DocumentCode
2715904
Title
Locally Orderless Tracking
Author
Oron, Shaul ; Bar-Hillel, Aharon ; Levi, Dan ; Avidan, Shai
Author_Institution
Tel Aviv Univ., Tel Aviv, Israel
fYear
2012
fDate
16-21 June 2012
Firstpage
1940
Lastpage
1947
Abstract
Locally Orderless Tracking (LOT) is a visual tracking algorithm that automatically estimates the amount of local (dis)order in the object. This lets the tracker specialize in both rigid and deformable objects on-line and with no prior assumptions. We provide a probabilistic model of the object variations over time. The model is implemented using the Earth Mover´s Distance (EMD) with two parameters that control the cost of moving pixels and changing their color. We adjust these costs on-line during tracking to account for the amount of local (dis)order in the object. We show LOT´s tracking capabilities on challenging video sequences, both commonly used and new, demonstrating performance comparable to state-of-the-art methods.
Keywords
distance measurement; image colour analysis; image sequences; object tracking; statistical distributions; video signal processing; Earth mover distance; LOT; color changing; cost control; locally orderless tracking; probabilistic model; video sequences; visual tracking algorithm; Maximum likelihood estimation; Noise; Optimization; Probabilistic logic; Target tracking; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location
Providence, RI
ISSN
1063-6919
Print_ISBN
978-1-4673-1226-4
Electronic_ISBN
1063-6919
Type
conf
DOI
10.1109/CVPR.2012.6247895
Filename
6247895
Link To Document