Abstract
The problem addressed in this chapter is the pervasive issue of road defects, specifically potholes, on Indian roads. These defects pose significant challenges for both human drivers and autonomous driving technology. For human drivers, potholes can lead to vehicle damage and even pose risks to human life due to accidents caused by sudden manoeuvers to avoid these defects. For autonomous driving technology, the detection and accurate classification of such road defects is a critical task. The solution proposed involves a deep learning model that performs three tasks: classification, pothole detection, and area and distance estimation. The model is trained to detect and classify road defects into three categories. A novel aspect of this work is the estimation of the area and distance of the detected potholes. By calculating the size of the bounding box surrounding the pothole that was spotted in the image, the pothole’s area may be determined. The distance of the pothole is estimated from the bottom of the image, assuming a certain scale between the pixels and actual distance. The results obtained surpass those reported in existing literature, indicating the effectiveness of the proposed methodology.
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
Similar content being viewed by others
References
Kim T, Ryu S-K (2014) Review and analysis of pothole detection methods. J Emerg Trends Comput Inf Sci 6(8):603–608
Dhiman A, Klette R (2020) Pothole detection using computer vision and learning. IEEE transactions on intell transp syst 21
Song H, Baek K, Byun Y (2018) Pothole detection using machine learning. Adv Sci Technol Lett 150:151–155
Kumar A, Chakrapani A, Kalita DJ, Singh VP (2020) A modern pothole detection technique using deep learning. In: Proceedings of the 2nd international conference on data, engineering and applications (IDEA), Bhopal, India, pp 1–5
Chen H, Yao M, Gu Q (2020) Pothole detection using location-aware convolutional neural networks. Int J Mach Learn Cybern 11:899–911
Shaghouri AA, Alkhatib R, Berjaoui S (2021) Real-time pothole detection using deep learning. arXiv preprint arXiv:2107.06356
Egaji OA, Evans G, Griffiths MG, Islas G (2021) Real-time machine learning-based approach for pothole detection. Expert Syst Appl 184:115562
Pandey AK, Iqbal R, Maniak T, Karyotis C, Akuma S, Palade V (2022) Convolution neural networks for pothole detection of critical road infrastructure. Comput Electr Eng 99(107725)
Kang B-H, Choi S-I (2017) Pothole detection system using 2D LiDAR and camera. In: Proceedings of the 2017 ninth international conference on ubiquitous and future networks (ICUFN), Milan, Italy pp 744–746
Bhatt U, Mani S, Xi E, Kolter JZ (2017) Intelligent pothole detection and road condition assessment. arXiv preprint arXiv:1710.02595v2
Yeoh YK, Alias NE, Yusof Y, Isaak S (2021) A real-time Pothole detection based on deep learning approach. J Phys Conf Series 1828
Darapaneni N et al (2021) Pothole detection using advanced neural networks. In: Proceedings of the 2021 IEEE 12th annual information technology, electronics and mobile communication conference (IEMCON), Vancouver, BC, Canada, pp 0567–0572
Her AY, Yew WK, Yew PJ, Ying MCJ (2022) Real-time pothole detection system on vehicle using improved YOLOv5 in Malaysia. In: Proceedings of the IECON 2022—48th annual conference of the IEEE industrial electronics society, Brussels, Belgium, pp 1–5
Ajmera S, Kumar CA, Yakaiah P, Kumar B, Chowdary KY (2022) Real-time pothole detection using YOLOv5. In: Proceedings of the 2022 international conference on advancements in smart, secure and intelligent computing (ASSIC), Bhubaneswar, India, pp 1–5
Vimalkumar K, Vinodhini RE, Archanaa R (2017) An early detection-warning system to identify speed breakers and bumpy roads using sensors in smartphones. Int J Electr Comput Eng (IJECE) 7(3):1377–1384
Gayathri K, Thangavelu S (2021) Novel deep learning model for vehicle and pothole detection. Indonesian J Electr Engi Comput Sci 23(3):1576–1582. https://doi.org/10.11591/ijeecs.v23.i3.pp1576-1582 ISSN: 2502–4752.
Pooja PR, Hariharan B (2017) An early warning system for traffic and road safety hazards using collaborative crowdsourcing. In: Proceedings of the international conference on communication and signal processing, April 6–8, India, pp 4 IEEE ISBN: 978-1-5090-3800-8
Aparna A, Bhatia Y, Rai R, Gupta V, Aggarwal N, Akula A (2022) Convolutional neural networks based potholes detection using thermal imaging. J King Saud Uni—Comput Inf Sci 34:578–588
Dharneeshkar J, Soban Dhakshana V, Aniruthan SA, Karthika R, Parameswaran L (2020) Deep learning based detection of potholes in Indian roads using YOLO. In: Proceedings of the fifth international conference on inventive computation technologies (ICICT-2020), pp 157–161, IEEE Xplore Part Number: CFP20F70-ART, ISBN: 978-1728-1-4685-0
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Tan M, Le Q (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th international conference on machine learning, PMLR 97, pp 6105–6114
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv: Computer Vision Pattern Recognition
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference for learning representations, San Diego
Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. arXiv preprint arXiv:1403.6382
Zhang C, Nateghinia E, Miranda-Moreno LF, Sun L (2021) Pavement distress detection using convolutional neural network (cnn): a case study in montreal, Canada. Int J Transp Sci Technol 1
Acknowledgements
We would like to express our heartfelt appreciation to Amrita School of Computing, Bangalore, for granting us the opportunity to conduct this research and providing us with the necessary infrastructure.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Kulkarni, V.V., Vishal, S., Mohanty, M., Pati, P.B. (2023). City Road Anomaly Alert for Autonomous Vehicles: Pothole Dimension Estimation with YOLOv5. In: Shakya, S., Tavares, J.M.R.S., Fernández-Caballero, A., Papakostas, G. (eds) Fourth International Conference on Image Processing and Capsule Networks. ICIPCN 2023. Lecture Notes in Networks and Systems, vol 798. Springer, Singapore. https://doi.org/10.1007/978-981-99-7093-3_33
Download citation
DOI: https://doi.org/10.1007/978-981-99-7093-3_33
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7092-6
Online ISBN: 978-981-99-7093-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)