Human Spine Motion Capture using Perforated Kinesiology Tape

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
UntertitelCVPRW 2023
Herausgeber (Verlag)IEEE Computer Society
Seiten5149-5157
Seitenumfang9
ISBN (elektronisch)9798350302493
PublikationsstatusVeröffentlicht - 2023
Veranstaltung2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Kanada
Dauer: 17 Juni 202324 Juni 2023

Publikationsreihe

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Band2023-June
ISSN (Print)2160-7508
ISSN (elektronisch)2160-7516

Abstract

In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.

ASJC Scopus Sachgebiete

Zitieren

Human Spine Motion Capture using Perforated Kinesiology Tape. / Hachmann, Hendrik; Rosenhahn, Bodo.
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023. IEEE Computer Society, 2023. S. 5149-5157 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Band 2023-June).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Hachmann, H & Rosenhahn, B 2023, Human Spine Motion Capture using Perforated Kinesiology Tape. in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Bd. 2023-June, IEEE Computer Society, S. 5149-5157, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, Vancouver, Kanada, 17 Juni 2023. https://doi.org/10.48550/arXiv.2306.02930, https://doi.org/10.1109/CVPRW59228.2023.00543
Hachmann, H., & Rosenhahn, B. (2023). Human Spine Motion Capture using Perforated Kinesiology Tape. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023 (S. 5149-5157). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Band 2023-June). IEEE Computer Society. https://doi.org/10.48550/arXiv.2306.02930, https://doi.org/10.1109/CVPRW59228.2023.00543
Hachmann H, Rosenhahn B. Human Spine Motion Capture using Perforated Kinesiology Tape. in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023. IEEE Computer Society. 2023. S. 5149-5157. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.48550/arXiv.2306.02930, 10.1109/CVPRW59228.2023.00543
Hachmann, Hendrik ; Rosenhahn, Bodo. / Human Spine Motion Capture using Perforated Kinesiology Tape. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023. IEEE Computer Society, 2023. S. 5149-5157 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
Download
@inproceedings{4a765e3b6cb84d108c89bdf9fe3ce14d,
title = "Human Spine Motion Capture using Perforated Kinesiology Tape",
abstract = "In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.",
author = "Hendrik Hachmann and Bodo Rosenhahn",
note = "Funding Information: This work was supported by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizKILabor (grant no. 01DD20003) and the AI service center KISSKI (grant no. 01IS22093C), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungsgemeinschaft (DFG) under Germany{\textquoteright}s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122). The authors also thank Dr. Oliver M{\"u}ller for fruitful discussions and hints. ; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 ; Conference date: 17-06-2023 Through 24-06-2023",
year = "2023",
doi = "10.48550/arXiv.2306.02930",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "5149--5157",
booktitle = "2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops",
address = "United States",

}

Download

TY - GEN

T1 - Human Spine Motion Capture using Perforated Kinesiology Tape

AU - Hachmann, Hendrik

AU - Rosenhahn, Bodo

N1 - Funding Information: This work was supported by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizKILabor (grant no. 01DD20003) and the AI service center KISSKI (grant no. 01IS22093C), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungsgemeinschaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122). The authors also thank Dr. Oliver Müller for fruitful discussions and hints.

PY - 2023

Y1 - 2023

N2 - In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.

AB - In this work, we present a marker-based multi-view spine tracking method that is specifically adjusted to the requirements for movements in sports. A maximal focus is on the accurate detection of markers and fast usage of the system. For this task, we take advantage of the prior knowledge of the arrangement of dots in perforated kinesiology tape. We detect the tape and its dots using a Mask R-CNN and a blob detector. Here, we can focus on detection only while skipping any image-based feature encoding or matching. We conduct a reasoning in 3D by a linear program and Markov random fields, in which the structure of the kinesiology tape is modeled and the shape of the spine is optimized. In comparison to state-of-the-art systems, we demonstrate that our system achieves high precision and marker density, is robust against occlusions, and capable of capturing fast movements.

UR - http://www.scopus.com/inward/record.url?scp=85170829141&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2306.02930

DO - 10.48550/arXiv.2306.02930

M3 - Conference contribution

AN - SCOPUS:85170829141

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 5149

EP - 5157

BT - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops

PB - IEEE Computer Society

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

Y2 - 17 June 2023 through 24 June 2023

ER -

Von denselben Autoren