Abstract:
Correlation filtering-based visual tracking has achieved impressive success in terms of both tracking accuracy and computational efficiency. In this paper, a novel correl...Show MoreMetadata
Abstract:
Correlation filtering-based visual tracking has achieved impressive success in terms of both tracking accuracy and computational efficiency. In this paper, a novel correlation filtering approach is proposed by means of joint learning to bridge the gap between the circulant filtering and the classical filtering methods. The circulant structure of tracking and the information from successive frames are simultaneously exploited in the proposed work. A new formulation for the correlation filter learning is proposed to enhance the discrimination of the learned filter by integrating both the kernel and the image feature domains. The proposed approach is computationally efficient since a closed-form solution is derived for the new formulation. Extensive experiments are conducted on two popular tracking benchmarks, and the experimental results demonstrate that the proposed tracker outperforms most of the state-of-the-art trackers.
Published in: IEEE Transactions on Circuits and Systems for Video Technology ( Volume: 30, Issue: 1, January 2020)
Funding Agency:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Correlation Filter ,
- Computational Efficiency ,
- Domain Features ,
- Filtering Approach ,
- Circulator ,
- Joint Learning ,
- Successive Frames ,
- Popular Benchmark ,
- Learned Filters ,
- Frequency Domain ,
- Target Location ,
- Tracking Performance ,
- Discrimination Performance ,
- Discrete Fourier Transform ,
- Image Domain ,
- Video Sequences ,
- Sparse Representation ,
- Element-wise Multiplication ,
- Strongest Response ,
- Previous Frame ,
- Filter Response ,
- Cyclic Shift ,
- Anisotropic Response ,
- Background Clutter ,
- Response Map ,
- Degree Of Discrimination ,
- Non-rigid Deformation ,
- Subspace Learning ,
- High Computational Efficiency ,
- Fourier Transform
- Author Keywords
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Correlation Filter ,
- Computational Efficiency ,
- Domain Features ,
- Filtering Approach ,
- Circulator ,
- Joint Learning ,
- Successive Frames ,
- Popular Benchmark ,
- Learned Filters ,
- Frequency Domain ,
- Target Location ,
- Tracking Performance ,
- Discrimination Performance ,
- Discrete Fourier Transform ,
- Image Domain ,
- Video Sequences ,
- Sparse Representation ,
- Element-wise Multiplication ,
- Strongest Response ,
- Previous Frame ,
- Filter Response ,
- Cyclic Shift ,
- Anisotropic Response ,
- Background Clutter ,
- Response Map ,
- Degree Of Discrimination ,
- Non-rigid Deformation ,
- Subspace Learning ,
- High Computational Efficiency ,
- Fourier Transform
- Author Keywords