MirrorCalib: Utilizing Human Pose Information for Mirror-based Virtual Camera Calibration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Longyun, Zheng, Rong, Mitchell, Andrew
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911880230993920
author Liao, Longyun
Zheng, Rong
Mitchell, Andrew
author_facet Liao, Longyun
Zheng, Rong
Mitchell, Andrew
contents In this paper, we present the novel task of estimating the extrinsic parameters of a virtual camera relative to a real camera in exercise videos with a mirror. This task poses a significant challenge in scenarios where the views from the real and mirrored cameras have no overlap or share salient features. To address this issue, prior knowledge of a human body and 2D joint locations are utilized to estimate the camera extrinsic parameters when a person is in front of a mirror. We devise a modified eight-point algorithm to obtain an initial estimation from 2D joint locations. The 2D joint locations are then refined subject to human body constraints. Finally, a RANSAC algorithm is employed to remove outliers by comparing their epipolar distances to a predetermined threshold. MirrorCalib achieves a rotation error of 1.82° and a translation error of 69.51 mm on a collected real-world dataset, which outperforms the state-of-art method.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02791
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MirrorCalib: Utilizing Human Pose Information for Mirror-based Virtual Camera Calibration
Liao, Longyun
Zheng, Rong
Mitchell, Andrew
Computer Vision and Pattern Recognition
In this paper, we present the novel task of estimating the extrinsic parameters of a virtual camera relative to a real camera in exercise videos with a mirror. This task poses a significant challenge in scenarios where the views from the real and mirrored cameras have no overlap or share salient features. To address this issue, prior knowledge of a human body and 2D joint locations are utilized to estimate the camera extrinsic parameters when a person is in front of a mirror. We devise a modified eight-point algorithm to obtain an initial estimation from 2D joint locations. The 2D joint locations are then refined subject to human body constraints. Finally, a RANSAC algorithm is employed to remove outliers by comparing their epipolar distances to a predetermined threshold. MirrorCalib achieves a rotation error of 1.82° and a translation error of 69.51 mm on a collected real-world dataset, which outperforms the state-of-art method.
title MirrorCalib: Utilizing Human Pose Information for Mirror-based Virtual Camera Calibration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.02791