Abstract
Lane detection is an indispensable part in advanced driving systems. The task is typically tackled with a two-step pipeline: predicting a segmentation of lane markings and fitting the lane markings by a suitable curve model. In this work, we propose a method to optimally fit lane lines by applying a learned perspective transformation, according to the input image. We leverage fundamental computer vision theories and integrate prior geometric knowledge into a deep learning framework, which can be trained in a self-supervised manner. By doing this, we perform multi-lane joint fitting in a realistic top-view space, which is robust against ground-planes slope changes. We tested our model on the CULane dataset. The results show that the proposed fitting method can also improve the location accuracy of lane markings effectively.
The first author is a student.
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
References
Aly, M.: Real time detection of lane markers in urban streets. In: 2008 IEEE Intelligent Vehicles Symposium, pp. 7–12. IEEE (2008)
Bertozzi, M., Broggi, A.: Real-time lane and obstacle detection on the gold system. In: Proceedings of Conference on Intelligent Vehicles, pp. 213–218. IEEE (1996)
Gackstatter, C., Heinemann, P., Thomas, S., Klinker, G.: Stable road lane model based on clothoids. In: Meyer, G., Valldorf, J. (eds.) Advanced Microsystems for Automotive Applications 2010. VDI-Buch, pp. 133–143. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16362-3_14
Girija, S.S.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. tensorflow. org (2016)
Huval, B., et al.: An empirical evaluation of deep learning on highway driving. arXiv preprint arXiv:1504.01716 (2015)
Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017–2025 (2015)
Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5974–5983 (2017)
Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938–2946 (2015)
Kim, J., Lee, M.: Robust lane detection based on convolutional neural network and random sample consensus. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds.) ICONIP 2014. LNCS, vol. 8834, pp. 454–461. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-12637-1_57
Lee, S., et al.: VPGNet: vanishing point guided network for lane and road marking detection and recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1947–1955 (2017)
Loose, H., Franke, U., Stiller, C.: Kalman particle filter for lane recognition on rural roads. In: 2009 IEEE Intelligent Vehicles Symposium, pp. 60–65. IEEE (2009)
Neven, D., De Brabandere, B., Georgoulis, S., Proesmans, M., Van Gool, L.: Towards end-to-end lane detection: an instance segmentation approach. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 286–291. IEEE (2018)
Pan, X., Shi, J., Luo, P., Wang, X., Tang, X.: Spatial as deep: spatial CNN for traffic scene understanding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)
Smuda, P., Schweiger, R., Neumann, H., Ritter, W.: Multiple cue data fusion with particle filters for road course detection in vision systems. In: 2006 IEEE Intelligent Vehicles Symposium, pp. 400–405. IEEE (2006)
Yan, X., Yang, J., Yumer, E., Guo, Y., Lee, H.: Perspective transformer nets: learning single-view 3D object reconstruction without 3D supervision. In: Advances in Neural Information Processing Systems, pp. 1696–1704 (2016)
Acknowledgment
The work is supported by NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization under grant No. U1709214 and NSFC grant No. 61571390.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y., Du, W., Xiang, Z., Zou, N., Chen, S., Qiao, C. (2019). Self-supervised Homography Prediction CNN for Accurate Lane Marking Fitting. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11859. Springer, Cham. https://doi.org/10.1007/978-3-030-31726-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-31726-3_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31725-6
Online ISBN: 978-3-030-31726-3
eBook Packages: Computer ScienceComputer Science (R0)