The i3DPost Multi-View and 3D Human Action/Interaction Database

Authors:
Nikolaos Gkalelis;Hansung Kim;Adrian Hilton;Nikos Nikolaidis;Ioannis Pitas
Affiliations:
Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece/ and Department of Informatics, Aristotle University of Thessalonika, Greece;University of Surrey, Guildford, UK;University of Surrey, Guildford, UK;Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece/ and Department of Informatics, Aristotle University of Thessalonika, Greece;Informatics and Telematics Institute, Centre for Research and Technology Hellas, Greece/ and Department of Informatics, Aristotle University of Thessalonika, Greece
Venue:
CVMP '09 Proceedings of the 2009 Conference for Visual Media Production
Year:
2009

Citing 0
Cited 11

Learning human identity using view-invariant multi-view movement representation

BioID'11 Proceedings of the COST 2101 European conference on Biometrics and ID management
Human action recognition using multiple views: a comparative perspective on recent developments

J-HGBU '11 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding
Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis

Computer Vision and Image Understanding
Real-time pose estimation using constrained dynamics

AMDO'12 Proceedings of the 7th international conference on Articulated Motion and Deformable Objects
Model-based recognition of human actions by trajectory matching in phase spaces

Image and Vision Computing
Multi-view action recognition based on action volumes, fuzzy distances and cluster discriminant analysis

Signal Processing
Motion history of skeletal volumes and temporal change in bounding volume fusion for human action recognition

MPRSS'12 Proceedings of the First international conference on Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction
A survey of video datasets for human action and activity recognition

Computer Vision and Image Understanding
Learning sparse representations for view-independent human action recognition based on fuzzy distances

Neurocomputing
Dynamic action recognition based on dynemes and Extreme Learning Machine

Pattern Recognition Letters
On 3D object retrieval benchmarking

3D Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a new multi-view/3D human action/interaction database is presented. The database has been created using a convergent eight camera setup to produce high definition multi-view videos, where each video depicts one of eight persons performing one of twelve different human motions. Various types of motions have been recorded, i.e., scenes where one person performs a specific movement, scenes where a person executes different movements in a succession and scenes where two persons interact with each other. Moreover, the subjects have different body sizes, clothing and are of different sex, nationalities, etc.. The multi-view videos have been further processed to produce a 3D mesh at each frame describing the respective 3D human body surface. To increase the applicability of the database, for each person a multi-view video depicting the person performing sequentially the six basic facial expressions separated by the neutral expression has also been recorded. The database is freely available for research purposes.