Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification

William Grolleau, Achraf Chaouch, Astrid Sabourin, Guillaume Lapouge, Catherine Achard

Abstract

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.

MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification

Abstract

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 cattle individuals captured from uniformly sampled viewpoints ( 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.
Paper Structure (16 sections, 3 figures, 4 tables)

This paper contains 16 sections, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Dataset Limitations
  4. Viewpoint-Agnostic ReID
  5. Dataset description
  6. Generation Pipeline
  7. Metadata
  8. Evaluation Protocols
  9. Viewpoint Analysis
  10. Implementation Details
  11. Elevation Impact
  12. Azimuth Impact
  13. Experiments
  14. MOO Benchmark
  15. Real-World Transferability
  16. ...and 1 more sections

Figures (3)

  • Figure 1: MOO: A synthetic dataset for systematic analysis and real-world transferability. The workflow encompasses (1) individual generation; (2) dataset rendering; and (3) systematic analysis and real-world transfer.
  • Figure 2: mAP per training elevation range across eight partitions evaluated in a same-view setup, where Query and gallery images share the same elevation.
  • Figure 3: mAP for the best Single-View expert (black dot) and All-View model (blue curve) across eight partitions evaluated in a same-view setup, where Query and gallery images share the same elevation.