Inverse Compositional Estimation of 3D Pose And Lighting in Dynamic Scenes

In this paper, we show how we can estimate, accurately and efficiently, the 3D motion of a rigid object and time-varying lighting in a dynamic scene. This is achieved in an inverse compositional tracking framework with a novel warping function that involves a 2D rarr 3D rarr 2D transformation. This...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 30; no. 7; pp. 1300 - 1307
Main Authors: Xu, Yilei, Roy-Chowdhury, Amit
Format: Journal Article
Language:English
Published: Los Alamitos, CA IEEE 01.07.2008
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
Cameras
Computation
Computer science; control theory; systems
Convergence
Dynamics
Exact sciences and technology
Illumination
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Imaging, Three-Dimensional - methods
Integrated circuit modeling
Inverse
Layout
Lighting
Lighting - methods
Motion
Motion estimation
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Reflectivity
Reproducibility of Results
Sensitivity and Specificity
Shape
Target tracking
Three dimensional
Tracking
Two dimensional
Video analysis
Video Recording - methods
Video sequences
Motion
Video analysis
Inverse composition
Tracking
Image processing
Warping
High precision
Posture
Multiple view
Time varying system
Image analysis
Luminance
Scene analysis
Lighting
Illumination
Pattern analysis
Artificial intelligence
Numerical convergence
3D pose
ISSN:0162-8828, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we show how we can estimate, accurately and efficiently, the 3D motion of a rigid object and time-varying lighting in a dynamic scene. This is achieved in an inverse compositional tracking framework with a novel warping function that involves a 2D rarr 3D rarr 2D transformation. This also allows us to extend traditional two-frame inverse compositional tracking to a sequence of frames, leading to even higher computational savings. We prove the theoretical convergence of this method and show that it leads to significant reduction in computational burden. Experimental analysis on multiple video sequences shows impressive speedup over existing methods while retaining a high level of accuracy.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2008.81