A smartphone-cloud application as an aid for street safety inventory
Ali Kattan, Mohammed Faiz Aboalmaaly · 2014
Potholes, debris, sunken manhole covers and others are common street safety hazards drivers experience daily as they “bump” into them unexpectedly while driving. The repair and maintenance process by municipals is an ongoing effort that requires periodic streets inventory to guarantees safety. Unless someone reports the location of a street problem, such process cannot take place. This paper presents a simple, yet an effective technique to aid in reporting such street hazards automatically using a smartphone application. The smartphone's accelerometer is used to detect bumps during driving and report the data and location to cloud service. The cloud application utilizes an artificial neural network that is trained to differentiate between a “shock” resulting from normal driving maneuvers from those possibly resulting from road problem. It also analyzes the location and based on the frequency of reporting a certain “shock” data from the same geographical location it reports a street hazard location. The city's municipal can then take the suitable actions for inspection and repairs. Promising results were obtained by using a preliminary test implementation indicating the effectiveness of the proposed technique.