Generating human motion along pre-defined path in real-time

Man Lung Lau; Bartholomew Iu; Chapmann Chow; Pouro Lee

Generating human motion along pre-defined path in real-time

Man Lung Lau, Bartholomew Iu, Chapmann Chow, Pouro Lee

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

While many previous works to generate human motion has been proposed, these techniques are offline, memory inefficient and may require past and future time frames during the synthesis process. The objective of this paper is to propose an algorithm for human motion synthesis which targets for real-time applications. This algorithm was originally developed under a crowd simulation project which simulates the motion of the people by using a motion captured data library. Four main features of this synthesis algorithm include generating motion along a given path with the speed matched, adapting the motion to the scaled skeleton, running with an interactive speed and small memory footprint.

Original language	English
Title of host publication	5th International Conference on Information Technology and Applications, ICITA 2008
Pages	695-700
Number of pages	6
Publication status	Published - 1 Dec 2008
Event	5th International Conference on Information Technology and Applications, ICITA 2008 - Cairns, QLD, Australia Duration: 23 Jun 2008 → 26 Jun 2008

Conference

Conference	5th International Conference on Information Technology and Applications, ICITA 2008
Country/Territory	Australia
City	Cairns, QLD
Period	23/06/08 → 26/06/08

Keywords

Crowd simulation
Motion synthesis
Online algorithm
Real-time application

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Information Systems
Software

Cite this

@inproceedings{df25d42c2e7a48d1851b3a2a17749895,

title = "Generating human motion along pre-defined path in real-time",

abstract = "While many previous works to generate human motion has been proposed, these techniques are offline, memory inefficient and may require past and future time frames during the synthesis process. The objective of this paper is to propose an algorithm for human motion synthesis which targets for real-time applications. This algorithm was originally developed under a crowd simulation project which simulates the motion of the people by using a motion captured data library. Four main features of this synthesis algorithm include generating motion along a given path with the speed matched, adapting the motion to the scaled skeleton, running with an interactive speed and small memory footprint.",

keywords = "Crowd simulation, Motion synthesis, Online algorithm, Real-time application",

author = "Lau, {Man Lung} and Bartholomew Iu and Chapmann Chow and Pouro Lee",

year = "2008",

month = dec,

day = "1",

language = "English",

isbn = "9780980326727",

pages = "695--700",

booktitle = "5th International Conference on Information Technology and Applications, ICITA 2008",

note = "5th International Conference on Information Technology and Applications, ICITA 2008 ; Conference date: 23-06-2008 Through 26-06-2008",

}

TY - GEN

T1 - Generating human motion along pre-defined path in real-time

AU - Lau, Man Lung

AU - Iu, Bartholomew

AU - Chow, Chapmann

AU - Lee, Pouro

PY - 2008/12/1

Y1 - 2008/12/1

N2 - While many previous works to generate human motion has been proposed, these techniques are offline, memory inefficient and may require past and future time frames during the synthesis process. The objective of this paper is to propose an algorithm for human motion synthesis which targets for real-time applications. This algorithm was originally developed under a crowd simulation project which simulates the motion of the people by using a motion captured data library. Four main features of this synthesis algorithm include generating motion along a given path with the speed matched, adapting the motion to the scaled skeleton, running with an interactive speed and small memory footprint.

AB - While many previous works to generate human motion has been proposed, these techniques are offline, memory inefficient and may require past and future time frames during the synthesis process. The objective of this paper is to propose an algorithm for human motion synthesis which targets for real-time applications. This algorithm was originally developed under a crowd simulation project which simulates the motion of the people by using a motion captured data library. Four main features of this synthesis algorithm include generating motion along a given path with the speed matched, adapting the motion to the scaled skeleton, running with an interactive speed and small memory footprint.

KW - Crowd simulation

KW - Motion synthesis

KW - Online algorithm

KW - Real-time application

UR - http://www.scopus.com/inward/record.url?scp=67649160921&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 9780980326727

SP - 695

EP - 700

BT - 5th International Conference on Information Technology and Applications, ICITA 2008

T2 - 5th International Conference on Information Technology and Applications, ICITA 2008

Y2 - 23 June 2008 through 26 June 2008

ER -

Generating human motion along pre-defined path in real-time

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this