An early warning system for traffic and road safety hazards using collaborative crowd sourcing

The increase in the number of vehicles running on the roads challenges the road maintenance department to meet the demand for timely repair of the road and therefore, find a unified solution to identify the road construction problems such as potholes, bumps, corrugations, waves, defective street cuts, etc. Without a better real-time traffic alerts system, efficient maintenance of city roads will be difficult. So, a more effective monitoring system is required for detecting and solving road infrastructure problems. This research work presents an analytical model of a system that detects pavement deformities. The system presents a mobile application that captures the accelerometer profile using the in-built accelerometer in smartphone, to obtain the location of pavement deformities. The variations in the accelerometer values with respect to the vehicle speed are taken into account.

[1]  Girts Strazdins,et al.  Real time pothole detection using Android smartphones with accelerometers , 2011, 2011 International Conference on Distributed Computing in Sensor Systems and Workshops (DCOSS).

[2]  Dilip Krishnaswamy,et al.  Collision avoidance at intersections using vehicle detectors and smartphones , 2015, 2015 International Conference on Connected Vehicles and Expo (ICCVE).

[3]  P. Narasimhan,et al.  Panoptes: Crowd-sourced Cars with a Cause , 2012, 2012 International Conference on Connected Vehicles and Expo (ICCVE).

[4]  Aniket Kulkarni,et al.  Pothole Detection System using Machine Learning on Android , 2014 .

[5]  Ramachandran Ramjee,et al.  Nericell: using mobile smartphones for rich monitoring of road and traffic conditions , 2008, SenSys '08.

[6]  Ryan Newton,et al.  The pothole patrol: using a mobile sensor network for road surface monitoring , 2008, MobiSys '08.

[7]  Pravin Varaiya,et al.  In-pavement wireless sensor network for vehicle classification , 2011, Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks.