Paper Info
Title
Particle Filter Tracking with Online Multiple Instance Learning
Abstract
This paper addresses the problem of object tracking by learning a discriminative classifier to separate the object from its background. The online-learned classifier is used to adaptively model object's appearance and its background. To solve the typical problem of erroneous training examples generated during tracking, an online multiple instance learning (MIL) algorithm is used by allowing false positive examples. In addition, particle filter is applied to make best use of the learned classifier and help to generate a better representative set of training examples for the online MIL learning. The effectiveness of the proposed algorithm is demonstrated in some challenging environdments for human tracking.
Year
DOI
Venue
2010
10.1109/ICPR.2010.641
ICPR
Keywords
Field
DocType
erroneous training example,online mil learning algorithm,particle filtering (numerical methods),learning (artificial intelligence),discriminative classifier,online-learned classifier,particle filter tracking,discriminative classifier learning,model object,image classification,object tracking,tracking,proposed algorithm,object detection,computer vision,online mil learning,multiple instance learning,object appearance model,training example,online multiple instance learning,human tracking,online multiple instance learning algorithm,learning artificial intelligence,boosting,robustness,particle filter,histograms,false positive
Computer science,Particle filter,Robustness (computer science),Artificial intelligence,Classifier (linguistics),Discriminative model,Computer vision,Object detection,Stability (learning theory),Pattern recognition,Video tracking,Boosting (machine learning),Machine learning
Conference
ISSN
ISBN
Citations 
1051-4651
978-1-4244-7542-1
5
PageRank 
References 
Authors
0.47
4
4
Name
Order
Citations
PageRank
Zefeng Ni1858.07
Santhoshkumar Sunderrajan2414.89
Amir Rahimi3273.23
B. S. Manjunath4201.85