PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Kinecting the dots: Particle based scene flow from depth sensors
Simon Hadfield and Richard Bowden
In: ICCV 2011, 6-13 Nov, Barcelona, Spain.

Abstract

The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion field of the scene, and is more difficult to estimate than it's 2D counterpart, optical flow. Current approaches use a smoothness cost for regularisation, which tends to over-smooth at object boundaries. This paper presents a novel formulation for scene flow estimation, a collection of moving points in 3D space, modelled using a particle filter that supports multiple hypotheses and does not oversmooth the motion field. In addition, this paper is the first to address scene flow estimation, while making use of modern depth sensors and monocular appearance images, rather than traditional multi-viewpoint rigs. The algorithm is applied to an existing scene flow dataset, where it achieves comparable results to approaches utilising multiple views, while taking a fraction of the time.

PDF (Pre-print) - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Theory & Algorithms
ID Code:9224
Deposited By:Simon Hadfield
Deposited On:21 February 2012