VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915983864627200 |
|---|---|
| author | Ginige, Yasod Gunasekara, Ransika Hewavitharana, Darsha Ariyarathne, Manjula Jayasekara, Peshala Rodrigo, Ranga |
| author_facet | Ginige, Yasod Gunasekara, Ransika Hewavitharana, Darsha Ariyarathne, Manjula Jayasekara, Peshala Rodrigo, Ranga |
| contents | Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle dataset and a thermal maritime dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above datasets in mAP scores, respectively. We also plan to make our thermal dataset available, the first of its kind for maritime vessel identification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04750 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision Ginige, Yasod Gunasekara, Ransika Hewavitharana, Darsha Ariyarathne, Manjula Jayasekara, Peshala Rodrigo, Ranga Computer Vision and Pattern Recognition Systems and Control Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle dataset and a thermal maritime dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above datasets in mAP scores, respectively. We also plan to make our thermal dataset available, the first of its kind for maritime vessel identification. |
| title | VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision |
| topic | Computer Vision and Pattern Recognition Systems and Control |
| url | https://arxiv.org/abs/2605.04750 |