Context-aware Training Image Synthesis for Traffic Sign Recognition

Akira Sekizawa, Katsuto Nakajima

2019

Abstract

In this paper, we propose a method for training traffic sign detectors without using actual images of the traffic signs. The method involves using training images of road scenes that were synthetically generated to train a deep-learning based end-to-end traffic sign detector (which includes detection and classification). Conventional methods for generating training data mostly focus only on producing small images of the traffic sign alone and cannot be used for generating images for training end-to-end traffic sign detectors, which use images of the overall scenes as the training data. In this paper, we propose a method for synthetically generating road scenes to use as the training data for end-to-end traffic sign detectors. We also show that considering the context information of the surroundings of the traffic signs when generating scenes is effective for improving the precision.

Paper Citation

in Harvard Style

Sekizawa A. and Nakajima K. (2019). Context-aware Training Image Synthesis for Traffic Sign Recognition. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 466-473. DOI: 10.5220/0007387904660473

in Bibtex Style

@conference{visapp19,
author={Akira Sekizawa and Katsuto Nakajima},
title={Context-aware Training Image Synthesis for Traffic Sign Recognition},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={466-473},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007387904660473},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Context-aware Training Image Synthesis for Traffic Sign Recognition
SN - 978-989-758-354-4
AU - Sekizawa A.
AU - Nakajima K.
PY - 2019
SP - 466
EP - 473
DO - 10.5220/0007387904660473
PB - SciTePress