PotSense

Abstract

An Intelligent Transport System is an essential facet of today's world. The Indian traffic scenario has many distinct challenges that are not common in other countries. These embody less-disciplined/chaotic lane traffic, varied vehicle types plying at the same time and poor road conditions such as potholes. As per MoRTH (Ministry of Road Transport and Highways) India, around a million accidents and nearly 10,000 road accident-based deaths happen every year solely owing to potholes. Given the humongous road network in India, combined with limitations of Government Departments, typically only a few roads are well-maintained. In this regard, this work proposes an economical yet efficient system called PotSense. PotSense uses smartphone-based sensors, particularly accelerometer and camera sensors, to crowd-source information of potholes on public roads. Furthermore, it is broadcasted to all road users to ensure their safety. PotSense also investigates the utilization of different neural network techniques for processing the data obtained from the camera. Moreover, the collected data is analyzed to perceive substantial insight on road quality and potholes. Notably, it is observed that irrespective of the dimension, depth, and other characteristics of the pothole, the proposed solution, "PotSense" accurately detects the pothole in more than 60\% of the typical Indian road scenarios.