3D motion segmentation using intensity trajectory

Authors:
Hua Yang;Greg Welch;Jan-Michael Frahm;Marc Pollefeys
Affiliations:
Kitware, Inc;Computer Science Department, University of North Carolina at Chapel Hill;Computer Science Department, University of North Carolina at Chapel Hill;Computer Science Department, University of North Carolina at Chapel Hill
Venue:
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Year:
2009

Citing 16
Cited 0

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Readings in computer vision: issues, problems, principles, and paradigms
Visual learning and recognition of 3-D objects from appearance

International Journal of Computer Vision
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
Multibody Grouping from Motion Images

International Journal of Computer Vision
Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture-Mapped 3D Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Direct Interpretation of Dynamic Images with Camera and Object Motions for Vision Guided Robot Control

International Journal of Computer Vision - Special issue on image-based servoing
Multi-Frame Correspondence Estimation Using Subspace Constraints

International Journal of Computer Vision
A Robust Model-Based Approach for 3D Head Tracking in Video Sequences

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
A multi-body factorization method for motion analysis

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Accurate Motion Layer Segmentation and Matting

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Multi-body Factorization with Uncertainty: Revisiting Motion Consistency

International Journal of Computer Vision
Real-Time Object Tracking without Feature Extraction

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Multiview 3D Tracking with an Incrementally Constructed 3D Model

3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Motion segmentation with missing data using power factorization and GPCA

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
A general framework for motion segmentation: independent, articulated, rigid, non-rigid, degenerate and non-degenerate

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Incorporating constraints and prior knowledge into factorization algorithms – an application to 3d recovery

SLSFS'05 Proceedings of the 2005 international conference on Subspace, Latent Structure and Feature Selection

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motion segmentation is a fundamental aspect of tracking in a scene with multiple moving objects. In this paper we present a novel approach to clustering individual image pixels associated with different 3D rigid motions. The basic idea is that the change of the intensity of a pixel can be locally approximated as a linear function of the motion of the corresponding imaged surface. To achieve appearance-based 3D motion segmentation we capture a sequence of local image samples at nearby poses, and assign for each pixel a vector that represents the intensity changes for that pixel over the sequence. We call this vector of intensity changes a pixel “intensity trajectory”. Similar to 2D feature trajectories, the intensity trajectories of pixels corresponding to the same motion span a local linear subspace. Thus the problem of motion segmentation can be cast as that of clustering local subspaces. We have tested this novel approach using some real image sequences. We present results that demonstrate the expected segmentation, even in some challenging cases.