Tracking multiple moving objects in images using Markov Chain Monte Carlo

TL;DR

This paper introduces a Bayesian MCMC-based algorithm for multiple target tracking directly from images, improving accuracy especially in challenging scenarios like dim or overlapping targets.

Contribution

It presents a novel MCMC algorithm that models image generation directly, avoiding information loss from traditional pre-processing in multiple target tracking.

Findings

Enhanced tracking accuracy over existing methods

Effective in dim and overlapping target scenarios

Validated on synthetic and real microscopy data

Abstract

A new Bayesian state and parameter learning algorithm for multiple target tracking (MTT) models with image observations is proposed. Specifically, a Markov chain Monte Carlo algorithm is designed to sample from the posterior distribution of the unknown number of targets, their birth and death times, states and model parameters, which constitutes the complete solution to the tracking problem. The conventional approach is to pre-process the images to extract point observations and then perform tracking. We model the image generation process directly to avoid potential loss of information when extracting point observations. Numerical examples show that our algorithm has improved tracking performance over commonly used techniques, for both synthetic examples and real florescent microscopy data, especially in the case of dim targets with overlapping illuminated regions.