Abstract
Correlation filter (CF) based tracking algorithms have tremendously contributed to the field of visual tracking due to the high computational efficiency and competitive performance. Nonetheless, most CF-based trackers are vulnerable to the influence of occlusion and boundary effect, which results in suboptimal performance. In this article, we propose saliency guided visual tracking via correlation filter with log-Gabor filter to robustify its performance under occlusion and boundary effect challenges. Firstly, we propose the CF with log-Gabor filter to get a robust appearance model. The log-Gabor filter is adopted to preprocess the sequence to gain the log-Gabor feature, which provides important cues for tracking since it encodes the texture information. Secondly, considering the prior information, we embed the novel saliency guided adaptive spatial feature selection to filter learning to preserve the spatial structure in the lower manifold and mitigate boundary distortion. Thirdly, the occlusion estimating strategy, performing on-line evaluation of tracking, triggers the motion estimation module to optimize the optimal location. Experiments on benchmark databases demonstrate the enhanced discrimination and interpretability of the proposed tracker and its superiority over other trackers.
Highlights
Visual tracking is a classical and rapidly evolving research topic in computer vision with various real-world applications including video surveillance, human-computer interaction, unmanned aerial vehicles (UAVs) and autonomous driving
We denote the tracker without the saliency-embedded adaptive feature selection as OURS_SAL, without the Correlation filter (CF) with log-Gabor filter as OURS_GAR, and without the motion estimation module as OURS_MOD
In this article, we propose a robust visual tracking method based on the saliency-embedded adaptive spatial feature selection to handle occlusion and boundary effect challenges
Summary
Visual tracking is a classical and rapidly evolving research topic in computer vision with various real-world applications including video surveillance, human-computer interaction, unmanned aerial vehicles (UAVs) and autonomous driving. Ma et al [17] use a discriminative correlation filter to estimate the confidence of current tracking state and train an online learned random forest classifier to re-detect the target. (1) A novel saliency guided adaptive spatial feature selection is proposed for spatial-temporal filter training enabling an optimal discriminative feature selection. (2) The CF with log-Gabor filter containing comprehensive description of the target is proposed, which equips the tracker with a more robust feature representation across varieties of challenging attributes. Danelljan et al introduce a spatial regularization component to restrain correlation filter coefficients, which solves the boundary effects efficiently caused by periodic assumption [6]. BACF [24] exploits the variations of foreground and background to build a discriminative classifier This alleviates boundary effect and maintains real-time tracking speed. Has been extended by exploiting sophisticated tracking techniques, such as contextual information [26], [27], sparse representation [28], deep neural network [29]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
