Journal
NATURE METHODS
Volume 19, Issue 4, Pages 496-504Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41592-022-01443-0
Keywords
-
Categories
Funding
- Rowland Institute at Harvard University
- Chan Zuckerberg Initiative DAF
- SNSF
- EPFL - Office of Naval Research [N000141410533, N00014-15-1-2234]
- HHMI
- NIH [1R01NS116593-01]
- Bertarelli Foundation Chair of Integrative Neuroscience
Ask authors/readers for more resources
This research extends the DeepLabCut toolbox to enable multi-animal pose estimation, animal identification, and tracking. It is of great significance for solving computer vision problems in multi-animal scenarios and provides a benchmark dataset for algorithm development.
Estimating the pose of multiple animals is a challenging computer vision problem: frequent interactions cause occlusions and complicate the association of detected keypoints to the correct individuals, as well as having highly similar looking animals that interact more closely than in typical multi-human scenarios. To take up this challenge, we build on DeepLabCut, an open-source pose estimation toolbox, and provide high-performance animal assembly and tracking-features required for multi-animal scenarios. Furthermore, we integrate the ability to predict an animal's identity to assist tracking (in case of occlusions). We illustrate the power of this framework with four datasets varying in complexity, which we release to serve as a benchmark for future algorithm development. DeepLabCut is extended to enable multi-animal pose estimation, animal identification and tracking, thereby enabling the analysis of social behaviors.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available