Abstract | ||
---|---|---|
Sparse coding has been used for target appearance modeling and applied successfully in visual tracking. However, noise may be inevitably introduced into the representation due to background clutter. To cope with this problem, we propose a saliency weighted sparse coding appearance model for visual tracking. Firstly, a spectral filtering based visual attention computational model, which combines both bottom-up and top-down visual attention, is proposed to calculate saliency map. Secondly, pooling operation in sparse coding is weighted by calculated saliency map to help target representation focus on distinctive features and suppress background clutter. Extensive experiments on a recently proposed tracking benchmark demonstrate that the proposed algorithm outperforms state-of-the-art methods in tracking objects under background clutter. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICPR.2014.701 | ICPR |
Keywords | Field | DocType |
saliency-weighted sparse coding appearance model,calculate saliency map,visual tracking,image coding,spectral filtering-based visual attention computational model,background clutter suppression,top-down visual attention,target appearance modeling,sparse coding,visual tracking, saliency, visual attention, sparse coding,background clutter,object tracking,visual attention,bottom-up visual attention,saliency,tracking objects,pooling operation,distinctive features | Computer vision,Pattern recognition,Computer science,Salience (neuroscience),Clutter,Neural coding,Pooling,Active appearance model,Eye tracking,Visual attention,Artificial intelligence,Appearance modeling | Conference |
ISSN | Citations | PageRank |
1051-4651 | 2 | 0.36 |
References | Authors | |
8 | 3 |