Close
Metadata

1. Identity statement
Reference TypeOther (Misc)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/45CU7H5
Repositorysid.inpe.br/sibgrapi/2021/09.06.18.32
Last Update2021:09.06.18.32.08 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.06.18.32.09
Metadata Last Update2022:05.15.22.30.30 (UTC) administrator
Citation KeyCostaFigTeiLimTei:2021:HaPoEs
TitleAn Investigation of 2D Keypoints Detection on Challenging Scenarios Using Depthwise Separable Convolutions: A Hand Pose Estimation Case Study
Short TitleSupplementary material
FormatOn-line
Year2021
Date18-22 Oct. 2021
Access Date2024, May 19
Number of Files1
Size2980 KiB
2. Context
Author1 Costa, Willams
2 Figueiredo, Lucas
3 Teixeira, João Marcelo
4 Lima, João Paulo
5 Teichrieb, Veronica
Affiliation1 Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco
2 Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco
3 Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco
4 Departamento de Computação, Universidade Federal Rural de Pernambuco
5 Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco
e-Mail Addresswlc2@cin.ufpe.br
History (UTC)2021-09-06 18:32:09 :: wlc2@cin.ufpe.br -> administrator ::
2022-05-15 22:30:30 :: administrator -> wlc2@cin.ufpe.br :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordsreal-time hand pose estimation
human-computer interaction
depthwise separable convolutions
Abstract2D keypoints detection is a computer vision task applicable to several fields such as hand, face, and body tracking, which provides useful information for spatial analytics, gestural interactions, and augmented reality applications. This work investigates the usage of depthwise separable convolutions (an optimized convolution operation) to speed up the inference time on a largely used architecture for 2D keypoints estimation. We evaluate the impacts on the precision and performance of such optimization on a hand pose estimation task. We also extend the evaluation towards simulated challenging scenarios of defocused lens, motion blur, occlusions, and noisy images to understand how these stress situations affect both the original and the optimized architectures. We show that the execution time can be improved on average by 12.8\% with an accuracy compromise of less than 1 pixel (mean EPE). The experiments on challenging scenarios revealed that the model powered by depthwise separable convolutions is most fit for the occlusion cases and noisy environments while suffering more on the motion blur simulated scenarios.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > An Investigation of... > Supplementary material
Arrangement 2urlib.net > SDLA > Fonds > Full Index > An Investigation of... > Supplementary material
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 06/09/2021 15:32 2.0 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CU7H5
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CU7H5
Languageen
Target FileHand3d_supplementary_material.pdf
User Groupwlc2@cin.ufpe.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/45C6J72
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber city contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode howpublished isbn issn label lineage mark nextedition notes number numberofpages orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype session sponsor subject tertiarymark tertiarytype type url versiontype
7. Description control
e-Mail (login)wlc2@cin.ufpe.br
update 


Close