Scribd
Upload
64 views1 page

Deep Learning For Pothole Detection: Exploring YOLO V8 Algorithm's Performance in Pavement Detection

Uploaded by

vishnurajanme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
64 views1 page

Deep Learning For Pothole Detection: Exploring YOLO V8 Algorithm's Performance in Pavement Detection

Uploaded by

vishnurajanme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

IEEE.

org IEEE Xplore IEEE SA IEEE Spectrum More Sites Subscribe Donate Cart Create Account Personal Sign In

Browse  My Settings  Help  Institutional Sign In

All  

ADVANCED SEARCH

Conferences > 2024 International Conference... 

Deep Learning for Pothole Detection: Exploring YOLO V8 Algorithm's Performance


in Pavement Detection
Publisher: IEEE Cite This  PDF

Greeshma K Arun ; Vishnu Rajan ; G.R Gnana King All Authors

19
Full ®  ©  
Text Views

More Like This

Abstract Abstract: Water Quality Monitoring using


Potholes present substantial hazards to both the safety and effectiveness of roads, hence requiring precise methods for Modified Support Vector Machine
Document Sections detection. This paper presents an innovative approach utilizing deep learning techniques, specifically focusing on the YOLO V8 Algorithm in Comparison of
model. We compare four models-YOLO V3, Faster R-CNN, grayscale image with SVM and YOLO V8- on their ability to Accuracy with Artificial Neural
I. Introduction
automatically detect potholes. The study involves collecting and labeling initial images featuring potholes and non-potholes, Network
II. Related Work and Literature followed by training and testing phases to evaluate accuracy and loss using a preprocessed dataset. Analysis reveals the 2023 Second International Conference
On Smart Technologies For Smart
superior performance of the YOLO V8 model, attributed to its speed and reliability in detection, with validated procedures
III. The Proposed YOLOv8 Nation (SmartTechCon)
yielding a remarkable 91% accuracy rate. Notably, our approach demonstrates faster pothole detection times compared to Published: 2023
Algorithm
conventional methods. This research contributes to enhancing road infrastructure management by providing a robust tool for
IV. Result monitoring road surface quality and promptly identifying potholes, thus offering significant potential for improving road safety A System to Monitor Facial
and reducing maintenance expenses. Expression Recognition using
V. Conclusion and Future
Support Vector Machine over
Work
Published in: 2024 International Conference on Data Science and Network Security (ICDSNS) Deep Belief Network Algorithm
2024 15th International Conference on
Authors Computing Communication and
Date of Conference: 26-27 July 2024 DOI: 10.1109/ICDSNS62112.2024.10690953 Networking Technologies (ICCCNT)
Figures Published: 2024
Date Added to IEEE Xplore: 01 October 2024 Publisher: IEEE
References Show More
 ISBN Information: Conference Location: Tiptur, India
Keywords

Metrics I. Introduction
India possesses the second most extensive road network globally, surpassed only by the United States. Driven by recent economic growth, the road
construction industry has witnessed a harmonious integration of maintenance and construction efforts. With substantial government funding
allocated to road repair annually, accurate identification of road surface cracks has become imperative to mitigate maintenance expenses. Road
condition monitoring, or road condition assessments, comprises three primary stages: data collection, identification and classification, and eventually
Sign in to Continue Reading
evaluating the condition of the roads. In developing countries, namely India, the data collecting and road distress identification processes generally
rely on manual methods. Surveyors fill out forms or use specialized vehicles to record road surface photographs, which are then analyzed using
image processing software. These procedures require a substantial commitment in terms of time and labor[1]. Therefore, it is necessary to have
accurate detection to identify the suitable road repair schedule.

Authors 
Figures 
References 
Keywords 
Metrics 

IEEE Personal Account Purchase Details Profile Information Need Help? Follow

CHANGE USERNAME/PASSWORD PAYMENT OPTIONS COMMUNICATIONS PREFERENCES US & CANADA: +1 800 678 4333    
VIEW PURCHASED DOCUMENTS PROFESSION AND EDUCATION WORLDWIDE: +1 732 981 0060

TECHNICAL INTERESTS CONTACT & SUPPORT

About IEEE Xplore | Contact Us | Help | Accessibility | Terms of Use | Nondiscrimination Policy | IEEE Ethics Reporting  | Sitemap | IEEE Privacy Policy
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.

© Copyright 2024 IEEE - All rights reserved, including rights for text and data mining and training of artificial intelligence and similar technologies.

You might also like