Multi-Target Tracking With Time-Varying Clutter Rate and Detection Profile: Application to Time-Lapse Cell Microscopy Sequences

Abstract

Abstract-Quantitative analysis of the dynamics of tiny cellular and sub-cellular structures, known as particles, in time-lapse cell microscopy sequences requires the development of a reliable multi-target tracking method capable of tracking numerous similar targets in the presence of high levels of noise, high target density, complex motion patterns and intricate interactions. In this paper, we propose a framework for tracking these structures based on the random finite set Bayesian filtering framework. We focus on challenging biological applications where image characteristics such as noise and background intensity change during the acquisition process. Under these conditions, detection methods usually fail to detect all particles and are often followed by missed detections and many spurious measurements with unknown and time-varying rates. To deal with this, we propose a bootstrap filter composed of an estimator and a tracker. The estimator adaptively estimates the required meta parameters for the tracker such as clutter rate and the detection probability of the targets, while the tracker estimates the state of the targets. Our results show that the proposed approach can outperform state-of-the-art particle trackers on both synthetic and real data in this regime.

Multiple Object Tracking in Unknown Backgrounds With Labeled Random Finite Sets

“…Thus by applying Proposition 1, the hybrid multi-object filtering density at time k + 1 is given by (12)(13)(14)(15)(16)(17)(18)(19)(20). Substituting (34), (35), (21)(22)(23) into (12)(13)(14)(15)(16)(17)(18)(19)(20), decomposing…”

“…While this approach is quite general it is not directly applicable to time-varying clutter rate and detection profile, and is also too computationally intensive for an on-line tracker. Previous work on CPHD/PHD, multi-Bernoulli and multi-target Bayes filters for unknown clutter rate and detection profile [9], [18]- [23] do not output object tracks. Further, the CPHD/PHD, multi-Bernoulli filters require more drastic approximations than the GLMB filter.…”

Piecewise-Stationary Motion Modeling and Iterative Smoothing to Track Heterogeneous Particle Motions in Dense Environments

“…The IMM filter borrowed from the radar literature was first applied by [13]. It is well characterized and by now widespread in MPT [11], [7], [18], [27]. The dynamic filtering approaches used in the u-track method [3] has not been described as formally yet.…”

“…Transient disappearances, object misdetection and particle merging have been recovered by either considering link cost minimization on a group of frames for optimization [6], [7], [8] or using a post-processing step applied on tracklets [3]. Particle detection and linking is an efficient framework to estimate trajectories when the signal-to-noise ratio (SNR) is sufficient, lower SNR acquisition can be handled using pixel-based probabilistic approaches such as particle filters [14], [15], JPDA methods [5], [16], [17] modeling of perceivability [7], target cardinality [18] or iterative and alternative object detection and tracking [4]. …”

Tracking Virus Particles in Fluorescence Microscopy Images Using Multi-Scale Detection and Multi-Frame Association

“…While being computationally efficient, deterministic approaches have difficulties in dealing with spurious objects and detection errors [3]. In comparison, probabilistic approaches perform spatial-temporal filtering to robustly estimate the position of particles under noisy conditions (e.g., [4], [3], [5], [6], [7], [8], [9], [10], [11]). However, a disadvantage of certain probabilistic approaches is that for multiple particle tracking only two frames are taken into account for association finding (e.g., [5]).…”