Academic Journal
Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification
| العنوان: | Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification |
|---|---|
| المؤلفون: | Yasong An, Xiaofei Zhang, Bodong Shi, Xiaojun Tan |
| المصدر: | Applied Sciences, Vol 14, Iss 10, p 3968 (2024) |
| بيانات النشر: | MDPI AG |
| سنة النشر: | 2024 |
| المجموعة: | Directory of Open Access Journals: DOAJ Articles |
| مصطلحات موضوعية: | computer vision, vehicle re-identification, discriminative feature, spatial-temporal probability, intelligent transportation systems, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999 |
| الوصف: | 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. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| تدمد: | 2076-3417 |
| Relation: | https://www.mdpi.com/2076-3417/14/10/3968; https://doaj.org/toc/2076-3417; https://doaj.org/article/f4b81b1d526340328150a1297b342913 |
| DOI: | 10.3390/app14103968 |
| الاتاحة: | https://doi.org/10.3390/app14103968 https://doaj.org/article/f4b81b1d526340328150a1297b342913 |
| رقم الانضمام: | edsbas.491CE482 |
| قاعدة البيانات: | BASE |
Full Text Finder | تدمد: | 20763417 |
|---|---|
| DOI: | 10.3390/app14103968 |