Conference item icon

Conference item

2D human pose estimation in TV shows

Abstract:

The goal of this work is fully automatic 2D human pose estimation in unconstrained TV shows and feature films. Direct pose estimation on this uncontrolled material is often too difficult, especially when knowing nothing about the location, scale, pose, and appearance of the person, or even whether there is a person in the frame or not.

We propose an approach that progressively reduces the search space for body parts, to greatly facilitate the task for the pose estimator. Moreover, when video is available, we propose methods for exploiting the temporal continuity of both appearance and pose for improving the estimation based on individual frames.

The method is fully automatic and self-initializing, and explains the spatio-temporal volume covered by a person moving in a shot by soft-labeling every pixel as belonging to a particular body part or to the background. We demonstrate upper-body pose estimation by running our system on four episodes of the TV series Buffy the vampire slayer (i.e. three hours of video). Our approach is evaluated quantitatively on several hundred video frames, based on ground-truth annotation of 2D poses. Finally, we present an application to full-body action recognition on the Weizmann dataset.

Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-642-03061-1_7

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
Springer
Host title:
Statistical and Geometrical Approaches to Visual Motion Analysis
Pages:
128-147
Series:
Lecture Notes in Computer Science
Series number:
5604
Publication date:
2009-01-01
Event title:
Statistical and Geometrical Approaches to Visual Motion Analysis. 14th Workshop “Theoretic Foundations of Computer Vision”
Event location:
Dagstuhl Castle, Germany
Event website:
https://www.dagstuhl.de/en/seminars/seminar-calendar/seminar-details/08091
Event start date:
2008-07-13
Event end date:
2008-07-18
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
EISBN:
9783642030611
ISBN:
9783642030604


Language:
English
Pubs id:
719083
Local pid:
pubs:719083
Deposit date:
2024-07-23

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP