NDLI: Action Recognition from Arbitrary Views using 3D Exemplars

Content Provider	IEEE Xplore Digital Library
Author	Weinland, D. Boyer, E. Ronfard, R.
Copyright Year	2007
Description	Author affiliation: LJK INRIA, Grenoble (Weinland, D.; Boyer, E.)
Abstract	In this paper, we address the problem of learning compact, view-independent, realistic 3D models of human actions recorded with multiple cameras, for the purpose of recognizing those same actions from a single or few cameras, without prior knowledge about the relative orientations between the cameras and the subjects. To this aim, we propose a new framework where we model actions using three dimensional occupancy grids, built from multiple viewpoints, in an exemplar-based HMM. The novelty is, that a 3D reconstruction is not required during the recognition phase, instead learned 3D exemplars are used to produce 2D image information that is compared to the observations. Parameters that describe image projections are added as latent variables in the recognition process. In addition, the temporal Markov dependency applied to view parameters allows them to evolve during recognition as with a smoothly moving camera. The effectiveness of the framework is demonstrated with experiments on real datasets and with challenging recognition scenarios.
Starting Page	1
Ending Page	7
File Size	696854
Page Count	7
File Format	PDF
ISBN	9781424416301
ISSN	15505499
DOI	10.1109/ICCV.2007.4408849
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2007-10-14
Publisher Place	Brazil
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Cameras Hidden Markov models Humans Image recognition Image reconstruction Solid modeling Layout Parametric statistics Kinematics Image motion analysis
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Action modeling with volumetric data

Recognizing human action in time-sequential images using hidden Markov model

Monocular 3D pose estimation and tracking by detection

Inferring 3D body pose from silhouettes using activity manifold learning

Using Bilinear Models for View-invariant Action and Identity Recognition

Augmenting monocular motion estimation using intermittent 3D models from depth sensors

Interactive construction of 3D models from panoramic mosaics

Geometric context from a single image

Toward Flexible 3D Modeling using a Catadioptric Camera

Action Recognition from Arbitrary Views using 3D Exemplars

Similar Documents

Action modeling with volumetric data

Recognizing human action in time-sequential images using hidden Markov model

Monocular 3D pose estimation and tracking by detection

Inferring 3D body pose from silhouettes using activity manifold learning

Using Bilinear Models for View-invariant Action and Identity Recognition

Augmenting monocular motion estimation using intermittent 3D models from depth sensors

Interactive construction of 3D models from panoramic mosaics

Geometric context from a single image

Toward Flexible 3D Modeling using a Catadioptric Camera

Action Recognition from Arbitrary Views using 3D Exemplars