3D Tracking of Multiple Objects with Identical Appearance Using RGB-D Input

3D Tracking of Multiple Objects with Identical Appearance Using RGB-D Input

Most current approaches for 3D object tracking rely on distinctive object appearances. While several such trackers can be instantiated to track multiple objects independently, this not only neglects that objects should not occupy the same space in 3D, but also fails when objects have highly similar...

Full description

Saved in:
Bibliographic Details
Published in:2014 2nd International Conference on 3D Vision Vol. 1; pp. 47 - 54
Main Authors: Ren, Carl Yuheng, Prisacariu, Victor, Kaehler, Olaf, Reid, Ian, Murray, David
Format: Conference Proceeding
Language:English
Published: IEEE 01-12-2014
Subjects:
3D tracking
Cameras
Computational modeling
Iterative closest point algorithm
Multiple objects
real-time
Real-time systems
RGB-D
Shape
Solid modeling
Three-dimensional displays
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most current approaches for 3D object tracking rely on distinctive object appearances. While several such trackers can be instantiated to track multiple objects independently, this not only neglects that objects should not occupy the same space in 3D, but also fails when objects have highly similar or identical appearances. In this paper we develop a probabilistic graphical model that accounts for similarity and proximity and leads to robust real-time tracking of multiple objects from RGB-D data, without recourse to bolton collision detection.
ISSN:1550-6185
DOI:10.1109/3DV.2014.39