Action Recognition Based on Feature Extraction From Time Series

KEÇELİ A. S., CAN A. B.

22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Türkiye, 23 - 25 Nisan 2014, ss.485-488 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2014.6830271
  • Basıldığı Şehir: Trabzon
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.485-488
  • Hacettepe Üniversitesi Adresli: Evet

Özet

Usage of 3th dimension information obtained from depth sensors in human action recognition has gained importance in the recent years. In this study, basic human actions are tried to recognize on a human model derived from RGBD sensor. Joint angles and joint displacements used as time series and feature extraction from times series is applied to recognize actions. Actions are classified with the random forest and support vector machine approaches and classification accuracy is measured on MSRAction-3D and MSRC-12 datasets.