Activity recognition with volume motion templates and histograms of 3D gradients

Emre Dogan, Gonen Eren, Christian Wolf, Atilla BaskurtICIP 2015 · OpenReview

Abstract

We propose a new method for activity recognition based on a view independent representation of human motion. Robust 3D volume motion templates (VMTs) are calculated from tracklets. View independence is achieved through a rotation with respect to a canonical orientation. From this volumes, features based on 3D gradients are extracted, projected to a codebook and pooled into a bags-of-words model classified with an SVM classifier. Experiments show that the method outperforms the original HoG3D method.
BibTeX
@inproceedings{dogan2015activity,
  author = {Emre Dogan and Gonen Eren and Christian Wolf and Atilla Baskurt},
  title = {{Activity recognition with volume motion templates and histograms of 3D gradients}},
  booktitle = {ICIP},
  year = {2015},
  url = {https://openreview.net/forum?id=CzPNj7CGQPh},
}

Loading related content...

Figure