DEVELOPMENT AND IMPLEMENTATION OF A COMPUTER VISION-BASED POTHOLE DETECTOR USING INFRARED CAMERA

Authors

  • Arowolo, M.O.,

    Federal University Oye Ekiti, Nigeria

  • Adaralode, C.I.

  • Ogundigba, H.B

    Federal University Oye Ekiti, Nigeria

DOI:
https://doi.org/10.51459/futajeet.2023.17.2.586
Keywords:
Array, Array, Array
Abstract

Potholes are a significant road hazard and can lead to accidents and vehicle damage. Detecting potholes in real time and alerting drivers can help mitigate this risk. The study presents the methodology for creating a pothole detection system. This includes details about the computer vision algorithms employed, the use of infrared cameras to enhance detection in varying lighting conditions, and the overall system architecture. The study involved collecting a diverse dataset of road images or videos, both with and without potholes, for training and testing the computer vision model. Data preprocessing and augmentation techniques were also used to reduce processing time by rescaling the images. The system was designed to serve as a warning system for drivers. It includes real-time alerts, such as visual indicators within the vehicle or audible alarms, to notify drivers of potential potholes ahead. The study's success was measured by its accuracy in correctly detecting potholes. The metrics used included training, validation accuracy, and loss. The system achieved a training accuracy of 95%, a validation accuracy of 83%, and a loss function of 0.4531 indicating that the distance between the true class and the prediction is tolerable. Overall, this study contributes to the development of a proactive and efficient approach to address the persistent issue of potholes. By harnessing advanced techniques, data analysis techniques, and real-time monitoring capabilities, the pothole detector offers an innovative solution for improved public safety.

Author Biographies
  1. Arowolo, M.O., , Federal University Oye Ekiti, Nigeria

    Department of Mechatronics Engineering

  2. Ogundigba, H.B, Federal University Oye Ekiti, Nigeria

    Department of Mechatronics Engineering

References

Aparna, Bhatia, Y., Rai, R., Gupta, V., Aggarwal, N., and Akula, A. (2022). Convolutional neural networks based potholes detection using thermal imaging. Journal of King Saud University - Computer and Information Sciences, 34(3), 578–588.

Bhandari, S., Luo, X. and Wang, F. (2023). Understanding the effects of structural factors and traffic loading on flexible pavement performance. International Journal of Transportation Science and Technology, 12(1), 258–272.

Buza, E.; Omanovic, S.; Huseinovic, A. Pothole Detection with Image Processing and Spectral Clustering. In Proceedings of the 2nd International Conference on Information Technology and Computer Networks, Kunming, China, 21–23 September 2013; Volume 810, p. 4853.

Chouhan, T., Kumari, K. and Kumari, P. (2021). Detection of Pothole in Real-Time Using Android Based Application. SSRN Electronic Journal, 1–4.

Gupta, S., Sharma, P., Sharma, D., Gupta, V. and Sambyal, N. (2020). Detection and localization of potholes in thermal images using deep neural networks. Multimedia Tools and Applications, 79(35–36), 26265–26284.

Joubert, D., Tyatyantsi, A., Mphahlehle, J. and Manchidi, V. (2011). Pothole Tagging System. 4th Robotics and Mechatronics Conference of South Africa, 1–4.

Kamal, I. and Bas, Y. (2021). Materials and technologies in road pavements - an overview. Materials Today: Proceedings, 42, 2660–2667.

Koch, C. and Brilakis, I. (2011a). Improving Pothole Recognition through Vision Tracking for Automated Pavement Assessment. The 18th EG-ICE Workshop on Intelligent Computing in Engineering, 1–8.

Koch, C., and Brilakis, I. (2011b). Pothole detection in asphalt pavement images. Advanced Engineering Informatics, 25(3), 507–515.

Nienaber, S., (Thinus) Booysen, M. J., and Kroon, R. (2015). Detecting Potholes Using Simple Image Processing Techniques and Real-World Footage. 34th South African Transport Conference, 6–9.

OpenCV. (2023). The OpenCV Reference Manual Release 4.8.0. https://docs.opencv.org/4.8.0/d4/d86/group__imgproc__filter.htmlf

Sathya, R. and Saleena, B. (2022). A Framework for Designing Unsupervised Pothole Detection by Integrating Feature Extraction Using Deep Recurrent Neural Network. Wireless Personal Communications, 126(2), 1241–1271.

Sharmila, D., Nivedha, P., Niveditha, P. and Nivetha, R. (2020). Automatic Pothole Detection and Crime Alerting System. 6(12), 897–902.

Cover Image
Published
2023-11-30
Issue
Vol. 17 No. 2 (2023): FUTA Journal of Engineering and Engineering Technology
Section
Articles
License

Copyright (c) 2023 FUTA JOURNAL OF ENGINEERING AND ENGINEERING TECHNOLOGY

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Copyright

With the submission of a manuscript, the corresponding author confirms that the manuscript is not under consideration by another journal. With the acceptance of a manuscript, the Journal reserves the exclusive right of publication and dissemination of the information contained in the article. The veracity of the paper and all the claims therein is solely the opinion of the authors not the journal.

How to Cite

DEVELOPMENT AND IMPLEMENTATION OF A COMPUTER VISION-BASED POTHOLE DETECTOR USING INFRARED CAMERA. (2023). FUTA JOURNAL OF ENGINEERING AND ENGINEERING TECHNOLOGY, 17(2), 67-73. https://doi.org/10.51459/futajeet.2023.17.2.586

Similar Articles

61-70 of 85

You may also start an advanced similarity search for this article.