Abstract
Due to the fast speed and high efficiency, discriminant correlation filter (DCF) has drawn great attention in online object tracking recently. However, with the improvement of performance, the costs are the increase in parameters and the decline of speed. In this paper, we propose a novel visual tracking algorithm, namely VDCFNet, and combine DCF with a vector convolutional network (VCNN). We replace one traditional convolutional filter with two novel vector convolutional filters in the convolutional stage of our network. This enables our model with few memories (only 59 KB) trained offline to learn the generic image features. In the online tracking stage, we propose a coarse-to-fine search strategy to solve drift problems under fast motion. Besides, we update model selectively to speed up and increase robustness. The experiments on OTB benchmarks demonstrate that our proposed VDCFNet can achieve a competitive performance while running over real-time speed.
Highlights
Visual object tracking is one of the fundamental problems in computer vision with numerous applications [1,2], such as cameras surveillance and human–computer interaction
The results our VDCFNet can achieve a competitive performance with other state-of-the-art trackers
Demonstrate that our VDCFNet can achieve a competitive performance with other state-of-the-art trackers
Summary
Visual object tracking is one of the fundamental problems in computer vision with numerous applications [1,2], such as cameras surveillance and human–computer interaction. Several trackers design the feature models to represent targets and predict targets by searching for the image region to choose the most similar one. It proves that more accurate feature representations will lead to better tracking performance [5]. To match object appearance accurately, recent tracking algorithms focus on proposing effective representation schemes, such as points, texture [6], histograms, optical flow, or perceptual hashing [7]. Object tracking is still a challenging problem since the object appearance tends to change and be disturbed by surroundings from frame to frame
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.