Road Pothole Detection using Deep Learning Classifiers
Surekha Arjapure1, D. R. Kalbande2

1Surekha Arjapure, Associate Professor, Department of Computer Engineering, Sardar Patel Institute of Technology, Andheri (West), Mumbai, India.
2D. R. Kalbande, Professor, Department of Computer Engineering and Dean(Industry Relations), Sardar Patel Institute of Technology, Andheri (West),Mumbai, India.
Manuscript received on February 02, 2020. | Revised Manuscript received on February 10, 2020. | Manuscript published on March 30, 2020. | PP: 563-570 | Volume-8 Issue-6, March 2020. | Retrieval Number: F7349038620/2020©BEIESP | DOI: 10.35940/ijrte.F7349.038620

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Pothole is one of the major types of defects frequently found on the road whose assessment is necessary to process. It is one of the important reason of accidents on the road along with the wear and tear of vehicles. Road defects assessment is to be done through defects data collection and processing of this collected data. Currently, using various types of imaging systems data collection is near about becomes automated but an assessment of defects from collected data is still manual. Manual classification and evaluation of potholes are expensive, labour-intensive, time-consuming and thus slows down the overall road maintenance process. This paper describe a method for classification and detection of the potholes on road images using convolutional neural networks which are deep learning algorithms. In the proposed system we used convolutional neural networks based approach with pre-trained models to classify given input images into a pothole and non-pothole categories. The method was implemented in python using OpenCV library under windows and colab environment, trained on 722 and tested on 116 raw images. The results are evaluated and compared for convolutional neural networks and various seven pre-trained models through accuracy, precision and recall metrics. The results show that pre-trained models InseptionResNetV2 and DenseNet201 can detect potholes on road images with reasonably good accuracy of 89.66%.
Keywords: Convolution Neural Networks , Deep Learning ,Pothole Detection, , Pre-Trained Models
Scope of the Article: Deep Learning.