Action Recognition Robust to Background Clutter by Using Stereo Vision

Jordi Sanchez-Riera 1 Jan Cech 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : An action recognition algorithm which works with binocular videos is presented. The proposed method uses standard bag-of-words approach, where each action clip is represented as a histogram of visual words. However, instead of using classical monocular HoG/HoF features, we construct features from the scene-flow computed by a matching algorithm on the sequence of stereo images. The resulting algorithm has a comparable or slightly better recognition accuracy than standard monocular solution in controlled setup with a single actor present in the scene. However, we show its significantly improved performance in case of strong background clutter due to other people freely moving behind the actor.
Document type :
Conference papers
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-00768670
Contributor : Team Perception <>
Submitted on : Saturday, December 22, 2012 - 6:42:14 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:25 AM
Long-term archiving on : Saturday, March 23, 2013 - 3:47:42 AM

File

ws106.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Jordi Sanchez-Riera, Jan Cech, Radu Horaud. Action Recognition Robust to Background Clutter by Using Stereo Vision. 4th International Workshop on Video Event Categorization, Tagging and Retrieval, Oct 2012, Firenze, Italy. pp.332-341, ⟨10.1007/978-3-642-33863-2_33⟩. ⟨hal-00768670⟩

Share

Metrics

Record views

538

Files downloads

351