Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Two-stage RGB-based Action Detection using Augmented 3D Poses
PAPADOPOULOS, Konstantinos; GHORBEL, Enjie; BAPTISTA, Renato et al.
2019In 18th International Conference on Computer Analysis of Images and Patterns SALERNO, 3-5 SEPTEMBER, 2019
Peer reviewed
 

Files


Full Text
Springer_Lecture_Notes_in_Computer_Science_CAIP.pdf
Author preprint (2.76 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Action detection; LSTM; pose estimation; action proposals
Abstract :
[en] In this paper, a novel approach for action detection from RGB sequences is proposed. This concept takes advantage of the recent development of CNNs to estimate 3D human poses from a monocular camera. To show the validity of our method, we propose a 3D skeleton-based two-stage action detection approach. For localizing actions in unsegmented sequences, Relative Joint Position (RJP) and Histogram Of Displacements (HOD) are used as inputs to a k-nearest neighbor binary classifier in order to define action segments. Afterwards, to recognize the localized action proposals, a compact Long Short-Term Memory (LSTM) network with a de-noising expansion unit is employed. Compared to previous RGB-based methods, our approach offers robustness to radial motion, view-invariance and low computational complexity. Results on the Online Action Detection dataset show that our method outperforms earlier RGB-based approaches.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Disciplines :
Computer science
Author, co-author :
PAPADOPOULOS, Konstantinos ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
GHORBEL, Enjie  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
BAPTISTA, Renato ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
AOUADA, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
OTTERSTEN, Björn  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
Two-stage RGB-based Action Detection using Augmented 3D Poses
Publication date :
2019
Event name :
18th International Conference on Computer Analysis of Images and Patterns
Event date :
from 03-09-2019 to 05-09-2019
Main work title :
18th International Conference on Computer Analysis of Images and Patterns SALERNO, 3-5 SEPTEMBER, 2019
Peer reviewed :
Peer reviewed
FnR Project :
FNR10415355 - 3d Action Recognition Using Refinement And Invariance Strategies For Reliable Surveillance, 2015 (01/06/2016-31/05/2019) - Bjorn Ottersten
Funders :
FNR - Fonds National de la Recherche
Available on ORBilu :
since 01 July 2019

Statistics


Number of views
205 (12 by Unilu)
Number of downloads
696 (12 by Unilu)

Scopus citations®
 
6
Scopus citations®
without self-citations
4

Bibliography


Similar publications



Contact ORBilu