2D Human Pose Estimation in TV Shows

Vittorio Ferrari, Manuel Marín-Jiménez, Andrew Zisserman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationStatistical and Geometrical Approaches to Visual Motion Analysis
Subtitle of host publicationInternational Dagstuhl Seminar, Dagstuhl Castle, Germany, July 13-18, 2008. Revised Papers
EditorsDaniel Cremers, Bodo Rosenhahn, Alan L. Yuille, Frank R. Schmidt
PublisherSpringer Berlin Heidelberg
Number of pages20
ISBN (Electronic)978-3-642-03061-1
ISBN (Print)978-3-642-03060-4
Publication statusPublished - 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Dive into the research topics of '2D Human Pose Estimation in TV Shows'. Together they form a unique fingerprint.

Cite this