Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation

The autonomous landing of unmanned aerial vehicles (UAVs) relies on a precise relative 6D pose between platforms. Existing model-based monocular pose estimation methods need an accurate 3D model of the target. They cannot handle the absence of an accurate 3D model. This paper adopts the multi-view g...

Full description

Saved in:
Bibliographic Details
Main Authors: Liangchao Guo, Lin Chen, Qiufu Wang, Zhuo Zhang, Xiaoliang Sun
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/11/626
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267492839063552
author Liangchao Guo
Lin Chen
Qiufu Wang
Zhuo Zhang
Xiaoliang Sun
author_facet Liangchao Guo
Lin Chen
Qiufu Wang
Zhuo Zhang
Xiaoliang Sun
author_sort Liangchao Guo
collection DOAJ
description The autonomous landing of unmanned aerial vehicles (UAVs) relies on a precise relative 6D pose between platforms. Existing model-based monocular pose estimation methods need an accurate 3D model of the target. They cannot handle the absence of an accurate 3D model. This paper adopts the multi-view geometry constraints within the monocular image sequence to solve the problem. And a novel approach to monocular pose estimation is introduced, which jointly optimizes the target’s 3D model and the relative 6D pose. We propose to represent the target’s 3D model using a set of sparse 3D landmarks. The 2D landmarks are detected in the input image by a trained neural network. Based on the 2D–3D correspondences, the initial pose estimation is obtained by solving the PnP problem. To achieve joint optimization, this paper builds the objective function based on the minimization of the reprojection error. And the correction values of the 3D landmarks and the 6D pose are parameters to be solved in the optimization problem. By solving the optimization problem, the joint optimization of the target’s 3D model and the 6D pose is realized. In addition, a sliding window combined with a keyframe extraction strategy is adopted to speed up the algorithm processing. Experimental results on synthetic and real image sequences show that the proposed method achieves real-time and online high-precision monocular pose estimation with the absence of an accurate 3D model via the joint optimization of the target’s 3D model and pose.
format Article
id doaj-art-2017f11f96e04879a5163cfb2ccc9ae7
institution OA Journals
issn 2504-446X
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-2017f11f96e04879a5163cfb2ccc9ae72025-08-20T01:53:45ZengMDPI AGDrones2504-446X2024-10-0181162610.3390/drones8110626Joint Optimization of the 3D Model and 6D Pose for Monocular Pose EstimationLiangchao Guo0Lin Chen1Qiufu Wang2Zhuo Zhang3Xiaoliang Sun4School of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaSchool of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaSchool of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaSchool of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaSchool of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaThe autonomous landing of unmanned aerial vehicles (UAVs) relies on a precise relative 6D pose between platforms. Existing model-based monocular pose estimation methods need an accurate 3D model of the target. They cannot handle the absence of an accurate 3D model. This paper adopts the multi-view geometry constraints within the monocular image sequence to solve the problem. And a novel approach to monocular pose estimation is introduced, which jointly optimizes the target’s 3D model and the relative 6D pose. We propose to represent the target’s 3D model using a set of sparse 3D landmarks. The 2D landmarks are detected in the input image by a trained neural network. Based on the 2D–3D correspondences, the initial pose estimation is obtained by solving the PnP problem. To achieve joint optimization, this paper builds the objective function based on the minimization of the reprojection error. And the correction values of the 3D landmarks and the 6D pose are parameters to be solved in the optimization problem. By solving the optimization problem, the joint optimization of the target’s 3D model and the 6D pose is realized. In addition, a sliding window combined with a keyframe extraction strategy is adopted to speed up the algorithm processing. Experimental results on synthetic and real image sequences show that the proposed method achieves real-time and online high-precision monocular pose estimation with the absence of an accurate 3D model via the joint optimization of the target’s 3D model and pose.https://www.mdpi.com/2504-446X/8/11/626UAV autonomous landingmonocular pose estimationmulti-view geometry constraintsjoint optimizationsliding windowkeyframe
spellingShingle Liangchao Guo
Lin Chen
Qiufu Wang
Zhuo Zhang
Xiaoliang Sun
Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
Drones
UAV autonomous landing
monocular pose estimation
multi-view geometry constraints
joint optimization
sliding window
keyframe
title Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
title_full Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
title_fullStr Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
title_full_unstemmed Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
title_short Joint Optimization of the 3D Model and 6D Pose for Monocular Pose Estimation
title_sort joint optimization of the 3d model and 6d pose for monocular pose estimation
topic UAV autonomous landing
monocular pose estimation
multi-view geometry constraints
joint optimization
sliding window
keyframe
url https://www.mdpi.com/2504-446X/8/11/626
work_keys_str_mv AT liangchaoguo jointoptimizationofthe3dmodeland6dposeformonocularposeestimation
AT linchen jointoptimizationofthe3dmodeland6dposeformonocularposeestimation
AT qiufuwang jointoptimizationofthe3dmodeland6dposeformonocularposeestimation
AT zhuozhang jointoptimizationofthe3dmodeland6dposeformonocularposeestimation
AT xiaoliangsun jointoptimizationofthe3dmodeland6dposeformonocularposeestimation