Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Regressing local to global shape properties for online segmentation and tracking
Author: Ren, C.
Prisacariu, V.
Reid, I.
Citation: International Journal of Computer Vision, 2014; 106(3):269-281
Publisher: Kluwer Academic Publ
Issue Date: 2014
ISSN: 0920-5691
Statement of
Carl Yuheng Ren, Victor Prisacariu, Ian Reid Received
Abstract: We propose a novel regression based framework that uses online learned shape information to reconstruct occluded object contours. Our key insight is to regress the global, coarse, properties of shape from its local properties, i.e. its details. We do this by representing shapes using their 2D discrete cosine transforms and by regressing low frequency from high frequency harmonics. We learn this regression model using Locally Weighted Projection Regression 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.
Keywords: Occlusion recovery; incremental learning; level-set based tracking; discrete cosine transform
Rights: © Springer Science+Business Media New York 2013
DOI: 10.1007/s11263-013-0635-y
Appears in Collections:Aurora harvest 7
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access1.68 MBAdobe PDFView/Open

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