Urban Safety as a Service During Bike Navigation: My Smartphone Can Monitor My Street-Lights

Abstract

Existing street light monitoring systems use vehicle-borne sensor platforms, LiDAR etc. which are obtrusive for in-the-wild deployments. In this paper, we propose BikeL; a crowd sensed system to monitor street lighting conditions in a novel approach using smartphone sensors during Bike navigation. We identify the underlying issues and challenges from pilot experiments to make the system phone-invariant, robust, and user-friendly. We used regression models and unsupervised clustering to resolve these issues. We have carried out extensive experiments under various road type illumination scenarios and phones type covering more than 400 km. Over 80 night trips collecting 10,000 functional light pole samples to tune the system parameters. Results show that the overall system successfully detects both functioning and non-functioning light poles with good accuracy (F1 score > 0.85) and can produce uniformly calibrated illumination levels. This viable, economical, and easy to deploy solution can work effectively for under-developed regions of low and middle-economy countries.