Pothole Detection Using Deep Learning

Authors

  • Pratiksha Chavan  Department of Computer Engineering Zeal Education Society ZCOER Pune, Maharashtra, India
  • Dhanashri Mane  Department of Computer Engineering Zeal Education Society ZCOER Pune, Maharashtra, India
  • Diksha Chavan  Department of Computer Engineering Zeal Education Society ZCOER Pune, Maharashtra, India

Keywords:

Pothole detection, Deep Learning, Transfer Learning, Deep Learning, Tensor flow API, Accelerometer, Image Labelling, F-RCNN, inception-v2

Abstract

Connecting lines between different places are roads.There are over 64 or more millions kilometers of road in the world. India is the second-largest road network in the world.Potholes are not a new issue. All countries almost have the similar problem. One of the major problems in countries is maintenance of roads include potholes. Detecting and reporting the existence of potholes to responsible departments can save the roads from getting worse.However Detecting potholes manually is a labor-intensive and time-consuming task as well as expensive procedure.In order to solve this problem, various techniques have been implemented ranging from manual reporting to authorities to the use of vibration-based sensors to 3D reconstruction using laser imaging. But all these techniques have some drawbacks such as the high setup cost, risk while detection or no provision for night vision. Because of this we designed a smart pothole reporting system, so that all the problems could be reported to the concerned authorities as soon as the problem arises.In this paper we present our approach to building a generalized learning model for pothole detection. We apply four data-sets that contain a range of image and environment conditions. Using the Faster RCNN object detection model, we demonstrate the extent to which pothole detection models can generalize across various conditions. Our work is a contribution to bringing automated road maintenance techniques which helps for citizens and the government.

References

  1. Amita Dhiman and Reinhard Klette proposed “Pothole Detection Us- ing Computer Vision and Learning”, IEEE Transactions on Intelligent Transportation Systems (Volume: 21, Issue: 8, Aug. 2020).
  2. Ping Ping, Xiaohui Yang and Zeyu Gao proposed “A Deep Learning Approach for Street Pothole Detection”, 2020 IEEE Sixth International Conference on Big Data Computing Service and Applications (Big Data Service).
  3. MIT World Peace University, Pune, India have proposed “Deep Learning Approach to Detect Potholes in Real Time using Smartphone”, 2019 IEEE Pune Section International Conference (Pune Con).
  4. Pereira, V., Tamura, S., Hayamizu, S., Fukai, H. (2018, July). A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. In 2018 IEEE International Conference on Service Operations and Logistics,and Informatics (SOLI) (pp. 279-284). IEEE.
  5. https://www.kaggle.com/atulyakumar98/potholedetection-dataset.
  6. Google, ”Colaboratory Frequently Asked Questions,”[Online].Available: https://research.google.com/colaboratory/faq.html.[Accessed 13 May 2020].
  7. A. Bochkovskiy, C.-Y. Wang and H.-Y. Mark Liao, ”YOLOv4:Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2020
  8. J. Dharneeshkar, S. Aniruthan, R. Karthika and L. Parameswaran,”Deep Learning based Detection of potholes in Indian roads using YOLO,” 2020 International Conference on Inventive Computation Technologies (ICICT), pp. 381-385, 2020.
  9. M. Muslim, D. Sulistyaningrum and B. Setiyono, ”Detection and counting potholes using morphological method from road video,” AIP Conference Proceedings, vol.2242,no. 1, pp. 3-11, 2020.
  10. Tensorflow, ”Why TensorFlow,” 13 May 2020. [Online]. Avail- able:https://www.tensorflow.org/
  11. A. AB, ”YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet ),” May 2020.[On- line].Available:https://github.com/AlexeyAB/darknet.
  12. L. Luo, M. Q. Feng, J. Wu and R. Y. Leung, ”Autonomous pothole detection using deep region based convolutional,” Smart Structures and Systems, vol. 24, no. 6, pp. 745-757, 2019.
  13. A. F. Rita Justo-Silva, ”Pavement maintenance considering traffic acci- dent costs,” International Journal of Pavement Research and Technology, 2019
  14. S. a. D. C. Shah, ”Pothole and Bump detection using Convolution Neural Networks,” 2019 IEEE Transportation Electrification Conference (ITEC- India), pp. 1-4, 2019.
  15. E. N. Ukhwah, E. M. Yuniarno and Y. K. Suprapto, ”Asphalt Pavement Pothole Detection using Deep learning method based on YOLO Neural Network,” 2019 International Seminar on Intelligent Technology and Its Applications (ISITIA), pp. 35-40, 2019
  16. Z.-Q. Zhao, P. Zheng, S.-t. Xu and X. Wu, ”Object Detection with Deep Learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, November 2019

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2022-04-30

Issue

Volume 8, Issue 2, March-April-2022

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

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

How to Cite

[1]
Pratiksha Chavan, Dhanashri Mane, Diksha Chavan, " Pothole Detection Using Deep Learning" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 8, Issue 2, pp.454-460, March-April-2022.