Article (Scientific journals)
Localized Trajectories for 2D and 3D Action Recognition
Papadopoulos, Konstantinos; Demisse, Girum; Ghorbel, Enjie et al.
2019In Sensors
Peer Reviewed verified by ORBi
 

Files


Full Text
Localized_Trajectories_for_2D_and_3D_Action_Recognition____1_.pdf
Author preprint (1.98 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
action recognition; Dense Trajectories; Local Bag-of-Words; spatiotemporal features
Abstract :
[en] The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides an advanced discriminative representation of actions. Moreover, we generalize Localized Trajectories to 3D by using the depth modality. One of the main advantages of 3D Localized Trajectories is that they describe radial displacements that are perpendicular to the image plane. Extensive experiments and analysis were carried out on five different datasets.
Disciplines :
Computer science
Author, co-author :
Papadopoulos, Konstantinos ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Demisse, Girum ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Ghorbel, Enjie  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Antunes, Michel
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 :
Localized Trajectories for 2D and 3D Action Recognition
Publication date :
2019
Journal title :
Sensors
ISSN :
1424-3210
Publisher :
Multidisciplinary Digital Publishing Institute (MDPI), Basel, Switzerland
Peer reviewed :
Peer Reviewed verified by ORBi
FnR Project :
FNR10415355 - 3d Action Recognition Using Refinement And Invariance Strategies For Reliable Surveillance, 2015 (01/06/2016-31/05/2019) - Bjorn Ottersten
Available on ORBilu :
since 12 September 2019

Statistics


Number of views
153 (17 by Unilu)
Number of downloads
95 (11 by Unilu)

Scopus citations®
 
11
Scopus citations®
without self-citations
9
OpenCitations
 
9
WoS citations
 
9

Bibliography


Similar publications



Contact ORBilu