Back to Search
Start Over
Coupling cell detection and tracking by temporal feedback
- Source :
- Machine Vision and Applications. 31
- Publication Year :
- 2020
- Publisher :
- Springer Science and Business Media LLC, 2020.
-
Abstract
- The tracking-by-detection strategy is the backbone of many methods for tracking living cells in time-lapse microscopy. An object detector is first applied to the input images, and the resulting detection candidates are then linked by a data association module. The performance of such methods strongly depends on the quality of the detector because detection errors propagate to the linking step. To tackle this issue, we propose a joint model for segmentation, detection and tracking. The model is defined implicitly as limiting distribution of a Markov chain Monte Carlo algorithm and contains a temporal feedback, which allows to dynamically alter detector parameters using hints given by neighboring frames and, in this way, correct detection errors. The proposed method can integrate any detector and is therefore not restricted to a specific domain. The parameters of the model are learned using an objective based on empirical risk minimization. We use our method to conduct large-scale experiments for confluent cultures of endothelial cells and evaluate its performance in the ISBI Cell Tracking Challenge, where it consistently scored among the best three methods.
- Subjects :
- 0301 basic medicine
Coupling
Computer science
business.industry
Detector
Asymptotic distribution
Pattern recognition
Tracking (particle physics)
030218 nuclear medicine & medical imaging
Computer Science Applications
Domain (software engineering)
03 medical and health sciences
030104 developmental biology
0302 clinical medicine
Hardware and Architecture
Pattern recognition (psychology)
Segmentation
Computer Vision and Pattern Recognition
Empirical risk minimization
Artificial intelligence
business
Software
Subjects
Details
- ISSN :
- 14321769 and 09328092
- Volume :
- 31
- Database :
- OpenAIRE
- Journal :
- Machine Vision and Applications
- Accession number :
- edsair.doi...........058cc191f4b4d92c0ee6c14e792496bb