# movement-test-data

Sampe data for testing the movement Python package
- [GitHub repository](https://github.com/neuroinformatics-unit/movement)
- [Documentation](https://movement.neuroinformatics.dev/)


## Licensing information
The `single-crab_MOCA-crab-1_video.mp4` video and corresponding annotations are part of the [Moving Camouflaged Animals Dataset (MoCA) dataset](https://www.robots.ox.ac.uk/~vgg/data/MoCA/).
The MoCA dataset is available to download for commercial/research purposes under a [Creative Commons Attribution 4.0 International License](https://creativecommons.org/licenses/by/4.0/). The copyright remains with the original owners of the video. A complete version of the license for the MoCA dataset can be found [here](https://thor.robots.ox.ac.uk/MoCA/license_MoCA.txt).

The `VIA_single-crab_MOCA-crab-1_linear-interp.csv` file is linearly interpolated from the original data in the MoCA dataset and was contributed by GitHub contributor Mahima Sahu ([@Mahi7828](https://github.com/Mahi7828)).

The original annotation data for the selected clip (`crab_1`) was modified to follow the format of a [VIA tracks file](https://www.robots.ox.ac.uk/~vgg/software/via/docs/face_track_annotation.html). The associated video clip was generated from the frames provided in the MoCA dataset.

The `anipose_mouse-paw_anipose-paper.triangulation.csv` file was taken from `anipose` source data available [here](https://datadryad.org/stash/dataset/doi:10.5061/dryad.nzs7h44s4), released under a [Creative Commons Zero v1.0 Universal License](https://spdx.org/licenses/CC0-1.0.html). The data excerpt was renamed from `mouse-anipose/mouse-testing/020820_preDTreaches_day1/020820_JiDT12/pose-3d/preDT1_JiDT12_reach1_hit.csv`.

## 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](https://doi.org/10.48550/arXiv.2011.11630)