A line based pose representation for human action recognition
dc.citation.epage | 471 | en_US |
dc.citation.issueNumber | 5 | en_US |
dc.citation.spage | 458 | en_US |
dc.citation.volumeNumber | 28 | en_US |
dc.contributor.author | Baysal, S. | en_US |
dc.contributor.author | Duygulu, P. | en_US |
dc.date.accessioned | 2016-02-08T09:39:09Z | |
dc.date.available | 2016-02-08T09:39:09Z | |
dc.date.issued | 2013 | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description.abstract | In this paper, we utilize a line based pose representation to recognize human actions in videos. We represent the pose in each frame by employing a collection of line-pairs, so that limb and joint movements are better described and the geometrical relationships among the lines forming the human figure are captured. We contribute to the literature by proposing a new method that matches line-pairs of two poses to compute the similarity between them. Moreover, to encapsulate the global motion information of a pose sequence, we introduce line-flow histograms, which are extracted by matching line segments in consecutive frames. Experimental results on Weizmann and KTH datasets emphasize the power of our pose representation, and show the effectiveness of using pose ordering and line-flow histograms together in grasping the nature of an action and distinguishing one from the others. © 2013 Elsevier B.V. All rights reserved. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T09:39:09Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2013 | en |
dc.identifier.doi | 10.1016/j.image.2013.01.005 | en_US |
dc.identifier.issn | 0923-5965 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/20987 | en_US |
dc.language.iso | English | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1016/j.image.2013.01.005 | en_US |
dc.source.title | Signal Processing: Image Communication: theory, techniques & applications | en_US |
dc.subject | Action recognition | en_US |
dc.subject | Human motion | en_US |
dc.subject | Line - flow | en_US |
dc.subject | Pose matching | en_US |
dc.subject | Pose similarity | en_US |
dc.subject | Gesture recognition | en_US |
dc.subject | Graphic methods | en_US |
dc.subject | Image recognition | en_US |
dc.subject | Motion estimation | en_US |
dc.title | A line based pose representation for human action recognition | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- A line based pose representation for human action recognition.pdf
- Size:
- 1.36 MB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version