Sample data for the movement Python package. https://movement.neuroinformatics.dev/

Luigi Petrucco 75b18be45f anipose metadata fix há 1 ano atrás
bboxes 01ebce1d0e Add MoCA clip há 1 ano atrás
frames 01ebce1d0e Add MoCA clip há 1 ano atrás
poses a3b138d3ce anipose data há 1 ano atrás
videos 01ebce1d0e Add MoCA clip há 1 ano atrás
LICENSE 58cd7efc36 Initial commit há 3 anos atrás
README.md 5537394204 Cosmetic changes to licensing info há 1 ano atrás
bboxes_hashes.txt 01ebce1d0e Add MoCA clip há 1 ano atrás
frames_hashes.txt 01ebce1d0e Add MoCA clip há 1 ano atrás
get_sha256_hashes.py a27d980ca1 Update hashes script to include bboxes folder há 2 anos atrás
metadata.yaml 75b18be45f anipose metadata fix há 1 ano atrás
poses_hashes.txt 5d27b797ec git-annex in sfmig@Sofias-MacBook-Pro-SWC.local há 1 ano atrás
videos_hashes.txt 01ebce1d0e Add MoCA clip há 1 ano atrás

README.md

movement-test-data

Sampe data for testing the movement Python package

Licensing information

The single-crab_MOCA-crab-1_video.mp4 video and corresponding annotations are part of the Moving Camouflaged Animals Dataset (MoCA) dataset. The MoCA dataset is available to download for commercial/research purposes under a Creative Commons Attribution 4.0 International License. The copyright remains with the original owners of the video. A complete version of the license for the MoCA dataset can be found here.

The original annotation data for the selected clip (crab_1) was modified to follow the format of a VIA tracks file. The associated video clip was generated from the frames provided in the MoCA dataset.

References

Lamdouar, H., Yang, C., Xie, W., & Zisserman, A. (2020). "Betrayed by motion: Camouflaged object discovery via motion segmentation". In Proceedings of the Asian Conference on Computer Vision. doi: 10.48550/arXiv.2011.11630