Optimization of Lai Estimation Method Based on Smartphones with Fisheye Lens

Lichen Zhu, Peng Guan, Weiping Liu, Y. Zheng
{"title":"Optimization of Lai Estimation Method Based on Smartphones with Fisheye Lens","authors":"Lichen Zhu, Peng Guan, Weiping Liu, Y. Zheng","doi":"10.46300/9106.2023.17.14","DOIUrl":null,"url":null,"abstract":"Leaf area index (LAI) is an important biological factor reflecting vegetation growth and forest ecosystem. LAI can be used to obtain plant health status, carbon cycle, and surrounding ecological environment effectively. In this study, the smartphone was equipped with a fisheye lens, and the optimization method was used to estimate LAI, which was compared with digital hemispherical photography (DHP) to investigate the possibility of the new method for LAI estimation. The hemispherical image was divided into blocks, and the optimized Otsu method was used for algorithm segmentation, which can effectively distinguish vegetation from the sky. Concurrently, when the gap fraction inversion LAI was performed, the linear inversion algorithm was improved based on single-angle inversion, and the LAI was obtained by inversion through the linear fitting of the mul-tiangle gap fraction. The experimental sample was located in Olympic National Forest Park in Beijing. Three coniferous mixed forests and three broadleaved forests were selected from the experimental sample. LAI measurements from smartphones were compared with those from DHP. In the samples for mixed coniferous forests, the values for coefficients of determination R^2 were 0.835, 0.802, and 0.809, and root mean square errors (REMS) were 0.137, 0.120, and 0.147. For the broadleaf forest samples, the values for R² were 0.629, 0.679, and 0.758, and REMS were 0.144, 0.135, and 0.137. The R^2 and RMES for the overall data was 0.810 and 0.134, respectively, and a good agreement between the LAI measurements from the proposed method and those from the DHP supports an accurate estimation. The results show that the use of a fisheye lens on a smartphone can effectively and accurately obtain tree canopy LAI. This provides a fast and effective new method to measure LAI of forest vegetation near the ground, which is of great significance for studying the interaction between plant growth status, ecological environment, and phenological changes.","PeriodicalId":13929,"journal":{"name":"International Journal of Circuits, Systems and Signal Processing","volume":"57 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Circuits, Systems and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46300/9106.2023.17.14","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

Abstract

Leaf area index (LAI) is an important biological factor reflecting vegetation growth and forest ecosystem. LAI can be used to obtain plant health status, carbon cycle, and surrounding ecological environment effectively. In this study, the smartphone was equipped with a fisheye lens, and the optimization method was used to estimate LAI, which was compared with digital hemispherical photography (DHP) to investigate the possibility of the new method for LAI estimation. The hemispherical image was divided into blocks, and the optimized Otsu method was used for algorithm segmentation, which can effectively distinguish vegetation from the sky. Concurrently, when the gap fraction inversion LAI was performed, the linear inversion algorithm was improved based on single-angle inversion, and the LAI was obtained by inversion through the linear fitting of the mul-tiangle gap fraction. The experimental sample was located in Olympic National Forest Park in Beijing. Three coniferous mixed forests and three broadleaved forests were selected from the experimental sample. LAI measurements from smartphones were compared with those from DHP. In the samples for mixed coniferous forests, the values for coefficients of determination R^2 were 0.835, 0.802, and 0.809, and root mean square errors (REMS) were 0.137, 0.120, and 0.147. For the broadleaf forest samples, the values for R² were 0.629, 0.679, and 0.758, and REMS were 0.144, 0.135, and 0.137. The R^2 and RMES for the overall data was 0.810 and 0.134, respectively, and a good agreement between the LAI measurements from the proposed method and those from the DHP supports an accurate estimation. The results show that the use of a fisheye lens on a smartphone can effectively and accurately obtain tree canopy LAI. This provides a fast and effective new method to measure LAI of forest vegetation near the ground, which is of great significance for studying the interaction between plant growth status, ecological environment, and phenological changes.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于鱼眼镜头智能手机的Lai估计方法优化
叶面积指数(LAI)是反映植被生长和森林生态系统的重要生物因子。LAI可以有效地获取植物健康状况、碳循环和周围生态环境。本研究在智能手机上配置鱼眼镜头,采用优化方法估算LAI,并与数字半球摄影(DHP)进行比较,探讨新方法估算LAI的可能性。将半球形图像进行分块,采用优化后的Otsu方法进行算法分割,能够有效区分植被和天空。同时,在进行间隙分数反演LAI时,在单角度反演的基础上改进了线性反演算法,通过多三角形间隙分数的线性拟合进行反演得到LAI。实验样本位于北京奥林匹克国家森林公园。从实验样本中选取3个针叶混交林和3个阔叶林。智能手机的LAI测量值与DHP测量值进行了比较。混交林样品的决定系数R^2分别为0.835、0.802和0.809,均方根误差(REMS)分别为0.137、0.120和0.147。阔叶林样本的R²分别为0.629、0.679和0.758,REMS分别为0.144、0.135和0.137。总体数据的R^2和RMES分别为0.810和0.134,所提出方法的LAI测量值与DHP测量值之间的良好一致性支持了准确的估计。结果表明,在智能手机上使用鱼眼镜头可以有效准确地获取树冠LAI。这为近地森林植被LAI的测量提供了一种快速有效的新方法,对研究植物生长状况、生态环境和物候变化之间的相互作用具有重要意义。
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
International Journal of Circuits, Systems and Signal Processing
International Journal of Circuits, Systems and Signal Processing Engineering-Electrical and Electronic Engineering
自引率
0.00%
发文量
155
期刊最新文献
Stochastic Machine Learning Models for Mutation Rate Analysis of Malignant Cancer Cells in Patients with Acute Lymphoblastic Leukemia Detecting Small Objects Using a Smartphone and Neon Camera Optimization of New Energy Vehicle Road Noise Problem Based on Finite Element Analysis Method Base Elements for Artificial Neural Network: Structure Modeling, Production, Properties Distributed Generation Hosting Capacity Evaluation for Distribution Networks Considering Uncertainty
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1