High-speed Tracking with Multi-kernel Correlation Filters

TL;DR

This paper introduces MKCFup, a novel multi-kernel correlation filter tracker that significantly improves tracking accuracy and speed by reformulating the MKL objective to reduce kernel interference.

Contribution

The paper proposes a new way to incorporate MKL into KCF, improving discriminability and efficiency over previous methods like MKCF.

Findings

MKCFup outperforms KCF and MKCF in accuracy.

MKCFup operates at very high frame rates.

The method is effective for fast-moving small objects.

Abstract

Correlation filter (CF) based trackers are currently ranked top in terms of their performances. Nevertheless, only some of them, such as KCF~\cite{henriques15} and MKCF~\cite{tangm15}, are able to exploit the powerful discriminability of non-linear kernels. Although MKCF achieves more powerful discriminability than KCF through introducing multi-kernel learning (MKL) into KCF, its improvement over KCF is quite limited and its computational burden increases significantly in comparison with KCF. In this paper, we will introduce the MKL into KCF in a different way than MKCF. We reformulate the MKL version of CF objective function with its upper bound, alleviating the negative mutual interference of different kernels significantly. Our novel MKCF tracker, MKCFup, outperforms KCF and MKCF with large margins and can still work at very high fps. Extensive experiments on public datasets show that our method is superior to state-of-the-art algorithms for target objects of small move at very high speed.