Abstract
Detecting the field boundary is often one of the first steps in the vision pipeline of soccer robots. Conventional methods make use of a (possibly adaptive) green classifier, selection of boundary points and possibly model fitting. We present an approach to predict the coordinates of the field boundary column-wise in the image using a convolutional neural network. This is combined with a method to let the network predict the uncertainty of its output, which allows to fit a line model in which columns are weighted according to the network’s confidence. Experiments show that the resulting models are accurate enough in different lighting conditions as well as real-time capable. Code and data are available online (https://github.com/bhuman/DeepFieldBoundary, https://sibylle.informatik.uni-bremen.de/public/datasets/fieldboundary).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The optimization for the combination without uncertainty, grayscale, \(N=16\) stopped after only 9 epochs.
References
Blumenkamp, J., Baude, A., Laue, T.: Closing the reality gap with unsupervised sim-to-real image translation for semantic segmentation in robot soccer (2019). https://arxiv.org/abs/1911.01529
Dosovitskiy, A., et al.: An image is worth \(16\times 16\) words: transformers for image recognition at scale (2020). https://arxiv.org/abs/2010.11929
Dozat, T.: Incorporating Nesterov momentum into Adam. In: ICLR Workshop (2016)
Fiedler, N., Brandt, H., Gutsche, J., Vahl, F., Hagge, J., Bestmann, M.: An open source vision pipeline approach for RoboCup humanoid soccer. In: Chalup, S., Niemueller, T., Suthakorn, J., Williams, M.-A. (eds.) RoboCup 2019. LNCS (LNAI), vol. 11531, pp. 376–386. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-35699-6_29
Hess, T., Mundt, M., Weis, T., Ramesh, V.: Large-scale stochastic scene generation and semantic annotation for deep convolutional neural network training in the RoboCup SPL. In: Akiyama, H., Obst, O., Sammut, C., Tonidandel, F. (eds.) RoboCup 2017. LNCS (LNAI), vol. 11175, pp. 33–44. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00308-1_3
Jung, A.B., et al.: imgaug (2020). https://github.com/aleju/imgaug
Mahmoudi, H., et al.: MRL team description paper for humanoid KidSize league of RoboCup 2019. Technical report, Mechatronics Research Lab, Qazvin Islamic Azad University (2019)
Qian, Y., Lee, D.D.: Adaptive field detection and localization in robot soccer. In: Behnke, S., Sheh, R., Sarıel, S., Lee, D.D. (eds.) RoboCup 2016. LNCS (LNAI), vol. 9776, pp. 218–229. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68792-6_18
Reinhardt, T.: Kalibrierungsfreie Bildverarbeitungsalgorithmen zur echtzeitfähigen Objekterkennung im Roboterfußball. Master’s thesis, Hochschule für Technik, Wirtschaft und Kultur Leipzig (2011)
Richter-Klug, J., Frese, U.: Towards Meaningful uncertainty information for CNN based 6d pose estimates. In: Tzovaras, D., Giakoumis, D., Vincze, M., Argyros, A. (eds.) ICVS 2019. LNCS, vol. 11754, pp. 408–422. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34995-0_37
Rodriguez, D., et al.: RoboCup 2019 AdultSize winner NimbRo: deep learning perception, in-walk kick, push recovery, and team play capabilities. In: Chalup, S., Niemueller, T., Suthakorn, J., Williams, M.-A. (eds.) RoboCup 2019. LNCS (LNAI), vol. 11531, pp. 631–645. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-35699-6_51
Schnekenburger, F., Scharffenberg, M., Wülker, M., Hochberg, U., Dorer, K.: Detection and localization of features on a soccer field with feedforward fully convolutional neural networks (FCNN) for the adult-size humanoid robot Sweaty. In: Proceedings of the 12th Workshop on Humanoid Soccer Robots, IEEE-RAS International Conference on Humanoid Robots. Birmingham (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception architecture for computer vision (2015). https://arxiv.org/abs/1512.00567v3
Thielke, F., Hasselbring, A.: A JIT compiler for neural network inference. In: Chalup, S., Niemueller, T., Suthakorn, J., Williams, M.-A. (eds.) RoboCup 2019. LNCS (LNAI), vol. 11531, pp. 448–456. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-35699-6_36
Tilgner, R., et al.: Nao-Team HTWK team research report. Technical report, Hochschule für Technik, Wirtschaft und Kultur Leipzig (2020)
Acknowledgements
This work is partially funded by the German BMBF - Bundesministerium für Bildung und Forschung project Fast&Slow (FKZ 01IS19072). Furthermore, the authors would like to thank the past and current members of the team B-Human for developing the software base for this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Hasselbring, A., Baude, A. (2022). Soccer Field Boundary Detection Using Convolutional Neural Networks. In: Alami, R., Biswas, J., Cakmak, M., Obst, O. (eds) RoboCup 2021: Robot World Cup XXIV. RoboCup 2021. Lecture Notes in Computer Science(), vol 13132. Springer, Cham. https://doi.org/10.1007/978-3-030-98682-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-98682-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98681-0
Online ISBN: 978-3-030-98682-7
eBook Packages: Computer ScienceComputer Science (R0)