2005
DOI: 10.1007/11564386_15
|View full text |Cite
|
Sign up to set email alerts
|

Online Feature Selection Using Mutual Information for Real-Time Multi-view Object Tracking

Abstract: Abstract. It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online feature selection to acquire reliable features for tracking by making use of the images of the tracked object in previous frames to refine our model so that the refined model after online feature selection becomes more robust. The ability of our method to pick up reliable features in real time is demonstrated with multi-view o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2010
2010
2020
2020

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 20 publications
0
3
0
Order By: Relevance
“…Usually, a set of candidate features, such as the linear combinations of the basic R, G, B pixel values [22], and other multiple cues [23], [26], are chosen initially. Features can be evaluated and ranked in different ways, such as the variance ratios [22], principal component analysis [24], variance of mutual information [25], and Kullback-Leibler distance [27]. Then the best ones which make foreground most discriminative against surrounding background are selected for tracking.…”
Section: A Discriminative Feature Selection For Trackingmentioning
confidence: 99%
“…Usually, a set of candidate features, such as the linear combinations of the basic R, G, B pixel values [22], and other multiple cues [23], [26], are chosen initially. Features can be evaluated and ranked in different ways, such as the variance ratios [22], principal component analysis [24], variance of mutual information [25], and Kullback-Leibler distance [27]. Then the best ones which make foreground most discriminative against surrounding background are selected for tracking.…”
Section: A Discriminative Feature Selection For Trackingmentioning
confidence: 99%
“…[5] combine saliency information with color features to make tracking more robust to changing illumination. [6] use mutual information to track multi-view objects in real time. They use the variance of mutual information to acquire reliable features for tracking by making use of the images of the tracked object in previous frames to refine the target model.…”
Section: Introductionmentioning
confidence: 99%
“…A comparison of some of the most important algorithms with the method proposed here is given in Tab. 1 Juengling et al [13] Leung et al [14] Wang et al [26] Farenzena et al [5] …”
Section: State-of-the-artmentioning
confidence: 99%