Fast Local and Global Similarity Searches in Large Motion Capture Databases

In proceedings of 2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, Madrid, Spain, pages 1-10, Eurographics Association, Juli 2010
 

Abstract

Fast searching of content in large motion databases is essential for efficient motion analysis and synthesis. In this work we demonstrate that identifying locally similar regions in human motion data can be practical even for huge databases, if medium-dimensional (15–90 dimensional) feature sets are used for kd-tree-based nearest-neighbor-searches. On the basis of kd-tree-based local neighborhood searches we devise a novel fast method for global similarity searches. We show that knn-searches can be used efficiently within the problems of (a) numerical and logical similarity searches, (b) reconstruction of motions from sparse marker sets, and (c) building so called fat graphs, tasks for which previously algorithms with preprocessing time quadratic in the size of the database and thus only applicable to small collections of motions had been presented. We test our techniques on the two largest freely available motion capture databases, the CMU and HDM05 motion databases comprising more than 750 min of motion capture data proving that our approach is not only theoretically applicable but also solves the problem of fast similarity searches in huge motion databases in practice.

Stichwörter: Computer Graphics [I.3.7]: Three-Dimensional Graphics and Realism-[Animation] Information Storage and Retrieval [H.3]: Information Search and Retrieval

Bilder

Paper herunterladen

Paper herunterladen

Zusätzliches Material

Bibtex

@INPROCEEDINGS{krueger-2010-similaritysearches,
     author = {Kr{\"u}ger, Bj{\"o}rn and Tautges, Jochen and Weber, Andreas and Zinke, Arno},
      pages = {1--10},
      title = {Fast Local and Global Similarity Searches in Large Motion Capture Databases},
    journal = {Eurographics / ACM SIGGRAPH Symposium on Computer Animation},
  booktitle = {2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation},
     series = {SCA '10},
       year = {2010},
      month = jul,
  publisher = {Eurographics Association},
   location = {Madrid, Spain},
    address = {Aire-la-Ville, Switzerland, Switzerland},
   keywords = {Computer Graphics [I.3.7]: Three-Dimensional Graphics and Realism-[Animation] Information Storage
               and Retrieval [H.3]: Information Search and Retrieval},
   abstract = {Fast searching of content in large motion databases is essential for efficient motion analysis and
               synthesis.
               In this work we demonstrate that identifying locally similar regions in human motion data can be
               practical even for huge databases, if medium-dimensional (15--90 dimensional) feature sets are used
               for kd-tree-based nearest-neighbor-searches.
               On the basis of kd-tree-based local neighborhood searches we devise a novel fast method for global
               similarity searches.
               We show that knn-searches can be used efficiently within the problems of
               (a) numerical and logical similarity searches,
               (b) reconstruction of motions from sparse marker sets, and
               (c) building so called fat graphs,
               tasks for which previously algorithms with preprocessing time quadratic in the size of the database
               and thus only applicable to small collections of motions had been presented.
               We test our techniques on the two largest freely available motion capture databases, the CMU and
               HDM05 motion databases comprising more than 750 min of motion capture data proving that our approach
               is not only theoretically applicable but also solves the problem of fast similarity searches in huge
               motion databases in practice.},
        url = {http://portal.acm.org/citation.cfm?id=1921427.1921429},
        doi = {10.2312/SCA/SCA10/001-010}
}