ACTIVITY RECOGNITION WITH VOLUME MOTION TEMPLATES AND HISTOGRAMS OF 3D GRADIENTS

Dogan E., Eren G., Wolf C., Baskurt A.

IEEE International Conference on Image Processing (ICIP), Quebec City, Canada, 27 - 30 September 2015, pp.4421-4425 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/icip.2015.7351642
  • City: Quebec City
  • Country: Canada
  • Page Numbers: pp.4421-4425
  • Galatasaray University Affiliated: Yes

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.