3D human pose search using oriented cylinders

Creative Commons License

Pehlivan Tort S., DUYGULU ŞAHİN P.

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, Kyoto, Japan, 27 September - 04 October 2009, pp.16-22 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/iccvw.2009.5457722
  • City: Kyoto
  • Country: Japan
  • Page Numbers: pp.16-22
  • TED University Affiliated: Yes


In this study, we present a representation based on a new 3D search technique for volumetric human poses which is then used to recognize actions in three dimensional video sequences. We generate a set of cylinder like 3D kernels in various sizes and orientations. These kernels are searched over 3D volumes to find high response regions. The distribution of these responses are then used to represent a 3D pose. We use the proposed representation for (i) pose retrieval using Nearest Neighbor (NN) based classification and Support Vector Machine (SVM) based classification methods, and for (ii) action recognition on a set of actions using Dynamic Time Warping (DTW) and Hidden Markov Model (HMM) based classification methods. Evaluations on IXMAS dataset supports the effectiveness of such a robust pose representation. ©2009 IEEE.