Abstract
In vision-based navigation, image-to-image translation systems have been recently proposed to remove the effect of variable road conditions from images, in order to normalize the available data towards a common distribution (e.g. sunny condition). In this context, previous works have proposed image de-raining using generative adversarial networks (GAN) and evaluated performance based on pixel-to-pixel similarity measures that do not account for semantic content relevant for driving. Here, we propose to evaluate the performance of a de-raining GAN using an object detection neural network pretrained to find cars and pedestrians. We conducted experiments on the CARLA simulator to collect training and evaluation data under several weather conditions. Results indicate that GAN de-rained images achieve a high object detection performance in some conditions, but on average lower than object detection on the original rainy images. Future work will concentrate on improving semantic reconstruction and detection of other road elements (e.g. lanes, signs).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Rasshofer, R.H., Gresser, K.G.: Automotive radar and lidar systems for next generation driver assistance functions. Adv. Radio Sci. 3(B. 4), 205–209 (2005)
Wang, C., Xu, C., Wang, C., Tao, D.: Perceptual adversarial networks for image-to-image transformation. IEEE Trans. Image Process. 27(8), 4066–4079 (2018)
Uricár, M., Krízek, P., Hurych, D., Sobh, I., Yogamani, S.: Yes, we GAN: applying adversarial techniques for autonomous driving. arXiv preprint arXiv:1902.03442 (2019)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Dosovitskiy, A., Ros, G., Codevilla, F., López, A., Koltun, V.: CARLA: an open urban driving simulator. arXiv preprint arXiv:1711.03938 (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (2017)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.: SSD: single shot multibox detector. In: European Conference on Computer Vision. Springer, Cham (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Sudo, F., Hashimoto, Y., Lisi, G. (2020). Object Detection to Evaluate Image-to-Image Translation on Different Road Conditions. In: Ahram, T., Karwowski, W., Vergnano, A., Leali, F., Taiar, R. (eds) Intelligent Human Systems Integration 2020. IHSI 2020. Advances in Intelligent Systems and Computing, vol 1131. Springer, Cham. https://doi.org/10.1007/978-3-030-39512-4_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-39512-4_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-39511-7
Online ISBN: 978-3-030-39512-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)