 |
    |
Monocular Multiview Object Tracking with 3D Aspect Parts*
Yu Xiang1, 2, Changkyu Song2, Roozbeh Mottaghi1, and Silvio Savarese1
1Computer Science Department, Stanford University, Palo Alto, USA
roozbeh@cs.stanford.edu
ssilvio@stanford.edu
2Department of EECS, University of Michigan at Ann Arbor, Ann Arbor, USA
yuxiang@cs.stanford.edu
changkyu@umich.edu
Abstract. In this work, we focus on the problem of tracking objects under significant viewpoint variations, which poses a big challenge to traditional object tracking methods. We propose a novel method to track an object and estimate its continuous pose and part locations under severe viewpoint change. In order to handle the change in topological appearance introduced by viewpoint transformations, we represent objects with 3D aspect parts and model the relationship between viewpoint and 3D aspect parts in a part-based particle filtering framework. Moreover, we show that instance-level online-learned part appearance can be incorporated into our model, which makes it more robust in difficult scenarios with occlusions. Experiments are conducted on a new dataset of challenging YouTube videos and a subset of the KITTI dataset [14] that include significant viewpoint variations, as well as a standard sequence for car tracking. We demonstrate that our method is able to track the 3D aspect parts and the viewpoint of objects accurately despite significant changes in viewpoint.
Keywords: multiview object tracking, 3D aspect part representation
Electronic Supplementary Material:
LNCS 8694, p. 220 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014