While significant developments have been made in cell tracking algorithms, current datasets are still limited in size and diversity, especially for data-hungry generalized deep learning models. We introduce a new larger and more diverse cell tracking dataset in terms of number of sequences, length of sequences, and cell lines, accompanied with a public evaluation server and leaderboard to accelerate progress on this new challenging dataset. Our benchmarking of four top performing tracking algorithms highlights new challenges and opportunities to improve the state-of-the-art in cell tracking.
S. Anjum, and D. Gurari. CTMC: Cell Tracking With Mitosis Detection Dataset Challenge. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Computer Vision for Microscopy Images (CVMI), (pp. 982-983), 2020.
Download CTMC Dataset from MOTChallenge Website
Download CTMC Training Dataset (Images and Annotations)
Download CTMC Test Dataset (Images)
Note: Folders img1, gt, det follow the MOT Challenge format and TRA follows the CTC format. In addition, following the MOT Challenge guidelines, all frame numbers and target IDs are 1-based.
We gratefully acknowledge funding from the Chan Zuckerberg Initiative DAF, an advised fund of Silicon Valley Community Foundation. We also thank Microsoft for sponsoring the award to the winners of the 2021 Challenge.
For questions and/or comments, feel free to contact:
Samreen Anjum
samreen.anjum@colorado.edu