Quantifying agonistic interactions between group-housed animals to derive social hierarchies using computer vision: a case study with commercially group-housed rabbits

Analysis of rabbit videos to automatically infer dominance using group-housed rabbit doe videos recorded by ILVO.

Folder Structure

  1. Action Diagrams: Get segmentation of agonistic moments using optical flow algorithms and plot over time.
  2. Behaviour Detection: Detection scripts of agonistic behaviors using the tracklet information (more information inside README.md)
  3. Colab Scripts: Online module tests
  4. Detectron 2: Get random images for COCO format annotation
  5. Feeding Series: Analysis of the surrondings of the feeding stations over time
  6. HPC Analysis: Scripts that run on high-performance computing facility
  7. Heat Map Scripts: Temporal space usage detection module
  8. OOP Development: Object-oriented programming scripts
  9. Rabbit Over Platform: Detection of rabbit does on the top of the elevated platform
  10. Second Platform: Detection of rabbit does on the top of the second elevated platform used for treatment enhancement
  11. Tracking: Tracking rabbit does in the action clips using a custom algorithm based on the detection BBOX and re-identification data