Network Flow Method Integrates Skeleton Information for Multiple C. elegans Tracking
Open Access
Abstract
In order to solve the issues arising from collisions, this paper proposes a network flow method combined with skeleton information for multiple C. elegans tracking. In the intra-track stage, non-colliding C. elegans are identified and associated as trajectory fragments based on their motion and positional information, and colliding C. elegans are then segmented based on an improved skeleton algorithm and matched as trajectory fragments. Subsequently, the trajectory fragments are employed as vertices to construct a network flow model. The minimum-cost method is then utilized to solve the model, thereby obtaining the optimal solution for the multiple C. elegans trajectories. The proposed method was evaluated using video data of the C. elegans population at three distinct ages: L4, young adult, and D1. The experimental results demonstrate that the method proposed in this paper exhibits a MOTA between 0.86 and 0.92, and an MOTP between 0.78 and 0.83, which indicates that the proposed method can be employed in multiple C. elegans tracking. It is our hope that this method will prove beneficial to C. elegans laboratories, offering a novel approach to multiple C. elegans tracking.Keywords
This publication has 19 references indexed in Scilit:
- Deep-worm-tracker: Deep learning methods for accurate detection and tracking for behavioral studies in C. elegansApplied Animal Behaviour Science, 2023
- Multi-object tracking based on network flow model and ORB featureApplied Intelligence, 2022
- Small flexible automated system for monitoring Caenorhabditis elegans lifespan based on active vision and image processing techniquesScientific Reports, 2021
- Improving skeleton algorithm for helping Caenorhabditis elegans trackersScientific Reports, 2020
- A hybrid algorithm based on particle filter and genetic algorithm for target trackingExpert Systems with Applications, 2020
- Drug discovery technologies: Caenorhabditis elegans as a model for anthelmintic therapeuticsMedicinal Research Reviews, 2020
- A network approach to discerning the identities of C. elegans in a free moving populationScientific Reports, 2016
- A Predictable Worm: Application of Caenorhabditis elegans for Mechanistic Investigation of Movement DisordersNeurotherapeutics, 2012
- High-throughput behavioral analysis in C. elegansNature Methods, 2011
- Feature extraction based on the Bhattacharyya distancePattern Recognition, 2003