Detecting Various Road Damage Types in Global Countries Utilizing Faster R-CNN

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

Road damages are of great interest for federal road authorities and their infrastructure management as well as the automated driving task and thus safety and comfort of vehicle occupants. Therefore, we are investigating the automatic detection of different types of road damages by images from a front-facing camera in the vehicle. The data basis of our work is provided by the ’IEEE BigData Cup Challenge’ and its dataset ’RDD-2020’ with a large number of labelled images from Japan, India and the Czech Republic. Our Deep Learning approach utilizes the pre-trained Faster Region Based Convolutional Neural Networks (R-CNN). In the first step, we classify the destination of the image followed by expert networks for each region. Between the explanation of our applied Deep Learning methodology, some remaining sources of errors are discussed and further, partly failed approaches during our development period are displayed, which could be of interest for future work. Our results are convincing and we are able to achieve an F1 score of 0 . 487 across all regions for longitudinal and lateral cracks, alligator cracks and potholes.
OriginalspracheEnglisch
TitelProceedings - 2020 IEEE International Conference on Big Data, Big Data 2020 : Proceedings, Dec 10 - Dec 13, 2020 • Virtual Event
HerausgeberXintao Wu, Chris Jermaine, Li Xiong, Xiaohua Tony Hu, Olivera Kotevska, Siyuan Lu, Weijia Xu, Srinivas Aluru, Chengxiang Zhai, Eyhab Al-Masri, Zhiyuan Chen, Jeff Saltz
Anzahl der Seiten9
ErscheinungsortPiscataway
VerlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Erscheinungsdatum10.12.2020
Seiten5563-5571
Aufsatznummer9378245
ISBN (Print)978-1-7281-6252-2
ISBN (elektronisch)978-1-7281-6251-5
DOIs
PublikationsstatusErschienen - 10.12.2020
VeranstaltungIEEE International Conference on Big Data - BigData2020 - Atlanta, USA / Vereinigte Staaten
Dauer: 10.12.202013.12.2020
https://bigdataieee.org/BigData2020/

DOI