Infrared target tracking based on proximal robust principal component analysis method

TL;DR

This paper introduces a robust infrared target tracking method that decomposes observation data into low-rank and sparse components using proximal robust PCA, combined with particle filtering for precise localization.

Contribution

It proposes a novel infrared tracking algorithm utilizing proximal robust PCA and ADMM, improving robustness against occlusion and appearance changes.

Findings

Effective in handling occlusion and appearance variation

Demonstrates superior robustness over existing methods

Validated on real infrared sequences

Abstract

Infrared target tracking plays an important role in both civil and military fields. The main challenges in designing a robust and high-precision tracker for infrared sequences include overlap, occlusion and appearance change. To this end, this paper proposes an infrared target tracker based on proximal robust principal component analysis method. Firstly, the observation matrix is decomposed into a sparse occlusion matrix and a low-rank target matrix, and the constraint optimization is carried out with an approaching proximal norm which is better than L1-norm. To solve this convex optimization problem, Alternating Direction Method of Multipliers (ADMM) is employed to estimate the variables alternately. Finally, the framework of particle filter with model update strategy is exploited to locate the target. Through a series of experiments on real infrared target sequences, the effectiveness and robustness of our algorithm are proved.