A generic approach to design and querying of multi-purpose human motion database

Authors:
Wiktor Filipowicz;Piotr Habela;Krzysztof Kaczmarski;Marek Kulbacki
Affiliations:
Polish-Japanese Institute of Information Technology, Warsaw, Poland;Polish-Japanese Institute of Information Technology, Warsaw, Poland;Warsaw University of Technology, Warsaw, Poland;Polish-Japanese Institute of Information Technology, Warsaw, Poland
Venue:
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part I
Year:
2010

Citing 10
Cited 0

Multimedia Database Management Systems

Multimedia Database Management Systems
Automated extraction and parameterization of motions in large data sets

ACM SIGGRAPH 2004 Papers
Motion map: image-based retrieval and segmentation of motion data

SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
A system for analyzing and indexing human-motion databases

Proceedings of the 2005 ACM SIGMOD international conference on Management of data
Action synopsis: pose selection and illustration

ACM SIGGRAPH 2005 Papers
An efficient search algorithm for motion data using weighted PCA

Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation
Statistical analysis of natural human motion for animation

Statistical analysis of natural human motion for animation
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

International Journal of Computer Vision
Content-based retrieval for human motion data

Journal of Visual Communication and Image Representation
An information retrieval system for motion capture data

ECIR'06 Proceedings of the 28th European conference on Advances in Information Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

The advancement of motion recording, analysis and synthesis techniques, together with the standardization of respective data formats, constitutes a solid foundation for research based on motion data sets in the context of various disciplines. However, most of the motion data sets available offer groups of files as acquired from the motion capture systems. The problem with such data is that it usually represents a single viewpoint, its context varies and is more or less implicit, and the lack of functionality implemented atop of such data set limits the data analysis and search potential. This encourages us to look at this problem domain from the database management systems (DBMS) state of the art point of view. In this paper, we outline some important aspects of applying a DBMS to motion data with the aim to provide a highly universal, extensible, shareable and searchable resource. To avoid being locked into a specific area of application, we take a very abstract view of the data and attempt to assure, a versatility and genericity of the resulting system.