Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Learning similarity metrics for dynamic scene segmentation
Author: Teney, D.
Brown, M.
Kit, D.
Hall, P.
Citation: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015 / vol.07-12-June-2015, pp.2084-2093
Publisher: IEEE
Issue Date: 2015
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467369640
ISSN: 1063-6919
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (07 Jun 2015 - 12 Jun 2015 : Boston, MA)
Statement of
Damien Teney, Matthew Brown, Dimitry Kit Peter Hall
Abstract: This paper addresses the segmentation of videos with arbitrary motion, including dynamic textures, using novel motion features and a supervised learning approach. Dynamic textures are commonplace in natural scenes, and exhibit complex patterns of appearance and motion (e.g. water, smoke, swaying foliage). These are difficult for existing segmentation algorithms, often violate the brightness constancy assumption needed for optical flow, and have complex segment characteristics beyond uniform appearance or motion. Our solution uses custom spatiotemporal filters that capture texture and motion cues, along with a novel metric-learning framework that optimizes this representation for specific objects and scenes. This is used within a hierarchical, graph-based segmentation setting, yielding state-of-the-art results for dynamic texture segmentation. We also demonstrate the applicability of our approach to general object and motion segmentation, showing significant improvements over unsupervised segmentation and results comparable to the best task specific approaches.
Rights: © 2015 IEEE
RMID: 0030045317
DOI: 10.1109/CVPR.2015.7298820
Published version:
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_108879.pdfRestricted Access1.93 MBAdobe PDFView/Open

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