Academic Journal
Two-Stage Progressive Learning for Vehicle Re-Identification in Variable Illumination Conditions
| العنوان: | Two-Stage Progressive Learning for Vehicle Re-Identification in Variable Illumination Conditions |
|---|---|
| المؤلفون: | Zhihe Wu, Zhi Jin, Xiying Li |
| المصدر: | Electronics, Vol 12, Iss 24, p 4950 (2023) |
| بيانات النشر: | MDPI AG |
| سنة النشر: | 2023 |
| المجموعة: | Directory of Open Access Journals: DOAJ Articles |
| مصطلحات موضوعية: | vehicle re-identification, dataset, illumination aware, detail aware, discriminative feature learning, Electronics, TK7800-8360 |
| الوصف: | Vehicle matching in variable illumination environments can be challenging due to the heavy dependence of vehicle appearance on lighting conditions. To address this issue, we propose a two-stage progressive learning (TSPL) framework. In the first stage, illumination-aware metric learning is enforced using a two-branch network via two illumination-specific feature spaces, used to explicitly model differences in lighting. In the second stage, discriminative feature learning is introduced to extract distinguishing features from a given vehicle. This process consists of a local feature extraction attention module, a local constraint, and a balanced sampling strategy. During the metric learning phase, the model expresses the union of local features, extracted from the attention module, with illumination-specific global features to form joint vehicle features. As part of the study, we construct a large-scale dataset, termed VERI-DAN (vehicle re-identification across day and night), to address the current lack of vehicle datasets exhibiting variable lighting conditions. This set is composed of 200,004 images from 16,654 vehicles, collected in various natural illumination environments. Validation experiments conducted with the VERI-DAN and Vehicle-1M datasets demonstrated that our proposed methodology effectively improved vehicle re-identification Rank-1 accuracy. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| تدمد: | 2079-9292 |
| Relation: | https://www.mdpi.com/2079-9292/12/24/4950; https://doaj.org/toc/2079-9292; https://doaj.org/article/58b16827a88d4fa49c631211df4b6b28 |
| DOI: | 10.3390/electronics12244950 |
| الاتاحة: | https://doi.org/10.3390/electronics12244950 https://doaj.org/article/58b16827a88d4fa49c631211df4b6b28 |
| رقم الانضمام: | edsbas.F578989B |
| قاعدة البيانات: | BASE |
Full Text Finder | تدمد: | 20799292 |
|---|---|
| DOI: | 10.3390/electronics12244950 |