Simulator-based Dataset Generator for Pothole Detection in Autonomous Driving

View at publisher Summarise with VIRAT
Authors: Yuga Yano, Yukiya Fukuda, Hakaru Tamukoh
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Pothole detection is crucial for autonomous driving. However, the number of images and the quality of the dataset required for training a detection model are insufficient. Therefore, we propose a simulator-based RGB-D dataset generator for pothole detection. To achieve Sim2Real, a smoothing filter was applied to the depth image obtained from the simulator to make it resemble a real depth image.

Fields of Study & Subjects

Infrastructure Maintenance and Monitoring Autonomous Vehicle Technology and Safety Advanced Neural Network Applications

Publication details

Journal / source
CRC Press eBooks
Pages
22–31
Publication date
27 March 2026
Language
EN
Document type
Book chapter