MART: Mask-Aware Reasoning Transformer for Vehicle Re-Identification

Lu, Zefeng; Lin, Ronghao; Hu, Haifeng

doi:10.1109/tits.2022.3219593

Cited by 7 publications

(2 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our method with some state-of-the-art (SOTA) approaches from the last three years, categorized into three groups: (1) Global feature-based (GF) methods, such as SN [13], VARID [12], VAT [18], and MsKAT [32], mainly concentrate on extracting whole representation for vehicle images. (2) Local feature-based (LF) methods, including DPGM [14], LG-CoT [36], HPGN [37], DFR [38], DSN [39], SFMNet [40], GiT [31], SOFCT [22], MART [41] integrate local features with the global feature to learn reliable vehicle representations. (3) Spatial-temporal (ST) methods, such as DPGM-ST [14] and DFR-ST [38], exploit extra timestamp and camera location information to enhance vehicle re-identification using visual features.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

An,

Zhang,

Shi

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

As a core technology in intelligent transportation systems, vehicle re-identification has attracted growing attention. Most existing methods use CNNs to extract global and local features from vehicle images and roughly integrate them for identifying vehicles, addressing intra-class similarity and inter-class difference. However, a significant challenge arises from redundant information between global and local features and possible misalignment among local features, resulting in suboptimal efficiency when combined. To further improve vehicle re-identification, we propose a stripe-assisted global transformer (SaGT) method, which leverages a dual-branch network based on transformers to learn a discriminative whole representation for each vehicle image. Specifically, one branch exploits a standard transformer layer to extract a global feature, while the other branch employs a stripe feature module (SFM) to construct stripe-based features. To further facilitate the effective incorporation of local information into the learning process of the global feature, we introduce a novel stripe-assisted global loss (SaGL), which combines ID losses to optimize the model. Considering redundancy, we only use the global feature for inference, as we enhance the whole representation with stripe-specific details. Finally, we introduce a spatial-temporal probability (STPro) to provide a complementary metric for robust vehicle re-identification. Extensive and comprehensive evaluations on two public datasets validate the effectiveness and superiority of our proposed method.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

An,

Zhang,

Shi

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The second approach is based on visual features. The traditional feature descriptors such as SURF and deep learning features can be used [9] [10]. With this approach the candidate VBMs share visual features of their external images, and VPM will compare locally measured and shared visual features and determine if the CAV is matched.…”

Section: Introductionmentioning

confidence: 99%

Matching 5G Connected Vehicles to Sensed Vehicles for Safe Cooperative Autonomous Driving

Tang,

He,

Yang

et al. 2024

IEEE Network

View full text Add to dashboard Cite

5G connected autonomous vehicles (CAVs) help enhance perception of driving environment and cooperation among vehicles by sharing sensing and driving information, which is a promising technology to avoid accidents and improve road-use efficiency. A key issue for cooperation among CAVs is matching communicating vehicles to those captured in sensors such as cameras, LiDAR, etc.. Incorrect vehicle matching may cause serious accidents. While centimeter level positioning is now available for autonomous vehicles, matching connected vehicles to sensed vehicles (MCSV) is still challenging and has rarely been studied. In this paper, we are motivated to investigate the MCSV problem for 5G CAVs, propose and assess solutions for the problem to bridge the research gap. We formulate the MCSV problem and propose two MCSV approaches to support cooperative driving. The first approach is based on vehicle registration number (VRN), which is unique to identify a vehicle and can be shared among CAVs for MCSV. VRN is hashed before sharing to protect privacy, and will be compared to the shared one for vehicle matching. The second MCSV approach is based on visual features of vehicle's external views, which are shared with other CAVs and compared to those obtained from visual sensors to match the vehicles of interest. A new MCSV dataset is developed to assess the effectiveness of the proposed approaches. Experiment results show that both approaches are feasible and useful, and they achieve a very low false positive rate, which is critical for cooperative driving safety.

show abstract

Modality and Camera Factors Bi-Disentanglement for NIR-VIS Object Re-Identification

Lin

2023

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

MART: Mask-Aware Reasoning Transformer for Vehicle Re-Identification

Cited by 7 publications

References 61 publications

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

Matching 5G Connected Vehicles to Sensed Vehicles for Safe Cooperative Autonomous Driving

Modality and Camera Factors Bi-Disentanglement for NIR-VIS Object Re-Identification

Contact Info

Product

Resources

About