Crowdwatch: Pedestrian Safety Assistance With Mobile Crowd Sensing

Pedestrians distracted by smartphones are easy to meet with various dangers when crossing or walking on the street. To help them, we propose CrowdWatch, a system that leverages crowd-powered smartphone sensing to make fine-grained characterization of the sensing field and provides context-aware alerts to pedestrians for their safety. The crowd data including acceleration, orientation, and GPS reflects the behavior of the crowd in three different situations: crossing roads, waiting traffic lights, and encountering obstacles. We present details about applying the behavior of the crowd into the system in this paper. What's more, under different contexts/situations, different reminders are delivered. Experiment results indicate that CrowdWatch is effective in safety dynamics detection.