Skip to Main content Skip to Navigation
New interface
Journal articles

Free viewpoint action recognition using motion history volumes

Daniel Weinland 1 Rémi Ronfard 1 Edmond Boyer 1 
1 PERCEPTION - Interpretation and Modelling of Images and Videos
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understanding of social interaction. Yet, most current work in gesture or action interpretation remains rooted in view-dependent representations. This paper introduces Motion History Volumes (MHV) as a free-viewpoint representation for human actions in the case of multiple calibrated, and background-subtracted, video cameras. We present algorithms for computing, aligning and comparing MHVs of different actions performed by different people in a variety of viewpoints. Alignment and comparisons are performed efficiently using Fourier transforms in cylindrical coordinates around the vertical axis. Results indicate that this representation can be used to learn and recognize basic human action classes, independently of gender, body size and viewpoint.
Document type :
Journal articles
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download
Contributor : Rémi Ronfard Connect in order to contact the contributor
Submitted on : Tuesday, May 24, 2011 - 3:36:58 PM
Last modification on : Tuesday, May 17, 2022 - 9:08:01 AM
Long-term archiving on: : Thursday, August 25, 2011 - 2:20:36 AM


Files produced by the author(s)




Daniel Weinland, Rémi Ronfard, Edmond Boyer. Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding, 2006, 104 (2-3), pp.249-257. ⟨10.1016/j.cviu.2006.07.013⟩. ⟨inria-00544629⟩



Record views


Files downloads