Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
© 2019 IEEE. Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification clustering (3C), a technique that simultaneously tra...
| Main Authors: | , , , , , |
|---|---|
| 其他作者: | |
| 格式: | 文件 |
| 语言: | English |
| 出版: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| 在线阅读: | https://hdl.handle.net/1721.1/137351 |
| _version_ | 1826200142693269504 |
|---|---|
| author | Meirovitch, Yaron Mi, Lu Saribekyan, Hayk Matveev, Alexander Rolnick, David Shavit, Nir |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Meirovitch, Yaron Mi, Lu Saribekyan, Hayk Matveev, Alexander Rolnick, David Shavit, Nir |
| author_sort | Meirovitch, Yaron |
| collection | MIT |
| description | © 2019 IEEE. Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification clustering (3C), a technique that simultaneously tracks complex, interrelated objects in an image stack. The key idea in cross-classification is to efficiently turn a clustering problem into a classification problem by running a logarithmic number of independent classifications per image, letting the cross-labeling of these classifications uniquely classify each pixel to the object labels. We apply the 3C mechanism to achieve state-of-the-art accuracy in connectomics-The nanoscale mapping of neural tissue from electron microscopy volumes. Our reconstruction system increases scalability by an order of magnitude over existing single-object tracking methods (such as flood-filling networks). This scalability is important for the deployment of connectomics pipelines, since currently the best performing techniques require computing infrastructures that are beyond the reach of most laboratories. Our algorithm may offer benefits in other domains that require pixel-accurate tracking of multiple objects, such as segmentation of videos and medical imagery. |
| first_indexed | 2024-09-23T11:31:51Z |
| format | Article |
| id | mit-1721.1/137351 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:31:51Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1373512023-02-08T19:44:57Z Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics Meirovitch, Yaron Mi, Lu Saribekyan, Hayk Matveev, Alexander Rolnick, David Shavit, Nir Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science © 2019 IEEE. Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification clustering (3C), a technique that simultaneously tracks complex, interrelated objects in an image stack. The key idea in cross-classification is to efficiently turn a clustering problem into a classification problem by running a logarithmic number of independent classifications per image, letting the cross-labeling of these classifications uniquely classify each pixel to the object labels. We apply the 3C mechanism to achieve state-of-the-art accuracy in connectomics-The nanoscale mapping of neural tissue from electron microscopy volumes. Our reconstruction system increases scalability by an order of magnitude over existing single-object tracking methods (such as flood-filling networks). This scalability is important for the deployment of connectomics pipelines, since currently the best performing techniques require computing infrastructures that are beyond the reach of most laboratories. Our algorithm may offer benefits in other domains that require pixel-accurate tracking of multiple objects, such as segmentation of videos and medical imagery. 2021-11-04T15:48:42Z 2021-11-04T15:48:42Z 2019-06 2021-02-04T16:10:07Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137351 Meirovitch, Yaron, Mi, Lu, Saribekyan, Hayk, Matveev, Alexander, Rolnick, David et al. 2019. "Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics." Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June. en 10.1109/CVPR.2019.00862 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Meirovitch, Yaron Mi, Lu Saribekyan, Hayk Matveev, Alexander Rolnick, David Shavit, Nir Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title | Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title_full | Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title_fullStr | Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title_full_unstemmed | Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title_short | Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics |
| title_sort | cross classification clustering an efficient multi object tracking technique for 3 d instance segmentation in connectomics |
| url | https://hdl.handle.net/1721.1/137351 |
| work_keys_str_mv | AT meirovitchyaron crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics AT milu crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics AT saribekyanhayk crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics AT matveevalexander crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics AT rolnickdavid crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics AT shavitnir crossclassificationclusteringanefficientmultiobjecttrackingtechniquefor3dinstancesegmentationinconnectomics |