Non-contact Object Size Acquisition Based On Visual-Inertial Sensor Fusion

Authors

Kang Lai, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China;
Yingmei Wei, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China;
Jiang Jie, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China;
Yuxiang Xie, College of Systems Engineering, National University of Defense Technology, Changsha 410073, China;

Abstract

Abstract: In consideration of the visual data and the data from the inertial measurement unit (IMU) having the different characteristics, the 6D pose of the visual sensor is recovered from the captured video by using the vision-based 3D reconstruction techniques, the obtained pose information and inertial measurements is fused via the spatial-temporal alignment, and based on the determined scale of the visual 3D reconstruction the non-contact measurement of a scene is performed. The proposed approach achieves a relative measurement error of about 3% in the non-contact object size estimation experiment. As it does not require the additional calibration object or any special motion capture devices, the proposed method is flexible and is applicable in many potential areas.

Recommended Citation

Lai, Kang; Wei, Yingmei; Jie, Jiang; and Xie, Yuxiang (2020) "Non-contact Object Size Acquisition Based On Visual-Inertial Sensor Fusion," Journal of System Simulation: Vol. 32: Iss. 5, Article 16.
DOI: 10.16182/j.issn1004731x.joss.19-0432
Available at: https://dc-china-simulation.researchcommons.org/journal/vol32/iss5/16

First Page

892

Revised Date

2020-02-17

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.19-0432

Last Page

900

CLC

TP391

Recommended Citation

Kang Lai, Wei Yingmei, Jiang Jie, Xie Yuxiang. Non-contact Object Size Acquisition Based On Visual-Inertial Sensor Fusion[J]. Journal of System Simulation, 2020, 32(5): 892-900.

DOI

10.16182/j.issn1004731x.joss.19-0432