Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/102468
Title: Combining pose-invariant kinematic features and object context features for RGB-D action recognition
Authors: Ramanathan, Manoj
Kochanowicz, Jaroslaw
Thalmann, Nadia Magnenat
Keywords: Poseinvariant Kinematic Features
Real-time Action/Activity Recognition
Visual arts and music::Media
Issue Date: 2019
Source: Ramanathan, M., Kochanowicz, J., & Thalmann, N. M. (2019). Combining pose-invariant kinematic features and object context features for RGB-D action recognition. International Journal of Machine Learning and Computing, 9(1), 44-50. doi: 10.18178/ijmlc.2019.9.1.763
Series/Report no.: International Journal of Machine Learning and Computing
Abstract: Action recognition using RGB-D cameras is a popular research topic. Recognising actions in a pose-invariant manner is very challenging due to view changes, posture changes and huge intra-class variations. This study aims to propose a novel pose-invariant action recognition framework based on kinematic features and object context features. Using RGB, depth and skeletal joints, the proposed framework extracts a novel set of pose-invariant motion kinematic features based on 3D scene flow and captures the motion of body parts with respect to the body. The obtained features are converted to a human body centric space that allows partial viewinvariant recognition of actions. The proposed pose-invariant kinematic features are extracted for both foreground (RGB and depth) and skeleton joints and separate classifiers are trained. Bordacount based classifier decision fusion is employed to obtain an action recognition result. For capturing object context features, a convolutional neural network (CNN) classifier is proposed to identify the involved objects. The proposed context features also include temporal information on object interaction and help in obtaining a final action recognition. The proposed framework works even with non-upright human postures and allows simultaneous action recognition for multiple people, which are topics that remain comparatively unresearched. The performance and robustness of the proposed pose-invariant action recognition framework are tested on several benchmark datasets. We also show that the proposed method works in real-time.
URI: https://hdl.handle.net/10356/102468
http://hdl.handle.net/10220/49519
DOI: http://dx.doi.org/10.18178/ijmlc.2019.9.1.763
Rights: © 2019 The Author(s) (published by International Journal of Machine Learning and Computing). This is an open-access article distributed under the terms of the Creative Commons Attribution License.
metadata.item.grantfulltext: open
metadata.item.fulltext: With Fulltext
Appears in Collections:IMI Journal Articles

Page view(s)

34
checked on Dec 25, 2019

Download(s)

32
checked on Dec 25, 2019

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.