Skeletal Quads: Human Action Recognition Using Joint Quadruples

Georgios Evangelidis 1 Gurkirt Singh 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 : Recent advances on human motion analysis have made the extraction of human skeleton structure feasible, even from single depth images. This structure has been proven quite informative for discriminating actions in a recognition scenario. In this context, we propose a local skeleton descriptor that encodes the relative position of joint quadruples. Such a coding implies a similarity normalisation transform that leads to a compact (6D) view-invariant skeletal feature, referred to as skeletal quad. Further, the use of a Fisher kernel representation is suggested to describe the skeletal quads contained in a (sub)action. A Gaussian mixture model is learnt from training data, so that the generation of any set of quads is encoded by its Fisher vector. Finally, a multi-level representation of Fisher vectors leads to an action description that roughly carries the order of sub-action within each action sequence. Efficient classification is here achieved by linear SVMs. The proposed action representation is tested on widely used datasets, MSRAction3D and HDM05. The experimental evaluation shows that the proposed method outperforms state-of-the-art algorithms that rely only on joints, while it competes with methods that combine joints with extra cues.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download


https://hal.archives-ouvertes.fr/hal-00989725
Contributor : Team Perception <>
Submitted on : Tuesday, September 16, 2014 - 5:41:48 PM
Last modification on : Wednesday, April 11, 2018 - 1:59:08 AM
Long-term archiving on : Wednesday, December 17, 2014 - 11:45:44 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Georgios Evangelidis, Gurkirt Singh, Radu Horaud. Skeletal Quads: Human Action Recognition Using Joint Quadruples. International Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. pp.4513 - 4518, ⟨10.1109/ICPR.2014.772⟩. ⟨hal-00989725v2⟩

Share

Metrics

Record views

1246

Files downloads

3379