Learning similarity metrics for dynamic scene segmentation

Files

RA_hdl_108879.pdf (1.89 MB)
  (Restricted Access)

Date

2015

Authors

Teney, D.
Brown, M.
Kit, D.
Hall, P.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings / 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

Statement of Responsibility

Damien Teney, Matthew Brown, Dimitry Kit Peter Hall

Conference Name

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2015 IEEE

License

Grant ID

Call number

Persistent link to this record