Open Access Open Access  Restricted Access Subscription or Fee Access

Smart Pothole Reporting Based on Deep-Learning

Atul Gandhi

Abstract


In India, due to rage of rains and poor-quality construction the Indian state governments are facing the pothole and cracked road issues. The government is not able to assist faster to the people due to poor communication between people and govt. So, there exists a system which uses convolutional neural network (CNN) to detect the potholes. The peculiarity of this system is that it will process the pothole image reported by user directly to the stakeholders associated with that road. The system verifies the pothole image which has geographical location, that whether it is real or fake and if it is real then only it is further processed to the database. It is done using CNN. The model trained on number of images collected from a dataset. This system provides faster assistance to the people. 


Keywords


Pothole, convolutional neural network, cloud, geotagged

Full Text:

PDF

References


Kingma DP, Ba J. Adam. A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014 Dec 22.

Zhang A, Wang KC, Li B, Yang E, Dai X, Peng Y, Fei Y, Liu Y, Li JQ, Chen C. Automated pixel‐level pavement crack detection on 3D asphalt surfaces using a deep‐learning network. Computer‐Aided Civil and Infrastructure Engineering. 2017 Oct;32(10):805–19.

Cha YJ, Choi W, Büyüköztürk O. Deep learning‐based crack damage detection using convolutional neural networks. Computer‐Aided Civil and Infrastructure Engineering. 2017 May;32(5):361–78.

Pereira V, Tamura S, Hayamizu S, Fukai H. A deep learning-based approach for road pothole detection in timor leste. In2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) 2018 Jul 31, pp. 279– 284.

Lin J, Liu Y. Potholes detection based on SVM in the pavement distress image. In2010 Ninth International Symposium on Distributed Computing and Applications to Business, Engineering and Science 2010 Aug 10, pp. 544–547.

Amara J, Bouaziz B, Algergawy A. A deep learning-based approach for banana leaf diseases classification. Datenbanksysteme für Business, Technologie und Web (BTW 2017)- Workshopband. 2017.

Zhang L, Yang F, Zhang YD, Zhu YJ. Road crack detection using deep convolutional neural network. In2016 IEEE international conference on image processing (ICIP) 2016 Sep 25, pp. 3708– 3712.

Singh G, Kumar R, Kashtriya P. Detection of potholes and speed breaker on road. In2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC) 2018 Dec 15, pp. 490–495.

Maeda H, Sekimoto Y, Seto T, Kashiyama T, Omata H. Road damage detection using deep neural networks with images captured through a smartphone. arXiv preprint arXiv:1801.09454. 2018 Jan 29.

Rishiwal V, Khan H. Automatic pothole and speed breaker detection using android system. In 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) 2016 May 30, pp. 1270–1273.

Road video data. Available at: https://www.youtube.com/watch?v=ZUbD PhL2gEE.

Franois Chollet and others, Keras, GitHub, 2015.




DOI: https://doi.org/10.37591/joma.v7i3.4966

Refbacks

  • There are currently no refbacks.