Visual Tracking Via Multi-Layer Factorized Correlation Filter

Bin Kang

doi:10.1109/LSP.2019.2947185

Visual Tracking Via Multi-Layer Factorized Correlation Filter

2019-12-01

1

PRE

AI

DOI：10.1109/LSP.2019.2947185

Original

Original request for help

Save

Abstract

En 中文

Pruning the parameters of basis filters can effectively eliminate the negative effect of redundant deep features in discriminative correlation filter based trackers. However, traditional methods often treat feature maps in Convolutional Neural Networks (CNN) as isolate observations, ignore the intrinsic correlation between partially attentional feature maps in multiple convolutional layers, when basis filter pruning is pursued. In this letter, we propose a multi-layer factorized discriminant correlation filter (MLF-DCF) for visual tracking. By integrating the multi-view discriminant learning and the discriminative correlation filter into a unified optimization problem, we can explore the correlation between different target sub-regions from multi-layer viewpoint, thus can effectively prune multi-layer basis filters. To enhance the efficiency of MLF-DCF in terms of speed and accuracy, we not only adopt alternating directionmethod of multipliers (ADMM) to solve the unified optimization, but also employ a mask estimation strategy to eliminate the background noise in deep features. A large number of experiments on challenging video sequences are given to illustrate the superiority of our tracking method.

Keywords:

Visual tracking

factorized correlation filter

multi-view discriminant learning

ADMM

Visual Tracking Via Multi-Layer Factorized Correlation Filter

Abstract

AI Summary

Journal

Organization