Bridging the Gap between Real and Synthetic Traffic Sign Repositories

Diogo Lopes da Silva, António Fernandes

2022

Abstract

Current traffic sign image repositories for classification purposes suffer from scarcity of samples due to the compiling and labelling images being mainly a manual process. Thus, researchers resort to alternative approaches to deal with this issue, such as increasing the model architectural complexity or performing data augmentation. A third approach is the usage of synthetic data. This work addresses the data shortage issue by building a synthetic repository proposing a pipeline to build synthetic samples introducing previously unused image operators. Three use cases for synthetic data usage are explored: as a standalone training set, merging with real data, and ensembling. The first option provides results that not only clearly surpass any previous attempt on using synthetic data for traffic sign recognition but are also encouragingly placing the obtained accuracies closer to results with real images. Merging real and synthetic data in a single data set further improves those results. Due to the different nature of the datasets involved, ensembling provides a boost in accuracy results. Overall we got results in three different datasets that surpass previous state of the art results: GTSRB (99:85%), BTSC (99:76%), and rMASTIF (99:84%). Finally, cross testing amongst the three datasets hints that our synthetic datasets have the potential to provide better generalization ability than using real data.

Paper Citation

in Harvard Style

Lopes da Silva D. and Fernandes A. (2022). Bridging the Gap between Real and Synthetic Traffic Sign Repositories. In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-584-5, pages 44-54. DOI: 10.5220/0011301100003277

in Bibtex Style

@conference{delta22,
author={Diogo Lopes da Silva and António Fernandes},
title={Bridging the Gap between Real and Synthetic Traffic Sign Repositories},
booktitle={Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2022},
pages={44-54},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011301100003277},
isbn={978-989-758-584-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - Bridging the Gap between Real and Synthetic Traffic Sign Repositories
SN - 978-989-758-584-5
AU - Lopes da Silva D.
AU - Fernandes A.
PY - 2022
SP - 44
EP - 54
DO - 10.5220/0011301100003277