Mountain Image Analysis Suite (MIAS): A new plugin for converting oblique images to landcover maps in QGIS

IF 2.1 3区 地球科学 Q2 GEOGRAPHY
Claire Wright, Chris Bone, Darcy Mathews, James Tricker, Ben Wright, Eric Higgs
{"title":"Mountain Image Analysis Suite (MIAS): A new plugin for converting oblique images to landcover maps in QGIS","authors":"Claire Wright, Chris Bone, Darcy Mathews, James Tricker, Ben Wright, Eric Higgs","doi":"10.1111/tgis.13229","DOIUrl":null,"url":null,"abstract":"The objective of this article is to present a novel GIS plugin for classifying and georeferencing high‐resolution oblique imagery with the intention of creating landcover datasets for spatial analysis. The Mountain Image Analysis Suite (MIAS) is a newly released plugin for the open‐source software, QGIS. MIAS was developed with images from Mountain Legacy Project, the world's largest systematic collection of high‐resolution mountain images. It works with both grayscale and color imagery, including historical images that predate aerial and satellite imagery. MIAS encompasses four tools for classifying and georeferencing oblique images. The plugin accesses pretrained deep learning models from a PyTorch‐based segmentation network to automate the classification of landcover in oblique images. Monoplotting is accomplished through the construction of a virtual photograph simulating the view from the camera using a shaded relief model. Once the virtual photograph is produced, the user aligns the classified image to the virtual photograph using a set of control points. This allows the creation of a classified and georeferenced raster representing the landcover for the area visible in the original oblique image. Similar workflows to the one contained in MIAS have been used for landcover mapping with oblique images to a high level of accuracy. However, MIAS is the first piece of software to bring all stages of image analysis into a single platform. MIAS has many applications across diverse fields such as mountain research, ecological restoration, community‐based mapping, environmental planning, and more.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions in GIS","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1111/tgis.13229","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOGRAPHY","Score":null,"Total":0}
引用次数: 0

Abstract

The objective of this article is to present a novel GIS plugin for classifying and georeferencing high‐resolution oblique imagery with the intention of creating landcover datasets for spatial analysis. The Mountain Image Analysis Suite (MIAS) is a newly released plugin for the open‐source software, QGIS. MIAS was developed with images from Mountain Legacy Project, the world's largest systematic collection of high‐resolution mountain images. It works with both grayscale and color imagery, including historical images that predate aerial and satellite imagery. MIAS encompasses four tools for classifying and georeferencing oblique images. The plugin accesses pretrained deep learning models from a PyTorch‐based segmentation network to automate the classification of landcover in oblique images. Monoplotting is accomplished through the construction of a virtual photograph simulating the view from the camera using a shaded relief model. Once the virtual photograph is produced, the user aligns the classified image to the virtual photograph using a set of control points. This allows the creation of a classified and georeferenced raster representing the landcover for the area visible in the original oblique image. Similar workflows to the one contained in MIAS have been used for landcover mapping with oblique images to a high level of accuracy. However, MIAS is the first piece of software to bring all stages of image analysis into a single platform. MIAS has many applications across diverse fields such as mountain research, ecological restoration, community‐based mapping, environmental planning, and more.
山区图像分析套件 (MIAS):在 QGIS 中将倾斜图像转换为土地覆盖物地图的新插件
本文旨在介绍一种新颖的 GIS 插件,用于对高分辨率斜射图像进行分类和地理参照,以创建用于空间分析的土地覆盖数据集。山区图像分析套件(MIAS)是开源软件 QGIS 最新发布的一个插件。MIAS 是利用山区遗产项目的图像开发的,该项目是世界上最大的高分辨率山区图像系统收集项目。它可以处理灰度和彩色图像,包括航空和卫星图像之前的历史图像。MIAS 包含四个用于斜向图像分类和地理参照的工具。该插件从基于 PyTorch 的分割网络中获取预训练的深度学习模型,自动对斜射图像中的土地覆盖物进行分类。单图绘制是通过使用阴影浮雕模型模拟从相机拍摄的视图来构建虚拟照片完成的。虚拟照片制作完成后,用户可使用一组控制点将分类图像与虚拟照片对齐。这样就可以创建一个分类和地理参照栅格,代表原始倾斜图像中可见区域的土地覆盖情况。与 MIAS 所包含的类似工作流程已被用于利用倾斜图像绘制高精度的土地覆盖物地图。然而,MIAS 是第一个将图像分析的所有阶段整合到一个平台上的软件。MIAS 在山地研究、生态恢复、社区制图、环境规划等多个领域都有广泛应用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Transactions in GIS
Transactions in GIS GEOGRAPHY-
CiteScore
4.60
自引率
8.30%
发文量
116
期刊介绍: Transactions in GIS is an international journal which provides a forum for high quality, original research articles, review articles, short notes and book reviews that focus on: - practical and theoretical issues influencing the development of GIS - the collection, analysis, modelling, interpretation and display of spatial data within GIS - the connections between GIS and related technologies - new GIS applications which help to solve problems affecting the natural or built environments, or business
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信