Paper Info
Title
Maximum-likelihood object tracking from multi-view video by combining homography and epipolar constraints
Abstract
This paper addresses problem of object tracking in occlusion scenarios, where multiple uncalibrated cameras with overlapping fields of view are used. We propose a novel method where tracking is first done independently for each view and then tracking results are mapped between each pair of views to improve the tracking in individual views, under the assumptions that objects are not occluded in all views and move uprightly on a planar ground which may induce a homography relation between each pair of views. The tracking results are mapped by jointly exploiting the geometric constraints of homography, epipolar and vertical vanishing point. Main contributions of this paper include: (a) formulate a reference model of multi-view object appearance using region covariance for each view; (b) define a likelihood measure based on geodesics on a Riemannian manifold that is consistent with the destination view by mapping both the estimated positions and appearances of tracked object from other views; (c) locate object in each individual view based on maximum likelihood criterion from multi-view estimations of object position. Experiments have been conducted on videos from multiple uncalibrated cameras, where targets experience long-term partial or full occlusions. Comparison with two existing methods and performance evaluations are also made. Test results have shown effectiveness of the proposed method in terms of robustness against tracking drifts caused by occlusions.
Year
Venue
Keywords
2012
ICDSC
vertical vanishing point,differential geometry,epipolar geometry,multiview object position estimation,homography,overlapping field of view,maximum likelihood estimation,planar homography,video cameras,region covariance,multiple view geometry,riemannian manifold,visual object tracking,epipolar constraint,object tracking,epipolar point,geometric constraint,multiuncalibrated camera,multiview object appearance estimation,maximum likelihood object tracking,multiple cameras,occlusion,geodesics,multiview video processing,video surveillance,computer science,signal processing,information systems,natural sciences,discrete mathematics,mathematics,computer and information science
Field
DocType
ISBN
Computer vision,Reference model,Epipolar geometry,Computer science,Robustness (computer science),Homography,Video tracking,Artificial intelligence,Geodesic,Vanishing point,Covariance
Conference
978-1-4503-1772-6
Citations 
PageRank 
References 
4
0.47
11
Authors
3
Name
Order
Citations
PageRank
Yixiao Yun1365.09
Irene Yu-Hua Gu261335.06
Hamid K. Aghajan328235.49