Attribute and State Guided Structural Embedding Network for Vehicle Re-Identification

Abstract

Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for the Vehicle Re-ID models in the real world. To promote the Vehicle Re-ID models, this paper proposes to synthesize a large number of vehicle images in the target pose, whose idea is to project the vehicles of diverse poses into the unified target pose so as to enhance feature discrimination. Considering that the paired data of the same vehicles in different traffic surveillance cameras might be not available in the real world, we propose the first Pair-flexible Pose Guided Image Synthesis method for Vehicle Re-ID, named as VehicleGAN in this paper, which works for both supervised and unsupervised settings without the knowledge of geometric 3D models. Because of the feature distribution difference between real and synthetic data, simply training a traditional metric learning based Re-ID model with data-level fusion (i.e., data augmentation) is not satisfactory, therefore we propose a new Joint Metric Learning (JML) via effective feature-level fusion from both real and synthetic data. Intensive experimental results on the public VeRi-776 and VehicleID datasets prove the accuracy and effectiveness of our proposed VehicleGAN and JML.

Two-Stage Progressive Learning for Vehicle Re-Identification in Variable Illumination Conditions

“…Yan et al [19] proposed a multi-grain ranking loss to discriminate vehicles with a similar appearance. Studies have also shown that attributes, such as color, brand, and wheel pattern, can further improve re-ID efficacy [1,[20][21][22]. Other strategies [20,21,[23][24][25][26][27] have exploited the indirect attributes of a vehicle, such as camera perspective information and background information, making considerable improvements.…”

GLFNet: Combining Global and Local Information in Vehicle Re-Recognition

“…Method Type Advantage Limitation [19,20] Deep learning High recognition accuracy High cost; poor interpretability [21,22] Spatiotemporal information Works well for hard samples Additional complex spatiotemporal labels are required [16,17] Metrics learning High recognition accuracy High cost [23,24] Multidimensional information based…”