Abrupt Motion Tracking via Nearest Neighbor Field Driven Stochastic Sampling

TL;DR

This paper introduces a novel stochastic sampling method within Bayesian filtering for abrupt motion tracking, utilizing nearest neighbor fields and a smoothing Monte Carlo algorithm to improve efficiency and robustness in challenging scenarios.

Contribution

It proposes a new sampling-based approach that integrates nearest neighbor fields and a smoothing Monte Carlo algorithm for effective abrupt motion tracking.

Findings

Enhanced tracking accuracy on challenging sequences

Robustness to abrupt and smooth motions

Improved sampling efficiency

Abstract

Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years. However, conventional methods tend to use a two-stage sampling paradigm, in which the search space needs to be uniformly explored with an inefficient preliminary sampling phase. In this paper, we propose a novel sampling-based method in the Bayesian filtering framework to address the problem. Within the framework, nearest neighbor field estimation is utilized to compute the importance proposal probabilities, which guide the Markov chain search towards promising regions and thus enhance the sampling efficiency; given the motion priors, a smoothing stochastic sampling Monte Carlo algorithm is proposed to approximate the posterior distribution through a smoothing weight-updating scheme. Moreover, to track the abrupt and the smooth motions simultaneously, we develop an abrupt-motion detection scheme which can discover the presence of abrupt motions during online tracking. Extensive experiments on challenging image sequences demonstrate the effectiveness and the robustness of our algorithm in handling the abrupt motions.