loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis
Pose-Based Clustering in Action Sequences
Nice, France
October 17-October 17
ISBN: 0-7695-2049-9
ASCII Text
x 
 
Gareth Loy, Josephine Sullivan, Stefan Carlsson, "Pose-Based Clustering in Action Sequences," Higher-Level Knowledge in 3D Modeling and Motion Analysis, IEEE International Workshop on, pp. 66, First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003.
 
 
BibTex
x
 
@article{ 10.1109/HLK.2003.1240860,
author = {Gareth Loy and Josephine Sullivan and Stefan Carlsson},
title = {Pose-Based Clustering in Action Sequences},
journal ={Higher-Level Knowledge in 3D Modeling and Motion Analysis, IEEE International Workshop on},
volume = {0},
year = {2003},
isbn = {0-7695-2049-9},
pages = {66},
doi = {http://doi.ieeecomputersociety.org/10.1109/HLK.2003.1240860},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Higher-Level Knowledge in 3D Modeling and Motion Analysis, IEEE International Workshop on
TI - Pose-Based Clustering in Action Sequences
SN - 0-7695-2049-9
SP
EP
A1 - Gareth Loy,
A1 - Josephine Sullivan,
A1 - Stefan Carlsson,
PY - 2003
KW - null
VL - 0
JA - Higher-Level Knowledge in 3D Modeling and Motion Analysis, IEEE International Workshop on
ER -
 
Gareth Loy, Royal Institute of Technology (KTH)
Josephine Sullivan, Royal Institute of Technology (KTH)
Stefan Carlsson, Royal Institute of Technology (KTH)
A method is presented for automatically extracting key frames from an image sequence. The sequence is divided into clusters of frames with similar appearance, and the most central frame in each cluster defines a key frame. Clustering is done using an extension of the normalized cut segmentation technique based on the inter-frame similarities. The similarity between every pair of frames in the sequence is determined from the spatial image characteristics via a shape matching technique. Our algorithm is demonstrated successfully extracting 20 key frames for a tennis player in action over a 30 second (900 frame) video sequence.
Citation:
Gareth Loy, Josephine Sullivan, Stefan Carlsson, "Pose-Based Clustering in Action Sequences," hlk, pp.66, First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003
Usage of this product signifies your acceptance of the Terms of Use.