A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation

Lele Li; Zedong Liu; Dawei Liang; Chuanyu Si; Haotian Ju; Shouyi Zhang; Haoxiang Zhang; Hongwei Jing; Jian Qi; Tianjiao Zheng; Yanhe Zhu

doi:10.1007/978-981-95-2098-5_8

A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation

Lele Li
, Zedong Liu
, Dawei Liang
, Chuanyu Si
, Haotian Ju
, Shouyi Zhang
, Haoxiang Zhang
, Hongwei Jing
, Jian Qi
, Tianjiao Zheng^*
, Yanhe Zhu^*

^*Corresponding author for this work

School of Mechatronics Engineering

Harbin Institute of Technology

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

Abstract

This paper presents a low-cost and robust human pose estimation framework that fuses Inertial Measurement Units (IMUs) with Visual-inertial Odometry (VIO). A custom-designed wireless IMU module and distributed hardware architecture enable real-time estimation of 3D orientations using a quaternion-based Extended Kalman Filter (EKF). A hybrid static-dynamic alignment method is introduced to precisely map IMU frames to anatomical body frames. Based on this alignment, joint angles between adjacent body segments are computed, and the global body position is tracked via a pelvis-mounted VIO sensor. The proposed system is validated through visualization in the MuJoCo simulation platform, where full-body motion is accurately reproduced. Experimental results demonstrate the method’s high real-time performance and accuracy in reconstructing natural human motion, highlighting its applicability to wearable sensing and human-robot interaction.

Original language	English
Title of host publication	Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings
Editors	Takayuki Matsuno, Honghai Liu, Lianqing Liu, Zhouping Yin, Xiangyang Zhu, Weihong Ren, Zhiyong Wang, Yixuan Sheng
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	91-102
Number of pages	12
ISBN (Print)	9789819520978
DOIs	https://doi.org/10.1007/978-981-95-2098-5_8
State	Published - 2026
Event	18th International Conference on Intelligent Robotics and Applications, ICIRA 2025 - Okayama, Japan Duration: 6 Aug 2025 → 9 Aug 2025

Publication series

Name	Lecture Notes in Computer Science
Volume	16075 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	18th International Conference on Intelligent Robotics and Applications, ICIRA 2025
Country/Territory	Japan
City	Okayama
Period	6/08/25 → 9/08/25

Keywords

Human Pose Estimation
Human-robot Interaction
Wearable Sensing

Access to Document

10.1007/978-981-95-2098-5_8

Cite this

Li, L., Liu, Z., Liang, D., Si, C., Ju, H., Zhang, S., Zhang, H., Jing, H., Qi, J., Zheng, T., & Zhu, Y. (2026). A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation. In T. Matsuno, H. Liu, L. Liu, Z. Yin, X. Zhu, W. Ren, Z. Wang, & Y. Sheng (Eds.), Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings (pp. 91-102). (Lecture Notes in Computer Science; Vol. 16075 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-2098-5_8

Li, Lele ; Liu, Zedong ; Liang, Dawei et al. / A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation. Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings. editor / Takayuki Matsuno ; Honghai Liu ; Lianqing Liu ; Zhouping Yin ; Xiangyang Zhu ; Weihong Ren ; Zhiyong Wang ; Yixuan Sheng. Springer Science and Business Media Deutschland GmbH, 2026. pp. 91-102 (Lecture Notes in Computer Science).

@inproceedings{f2263b3e0cb54b6d9345fa553c762404,

title = "A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation",

abstract = "This paper presents a low-cost and robust human pose estimation framework that fuses Inertial Measurement Units (IMUs) with Visual-inertial Odometry (VIO). A custom-designed wireless IMU module and distributed hardware architecture enable real-time estimation of 3D orientations using a quaternion-based Extended Kalman Filter (EKF). A hybrid static-dynamic alignment method is introduced to precisely map IMU frames to anatomical body frames. Based on this alignment, joint angles between adjacent body segments are computed, and the global body position is tracked via a pelvis-mounted VIO sensor. The proposed system is validated through visualization in the MuJoCo simulation platform, where full-body motion is accurately reproduced. Experimental results demonstrate the method{\textquoteright}s high real-time performance and accuracy in reconstructing natural human motion, highlighting its applicability to wearable sensing and human-robot interaction.",

keywords = "Human Pose Estimation, Human-robot Interaction, Wearable Sensing",

author = "Lele Li and Zedong Liu and Dawei Liang and Chuanyu Si and Haotian Ju and Shouyi Zhang and Haoxiang Zhang and Hongwei Jing and Jian Qi and Tianjiao Zheng and Yanhe Zhu",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 18th International Conference on Intelligent Robotics and Applications, ICIRA 2025 ; Conference date: 06-08-2025 Through 09-08-2025",

year = "2026",

doi = "10.1007/978-981-95-2098-5\_8",

language = "英语",

isbn = "9789819520978",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "91--102",

editor = "Takayuki Matsuno and Honghai Liu and Lianqing Liu and Zhouping Yin and Xiangyang Zhu and Weihong Ren and Zhiyong Wang and Yixuan Sheng",

booktitle = "Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings",

address = "德国",

}

Li, L, Liu, Z, Liang, D, Si, C, Ju, H, Zhang, S, Zhang, H, Jing, H, Qi, J, Zheng, T & Zhu, Y 2026, A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation. in T Matsuno, H Liu, L Liu, Z Yin, X Zhu, W Ren, Z Wang & Y Sheng (eds), Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings. Lecture Notes in Computer Science, vol. 16075 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 91-102, 18th International Conference on Intelligent Robotics and Applications, ICIRA 2025, Okayama, Japan, 6/08/25. https://doi.org/10.1007/978-981-95-2098-5_8

A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation. / Li, Lele; Liu, Zedong; Liang, Dawei et al.
Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings. ed. / Takayuki Matsuno; Honghai Liu; Lianqing Liu; Zhouping Yin; Xiangyang Zhu; Weihong Ren; Zhiyong Wang; Yixuan Sheng. Springer Science and Business Media Deutschland GmbH, 2026. p. 91-102 (Lecture Notes in Computer Science; Vol. 16075 LNCS).

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

TY - GEN

T1 - A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation

AU - Li, Lele

AU - Liu, Zedong

AU - Liang, Dawei

AU - Si, Chuanyu

AU - Ju, Haotian

AU - Zhang, Shouyi

AU - Zhang, Haoxiang

AU - Jing, Hongwei

AU - Qi, Jian

AU - Zheng, Tianjiao

AU - Zhu, Yanhe

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - This paper presents a low-cost and robust human pose estimation framework that fuses Inertial Measurement Units (IMUs) with Visual-inertial Odometry (VIO). A custom-designed wireless IMU module and distributed hardware architecture enable real-time estimation of 3D orientations using a quaternion-based Extended Kalman Filter (EKF). A hybrid static-dynamic alignment method is introduced to precisely map IMU frames to anatomical body frames. Based on this alignment, joint angles between adjacent body segments are computed, and the global body position is tracked via a pelvis-mounted VIO sensor. The proposed system is validated through visualization in the MuJoCo simulation platform, where full-body motion is accurately reproduced. Experimental results demonstrate the method’s high real-time performance and accuracy in reconstructing natural human motion, highlighting its applicability to wearable sensing and human-robot interaction.

AB - This paper presents a low-cost and robust human pose estimation framework that fuses Inertial Measurement Units (IMUs) with Visual-inertial Odometry (VIO). A custom-designed wireless IMU module and distributed hardware architecture enable real-time estimation of 3D orientations using a quaternion-based Extended Kalman Filter (EKF). A hybrid static-dynamic alignment method is introduced to precisely map IMU frames to anatomical body frames. Based on this alignment, joint angles between adjacent body segments are computed, and the global body position is tracked via a pelvis-mounted VIO sensor. The proposed system is validated through visualization in the MuJoCo simulation platform, where full-body motion is accurately reproduced. Experimental results demonstrate the method’s high real-time performance and accuracy in reconstructing natural human motion, highlighting its applicability to wearable sensing and human-robot interaction.

KW - Human Pose Estimation

KW - Human-robot Interaction

KW - Wearable Sensing

UR - https://www.scopus.com/pages/publications/105020891001

U2 - 10.1007/978-981-95-2098-5_8

DO - 10.1007/978-981-95-2098-5_8

M3 - 会议稿件

AN - SCOPUS:105020891001

SN - 9789819520978

T3 - Lecture Notes in Computer Science

SP - 91

EP - 102

BT - Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings

A2 - Matsuno, Takayuki

A2 - Liu, Honghai

A2 - Liu, Lianqing

A2 - Yin, Zhouping

A2 - Zhu, Xiangyang

A2 - Ren, Weihong

A2 - Wang, Zhiyong

A2 - Sheng, Yixuan

PB - Springer Science and Business Media Deutschland GmbH

T2 - 18th International Conference on Intelligent Robotics and Applications, ICIRA 2025

Y2 - 6 August 2025 through 9 August 2025

ER -

Li L, Liu Z, Liang D, Si C, Ju H, Zhang S et al. A Low-Cost Multisensor IMU-VIO Framework for Real-Time Full-Body Human Pose Estimation. In Matsuno T, Liu H, Liu L, Yin Z, Zhu X, Ren W, Wang Z, Sheng Y, editors, Intelligent Robotics and Applications - 18th International Conference, ICIRA 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 91-102. (Lecture Notes in Computer Science). doi: 10.1007/978-981-95-2098-5_8