Abstract
A moving robot or moving camera causes motion blur in the robot’s vision and distorts recorded images. We show that motion blur, differing lighting, and other distortions heavily affect the object localization performance of deep learning architectures for RoboCup Humanoid Soccer scenes. The paper proposes deep conditional generative models to apply visual noise filtering. Instead of generating new samples for a specific domain our model is constrained by reconstructing RoboCup soccer images. The conditional DCGAN (deep convolutional generative adversarial network) works semi-supervised. Thus there is no need for labeled training data. We show that object localization architectures significantly drop in accuracy when supplied with noisy input data and that our proposed model can significantly increase the accuracy again.
Keywords
- TensorFlow
- Neural networks
- DCGAN
- GAN
- De-noising
- RoboCup
- Robotics
This is a preview of subscription content, access via your institution.
Buying options
References
Aitken, A., Ledig, C., Theis, L., Caballero, J., Wang, Z., Shi, W.: Checkerboard artifact free sub-pixel convolution: a note on sub-pixel convolution, resize convolution and convolution resize, July 2017. http://arxiv.org/abs/1707.02937
Dahl, R., Norouzi, M., Shlens, J.: Pixel recursive super resolution. arXiv preprint arXiv:1702.00783 (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680 (2014). http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf
Karpathy, A., Leung, T.: Large-scale video classification with convolutional neural networks. In: Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725–1732 (2014). https://doi.org/10.1109/CVPR.2014.223
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances In Neural Information Processing Systems, pp. 1–9 (2012)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network, September 2016. http://arxiv.org/abs/1609.04802
Mishkin, D., Sergievskiy, N., Matas, J.: Systematic evaluation of CNN advances on the ImageNet, June 2016. http://arxiv.org/abs/1606.02228
Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Drill 1(10), 1–14 (2016). https://doi.org/10.23915/distill.00003
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, pp. 1–16 (2016)
Szegedy, C., Reed, S., Sermanet, P., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions, pp. 1–12 (2014)
Zhang, H., Sindagi, V., Patel, V.M.: Image de-raining using a conditional generative adversarial network. arXiv preprint arXiv:1701.05957, pp. 1–13 (2017)
Acknowledgements
We are grateful to the NVIDIA corporation for supporting our research through the NVIDIA GPU Grant Program (https://developer.nvidia.com/academic_gpu_seeding). We used the donated NVIDIA Titan X (Pascal) to train our models. The work was made in collaboration with the TRR 169 “Crossmodal Learning”, funded by the DFG.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Speck, D., Barros, P., Wermter, S. (2018). De-noise-GAN: De-noising Images to Improve RoboCup Soccer Ball Detection. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11141. Springer, Cham. https://doi.org/10.1007/978-3-030-01424-7_72
Download citation
DOI: https://doi.org/10.1007/978-3-030-01424-7_72
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01423-0
Online ISBN: 978-3-030-01424-7
eBook Packages: Computer ScienceComputer Science (R0)