Automated parking-cruising detection and measurement using Bluetooth AVI Sensor network

Searching for street parking, a behavior known as cruising for parking, leads to excess congestion and pollution. Many recent smart parking interventions have attempted to address this issue, but the problem of effectively detecting and measuring cruising remains largely unsolved. The goal of this work is to develop methods to detect and measure cruising for parking and its effects on congestion using dense, low cost networks of automatic vehicle identification (AVI) sensors combined with novel parking occupancy prediction. Bluetooth AVI sensors are widely used for travel time measurement on freeways and arterials, as most new vehicles contain Bluetooth devices that can be passively detected and tracked across multiple stationary sensors. We have extended these techniques to urban environments for vehicle route reconstruction and travel time measurement. Cruising routes are sufficiently distinct from normal travel routes, so we are developing a classifier to reliably classify vehicles as traveling or cruising. To strengthen the classifier, parking occupancy prediction based on payment events from parking kiosks will be correlated with reconstructed routes. This approach continuously measures cruising for parking, allowing the evaluation of dynamic parking pricing and other smart parking interventions. Large-scale pilot tests will be deployed to evaluate this approach.