메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject
Humanities
General Humanities History Philosophy Religious Studies Linguistics and Literature Other Humanities
Social science
General Social Science Business Management Tourism Education Military Science Library and Information Science Law Sociology Journalism and Media Studies Psychological Science Political Science and Diplomacy Geography Public Administration Economics International Trade Anthropology Other Social Science
Natural science
General Natural Science Physics Biology Life Sciences Mathematics/Statistics Astronomy Earth Science Chemistry Other Natural Science
Engineering
General Engineering Architectural Engineering Mechanical Engineering Industrial Engineering Material/Energy Engineering Electrical and Electronic Engineering Marine and Ocean Engineering Chemical Engineering Computer Science Other Engineering
Medical science
General Medical Science Nursing Science Veterinary Pharmacy Traditional Korean Medicine Basic Medicine Clinical Medicine Other Medicine
Agriculture and Fishery
General Agriculture and Fishery Agriculture Fishery Science Food Science Forestry Animal Husbandry Marine Transportation Studies Other Agriculture and Fishery
Art and Kinesiology
General Arts Design Fine Arts Cosmetology Photography Music Fashion Kinesiology Performing Media Arts Other Arts and Kinesiology
Interdisciplinary Studies
Interdisciplinary Research Science and Technology Studies Brain and Cognitive Science Technology Policy Other Interdisciplinary Studies

KOR

A Study on Training Dataset Configuration for Deep Learning Based Image Matching of Multi-sensor VHR Satellite Images
Recommendations
Search

다중센서 고해상도 위성영상의 딥러닝 기반 영상매칭을 위한 학습자료 구성에 관한 연구

논문 기본 정보

Type
Academic journal
Author
Wonbin Kang (서울대학교) Minyoung Jung (서울대학교) Kim YongIl (서울대학교)
Journal
The Korean Society Of Remote Sensing 대한원격탐사학회지 대한원격탐사학회지 제38권 제6호 KCI Accredited Journals
Published
2022.12
Pages
1,505 - 1,514 (10page)

Usage

cover
A Study on Training Dataset Configuration for Deep Learning Based Image Matching of Multi-sensor VHR Satellite Images
Ask AI
Recommendations
Search

Research history (2)

2022

A Study on Training Dataset Configuration for Deep Learning Based Image Matching of Multi-sensor VHR Satellite Images
Wonbin Kang ,  Minyoung Jung ,  Kim YongIl 대한원격탐사학회지 2022.12 Academic journal
Evaluation of Deep Learning Based Matching Pair Extraction Algorithm with VHR Satellite Images using KOMPSAT-3A
Kang ,  Wonbin ,  Jung 한국측량학회 학술대회자료집 2022.04 Proceeding
  • Are you curious about the follow-up research of this article?
  • You can check more advanced research results through related academic papers or academic presentations.
  • Check the research history of this article

Abstract· Keywords

Report Errors
Image matching is a crucial preprocessing step for effective utilization of multi-temporaland multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which isattracting widespread interest has proven to be an efficient approach to measure the similarity betweenimage pairs in quick and accurate manner by extracting complex and detailed features from satelliteimages. However, Image matching of VHR satellite images remains challenging due to limitations ofDL models in which the results are depending on the quantity and quality of training dataset, as well asthe difficulty of creating training dataset with VHR satellite images. Therefore, this study examines thefeasibility of DL-based method in matching pair extraction which is the most time-consuming processduring image registration. This paper also aims to analyze factors that affect the accuracy based on theconfiguration of training dataset, when developing training dataset from existing multi-sensor VHRimage database with bias for DL-based image matching. For this purpose, the generated training datasetwere composed of correct matching pairs and incorrect matching pairs by assigning true and false labelsto image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for atotal of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network(SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with modellearning and measures similarities by passing two images in parallel to the two identical convolutionalneural network structures. The results from this study confirm that data acquired from VHR satelliteimage database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matchingtechniques using multi-sensor VHR satellite images are expected to replace existing manual-based featureextraction methods based on its stable performance, thus further develop into an integrated DL-basedimage registration framework.
#VHR satellite image #Image registration #Multi-sensor image matching #Deep learning #Siamese convolutional neural network

Contents

No content found

References (0)

Add References
If the reference is being serviced by DBpia, please register through [Add Reference]

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Recently viewed articles

'공동주택 에너지 리모델링(Energy Remodeling of Apartment)'
김용봉, 전춘식, 이경태2004
 The Present Status of Product Assurance in Development of Korea Space Launch Vehicle
Cho, Sang-Yeon, Shin 외 6명Korea Aerospace Research Institute2015.07

Comments(0)

0

Write first comments.