Abstract
This research work explores the possibility of using deep learning to produce an autonomous system for detecting potholes on video to assist in road monitoring and maintenance. Video data of roads was collected using a GoPro camera mounted on a car. Region-based Fully Convolutional Networks (RFCN) was employed to produce the model to detect potholes from images, and validated on the collected videos. The R-FCN model is able to achieve a Mean Average Precision (MAP) of 89% and a True Positive Rate (TPR) of 89% with no false positive.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
The Star Online, https://www.thestar.com.my/news/community/2014/03/10/crumbling-roads-exhausting-funds-huge-allocation-comes-with-hopes-of-better-maintenance, last accessed 2018/2/10.
Shen, G.: Road crack detection based on video image processing. 3RD INTERNATIONAL CONFERENCE ON SYSTEMS AND INFORMATICS 2016, pp. 912–917, IEEE, Shanghai (2016).
Huidrom, L., Das, L. K., Sud, S.: Method for automated assessment of potholes, cracks and patches from road surface video clips. Procedia - Social and Behavioral Sciences, 312–321 (2013).
Kawai, S., Takeuchi, K., Shibata, K., Horita, Y.: A method to distinguish road surface conditions for car-mounted camera images at night-time. 12TH INTERNATIONAL CONFERENCE ON ITS TELECOMMUNICATIONS 2012, pp. 668–672, IEEE (2012).
Sun, Z., Jia, K.: Road surface condition classification based on color and texture information, 9TH INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING, pp. 137–140), IEEE (2013).
Zhao-Zheng, C., Jia, L., Qi-Mei, C.: Real-time video detection of road visibility conditions. WORLD CONGRESS ON COMPUTER SCIENCE AND INFORMATION ENGINEERING 2009, pp. 472–476. IEEE (2009).
Raj, A., Krishna, D., Priya, H., Shantanu, K., Devi, N.: Vision based road surface detection for automotive systems. 2012 INTERNATIONAL CONFERENCE ON APPLIED ELECTRONICS, pp. 223–228, IEEE (2012).
Nienaber, S., Booysen, M.J., Kroon, R.S.: Detecting potholes using simple image processing techniques and real-world footage. SATC 2015, Pretoria, South Africa (2015).
Nienaber, S., Kroon, R.S., Booysen M.J.: A comparison of low-cost monocular vision techniques for pothole distance estimation. IEEE CIVTS 2015, IEEE, Cape Town, South Africa (2015).
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed/accuracy trade-offs for modern convolutional object detectors. CVPR 2017 (2017).
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., et al.: Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467 [cs.DC], (2016).
LabelImg, https://github.com/tzutalin/labelImg, last accessed 2018/2/10.
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: Object detection via region-based fully convolutional networks. arXiv:1605.06409 [cs.CV], (2016).
Acknowledgements
Financial support from the Ministry of Higher Education, Malaysia, under the Fundamental Research Grant Scheme with grant number FRGS/1/2015/SG07/MMU/02/1, as well as the Multimedia University Capex Fund with Project ID MMUI/CAPEX170008, are gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Koh, J.J. et al. (2019). Autonomous Road Potholes Detection on Video. In: Alfred, R., Lim, Y., Ibrahim, A., Anthony, P. (eds) Computational Science and Technology. Lecture Notes in Electrical Engineering, vol 481. Springer, Singapore. https://doi.org/10.1007/978-981-13-2622-6_14
Download citation
DOI: https://doi.org/10.1007/978-981-13-2622-6_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2621-9
Online ISBN: 978-981-13-2622-6
eBook Packages: EngineeringEngineering (R0)