An efficient real-time target tracking algorithm using adaptive feature fusion
Yanyan Liu, Changcheng Pan, Minglin Bie, and Jin Li

TL;DR
This paper introduces a real-time target tracking algorithm that adaptively fuses HOG and color features with dimension reduction, achieving high accuracy and robustness in complex environments at 50 fps.
Contribution
The paper proposes a novel adaptive feature fusion method with dimension reduction and confidence estimation for improved real-time target tracking.
Findings
Achieves the highest accuracy and success rate among nine algorithms on OTB100.
Outperforms traditional STAPLE algorithm in success rate and accuracy.
Operates at 50 frames per second in real-time conditions.
Abstract
Visual-based target tracking is easily influenced by multiple factors, such as background clutter, targets fast-moving, illumination variation, object shape change, occlusion, etc. These factors influence the tracking accuracy of a target tracking task. To address this issue, an efficient real-time target tracking method based on a low-dimension adaptive feature fusion is proposed to allow us the simultaneous implementation of the high-accuracy and real-time target tracking. First, the adaptive fusion of a histogram of oriented gradient (HOG) feature and color feature is utilized to improve the tracking accuracy. Second, a convolution dimension reduction method applies to the fusion between the HOG feature and color feature to reduce the over-fitting caused by their high-dimension fusions. Third, an average correlation energy estimation method is used to extract the relative confidence…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsConvolution
