|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Road potholes may seriously harm cars and are a major safety risk for motorists. Roadside potholes can harm automobiles and seriously traffic safety. We suggest applying the You Only Look Once (YOLO) object detection technique to real-time pothole detection. The goal of this project is to develop a YOLO model that can identify potholes in road photos and be used for real-time detection. In recent years, pothole detection in road pictures and videos has demonstrated encouraging results using deep learning algorithms. In this study, we examine the effectiveness of the You Only Look Once (YOLO) object detection algorithm is three different iterations, YOLOv5, YOLOv7, and YOLOv8, for spotting potholes on the road. According to our findings, all three algorithms are capable of identifying potholes, with YOLOv8 reaching the highest level of accuracy.
Keyword
Road Pothole Discovery, Computer Vision, Image Segmentation,YOLO
PDF Download (click here)
|
|
|
|
|