Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Regressing local to global shape properties for online segmentation and tracking
Author: Ren, C.Y.
Prisacariu, V.A.
Reid, I.
Citation: Proceedings of the British Machine Vision Conference 2011, 2011 / Hoey, J., McKenna, S., Trucco, E. (ed./s), pp.11.1-11.10
Publisher: BMVA Press
Issue Date: 2011
ISBN: 190172543X
Conference Name: 22nd British Machine Vision Conference BMVC 2011 (29 Aug 2011 - 02 Sep 2011 : Dundee, Scotland)
Statement of
Carl Yuheng Ren, Victor Adrian Prisacariu, Ian Reid
Abstract: We propose a regression based learning framework that learns a set of shapes online, which can then be used to recover occluded object shapes. We represent shapes using their 2D discrete cosine transforms, and the key insight we propose is to regress low frequency harmonics, which represent the global properties of the shape, from high frequency harmonics, that encode the details of the object's shape. We learn the regression model using Locally Weighted Projection Regression (LWPR) which expedites online, incremental learning. After sufficient observation of a set of unoccluded shapes, the learned model can detect occlusion and recover the full shapes from the occluded ones. We demonstrate the ideas using a level-set based tracking system that provides shape and pose, however, the framework could be embedded in any segmentation-based tracking system. Our experiments demonstrate the efficacy of the method on a variety of objects using both real data and artificial data.
Rights: © 2011. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
RMID: 0030031311
DOI: 10.5244/C.25.11
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_94949.pdfPublished version3.53 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.