Kinecting the dots: Particle Based Scene Flow From Depth Sensors
Hadfield, S and Bowden, R Kinecting the dots: Particle Based Scene Flow From Depth Sensors
Available under License : See the attached licence file.
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.
|Item Type:||Conference or Workshop Item (Conference Poster)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Identification Number :||https://doi.org/10.1109/ICCV.2011.6126509|
|Related URLs :|
|Additional Information :||Copyright 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
|Depositing User :||Symplectic Elements|
|Date Deposited :||22 May 2012 08:51|
|Last Modified :||18 Sep 2014 01:33|
Actions (login required)
Downloads per month over past year