Action Recognition based on a mixture of RGB and Depth based skeleton

Srijan Das 1 Michal Koperski 1 François Bremond 1 Gianpiero Francesca 2
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
2 Toyota Motor Europe (BELGIUM)
Abstract : In this paper, we study how different skeleton extraction methods affect the performance of action recognition. As shown in previous work skeleton information can be exploited for action recognition. Nevertheless, skeleton detection problem is already hard and very often it is difficult to obtain reliable skeleton information from videos. In this paper , we compare two skeleton detection methods: the depth-map based method used with Kinect camera and RGB based method that uses Deep Convolutional Neural Networks. In order to balance the pros and cons of mentioned skeleton detection methods w.r.t. action recognition task, we propose a fusion of classifiers trained based on each skeleton detection method. Such fusion lead to performance improvement. We validate our approach on CAD-60 and MSRDailyActiv-ity3D, achieving state-of-the-art results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download
https://hal.inria.fr/hal-01639504
Contributor : Srijan Das <>
Submitted on : Tuesday, November 21, 2017 - 1:09:46 PM
Last modification on : Monday, October 15, 2018 - 5:50:02 PM

File

fusing-rgb-depth.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01639504, version 1

Collections

INRIA | INRIA2017 | UNIV-COTEDAZUR

Citation

Srijan Das, Michal Koperski, François Bremond, Gianpiero Francesca. Action Recognition based on a mixture of RGB and Depth based skeleton. AVSS 2017 - 14-th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Aug 2017, Lecce, Italy. ⟨hal-01639504⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

152

Files downloads

289

Contact


archive-ouverte@inria.fr