Vehicle Re-Identification in Aerial Images and Videos: Dataset and Approach

Jiao, Bingliang; Yang, Lu; Gao, Liying; Wang, Peng; Zhang, Yanning

doi:10.1109/tcsvt.2023.3298788

Cited by 6 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vehicle re-identification (Re-ID) aims to retrieve specific target vehicles across a multicamera surveillance system [1][2][3]. Although some supervised learning works have achieved remarkable performance, the Re-ID system still suffers from the challenge of massive manual annotations.…”

Section: Introductionmentioning

confidence: 99%

Dual-Level Viewpoint-Learning for Cross-Domain Vehicle Re-Identification

Zhou,

Wang,

Cao

et al. 2024

Electronics

View full text Add to dashboard Cite

The definition of vehicle viewpoint annotations is ambiguous due to human subjective judgment, which makes the cross-domain vehicle re-identification methods unable to learn the viewpoint invariance features during source domain pre-training. This will further lead to cross-view misalignment in downstream target domain tasks. To solve the above challenges, this paper presents a dual-level viewpoint-learning framework that contains an angle invariance pre-training method and a meta-orientation adaptation learning strategy. The dual-level viewpoint-annotation proposal is first designed to concretely redefine the vehicle viewpoint from two aspects (i.e., angle-level and orientation-level). An angle invariance pre-training method is then proposed to preserve identity similarity and difference across the cross-view; this consists of a part-level pyramidal network and an angle bias metric loss. Under the supervision of angle bias metric loss, the part-level pyramidal network, as the backbone, learns the subtle differences of vehicles from different angle-level viewpoints. Finally, a meta-orientation adaptation learning strategy is designed to extend the generalization ability of the re-identification model to the unseen orientation-level viewpoints. Simultaneously, the proposed meta-learning strategy enforces meta-orientation training and meta-orientation testing according to the orientation-level viewpoints in the target domain. Extensive experiments on public vehicle re-identification datasets demonstrate that the proposed method combines the redefined dual-level viewpoint-information and significantly outperforms other state-of-the-art methods in alleviating viewpoint variations.

show abstract

Section: Introductionmentioning

confidence: 99%

Dual-Level Viewpoint-Learning for Cross-Domain Vehicle Re-Identification

Zhou,

Wang,

Cao

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…V EHICLE Re-identification (Re-ID) is an important task in intelligent transportation systems [1,2,3,4,5], as it allows for the retrieval of the same vehicle from multiple non-overlapping surveillance cameras. With the availability of vehicle surveillance datasets [6,7,8,9], many vehicle Re-ID models have been proposed [10,11,12,13], which have made significant progress in the past decade and gained wide interest among the research communities of human-machine systems, cybernetics, and transportation.…”

Section: Introductionmentioning

confidence: 99%

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

Zheng

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

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.

show abstract