Paper Info
Title
An improved real-time compressive tracking method
Abstract
Robust object tracking is very challenging due to object pose variation, illumination changing and occlusion etc.. Tracking Methods based on dimensionality reducing by applying random projection can extract target features efficiently and greatly improve the tracking speed and are getting more and more attentions. This paper proposed an improved real-time compress tracking algorithm, which adopted a small number of randomly generated linear measurements of raw image as object features. Then these features are combined with online updating mechanism and Bayesian classifier to implement tracking. Experimental results on some challenging sequences show that this method has both improved the tracking performance in some degree and reduced the algorithm complexity.
Year
DOI
Venue
2013
10.1145/2499788.2499870
ICIMCS
Keywords
Field
DocType
algorithm complexity,linear measurement,bayesian classifier,improved real-time compress,object feature,tracking performance,robust object tracking,improved real-time compressive tracking,challenging sequence,tracking speed
Small number,Random projection,Computer vision,Compressive tracking,Naive Bayes classifier,Pattern recognition,Algorithm complexity,Computer science,Curse of dimensionality,Video tracking,Artificial intelligence
Conference
Citations 
PageRank 
References 
0
0.34
12
Authors
5
Name
Order
Citations
PageRank
Yan He100.68
Guangzhu Xu2254.41
Bangjun Lei36314.04
Jing Jing400.68
Fangmin Dong5449.53