Online Neural Cell Tracking Using Blob-Seed Segmentation and Optical Flow
Abstract
Existing neural cell tracking methods generally use the morphology cell features for data association. However, these features are limited to the quality of cell segmentation and are prone to errors for mitosis determination. To overcome these issues, in this work we propose an online multi-object tracking method that leverages both cell appearance and motion features for data association. In particular, we propose a supervised blob-seed network (BSNet) to predict the cell appearance features and an unsupervised optical flow network (UnFlowNet) for capturing the cell motions. The data association is then solved using the Hungarian algorithm. Experimental evaluation shows that our approach achieves better performance than existing neural cell tracking methods.
Cite
Text
Yi et al. "Online Neural Cell Tracking Using Blob-Seed Segmentation and Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00138Markdown
[Yi et al. "Online Neural Cell Tracking Using Blob-Seed Segmentation and Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/yi2019cvprw-online/) doi:10.1109/CVPRW.2019.00138BibTeX
@inproceedings{yi2019cvprw-online,
title = {{Online Neural Cell Tracking Using Blob-Seed Segmentation and Optical Flow}},
author = {Yi, Jingru and Wu, Pengxiang and Huang, Qiaoying and Qu, Hui and Hoeppner, Daniel J. and Metaxas, Dimitris N.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {1057-1064},
doi = {10.1109/CVPRW.2019.00138},
url = {https://mlanthology.org/cvprw/2019/yi2019cvprw-online/}
}