Automatic Temporal Segmentation of Articulated Hand Motion

Katharina Stollenwerk, Anna Vögele, Björn Krüger, André Hinkenjann, and Reinhard Klein
In proceedings of Computational Science and Its Applications -- ICCSA 2016: 16th International Conference, Beijing, China, July 4-7, 2016, Proceedings, Part II, Beijing, China, pages 433-449, Springer International Publishing, July 2016
 

Abstract

This paper introduces a novel and efficient segmentation method designed for articulated hand motion. The method is based on a graph representation of temporal structures in human hand-object interaction. Along with the method for temporal segmentation we provide an extensive new database of hand motions. The experiments performed on this data set show that our method is capable of fully automatic hand motion segmentation which largely coincides with human user annotation.

Images

Download Paper

Download Paper

Bibtex

@INPROCEEDINGS{stollenwerk2016a,
     author = {Stollenwerk, Katharina and V{\"o}gele, Anna and Kr{\"u}ger, Bj{\"o}rn and Hinkenjann, Andr{\'e} and Klein,
               Reinhard},
      pages = {433--449},
      title = {Automatic Temporal Segmentation of Articulated Hand Motion},
    journal = {Lecture Notes in Computer Science, Computational Science and Its Applications - ICCSA 2016},
  booktitle = {Computational Science and Its Applications -- ICCSA 2016: 16th International Conference, Beijing,
               China, July 4-7, 2016, Proceedings, Part II},
       year = {2016},
      month = jul,
  publisher = {Springer International Publishing},
   location = {Beijing, China},
       note = {accepted for publication},
   abstract = {This paper introduces a novel and efficient segmentation
               method designed for articulated hand motion. The method is based on
               a graph representation of temporal structures in human hand-object interaction.
               Along with the method for temporal segmentation we provide
               an extensive new database of hand motions. The experiments performed
               on this data set show that our method is capable of fully automatic hand
               motion segmentation which largely coincides with human user annotation.},
       isbn = {978-3-319-42108-7},
        url = {http://dx.doi.org/10.1007/978-3-319-42108-7_33},
        doi = {10.1007/978-3-319-42108-7_33}
}