2018
DOI: 10.3390/rs10020291
|View full text |Cite
|
Sign up to set email alerts
|

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

Abstract: Abstract:Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction. State-of-the-art methods are mainly based on sorted residual for generating hypotheses. This scheme has acquired encouraging results in many remote sensing applications. Unfortunately, mainstream residual based methods may fail in estimating the transform between Unmanned Aerial Vehicle (UAV) low altitude remote sensing images, due to the fact that U… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 58 publications
0
3
0
Order By: Relevance
“…First, considering the large-scale outdoor scene of slope fieldwork, the vision-based mobile AR technology was selected, which could perceive a broad enough range, flexibly adjust perspectives and ensure rendering effects in outdoors. Furthermore, to settle the critical problem in mobile AR of camera pose estimation in the rock slope context [64], the model-based markerless tracking method was adopted which directly recognized the real slope rock mass, and the Simultaneous Localization and Mapping (SLAM) was used for assisting extended tracking. The advantages of this method include relative high overlapping accuracy, compact interaction process, and good feasibility and scalability without the workload of fiducial marker arrangement.…”
Section: Discussionmentioning
confidence: 99%
“…First, considering the large-scale outdoor scene of slope fieldwork, the vision-based mobile AR technology was selected, which could perceive a broad enough range, flexibly adjust perspectives and ensure rendering effects in outdoors. Furthermore, to settle the critical problem in mobile AR of camera pose estimation in the rock slope context [64], the model-based markerless tracking method was adopted which directly recognized the real slope rock mass, and the Simultaneous Localization and Mapping (SLAM) was used for assisting extended tracking. The advantages of this method include relative high overlapping accuracy, compact interaction process, and good feasibility and scalability without the workload of fiducial marker arrangement.…”
Section: Discussionmentioning
confidence: 99%
“…Then, a novel adjustment model for mosaic low-overlap sweeping images was proposed. Cai et al [26] proposed a robust transform estimator based on residual analysis and its application to UAV aerial images. Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction.…”
Section: Uav Remote Sensing Image Stitchingmentioning
confidence: 99%
“…Then, a novel adjustment model for mosaic low overlap sweeping images was proposed. Cai et al [13] proposed a robust transform estimator based on residual analysis and its application to UAV aerial images. Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction.…”
Section: Introductionmentioning
confidence: 99%