In recent years lot of research has been done on road surface anomaly detection due to the widespread availability of smartphones, pre-equipped with diverse sensors. The existing literature is mainly focused on speed bump, pot-hole and man-hole and does not provide any information about the type of bumps. Speed bumps have four major types i.e. sinusoidal-profile, flat-top, thermoplastic and round-top. The decision of deploying a particular type is made based upon the location and the speed limit in that area. In this paper we not only detect speed bumps but also identify the bump types. We first collected the speed bump dataset from smartphone sensors and performed series of dataset transformations. Using this dataset we proposed and experimented with deep learning-based speed bump detection and characterization system which is able to achieve the test accuracy of 98.92% and 95% respectively. This work can, not only help the government and policymakers to identify illegal speed bumps but also help decrease the number of road accidents, avoid damage to the vehicles, and reduce the environmental, health as well as financial losses due to non-standard or sub-standard bump types. Moreover, this work can be integrated into road navigation apps like Google Maps, Waze, etc. which can help determine the optimal routes for the drivers.
Read full abstract