利用高光谱成像进行空间光谱特征提取以估算田间叶绿素含量

IF 4.4 1区 农林科学 Q1 AGRICULTURAL ENGINEERING Biosystems Engineering Pub Date : 2024-08-20 DOI:10.1016/j.biosystemseng.2024.08.008
{"title":"利用高光谱成像进行空间光谱特征提取以估算田间叶绿素含量","authors":"","doi":"10.1016/j.biosystemseng.2024.08.008","DOIUrl":null,"url":null,"abstract":"<div><p>In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained R<sub>P</sub><sup>2</sup> of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (R<sub>P</sub><sup>2</sup> = 0.85) compared to RF bands (R<sub>P</sub><sup>2</sup> = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with R<sub>P</sub><sup>2</sup> of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved R<sub>P</sub><sup>2</sup> above 0.93 in individual years (R<sub>P</sub><sup>2</sup> = 0.96 in 2021, R<sub>P</sub><sup>2</sup> = 0.94 in 2021) and R<sub>P</sub><sup>2</sup> in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.</p></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spatial-spectral feature extraction for in-field chlorophyll content estimation using hyperspectral imaging\",\"authors\":\"\",\"doi\":\"10.1016/j.biosystemseng.2024.08.008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained R<sub>P</sub><sup>2</sup> of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (R<sub>P</sub><sup>2</sup> = 0.85) compared to RF bands (R<sub>P</sub><sup>2</sup> = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with R<sub>P</sub><sup>2</sup> of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved R<sub>P</sub><sup>2</sup> above 0.93 in individual years (R<sub>P</sub><sup>2</sup> = 0.96 in 2021, R<sub>P</sub><sup>2</sup> = 0.94 in 2021) and R<sub>P</sub><sup>2</sup> in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.</p></div>\",\"PeriodicalId\":9173,\"journal\":{\"name\":\"Biosystems Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biosystems Engineering\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1537511024001867\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biosystems Engineering","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1537511024001867","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

摘要

基于高光谱成像(HSI)的原位叶片叶绿素含量(LCC)估算对于田间管理中跟踪作物生长状况至关重要。然而,高光谱成像数据的空间和光谱特征会受到生长动态效应和土壤的干扰,对不同年份和生长阶段叶绿素含量估算的准确性和鲁棒性提出了挑战。因此,通过三维卷积神经网络(3DCNN)和长短期记忆(LSTM)的级联,提出了一种光谱空间联合特征提取方法,以减少干扰,优化 LCC 估算。首先,利用植被指数分割法将作物像素从土壤中分离出来。其次,在输入原始图像和分割后的像素时,通过随机蛙法(RF 波段)选择敏感波段,并使用 3DCNN-LSTM 提取光谱空间联合特征。最后,比较了 RF 波段、3DCNN 和 3DCNN-LSTM 所建立的模型,并验证了其在个别年份和阶段的鲁棒性。结果表明,RF 带和 3DCNN 在未分割时的 RP2 分别为 0.76 和 0.84。分割后,3DCNN 的性能比 RF 波段(RP2 = 0.80)有所提高(RP2 = 0.85)。3DCNN 的光谱空间特征减少了土壤的干扰。无分割和有分割的 3DCNN-LSTM 均获得了良好的性能,RP2 分别为 0.95 和 0.96。最优模型在个别年份的 RP2 超过了 0.93(2021 年的 RP2 = 0.96,2021 年的 RP2 = 0.94),在个别阶段的 RP2 在 0.87-0.97 之间。本文提供了一种跟踪土壤与作物生长变异性的方法,用于土地碳链估算优化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Spatial-spectral feature extraction for in-field chlorophyll content estimation using hyperspectral imaging

In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained RP2 of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (RP2 = 0.85) compared to RF bands (RP2 = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with RP2 of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved RP2 above 0.93 in individual years (RP2 = 0.96 in 2021, RP2 = 0.94 in 2021) and RP2 in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Biosystems Engineering
Biosystems Engineering 农林科学-农业工程
CiteScore
10.60
自引率
7.80%
发文量
239
审稿时长
53 days
期刊介绍: Biosystems Engineering publishes research in engineering and the physical sciences that represent advances in understanding or modelling of the performance of biological systems for sustainable developments in land use and the environment, agriculture and amenity, bioproduction processes and the food chain. The subject matter of the journal reflects the wide range and interdisciplinary nature of research in engineering for biological systems.
期刊最新文献
Effects of polyphenol-rich extracts and compounds on methane and ammonia emissions from pig slurry during 28-day incubation Optimising maize threshing process with temporal proximity soft actor-critic deep reinforcement learning algorithm Scaled experimental study of a ventilation system featuring partition jet and pit exhaust Simulation and experimental study on frictional wear of plough blades in soil cultivation process based on the Archard model Harvest motion planning for mango picking robot based on improved RRT-Connect
×
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