A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method

Dongdong Weng; Yihan Wang; Dong Li

doi:10.1109/VRW55335.2022.00237

A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method

Dongdong Weng, Yihan Wang, Dong Li^*

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper proposes a deep learning model based on time reversal symmetry for real-time recovery of continuous missing marker sequences in optical motion capture. This paper firstly uses time reversal symmetry of human motion as a constraint of the model. BiLSTM is used to describe the constraint and extract the bidirectional spatiotemporal features. This paper proposes a weight position loss function for model training, which describes the effect of different joints on the pose. Compared with the existing methods, the experimental results show that the proposed method has higher accuracy and good real-time performance.

Original language	English
Title of host publication	Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	772-773
Number of pages	2
ISBN (Electronic)	9781665484022
DOIs	https://doi.org/10.1109/VRW55335.2022.00237
Publication status	Published - 2022
Event	2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 - Virtual, Online, New Zealand Duration: 12 Mar 2022 → 16 Mar 2022

Publication series

Name	Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022

Conference

Conference	2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022
Country/Territory	New Zealand
City	Virtual, Online
Period	12/03/22 → 16/03/22

Keywords

Human computer interaction(HCI)
Human-centered computing
Interaction paradigms
Virtual reality

Access to Document

10.1109/VRW55335.2022.00237

Cite this

Weng, D., Wang, Y., & Li, D. (2022). A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method. In Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 (pp. 772-773). (Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VRW55335.2022.00237

Weng, Dongdong ; Wang, Yihan ; Li, Dong. / A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method. Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 772-773 (Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022).

@inproceedings{ec7a29162a894003ad6cac4fdd0a5bc0,

title = "A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method",

abstract = "This paper proposes a deep learning model based on time reversal symmetry for real-time recovery of continuous missing marker sequences in optical motion capture. This paper firstly uses time reversal symmetry of human motion as a constraint of the model. BiLSTM is used to describe the constraint and extract the bidirectional spatiotemporal features. This paper proposes a weight position loss function for model training, which describes the effect of different joints on the pose. Compared with the existing methods, the experimental results show that the proposed method has higher accuracy and good real-time performance.",

keywords = "Human computer interaction(HCI), Human-centered computing, Interaction paradigms, Virtual reality",

author = "Dongdong Weng and Yihan Wang and Dong Li",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022 ; Conference date: 12-03-2022 Through 16-03-2022",

year = "2022",

doi = "10.1109/VRW55335.2022.00237",

language = "English",

series = "Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "772--773",

booktitle = "Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022",

address = "United States",

}

Weng, D, Wang, Y & Li, D 2022, A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method. in Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022. Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022, Institute of Electrical and Electronics Engineers Inc., pp. 772-773, 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022, Virtual, Online, New Zealand, 12/03/22. https://doi.org/10.1109/VRW55335.2022.00237

A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method. / Weng, Dongdong; Wang, Yihan; Li, Dong.
Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 772-773 (Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method

AU - Weng, Dongdong

AU - Wang, Yihan

AU - Li, Dong

PY - 2022

Y1 - 2022

N2 - This paper proposes a deep learning model based on time reversal symmetry for real-time recovery of continuous missing marker sequences in optical motion capture. This paper firstly uses time reversal symmetry of human motion as a constraint of the model. BiLSTM is used to describe the constraint and extract the bidirectional spatiotemporal features. This paper proposes a weight position loss function for model training, which describes the effect of different joints on the pose. Compared with the existing methods, the experimental results show that the proposed method has higher accuracy and good real-time performance.

AB - This paper proposes a deep learning model based on time reversal symmetry for real-time recovery of continuous missing marker sequences in optical motion capture. This paper firstly uses time reversal symmetry of human motion as a constraint of the model. BiLSTM is used to describe the constraint and extract the bidirectional spatiotemporal features. This paper proposes a weight position loss function for model training, which describes the effect of different joints on the pose. Compared with the existing methods, the experimental results show that the proposed method has higher accuracy and good real-time performance.

KW - Human computer interaction(HCI)

KW - Human-centered computing

KW - Interaction paradigms

KW - Virtual reality

UR - http://www.scopus.com/inward/record.url?scp=85129597186&partnerID=8YFLogxK

U2 - 10.1109/VRW55335.2022.00237

DO - 10.1109/VRW55335.2022.00237

M3 - Conference contribution

AN - SCOPUS:85129597186

T3 - Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022

SP - 772

EP - 773

BT - Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022

Y2 - 12 March 2022 through 16 March 2022

ER -

Weng D, Wang Y, Li D. A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method. In Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 772-773. (Proceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022). doi: 10.1109/VRW55335.2022.00237

A Time Reversal Symmetry Based Real-time Optical Motion Capture Missing Marker Recovery Method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this