2012 IEEE Conference on Computer Vision and Pattern Recognition 2012
DOI: 10.1109/cvpr.2012.6247882
|View full text |Cite
|
Sign up to set email alerts
|

Robust object tracking via sparsity-based collaborative model

Abstract: In this paper we propose a robust object tracking algorithm using a collaborative model. As the main challenge for object tracking is to account for drastic appearance change, we propose a robust appearance model that exploits both holistic templates and local representations. We develop a sparsity-based discriminative classifier (SD-C) and a sparsity-based generative model (SGM). In the S-DC module, we introduce an effective method to compute the confidence value that assigns more weights to the foreground th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
527
0
1

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 767 publications
(528 citation statements)
references
References 30 publications
0
527
0
1
Order By: Relevance
“…The sample with minimal reconstruction errors is regarded as tracking result. Further, [15] consider the important of the background information. The dictionary is composed of target templates and background templates which overcomes the drawbacks of L1 tracker that provide more discrimination power than the dictionary used in [5].…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…The sample with minimal reconstruction errors is regarded as tracking result. Further, [15] consider the important of the background information. The dictionary is composed of target templates and background templates which overcomes the drawbacks of L1 tracker that provide more discrimination power than the dictionary used in [5].…”
Section: Related Workmentioning
confidence: 99%
“…The dictionary is composed of target templates and background templates which overcomes the drawbacks of L1 tracker that provide more discrimination power than the dictionary used in [5]. Another advantage of [15] is it selects discriminative features through the classification information which can decrease the dimension of the representation. In [16], they using a linear support vector machine (SVM) to train a discriminative model to separate the target object from the background.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…is the most representative work, and some extensions [5,[29][30][31][32] are developed to improve the l 1 tracker in terms of both speed and accuracy. In [29] , APG based solution is used to improve the l 1 tracker.…”
Section: Sparse Learning Based Trackersmentioning
confidence: 99%
“…It is an important and fundamental topic in computer vision, and has many applications including intelligent surveillance, motion recognition, robotic, human computer interface (HCI), augmented reality (AR), etc. Although great processes have been made and many tracking algorithms have been proposed [1][2][3][4][5][6][7][8] , it remains an open problem to design a robust tracker in the real-world scenarios due to severe occlusions, large appearance changes, illumination changes, background clutter and abrupt motion, etc.…”
Section: Introductionmentioning
confidence: 99%