Exploiting superpixel and hybrid hash for kernel-based visual tracking

Superpixel analysis approach is employed to reconstruct target appearance in visual tracking.Representative superpixel blocks combined with kernel-based filter are exploited for roughly target location.Superpixel block modification method based on hybrid hash is proposed to accurately locate target.Conventional kernel-based filter is improved with peak-response scale estimation and color features.Comprehensive experiments on publicly available datasets demonstrate our tracker superior to state-of-the-art trackers. In recent years, significant advances in visual tracking have been made, and numerous outstanding algorithms have been proposed. However, the constraint between tracking accuracy and speed has not yet been comprehensively addressed. In this paper, to address the challenging aspects of visual tracking and, in particular, to achieve accurate real-time tracking, we propose a novel real-time kernel-based visual tracking algorithm based on superpixel clustering and hybrid hash analysis. By adopting superpixel clustering and segmentation, we reconstruct the appearance model of the target and its surrounding context in the initialization step. Via introducing the approach of overlap and intensity analysis, we divide the reconstructed model into several superpixel blocks. Based on the theory of circulant matrices and Fourier analysis, we build a Gaussian kernel correlation filter to roughly locate the position of each candidate block. To further improve the kernel correlation filter method, we compute each block's maximal response value in the confidence map and estimate each block's scale variation based on a peak value comparison. Additionally, we also propose a hybrid hash analysis strategy and integrate it with superpixel analysis for target blocks modification. By calculating a hybrid hash sequence based on L*A*B color and the discrete cosine transform, we conduct superpixel block modification to accurately locate the target and estimate the target's scale variation. Extensive experiments on visual tracking benchmark datasets show that our tracking algorithm outperforms the state-of-the-art algorithms and demonstrate its effectiveness and efficiency.