| Issue |
E3S Web Conf.
Volume 430, 2023
15th International Conference on Materials Processing and Characterization (ICMPC 2023)
|
|
|---|---|---|
| Article Number | 01160 | |
| Number of page(s) | 10 | |
| DOI | https://doi.org/10.1051/e3sconf/202343001160 | |
| Published online | 06 October 2023 | |
Detecting Danger: AI-Enabled Road Crack Detection for Autonomous Vehicles
1 KG Reddy College of Engineering and Technology, Moinabad, Hyderabad, Telangana, 500075, India.
2 IIT Dhanbad, Dhanbad, Jharkhand, 826004, India.
3 Associate Professor, Department of Information Technology, GRIET, Bachupally, Hyderabad, Telangana.
4 Uttaranchal Instiiute of Technology, Uttaranchal University, Dehradun, 248007
* Corresponding author: devnarayan87@gmail.com
The present article proposes the deep learning concept termed ―Faster-Region Convolutional Neural Network‖ (Faster-RCNN) technique to detect cracks on road for autonomous cars. Feature extraction, preprocessing, and classification techniques have been used in this study. Several types of image datasets, such as camera images, faster-RCNN laser images, and real-time images, have been considered. With the help of GPU (graphics processing unit), the input image is processed. Thus, the density of the road is measured and information regarding the classification of road cracks is acquired. This model aims to determine road crack precisely as compared to the existing techniques.
Key words: Deep Learning / Faster-RCNN / GPU / Autonomous Driving / Feature Extraction
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.