Learning similarity metrics for dynamic scene segmentation

Simple item page
dc.contributor.authorTeney, D.
dc.contributor.authorBrown, M.
dc.contributor.authorKit, D.
dc.contributor.authorHall, P.
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)
dc.date.issued2015
dc.description.abstractThis 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.
dc.description.statementofresponsibilityDamien Teney, Matthew Brown, Dimitry Kit Peter Hall
dc.identifier.citationProceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, vol.07-12-June-2015, pp.2084-2093
dc.identifier.doi10.1109/CVPR.2015.7298820
dc.identifier.isbn9781467369640
dc.identifier.issn1063-6919
dc.identifier.orcidTeney, D. [0000-0003-2130-6650]
dc.identifier.urihttp://hdl.handle.net/2440/108879
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rights© 2015 IEEE
dc.source.urihttp://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7293313
dc.titleLearning similarity metrics for dynamic scene segmentation
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RA_hdl_108879.pdf
Size:
1.89 MB
Format:
Adobe Portable Document Format
Description:
Restricted Access
Download

Collections

Computer Science publications