V3I-STAL
Xiaobai Liu · 2016
This paper investigates a visual interaction system for vehicle-to-vehicle (V2V) platform, called V3I. Our system employs common visual cameras that are mounted on connected vehicles to perceive the existence of isolated vehicles in the same roadway, and provides human drivers with imagery situational awareness. This allows effective interactions between vehicles even with a low permeation rate of V2V devices. The underlying research problem for V3I includes two aspects: i) tracking isolated vehicles of interest over time through local cameras; ii) at each time-step fusing the results of local visual perceptions to obtain a global location map that involves both isolated and connected vehicles. In this paper, we introduce a unified probabilistic approach to solve the above two problems, i.e., tracking and localization, in a joint fashion. Our approach will explore both the visual features of individual vehicles in images and the pair-wise spatial relationships between vehicles. We develop a fast Markov Chain Monte Carlo (MCMC) algorithm to search the joint solution space efficiently, which enables real-time application. To evaluate the performance of the proposed approach, we collect and annotate a set of video sequences captured with a group of vehicle-resident cameras. Extensive experiments with comparisons clearly demonstrate that the proposed V3I approach can precisely recover the dynamic location map of the surrounding and thus enable direct visual interactions between vehicles .