Tracking Cells and Their Lineages Via Labeled Random Finite Sets

Determining the trajectories of cells and their lineages or ancestries in live-cell experiments are fundamental to understanding how behave divide. This paper proposes novel online algorithms for jointly tracking resolving an unknown time-varying number from time-lapse video data. Our approach involves modeling cell ensemble as a labeled random finite set with labels representing identities lineages. A spawning model is developed take into account changes appearance prior division. We then derive analytic filters propagate multi-object distributions that contain information on current including also develop numerical implementations resulting filters. Experiments using simulation, synthetic migration video, real sequence, presented demonstrate capability solutions.