2014 | OriginalPaper | Buchkapitel
A Novel Ant System with Multiple Tasks for Spatially Adjacent Cell State Estimate
verfasst von : Mingli Lu, Benlian Xu, Peiyi Zhu, Jian Shi
Erschienen in: Advances in Swarm Intelligence
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Multi-cell tracking is an important problem in studies of dynamic cell cycle behaviors. This paper models a novel multi-tasking ant system that jointly estimates the number of cells and their individual states in cell image sequences. Our ant system adopts an interactive mode with cooperation and competition. In simulations of real cell image sequences, the multi-tasking ant system integrated with interactive mode yielded better tracking results . Furthermore, the results suggest that our algorithm can automatically and accurately track numerous cells in various scenarios, and is competitive with state-of-the-art multi-cell tracking methods.