Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking

TL;DR

This paper introduces a new visual tracking framework combining iterative particle filtering, deep convolutional neural networks, and correlation filters, which improves accuracy and efficiency by reducing resampling and leveraging clustering for likelihood assessment.

Contribution

It presents a novel integration of iterative particle filtering with deep learning and correlation filters, using K-means clustering for likelihood evaluation, enhancing tracking performance.

Findings

Outperforms state-of-the-art trackers on benchmark datasets.

Reduces the need for resampling, improving computational efficiency.

Provides more accurate target localization through iterative correction.

Abstract

This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter. The iterative particle filter enables the particles to correct themselves and converge to the correct target position. We employ a novel strategy to assess the likelihood of the particles after the iterations by applying K-means clustering. Our approach ensures a consistent support for the posterior distribution. Thus, we do not need to perform resampling at every video frame, improving the utilization of prior distribution information. Experimental results on two different benchmark datasets show that our tracker performs favorably against state-of-the-art methods.