Rule-based Motion Retrieval Using Inductive Logic

Generating Concise Rules for Retrieving Human Motions from Large Datasets

Abstract

We proposes a method for retrieving human motion data with concise retrieval rules based on the spatio-temporal features of motion appearance. Our method first converts motion clip into a form of clausal language that represents geometrical relations between body parts and their temporal relationship. A retrieval rule is then learned from the set of manually classified examples using inductive logic programming (ILP). ILP automatically discovers the essential rule in the same clausal form with a user-defined hypothesis-testing procedure. All motions are indexed using this clausal language, and the desired clips are retrieved by subsequence matching using the rule. Such rule-based retrieval offers reasonable performance and the rule can be intuitively edited in the same language form.

Publications

1. Tomohiko Mukai, Ken-ichi Wakisaka, and Shigeru Kuriyama, "Generating Concise Rules for Retrieving Human Motionsfrom Large Datasets", Computer Animation and Social Agents 2009 (CASA2009), Short Paper, 2009.6.
   Paper (preprint, PDF: 115KB)
   
2. Tomohiko Mukai, Ken-ichi Wakisaka, and Shigeru Kuriyama, "Rule-based Retrieval of Human Motion Data Using Inductive Logic Programming", ACM SIGGRAPH/Eurographics Symposium on Computer Animation 2007 (SCA2007), Posters and Demos, pp.22-23, 2007.8.
   Paper (preprint, PDF: 524KB)
   Poster (PDF: 196KB)

Results

	CASA 2009 video QuickTime: 24.0 MB, without Audio 640×480, 3:00
	SCA 2007 video QuickTime: 26.0 MB, without Audio 512×512, 3:05