Introducing semantic information into motion graph

Abstract

To improve motion graph based motion synthesis, semantic control was introduced. Hybrid motion features including both numerical and user-defined semantic relational features were extracted to encode the characteristic aspects contained in the character’s poses of the given motion sequences. Motion templates were then automatically derived from the training motions for capturing the spatio-temporal characteristics of an entire given class of semantically related motions. The data streams of motion documents were automatically annotated with semantic motion class labels by matching their respective motion class templates. Finally, the semantic control was introduced into motion graph based human motion synthesis. Experiments of motion synthesis demonstrate the effectiveness of the approach which enables users higher level of semantically intuitive control and high quality in human motion synthesis from motion capture database.

Keywords

motion synthesis / motion graph / motion similarity / semantic motion analysis / motion annotation / motion capture data

References

[1] SchödlA., SzeliskiR., SalesinD. H., EssaI.. Video textures [C]. ACM SIGGRAPH 2000, 2000, New Orleans, ACM Press: 489-498

[2] KovarL., GleicherM., PighinF.. Motion graphs [C]. ACM SIGGRAPH 2002, 2002, San Antonio, ACM Press: 473-482

[3] ArikanO., ForsythD. A.. Interactive motion generation from examples [C]. ACM SIGGRAPH 2002, 2002, San Antonio, ACM Press: 483-490

[4] LeeJ., ChaiJ., ReitsmaP. S. A., HodginsJ. K., PollardN. S.. Interactive control of avatars animated with human motion data [C]. ACM SIGGRAPH 2002, 2002, San Antonio, ACM Press: 491-500

[5] SafonovaA., HodginsJ. K.. Construction and optimal search of interpolated motion graphs [C]. ACM SIGGRAPH 2007, 2007, San Diego, ACM Press: 106

[6] IkemotoL., ArikanO., ForsythD.. Quick transitions with cached multi-way blends [C]. ACM Symposium on Interactive 3D Graphics 2007, 2007, Seattle, ACM Press: 145-151

[7] TreuilleA., LeeY., PopovicZ.. Near-optimal character animation with continuous control [C]. ACM SIGGRAPH 2007, 2007, San Diego, ACM Press: 7

[8] ZhaoL., NormoyleA., KhannaS., SafonovaA.. Automatic construction of a minimum size motion graph [C]. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2009, New Orleans, ACM Press: 27-35

[9] RenC., ZhaoL., SafonovaA.. Human motion synthesis with optimization-based graphs [J]. Computer Graphics Forum (Eurographics 2010), 2010, 29(2): 545-554

[10] MÜLLERM., RÖDERT., ClausenM.. Efficient content-based retrieval of motion capture data [C]. ACM SIGGRAPH 2005, 2005, Los Angeles, ACM Press: 677-685

[11] MÜLLERM.Information retrieval for music and motion [M], 2007, Secaucus, Springer-Verlag New York, Inc.: 184-296

[12] WangJ., BodenheimerB.. An evaluation of a cost metric for selecting transitions between motion segments [C]. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2003, San Diego, ACM Press: 232-238

[13] CARDLE M. Automated motion editing [R/OL]. Cambridge, UK: Computer Laboratory, University of Cambridge, (2004-5)/[2007-1]. http://www.cardle.info/lab/Cardle-Mocap-Matching-techreport-2004. pdf

[14] MÜLLERM., RÖDERT.. Motion templates for automatic classification and retrieval of motion capture data [C]. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2006, Vienna, ACM Press: 137-146

[15] MÜLLERM., BaakA., SeidelH. P.. Efficient and robust annotation of motion capture data [C]. ACM SIGGRAPH/ Eurographics Symposium on Computer Animation, 2009, New Orleans, ACM Press: 17-26

[16] WangJ., BodenheimerB.. Computing the duration of motion transitions: An empirical approach [C]. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2004, Grenoble, ACM Press: 335-344