Efficient Unsupervised Temporal Segmentation of Motion Data

In: IEEE Transactions on Multimedia (Apr. 2017), 19:4(797-812)
 

Abstract

We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence. We use neighborhood graphs for the partitioning and the similarity information in the graph is further exploited to cluster the motion primitives into larger entities of semantic significance. The method requires no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique to make the segmentation more robust to noise, as well as a notion of motion symmetry for more refined primitive detection. We test our method on several sensor modalities, including markered and markerless motion capture as well as on electromyograph and accelerometer recordings. The results highlight our system’s capabilities for both segmentation and for analysis of the finer structures of motion data, all in a completely unsupervised manner.

Source code

Source code and additional data for this paper are available: http://cg.cs.uni-bonn.de/en/projects/gemmquad/motionsegmentation/

Bilder

Bibtex

@ARTICLE{krueger2017Segmentation,
    author = {Kr{\"u}ger, Bj{\"o}rn and V{\"o}gele, Anna and Willig, Tobias and Yao, Angela and Klein, Reinhard and Weber,
              Andreas},
     pages = {797--812},
     title = {Efficient Unsupervised Temporal Segmentation of Motion Data},
   journal = {IEEE Transactions on Multimedia},
    volume = {19},
    number = {4},
      year = {2017},
     month = apr,
  abstract = {We introduce a method for automated temporal segmentation of human motion data into distinct actions
              and compositing motion primitives based on self-similar structures in the motion sequence. We use
              neighborhood graphs for the partitioning and the similarity information in the graph is further
              exploited to cluster the motion primitives into larger entities of semantic significance. The method
              requires no assumptions about the motion sequences at hand and no user interaction is required for
              the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique
              to make the segmentation more robust to noise, as well as a notion of motion symmetry for more
              refined primitive detection. We test our method on several sensor modalities, including markered and
              markerless motion capture as well as on electromyograph and accelerometer recordings. The results
              highlight our system’s capabilities for both segmentation and for analysis of the finer structures
              of motion data, all in a completely unsupervised manner.},
      issn = {1520-9210},
       doi = {10.1109/TMM.2016.2635030}
}