Abstract | ||
---|---|---|
This paper presents a simple but robust visual tracking algorithm based on representing the appearances of objects using affine warps of learned linear subspaces of the image space. The tracker adaptively updates this subspace while tracking by finding a linear subspace that best approximates the observations made in the previous frames. Instead of the traditional L-2-reconstruction error norm which leads to subsapce estimation using PCA or SVD, we argue that a variant of it, the uniform L-2-reconstruction error norm, is the right one for tracking. Under this framework, we provide a simple and a computationally inexpensive algorithm for finding a subspace whose uniform L-2-reconstruction error norm for a given collection of data samples is below some threshold, and a simple tracking algorithm is an immediate consequence. We show experimental results on a variety of image sequences of people and man-made objects moving under challenging imaging conditions, which include drastic illumination variation, partial occlusion and extreme pose variation. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/CVPR.2004.1315111 | PROCEEDINGS OF THE 2004 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1 |
Keywords | Field | DocType |
image reconstruction,singular value decomposition,principal component analysis,tracking,learning artificial intelligence,visual tracking | Affine transformation,Iterative reconstruction,Singular value decomposition,Computer vision,Pattern recognition,Subspace topology,Computer science,Image representation,Linear subspace,Eye tracking,Artificial intelligence,Principal component analysis | Conference |
ISSN | Citations | PageRank |
1063-6919 | 96 | 7.47 |
References | Authors | |
16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeffrey Ho | 1 | 2190 | 101.78 |
Kuang-chih Lee | 2 | 2297 | 104.80 |
Yang Ming-Hsuan | 3 | 15303 | 620.69 |
David Kriegman | 4 | 7693 | 451.96 |