University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Kinecting the dots: Particle Based Scene Flow From Depth Sensors

Hadfield, Simon J. and Bowden, Richard (2011) Kinecting the dots: Particle Based Scene Flow From Depth Sensors In: International Conference on Computer Vision 2011, 6th November 2011, Barcelona, Spain.

Text (Camera ready version of paper)
Kinecting_the_dots_Particle_Based_Scene_Flow_From_Depth_Sensors.pdf - Accepted version Manuscript
Available under License Creative Commons Attribution.

Download (1MB)
[img] Video (Supplementary video of motion estimation on the kicks sequence.)
kicks_scene_flow.avi - Supplemental Material
Available under License Creative Commons Attribution.

Download (8MB)


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 Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Hadfield, Simon
Date : 6 November 2011
DOI : 10.1109/ICCV.2011.6126509
Uncontrolled Keywords : motion estimation, scene flow, particle filter, monte carlo, optical flow, depth, kinect, 3d, 3d motion
Additional Information : © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Depositing User : Simon Hadfield
Date Deposited : 05 Sep 2012 14:43
Last Modified : 06 Jul 2019 05:10

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800