Imperial College London

Professor Yiannis Demiris

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Professor of Human-Centred Robotics, Head of ISN



+44 (0)20 7594 6300y.demiris Website




1014Electrical EngineeringSouth Kensington Campus






BibTex format

author = {Goncalves, Nunes U and Demiris, Y},
publisher = {British Machine Vision Association (BMVA)},
title = {3D motion segmentation of articulated rigid bodies based on RGB-D data},
url = {},
year = {2018}

RIS format (EndNote, RefMan)

AB - This paper addresses the problem of motion segmentation of articulated rigid bodiesfrom a single-view RGB-D data sequence. Current methods either perform dense motionsegmentation, and consequently are very computational demanding, or rely on sparse 2Dfeature points, which may not be sufficient to represent the entire scene. In this paper,we advocate the use of 3D semi-dense motion segmentation which also bridges somelimitations of standard 2D methods (e.g. background removal). We cast the 3D motionsegmentation problem into a subspace clustering problem, adding an adaptive spectralclustering that estimates the number of object rigid parts. The resultant method has fewparameters to adjust, takes less time than the temporal length of the scene and requiresno post-processing.
AU - Goncalves,Nunes U
AU - Demiris,Y
PB - British Machine Vision Association (BMVA)
PY - 2018///
TI - 3D motion segmentation of articulated rigid bodies based on RGB-D data
UR -
ER -