Abstract
Recent discriminative trackers especially based on Correlation Filters (CFs) have shown dominant performance for visual tracking. This kind of trackers benefit from multi-resolution deep features a lot, taking the expressive power of deep Convolutional Neural Networks (CNN). However, distractors in complex scenarios, such as similar targets, occlusion, and deformation, lead to model drift. Meanwhile, learning deep features results in feature redundancy that the increasing number of learning parameters introduces the risk of over-fitting. In this paper, we propose a discriminative CFs based visual tracking method, called dimension adaption correlation filters (DACF). First, the framework adopts the multi-channel deep CNN features to obtain a discriminative sample appearance model, resisting the background clutters. Moreover, a dimension adaption operation is introduced to reduce relatively irrelevant parameters as possible, which tackles the issue of over-fitting and promotes the model effectively adapting to different tracking scenes. Furthermore, the DACF formulation optimization can be efficiently performed on the basis of implementing the alternating direction method of multipliers (ADMM). Extensive evaluations are conducted on benchmarks, including OTB2013, OTB2015, VOT2016, and UAV123. The experiments results show that our tracker gains remarkable performance. Especially, DACF obtains an AUC score of 0.698 on OTB2015.
Highlights
Visual tracking is one of the fundamental computer vision tasks that has received much attention [1]–[3]
We develop a robust and efficient tracker called dimension adaption correlation filters (DACF) for making full use of multi-level deep Convolutional Neural Networks (CNN) features and address the problems of over-fitting
The Discriminative Correlation Filters (DCFs) for visual tracking have been popularized in recent years and many discriminative trackers have been proposed
Summary
Visual tracking is one of the fundamental computer vision tasks that has received much attention [1]–[3]. We develop a robust and efficient tracker called dimension adaption correlation filters (DACF) for making full use of multi-level deep CNN features and address the problems of over-fitting. We propose a dimension adaption component to adaptively adopt part effective multi-level features during different tracking scenarios Benefiting from this dimension adaption method, our DACF reduces the number of parameters without excessive information loss, which simultaneously remits the problems of over-fitting. Our approach outperforms the baseline STRCF both in accuracy and robustness on OTB2013 and OTB2015 benchmarks
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.
