Identification of rural courtyards’ utilization status using deep learning and machine learning methods on unmanned aerial vehicle images in north China

IF 6.1 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY Building Simulation Pub Date : 2024-02-02 DOI:10.1007/s12273-023-1099-9

{"title":"Identification of rural courtyards’ utilization status using deep learning and machine learning methods on unmanned aerial vehicle images in north China","authors":"","doi":"10.1007/s12273-023-1099-9","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>The issue of unoccupied or abandoned homesteads (courtyards) in China emerges given the increasing aging population, rapid urbanization and massive rural-urban migration. From the aspect of rural vitalization, land-use planning, and policy making, determining the number of unoccupied courtyards is important. Field and questionnaire-based surveys were currently the main approaches, but these traditional methods were often expensive and laborious. A new workflow is explored using deep learning and machine learning algorithms on unmanned aerial vehicle (UAV) images. Initially, features of the built environment were extracted using deep learning to evaluate the courtyard management, including extracting complete or collapsed farmhouses by Alexnet, detecting solar water heaters by YOLOv5s, calculating green looking ratio (GLR) by FCN. Their precisions exceeded 98%. Then, seven machine learning algorithms (Adaboost, binomial logistic regression, neural network, random forest, support vector machine, decision trees, and XGBoost algorithms) were applied to identify the rural courtyards’ utilization status. The Adaboost algorithm showed the best performance with the comprehensive consideration of most metrics (Accuracy: 0.933, Precision: 0.932, Recall: 0.984, F1-score: 0.957). Results showed that identifying the courtyards’ utilization statuses based on the courtyard built environment is feasible. It is transferable and cost-effective for large-scale village surveys, and may contribute to the intensive and sustainable approach to rural land use.</p>","PeriodicalId":49226,"journal":{"name":"Building Simulation","volume":"1 1","pages":""},"PeriodicalIF":6.1000,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Building Simulation","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12273-023-1099-9","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

The issue of unoccupied or abandoned homesteads (courtyards) in China emerges given the increasing aging population, rapid urbanization and massive rural-urban migration. From the aspect of rural vitalization, land-use planning, and policy making, determining the number of unoccupied courtyards is important. Field and questionnaire-based surveys were currently the main approaches, but these traditional methods were often expensive and laborious. A new workflow is explored using deep learning and machine learning algorithms on unmanned aerial vehicle (UAV) images. Initially, features of the built environment were extracted using deep learning to evaluate the courtyard management, including extracting complete or collapsed farmhouses by Alexnet, detecting solar water heaters by YOLOv5s, calculating green looking ratio (GLR) by FCN. Their precisions exceeded 98%. Then, seven machine learning algorithms (Adaboost, binomial logistic regression, neural network, random forest, support vector machine, decision trees, and XGBoost algorithms) were applied to identify the rural courtyards’ utilization status. The Adaboost algorithm showed the best performance with the comprehensive consideration of most metrics (Accuracy: 0.933, Precision: 0.932, Recall: 0.984, F1-score: 0.957). Results showed that identifying the courtyards’ utilization statuses based on the courtyard built environment is feasible. It is transferable and cost-effective for large-scale village surveys, and may contribute to the intensive and sustainable approach to rural land use.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用深度学习和机器学习方法在无人机图像上识别中国北方农村庭院的利用状况

摘要随着人口老龄化加剧、城市化进程加快以及大量人口从农村向城市迁移，中国出现了闲置或废弃的宅基地（院落）问题。从农村振兴、土地利用规划和政策制定的角度来看，确定闲置庭院的数量非常重要。实地调查和问卷调查是目前的主要方法，但这些传统方法往往成本高昂且费时费力。我们利用无人机（UAV）图像上的深度学习和机器学习算法，探索了一种新的工作流程。最初，利用深度学习提取建筑环境的特征来评估庭院管理，包括利用 Alexnet 提取完整或倒塌的农舍，利用 YOLOv5s 检测太阳能热水器，利用 FCN 计算绿化率（GLR）。它们的精确度都超过了 98%。然后，应用七种机器学习算法（Adaboost 算法、二叉逻辑回归算法、神经网络算法、随机森林算法、支持向量机算法、决策树算法和 XGBoost 算法）来识别农村庭院的利用状况。综合考虑大多数指标，Adaboost 算法表现最佳（准确率：0.933，精确率：0.932，召回率：0.984，F1-分数：0.957）。结果表明，基于庭院建筑环境识别庭院利用状况是可行的。该方法在大规模村庄调查中具有可移植性和成本效益，可促进农村土地利用的集约化和可持续发展。

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分钟内获得全文去求助

来源期刊

Building Simulation THERMODYNAMICS-CONSTRUCTION & BUILDING TECHNOLOGY

CiteScore

10.20

自引率

16.40%

发文量

审稿时长

>12 weeks

期刊介绍： Building Simulation: An International Journal publishes original, high quality, peer-reviewed research papers and review articles dealing with modeling and simulation of buildings including their systems. The goal is to promote the field of building science and technology to such a level that modeling will eventually be used in every aspect of building construction as a routine instead of an exception. Of particular interest are papers that reflect recent developments and applications of modeling tools and their impact on advances of building science and technology.