Vehicle Re-identification for Lane-level Travel Time Estimations on Congested Urban Road Networks Using Video Images

The provision of lane-level travel time information can enable accurate traffic control and route guidance in urban roads with distinctive conditions among lanes. However, few studies the literature have been conducted to estimate distributions. This study proposes a new vehicle re-identification (V-ReID) method for estimating distributions using video images from widely deployed surveillance cameras. In proposed method, lane-based bipartite graph matching is introduced obtain optimal matches between upstream downstream vehicles by considering vehicles’ lane changing behaviors visual features. A estimation technique real-time full spectrum distribution parameters, including not only mean but also standard deviation type. comprehensive case carried out on congested road Hong Kong. Results show that outperforms state-of-the-art link-based V-ReID capable providing roads.