Detailed Information

Cited 4 time in webofscience Cited 4 time in scopus
Metadata Downloads

Image representation of pose-transition feature for 3D skeleton-based action recognition

Authors
Thien Huynh-TheHua, Cam-HaoTrung-Thanh NgoKim, Dong-Seong
Issue Date
Mar-2020
Publisher
ELSEVIER SCIENCE INC
Keywords
Pose-transition feature to image (PoT2I) encoding technique; Depth camera; Human action recognition; Deep convolutional neural networks
Citation
INFORMATION SCIENCES, v.513, pp.112 - 126
Journal Title
INFORMATION SCIENCES
Volume
513
Start Page
112
End Page
126
URI
https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/96
DOI
10.1016/j.ins.2019.10.047
ISSN
0020-0255
Abstract
Recently, skeleton-based human action recognition has received more interest from industrial and research communities for many practical applications thanks to the popularity of depth sensors. A large number of conventional approaches, which have exploited handcrafted features with traditional classifiers, cannot learn high-level spatiotemporal features to precisely recognize complex human actions. In this paper, we introduce a novel encoding technique, namely Pose-Transition Feature to Image (PoT2I), to transform skeleton information to image-based representation for deep convolutional neural networks (CNNs). The spatial joint correlations and temporal pose dynamics of an action are exhaustively depicted by an encoded color image. For learning action models, we fine-tune end-to-end a pre-trained network to thoroughly capture multiple high-level features at multi-scale action representation. The proposed method is benchmarked on several challenging 3D action recognition datasets (e.g., UTKinect-Action3D, SBU-Kinect Interaction, and NTU RGB+D) with different parameter configurations for performance analysis. Outstanding experimental results with the highest accuracy of 90.33% on the most challenging NTU RGB+D dataset demonstrate that our action recognition method with PoT2I outperforms state-of-the-art approaches. (C) 2019 Elsevier Inc. All rights reserved.
Files in This Item:
There are no files associated with this item.
Appears in
Collections:
School of Electronic Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

KIM, DONG SEONG
전자공학부
Read more

Views & Downloads

MENU