Applying Detection Proposals to Visual Tracking for Scale and Aspect Ratio Adaptability

@article{Huang2016ApplyingDP,
  title={Applying Detection Proposals to Visual Tracking for Scale and Aspect Ratio Adaptability},
  author={Dafei Huang and Lei Luo and Zhaoyun Chen and Mei Wen and Chunyuan Zhang},
  journal={International Journal of Computer Vision},
  year={2016},
  volume={122},
  pages={524-541}
}
The newly proposed correlation filter based trackers can achieve appealing performance despite their great simplicity and superior speed. However, this kind of object trackers is not born with scale and aspect ratio adaptability, thus resulting in suboptimal tracking accuracy. To tackle this problem, this paper integrates the class-agnostic detection proposal method, which is widely adopted in object detection area, into a correlation filter tracker. In the tracker part, optimizations such as… CONTINUE READING
Highly Cited
This paper has 17 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 49 references

BING: Binarized Normed Gradients for Objectness Estimation at 300fps

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 11 Excerpts
Highly Influenced

What Makes for Effective Detection Proposals?

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2016
View 8 Excerpts
Highly Influenced

High-Speed Tracking with Kernelized Correlation Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 18 Excerpts
Highly Influenced

Adaptive Color Attributes for Real-Time Visual Tracking

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 20 Excerpts
Highly Influenced

Online Object Tracking: A Benchmark

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 5 Excerpts
Highly Influenced

PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid Objects

2013 IEEE International Conference on Computer Vision • 2013
View 4 Excerpts
Highly Influenced

Robust object tracking via sparsity-based collaborative model

2012 IEEE Conference on Computer Vision and Pattern Recognition • 2012
View 8 Excerpts
Highly Influenced

P-N learning: Bootstrapping binary classifiers by structural constraints

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition • 2010
View 9 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…