Wi-Eye: Tracking Urban Private Vehicles with Inter-Vehicle Communications and Sparse Video Surveillance Cameras

Due to the sparse distribution of video surveillance cameras and low installation rate of dash-mounted online telematics systems, tracking precise trajectories of urban private vehicles is a challenging task. Previous studies on vehicle tracking are mostly concerned with recovering trajectories with low- sampling rate GPS coordinates or captured surveillance information by identifying road traffic patterns from this information. Nevertheless, to the best of our knowledge, none of them have considered using the vehicle encounter information to enhance the sampling rate as well as the time-varying and in-group characteristics of vehicle traffic patterns, let alone to achieve vehicle tracking. With this insight, we divide all vehicles into clusters with a Canopy and K- means combined algorithm for different time periods and use an exponential distribution to approximate the time that vehicles from one cluster encounter a fixed Wi-Fi hotspot in the future during a given time period and at a specific location. Based on these preliminary results, we propose a novel approach to select the optimal data packet transmission scheme between encountered vehicles to transfer vehicle encounter information to the server as much and quickly as possible, and then calculate the trajectories of all private vehicles accurately. We evaluate our solution via real-world private vehicles and road surveillance system datasets. Experimental results demonstrate that our approach outperforms other solutions in terms of the accuracy ratio of vehicle tracking.