出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Identifying whether two vehicles in different images are same or not is called vehicle reidentification.In cities, there are lots of cameras, but cameras cannot cover all the areas. If wecan re-identify a car disappearing from one camera and appearing in another in two adjacentregions, we can easily track the vehicle and use the information help with traffic management.In this paper, we propose a two-branch deep learning model. This model extracts two kinds offeatures for each vehicle. The first one is license plate feature and the other is the global featureof the vehicle. Then the two kinds of features are fused together with a weight learned by thenetwork. After, the Euclidean distance is used to calculate the distance between features ofdifferent inputs. Finally, we can re-identify vehicles according to their distance. We conductsome experiments to validate the effectiveness of the proposed model.
关键词：vehicle re-identification; deep learning model; feature fusion
