Abstract | ||
---|---|---|
We propose an algorithm for accurate tracking of articulated objects using online update of appearance and shape. The challenge here is to model foreground appearance with histograms in a way that is both efficient and accurate. In this algorithm, the constantly changing foreground shape is modeled as a small number of rectangular blocks, whose positions within the tracking window are adaptively determined. Under the general assumption of stationary foreground appearance, we show that robust object tracking is possible by adaptively adjusting the locations of these blocks. Implemented in MATLAB without substantial optimization, our tracker runs already at 3.7 frames per second on a 3GHz machine. Experimental results have demonstrated that the algorithm is able to efficiently track articulated objects undergoing large variation in appearance and shape. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.cviu.2010.04.002 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
general assumption,object detection,tracking window,image segmentation,articulated object,model foreground appearance,accurate tracking,online visual tracking,articulating block,robust object tracking,foreground shape,stationary foreground appearance,object tracking,large variation,visual tracking,frames per second | Object detection,Histogram,Computer vision,Image segmentation,Eye tracking,Video tracking,Artificial intelligence,Frame rate,Motion estimation,Mathematics,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
114 | 8 | Computer Vision and Image Understanding |
Citations | PageRank | References |
33 | 1.12 | 32 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
S.M. Shahed Nejhum | 1 | 33 | 1.12 |
Jeffrey Ho | 2 | 2190 | 101.78 |
Yang Ming-Hsuan | 3 | 15303 | 620.69 |