Recognition of freely selected keypoints on human limbs

  • Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points are desired, they have to be manually annotated and the model needs to be retrained. Our approach leverages the Vision Transformer architecture to extend the capability of the model to detect arbitrary keypoints on the limbs of persons. We propose two different approaches to encode the desired keypoints. (1) Each keypoint is defined by its position along the line between the two enclosing key-points from the fixed set and its relative distance between this line and the edge of the limb. (2) Keypoints are defined as coordinates on a norm pose. Both approaches are based on the TokenPose [12] architecture, while the key-point tokens that correspond to the fixed keypoints are replaced with our novel module. Experiments show that our approaches achieve similar results to TokenPose on the fixed keypoints and areNearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points are desired, they have to be manually annotated and the model needs to be retrained. Our approach leverages the Vision Transformer architecture to extend the capability of the model to detect arbitrary keypoints on the limbs of persons. We propose two different approaches to encode the desired keypoints. (1) Each keypoint is defined by its position along the line between the two enclosing key-points from the fixed set and its relative distance between this line and the edge of the limb. (2) Keypoints are defined as coordinates on a norm pose. Both approaches are based on the TokenPose [12] architecture, while the key-point tokens that correspond to the fixed keypoints are replaced with our novel module. Experiments show that our approaches achieve similar results to TokenPose on the fixed keypoints and are capable of detecting arbitrary keypoints on the limbs.show moreshow less

Download full text files

  • 94800.pdfeng
    (26959KB)

    Postprint. © 2022 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.

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Katja LudwigGND, Daniel KienzleGND, Rainer LienhartORCiDGND
URN:urn:nbn:de:bvb:384-opus4-948002
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/94800
ISBN:978-1-6654-8740-5OPAC
ISSN:2160-7516OPAC
Parent Title (English):2022 IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, LA, USA, 19-24 June 2022
Publisher:IEEE
Place of publication:Piscataway, NJ
Editor:Rama Chellappa, Jiri Matas, Long Quan, Mubarak Shah, Eric Mortensen
Type:Conference Proceeding
Language:English
Year of first Publication:2022
Publishing Institution:Universität Augsburg
Release Date:2022/04/25
First Page:3530
Last Page:3538
DOI:https://doi.org/10.1109/CVPRW56347.2022.00397
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Maschinelles Lernen und Maschinelles Sehen
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):Deutsches Urheberrecht