Published June 28, 2023 | Version 1.0

Deeptangle Dataset: Labelled Experimental and Synthetic Videos of Swimming and Overlapping C. elegans worms

  • 1. University of Copenhagen

Description

This repository contains the dataset employed in the paper Fast spline detection in high density microscopy data.

Three files are provided:

1. videos.zip: raw experimental videos.
2. labeled_data.zip: labelled sections of experimental videos used for evaluation
3. syntehthic_dataset.zip: synthetic dataset used for training

Labelled data

Sections are named as VIDEONAME_FRAMENUMBER_SECTIONID.
All labels are in labels.json and correspond to the middle frame of the clip (05.png).
Example plotting script is provided (plot_data.py).

Synthetic data

Clips are named as NUMBEROFWORMS_ID.
Labels (for all frames) are stored in labels.npy.
Example plotting script is provided (plot_data.py).

 

Related

Paper: https://arxiv.org/abs/2301.04460

Deeptangle code: https://github.com/kirkegaardlab/deeptangle

Labelling tool: https://github.com/kirkegaardlab/deeptanglelabel

---

If used, please cite

Albert Alonso & Julius B. Kirkegaard. Fast spline detection in high density microscopy data. 2023.

Notes

Experimental videos were provided by Celia Raimondi, Sunehera Sarwat and Michele Perni. This work was supported by the Novo Nordisk Foundation, Grant Agreement NNF20OC0062047.

Files

labeled_data.zip

Files (8.7 GB)

Name Size
md5:100fe44d8b5d5d6864f4f995ffe817e4
57.5 MB Preview Download
md5:90854a303d0bd84e0992a3e8ff488e68
643.1 MB Preview Download
md5:e5e1dc48fc95c8849b976bd251e2b31d
8.0 GB Preview Download

Additional details

Related works

Is supplement to
Journal article: arXiv:2301.04460 (arXiv)
Software: 10.5281/zenodo.8093334 (DOI)