Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.04314 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917543651835904 |
|---|---|
| author | Grolleau, William Chaouch, Achraf Sabourin, Astrid Lapouge, Guillaume Achard, Catherine |
| author_facet | Grolleau, William Chaouch, Achraf Sabourin, Astrid Lapouge, Guillaume Achard, Catherine |
| contents | Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04314 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification Grolleau, William Chaouch, Achraf Sabourin, Astrid Lapouge, Guillaume Achard, Catherine Computer Vision and Pattern Recognition Artificial Intelligence Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO. |
| title | MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.04314 |