GAN-Siamese Network for Cross-Domain Vehicle Re-Identification in Intelligent Transport Systems

Zhou, Zhili; Li, Yujiang; Li, Jin; Yu, Keping; Kou, Guang; Wang, Meimin; Gupta, Brij B.

doi:10.1109/tnse.2022.3199919

Cited by 53 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-domain Re-ID [26,27] transfers knowledge to the unlabeled target domain for unsupervised training through pre-training in the labeled source domain to reduce the labor cost of the new domain. Yu et al [28] proposed an unsupervised vehicle Re-ID approach that uses label-free datasets through self-supervised metric learning (SSML) based on a feature dictionary.…”

Section: Cross-domain Learning For Vehicle Re-idmentioning

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: Cross-domain Learning For Vehicle Re-idmentioning

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

“…The discriminator receives the data from the generator and judges the data, and finally reaches a balanced state. Zhou et al [106] presented a GAN-siame network to solve the unsupervised V-reID cross-domain problem. The algorithm learns the distance measurement between two domains by connecting the network, which improves the performance of model matching.…”

Section: Vehicle Re-identification Based On Unsupervised Learningmentioning

confidence: 99%

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Fei

Han

2023

Sensors

View full text Add to dashboard Cite

Multi-Objective Multi-Camera Tracking (MOMCT) is aimed at locating and identifying multiple objects from video captured by multiple cameras. With the advancement of technology in recent years, it has received a lot of attention from researchers in applications such as intelligent transportation, public safety and self-driving driving technology. As a result, a large number of excellent research results have emerged in the field of MOMCT. To facilitate the rapid development of intelligent transportation, researchers need to keep abreast of the latest research and current challenges in related field. Therefore, this paper provide a comprehensive review of multi-object multi-camera tracking based on deep learning for intelligent transportation. Specifically, we first introduce the main object detectors for MOMCT in detail. Secondly, we give an in-depth analysis of deep learning based MOMCT and evaluate advanced methods through visualisation. Thirdly, we summarize the popular benchmark data sets and metrics to provide quantitative and comprehensive comparisons. Finally, we point out the challenges faced by MOMCT in intelligent transportation and present practical suggestions for the future direction.

show abstract

“…This affects the overall performance of SGM when using these data for training [22]. LM (Levenberg-Marquardt) optimization algorithm is a commonly used nonlinear least square method, which combines the respective advantages of steepest descent method and Gaussian Newton method [32]. In one iteration of the algorithm, when the obtained solution deviates far from the optimal solution, the algorithm can be approximately regarded as the steepest descent method [33].…”

Section: B 3d Image Vrmentioning

confidence: 99%

A Kruppa Equation-Based Virtual Reconstruction Method for 3D Images Under Visual Communication Scenes

Yang,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

Visual communication (VC) manages to demonstrate optimal perception effect through reasonable element planning. It has been a more prevalent tendency to introduce 3D image reconstruction into VC activities. Currently, there still lacks reliable solution for this purpose under VC scenes. To deal with this issue, we propose a Kruppa equation-based virtual reconstruction method for 3D images under VC scenes. Firstly, the feature descriptor procedure in scale-invariant feature transform (SIFT) algorithm is introduced into image matching. Then, Harris corner extraction (HCE) algorithm is utilized for selection of feature points. And according to HCE algorithm, we develop a specific direction feature description method. In the proposal, main camera points are calibrated separately, which not only makes the calibration accuracy of the main points higher, but also reduces the unknown parameters of Kruppa equation. Finally, we conduct some experiments to verify efficiency of the proposal. The obtained results show that calibration accuracy of the proposal is 12% higher than other comparison methods, and better virtual reconstruction results can be achieved.

show abstract

GAN-Siamese Network for Cross-Domain Vehicle Re-Identification in Intelligent Transport Systems

Cited by 53 publications

References 59 publications

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

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

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

A Kruppa Equation-Based Virtual Reconstruction Method for 3D Images Under Visual Communication Scenes

Contact Info

Product

Resources

About