road surface. Moreover, it can also endanger lives of passengers. According to the report titled Road Accidents in India — 2021, the number of accidents caused by potholes is 3,625 while in 2020 it was 3564.
pothole-detection-system-2
FREE DOWNLOAD
@ engpaper.com published paper
PUBLICATION PROCEDURE WITH US ENGPAPER.COM
ENGPAPER.COM PUBLISHED PAPERS