A learning-based markerless approach for full-body kinematics estimation in-natura from a single image

Simple item page
dc.contributor.authorDrory, Ami
dc.contributor.authorLi, Hongdong
dc.contributor.authorHartley, Richard
dc.date.accessioned2017-06-30T06:24:48Z
dc.date.issued2017-04-11
dc.description.abstractWe present a supervised machine learning approach for markerless estimation of human full-body kinematics for a cyclist from an unconstrained colour image. This approach is motivated by the limitations of existing marker-based approaches restricted by infrastructure, environmental conditions, and obtrusive markers. By using a discriminatively learned mixture-of-parts model, we construct a probabilistic tree representation to model the configuration and appearance of human body joints. During the learning stage, a Structured Support Vector Machine (SSVM) learns body parts appearance and spatial relations. In the testing stage, the learned models are employed to recover body pose via searching in a test image over a pyramid structure. We focus on the movement modality of cycling to demonstrate the efficacy of our approach. In natura estimation of cycling kinematics using images is challenging because of human interaction with a bicycle causing frequent occlusions. We make no assumptions in relation to the kinematic constraints of the model, nor the appearance of the scene. Our technique finds multiple quality hypotheses for the pose. We evaluate the precision of our method on two new datasets using loss functions. Our method achieves a score of 91.1 and 69.3 on mean Probability of Correct Keypoint (PCK) measure and 88.7 and 66.1 on the Average Precision of Keypoints (APK) measure for the frontal and sagittal datasets respectively. We conclude that our method opens new vistas to robust user-interaction free estimation of full body kinematics, a prerequisite to motion analysis.en_AU
dc.format.mimetypeapplication/pdfen_AU
dc.identifier.issn0021-9290en_AU
dc.identifier.urihttp://hdl.handle.net/1885/118421
dc.publisherElsevieren_AU
dc.rights© 2017 Elsevier Ltden_AU
dc.sourceJournal of biomechanicsen_AU
dc.subjectcyclingen_AU
dc.subjectmarkerless motion captureen_AU
dc.subjectmixture of partsen_AU
dc.subjectpose estimationen_AU
dc.subjectskeletal kinematicsen_AU
dc.titleA learning-based markerless approach for full-body kinematics estimation in-natura from a single imageen_AU
dc.typeJournal articleen_AU
dcterms.accessRightsOpen Accessen_AU
local.bibliographicCitation.lastpage10en_AU
local.bibliographicCitation.startpage1en_AU
local.contributor.affiliationDrory, A., The Australian National Universityen_AU
local.contributor.affiliationLi, Hongdong, Research School of Engineering, The Australian National Universityen_AU
local.contributor.affiliationHartley, R., Research School of Engineering, The Australian National Universityen_AU
local.contributor.authoremailu4970671@anu.edu.auen_AU
local.contributor.authoruidu4970671en_AU
local.description.embargo2037-12-31
local.identifier.citationvolume55en_AU
local.identifier.doi10.1016/j.jbiomech.2017.01.028en_AU
local.identifier.essn1873-2380en_AU
local.identifier.uidSubmittedByu1005913en_AU
local.publisher.urlhttp://www.elsevier.com/en_AU
local.type.statusPublished Versionen_AU

Downloads

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
01_Drory_A_Learning-based_markerless_2017.pdf
Size:
2.52 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
884 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS