3-D Canonical pose estimation and abnormal gait recognition with a single RGB-D camera

File Description SizeFormat 
_RAL_IROS_accepted_3D_Canonical_Pose_Estimation_and_Abnormal_Gait_Recognition.pdfAccepted version3.68 MBAdobe PDFView/Open
Title: 3-D Canonical pose estimation and abnormal gait recognition with a single RGB-D camera
Authors: Guo, Y
Deligianni, F
Gu, X
Yang, G-Z
Item Type: Journal Article
Abstract: Assistive robots play an important role in improving the quality of life of patients at home. Among all the monitoring tasks, gait disorders are prevalent in elderly and people with neurological conditions and this increases the risk of fall. Therefore, the development of mobile systems for gait monitoring at home in normal living conditions is important. Here, we present a mobile system that is able to track humans and analyze their gait in canonical coordinates based on a single RGB-D camera. First, view-invariant three-dimensional (3-D) lower limb pose estimation is achieved by fusing information from depth images along with 2-D joints derived in RGB images. Next, both the 6-D camera pose and the 3-D lower limb skeleton are real-time tracked in a canonical coordinate system based on simultaneously localization and mapping (SLAM). A mask-based strategy is exploited to improve the re-localization of the SLAM in dynamic environments. Abnormal gait is detected by using the support vector machine and the bidirectional long-short term memory network with respect to a set of extracted gait features. To evaluate the robustness of the system, we collected multi-cameras, ground truth data from 16 healthy volunteers performing 6 gait patterns that mimic common gait abnormalities. The experiment results demonstrate that our proposed system can achieve good lower limb pose estimation and superior recognition accuracy compared to previous abnormal gait detection methods.
Issue Date: 1-Oct-2019
Date of Acceptance: 1-Jul-2019
URI: http://hdl.handle.net/10044/1/73046
DOI: https://doi.org/10.1109/LRA.2019.2928775
ISSN: 2377-3766
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 3617
End Page: 3624
Journal / Book Title: IEEE Robotics and Automation Letters
Volume: 4
Issue: 4
Copyright Statement: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Keywords: Science & Technology
Technology
Robotics
Computer vision for medical robotics
human detection and tracking
recognition
Science & Technology
Technology
Robotics
Computer vision for medical robotics
human detection and tracking
recognition
Publication Status: Published
Online Publication Date: 2019-07-15
Appears in Collections:Division of Surgery
Computing
Faculty of Medicine



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

Creative Commons