Skip to Main content Skip to Navigation
Conference papers

Activity Recognition with Volume Motion Templates and Histograms of 3D Gradients

Emre Dogan 1 Gonen Eren Christian Wolf 1 Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01147957
Contributor : Christian Wolf <>
Submitted on : Sunday, May 3, 2015 - 10:46:30 PM
Last modification on : Thursday, November 21, 2019 - 2:22:17 AM

Identifiers

  • HAL Id : hal-01147957, version 1

Citation

Emre Dogan, Gonen Eren, Christian Wolf, Atilla Baskurt. Activity Recognition with Volume Motion Templates and Histograms of 3D Gradients. International Conference on Image Processing, Sep 2015, Quebec City, Canada. ⟨hal-01147957⟩

Share

Metrics

Record views

292