Subject: Computer Science, Systems and Electrical Engineering
Author Organization: University of Konstanz
Author Organization: Max Planck Institute of Animal Behavior
Study Type: experimental
1 to 3 of 3 Results
Jun 13, 2024
Chimento, Michael; Chan, Hoi Hang; Aplin, Lucy; Kano, Fumihiro, 2024, "Additional dataset for: Peering into the world of wild passerines with 3D-SOCS: synchronized video capture for posture estimation", https://doi.org/10.17617/3.ZQMOJ3, Edmond, V1
This dataset includes sample data to reproduce the 3D-SOCS pipeline, as well as an annotated dataset and trained model weights for object detection and 2D keypoint estimation for Great tits and Blue tits. For more details, code and implementation of the pipeline, we refer to: htt... |
May 7, 2024
Naik, Hemal; Chan, Alex Hoi Hang; Yang, Junran; Delacoux, Mathilde; Couzin, D. Iain; Kano, Fumihiro; Nagy, Mate, 2023, "3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture", https://doi.org/10.17617/3.HPBBC7, Edmond, V6
The 3DPOP dataset is a large scale 2D to 3D posture, identity and trajectory dataset for freely moving pigeons. We use marker-based motion tracking to first track precise head and body position and orientation for multiple individuals, then propagated custom keypoints based on th... |
Jan 3, 2024
Waldmann, Urs; Chan, Hoi Hang Alex; Naik, Hemal; Nagy, Mate; Couzin, Iain D.; Deussen, Oliver; Goldluecke, Bastian; Kano, Fumihiro, 2024, "Wild-MuPPET - Multi-view posture dataset of foraging pigeons in the wild", https://doi.org/10.17617/3.ENDMTI, Edmond, V1
Wild-MuPPET is a multi-view posture dataset of foraging pigeons outdoors, with 500 frames of 3D-ground truth and 2000 frames of 2D-ground truth of 9 keypoints. Paper: https://doi.org/10.48550/arXiv.2308.15316 Git repository: https://github.com/alexhang212/3D-MuPPET |