Abstract
Sparse
representation has been applied to visual tracking by finding the best
candidate with minimal reconstruction error using target templates.
However most sparse
representation based trackers only consider the holistic representation and do
not make full use of the sparse coefficients to discriminate between the target
and the background, and hence may fail with more possibility when there is
similar object or occlusion in the scene.
In this paper we
develop a simple yet robust tracking method based on the structural local sparse
appearance model.
This representation
exploits both partial information and spatial information of the target based
on a novel alignment-pooling method.
The similarity
obtained by pooling across the local patches helps not only locate the target
more accurately but also handle occlusion.
In addition, we
employ a template update strategy which combines incremental subspace learning
and sparse representation.
This strategy
adapts the template to the appearance change of the target with less
possibility of drifting and reduces the influence of the occluded target
template as well.
Both qualitative
and quantitative evaluations on challenging benchmark image sequences
demonstrate that the proposed tracking algorithm performs favorably against
several state-of-the-art methods.
Related Papers
Visual
Tracking via Adaptive Structural Local Sparse Appearance Model
Xu Jia, Huchuan
Lu, Ming-Hsuan Yang.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)，Providence, Rhode Island, [PDF][CODE][DATA].
Results and Datasets
Woman
[Download data (zip)]
[Precision
plot] This
sequence is from Adam et
al. |
|
Faceocc2
[Download data (zip)] [Precision plot] This
sequence is from Babenko et al. |
|
Caviar
[Download data
(zip)] [Precision
plot] This
sequence is from CAVIAR. |
|
Car 11
[Download data (zip)] [Precision plot] This
sequence is from Ross et al. |
|
David
[Download data (zip)]
[Precision plot] This
sequence is from Ross et al. |
|
Singer
[Download data (zip)] [Precision plot] This
sequence is from Kwon
et al. |
|
Board
[Download data (zip)] [Precision plot] This
sequence is from Santner et al. |
|
Stone
[Download data (zip)] [Precision plot] This
sequence is from our own |