SmartRoad

TLDR

SmartRoad uses participatory sensing data from in‑vehicle smartphone GPS sensors as an inexpensive alternative to traditional road surveys. The article introduces SmartRoad, a crowd‑sourced road sensing system that detects and identifies traffic regulators, traffic lights, and stop signs. SmartRoad processes GPS data from in‑vehicle smartphones, automatically selecting optimal representation and transmission schemes and dynamically refining its detection and identification engines to leverage external ground truth or manual labels. SmartRoad was deployed on 35 volunteer vehicles for two months, and experiments demonstrate that it robustly, effectively, and efficiently detects and identifies traffic regulators, traffic lights, and stop signs, providing data useful for assisted‑driving and navigation systems.

Abstract

In this article we present SmartRoad, a crowd-sourced road sensing system that detects and identifies traffic regulators, traffic lights, and stop signs, in particular. As an alternative to expensive road surveys, SmartRoad works on participatory sensing data collected from GPS sensors from in-vehicle smartphones. The resulting traffic regulator information can be used for many assisted-driving or navigation systems. In order to achieve accurate detection and identification under realistic and practical settings, SmartRoad automatically adapts to different application requirements by (i) intelligently choosing the most appropriate information representation and transmission schemes, and (ii) dynamically evolving its core detection and identification engines to effectively take advantage of any external ground truth information or manual label opportunity. We implemented SmartRoad on a vehicular smartphone test bed, and deployed it on 35 external volunteer users’ vehicles for two months. Experiment results show that SmartRoad can robustly, effectively, and efficiently carry out the detection and identification tasks.