Improved Correlation Filter Tracking with Hard Negative Mining
Qie C.2; Guo G.2; Yan Y.2; Zhang L.1; Wang H.2
Source PublicationProceedings - International Conference on Pattern Recognition
AbstractRecently, the correlation filter based trackers have achieved very good tracking performance. However, due to the boundary effects of the circulant matrix and the usage of cosine window, the lack of effective negative samples becomes a challenging problem for the correlation filter based trackers. This problem may cause overfitting so that these trackers become very sensitive to deformation and occlusion. In this paper, we propose a novel object tracker (i.e., STAPLE-HNM), which can effectively select hard negative samples and assign adaptive weights to these samples to train the correlation filter. Experimental results demonstrate that the proposed STAPLE-HNM tracker effectively improves the performance of the baseline STAPLE-CA tracker on the OTB-50 and OTB-100 datasets. Moreover, the proposed STAPLE-HNM tracker also achieves superior performance among several state-of-the-art trackers.
URLView the original
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionUniversity of Macau
Affiliation1.Universidade de Macau
2.Xiamen University
Recommended Citation
GB/T 7714
Qie C.,Guo G.,Yan Y.,et al. Improved Correlation Filter Tracking with Hard Negative Mining[C],2018:1646-1651.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qie C.]'s Articles
[Guo G.]'s Articles
[Yan Y.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qie C.]'s Articles
[Guo G.]'s Articles
[Yan Y.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qie C.]'s Articles
[Guo G.]'s Articles
[Yan Y.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.