High-speed Tracking with Multi-kernel Correlation Filters
This work addresses the problem of high-speed, accurate object tracking for computer vision applications, representing an incremental improvement over prior multi-kernel methods.
The paper tackles the limited performance and high computational cost of existing multi-kernel correlation filter trackers by reformulating the objective function with an upper bound, resulting in MKCFup, which outperforms KCF and MKCF by large margins and operates at very high fps.
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.