Abstract
Road markings are an essential and integral part of safe driving where main landmarks are used to guide drivers. Develo** a robust road-marking interpretation system is challenging because of several aspects such as changes in light conditions, varying weather conditions, shadows, and faded signs and text. This chapter investigates the use of deep learning methods such as convolutional neural networks (CNNs) to classify symbolic road markings. Previous work in the literature has reported techniques which are predominantly based on feature extraction and template matching which restricts the use of such methods in real time. For autonomous vehicles, road markings need to be interpreted in real time to make timely decisions. This book chapter investigates and presents CNN-based image preprocessing methods to detect road markings for autonomous vehicles. Several CNN architectures were investigated with multiple convolutional, max pooling, and fully connected layers. This chapter will contribute by develo** a model with low computational requirements which is essential for autonomous vehicles. It will further explore state-of-the-art image preprocessing methods such as grayscaling, top-hat, and Otsu’s method. The performance of the proposed road-marking detector will be benchmarked using a public dataset with labeled road-marking images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), pp. 580–587. https://doi.org/10.1109/CVPR.2014.81
R. Girshick, Fast R-CNN, in 2015 IEEE International Conference on Computer Vision (ICCV), (2015), pp. 1440–1448. https://doi.org/10.1109/ICCV.2015.169
K. Ren, R.G. He, J. Sun, Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), pp. 936–944. https://doi.org/10.1109/CVPR.2017.106
K. He, G. Gkioxari, P. Dollár, R. Girshick, Mask R-CNN, in 2017 IEEE International Conference on Computer Vision (ICCV), (2017), pp. 2980–2988. https://doi.org/10.1109/ICCV.2017.322
W. Liu, et al., SSD: Single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) Computer Vision – ECCV 2016. ECCV 2016. Lect. Notes Comput. Sci, vol 9905, (2016). https://doi.org/10.1007/978-3-319-46448-0_2
J. Redmon, A. Farhadi, YOLOv3: An incremental improvement. ar**v:1804.02767v1 (2018)., [online] Available: https://arxiv.org/abs/1804.02767
Cambridge-Driving Labeled Video Database (CamVid), 2018, [online] Available: http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/
Daimler Urban Segmentation Dataset, 2019, [online] Available: http://www.6d-vision.com/scene-labeling
The Málaga Stereo and Laser Urban Data Set—MRPT, 2018, [online] Available: https://www.mrpt.org/MalagaUrbanDataset
A. Geiger, P. Lenz, C. Stiller, R. Urtasun, Vision meets robotics: The KITTI dataset. Int. J. Robot. Res. 32(11) (2013)
T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, Focal loss for dense object detection. Proc. IEEE Int. Conf. Comput. Vis., 2999–3007 (2017)
J. Greenhalgh, M. Mirmehdi, Automatic detection and recognition of symbols and text on the road surface, in Pattern Recognition: Applications and Methods, ICPRAM 2015. Lecture Notes in Computer Science, ed. by A. Fred, M. De Marsico, M. Figueiredo, vol. 9493, (Springer, Cham, 2015). https://doi.org/10.1007/978-3-319-27677-9_8
T.M. Hoang, S.H. Nam, K.R. Park, Enhanced detection and recognition of road markings based on adaptive region of interest and deep learning. IEEE Access 7, 109817–109832 (2019). https://doi.org/10.1109/ACCESS.2019.2933598
R. Grompone von Gioi, J. Jakubowicz, J. Morel, G. Randall, LSD: A fast line segment detector with a false detection control. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 722–732 (2010). https://doi.org/10.1109/TPAMI.2008.300
J.Y. Lu, K. Li, L. Li, CannyLines: A parameter-free line segment detector, in 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, (2015), pp. 507–511. https://doi.org/10.1109/ICIP.2015.7350850
T. Ahmad, D. Ilstrup, E. Emami, G. Bebis, Symbolic road marking recognition using convolutional neural networks, in 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, vol. 2017, pp. 1428–1433. https://doi.org/10.1109/IVS.2017.7995910
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient based learning applied to document recognition. PIEEE 86(11), 2278–2324 (1998)
Z. Ouyang, J. Niu, Y. Liu, M. Guizani, Deep CNN-based real-time traffic light detector for self-driving vehicles. IEEE Trans. Mob. Comput. 19(2), 300–313 (2020). https://doi.org/10.1109/TMC.2019.2892451
T. Wu, A. Ranganathan, A practical system for road marking detection and recognition, in 2012 IEEE Intelligent Vehicles Symposium, Alcala de Henares, (2012), pp. 25–30. https://doi.org/10.1109/IVS.2012.6232144
D. Suarez-Mash, A. Ghani, C.H. See, S. Keates, H. Yu, Using deep neural networks to classify symbolic road markings for autonomous vehicles. EAI Endorsed Trans. Ind. Netw. Intell. Syst. 9(31), e2 (2022). https://doi.org/10.4108/eetinis.v9i31.985
A. Ghani, R. Hodeify, C.H. See, S. Keates, D.-J. Lee, A. Bouridane, Computer vision-based Kidney’s (HK-2) damaged cells classification with reconfigurable hardware accelerator (FPGA). Electronics 11, 4234 (2022). https://doi.org/10.3390/electronics11244234
Acknowledgments
The author would like to thank the M.Sc. thesis student(s) for contributing to the experimental simulations conducted in the IoT lab within the School of Computing, Electronics and Maths, Coventry University, UK.
Disclaimer
This is an original work conducted and supervised by Dr. Arfan Ghani at Coventry University, UK. This book chapter contains at least 20–30% unpublished work. Readers and researchers of this chapter are referred to the author’s previously published work [21, 22], where some of the methods and techniques are further elaborated.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Ghani, A., Iqbal, R. (2023). Accelerating Classification of Symbolic Road Markings (SRMs) in Autonomous Cars Through Computer Vision-Based Machine Learning. In: Kerrache, C.A., Calafate, C., Lakas, A., Lahby, M. (eds) Internet of Unmanned Things (IoUT) and Mission-based Networking. Internet of Things. Springer, Cham. https://doi.org/10.1007/978-3-031-33494-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-33494-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33493-1
Online ISBN: 978-3-031-33494-8
eBook Packages: EngineeringEngineering (R0)