Segmentation of Drivable Road Using Deep Fully Convolutional Residual Network with Pyramid Pooling
In recent years, the self-driving car has rapidly been developing around the world. Based on deep learning, monocular vision-based environmental perceptions of either ADAS or self-driving cars are regarded as a feasible and sophisticated solution, in terms of achieving human-level performance at a low cost. Perceived surroundings generally include lane markings, curbs, drivable roads, intersections, obstacles, traffic signs, and landmarks used for navigation. Reliable detection or segmentation of drivable roads provides a solid foundation for obstacle detection during autonomous driving of the self-driving car. This paper proposes an RPP model for monocular vision-based road detection based on the combination of fully convolutional network, residual learning, and pyramid pooling. Specifically, the RPP is a deep fully convolutional residual neural network with pyramid pooling. In order to greatly improve prediction accuracy on the KITTI-ROAD detection task, we present a new strategy through an addition of road edge labels and an introduction of an appropriate data augmentation so as to effectively handle small training samples contained in the KITTI road detection. The experiments demonstrate that our RPP has achieved remarkable results, which ranks second in both unmarked road and marked road tasks, fifth in multiple-marked-lane task, and third in combination task. In this paper, we propose a powerful 112-layer RPP model through the incorporation of residual connections and pyramid pooling into a fully convolutional neural network framework. For small training sample problems such as the KITTI-ROAD detection, we present a new strategy through an addition of road edge labels and data augmentation. It suggests that addition of more labels and introduction of appropriate data augmentation can help deal with small training image problems. Moreover, a larger size of crops or combination with more global information also benefit improvements in road segmentation accuracy. If regardless of restricted computing and memory resources for such large-scale networks like RPP, the use of raw images instead of any crops and the selection of a large batch size are expected to further increase road detection accuracy.
KeywordsCNN Drivable road Semantic segmentation Self-driving car
The authors are grateful to the reviewers for their valuable comments that considerably contributed to improving this paper.
Compliance with Ethical Standards
Conflict of interests
Xiaolong Liu and Zhidong Deng declare that they have no conflict of interest.
Informed consent was not required as no humans or animals were involved.
Human and Animal Rights
This article does not contain any studies with human participants or animals performed by any of the authors.
- 1.Alvarez J, Gevers T, LeCun Y, Lopez A. Road scene segmentation from a single image. Computer Vision–ECCV 2012;2012:376–389.Google Scholar
- 2.Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. 2014. Semantic image segmentation with deep convolutional nets and fully connected CRFS. arXiv:1412.7062.
- 4.Fang L, Wang X. Lane boundary detection algorithm based on vector fuzzy connectedness. Cogn Comput. 2017:1–12.Google Scholar
- 5.Fritsch J, Kuhnl T, Geiger A. A new performance measure and evaluation benchmark for road detection algorithms. 2013 16th international IEEE conference on intelligent transportation systems-(ITSC). Piscataway: IEEE; 2013. p. 1693–1700.Google Scholar
- 7.Goodfellow IJ, Warde-Farley D, Lamblin P, Dumoulin V, Mirza M, Pascanu R, Bergstra J, Bastien F, Bengio Y. 2013. Pylearn2: a machine learning research library. arXiv:1308.4214.
- 8.Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y. 2013. Maxout networks. arXiv:1302.4389.
- 9.Guo C, Mita S, McAllester D. Stereovision-based road boundary detection for intelligent vehicles in challenging scenarios. IROS 2009. IEEE/RSJ international conference on intelligent robots and systems, 2009. Piscataway: IEEE; 2009. p. 1723–1728.Google Scholar
- 10.He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770–778.Google Scholar
- 11.Huang G, Liu Z, Weinberger KQ, van der Maaten L. 2016. Densely connected convolutional networks. arXiv:1608.06993.
- 12.Ioffe S, Szegedy C. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167.
- 13.Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. 2014. Caffe: convolutional architecture for fast feature embedding. arXiv:1408.5093.
- 14.Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems; 2012. p. 1097–1105.Google Scholar
- 15.Laddha A, Kocamaz MK, Navarro-Serment LE, Hebert M. Map-supervised road detection. Intelligent vehicles symposium (IV), 2016 IEEE. Piscataway: IEEE; 2016. p. 118–123.Google Scholar
- 16.Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 3431–3440.Google Scholar
- 18.Mendes CCT, Frémont V, Wolf DF. Exploiting fully convolutional neural networks for fast road detection. 2016 IEEE international conference on Robotics and automation (ICRA). Piscataway: IEEE; 2016. p. 3174–3179.Google Scholar
- 19.Neto AM, Victorino AC, Fantoni I, Ferreira JV. Real-time estimation of drivable image area based on monocular vision. Intelligent vehicles symposium (IV), 2013 IEEE. Piscataway: IEEE; 2013. p. 63–68.Google Scholar
- 20.Oliveira GL, Burgard W, Brox T. Efficient deep methods for monocular road segmentation. IEEE/RSJ international conference on intelligent robots and systems (IROS 2016); 2016.Google Scholar
- 21.Ouyang W, Wang X, Zhang C, Yang X. Factors in finetuning deep model for object detection with long-tail distribution. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 864–873.Google Scholar
- 23.Simonyan K, Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556.
- 24.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 1–9.Google Scholar
- 25.Wang B, Frémont V, Rodríguez SA. Color-based road detection and its evaluation on the KITTI road benchmark. Intelligent vehicles symposium proceedings, 2014 IEEE. Piscataway: IEEE; 2014. p. 31–36.Google Scholar
- 27.Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, Macherey K, et al. 2016. Google’s neural machine translation system: bridging the gap between human and machine translation. arXiv:1609.08144.
- 29.Xiong W, Droppo J, Huang X, Seide F, Seltzer M, Stolcke A, Yu D, Zweig G. 2016. Achieving human parity in conversational speech recognition. arXiv:1610.05256.
- 30.Yu F, Koltun V. 2015. Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122.
- 31.Zeng X, Ouyang W, Yang B, Yan J, Wang X. Gated bi-directional CNN for object detection. European conference on computer vision. Berlin: Springer; 2016. p. 354–369.Google Scholar
- 32.Zhao H, Shi J, Qi X, Wang X, Jia J. 2016. Pyramid scene parsing network. arXiv:1612.01105.