AgriSenAI: Automating UAV thermal and multispectral image processing for precision agriculture

IF 2.4 4区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

SoftwareX Pub Date : 2025-02-11 DOI:10.1016/j.softx.2025.102083

Boaz B. Tulu , Fitsum Teshome , Yiannis Ampatzidis , Niguss Solomon Hailegnaw , Haimanote K Bayabil

{"title":"AgriSenAI: Automating UAV thermal and multispectral image processing for precision agriculture","authors":"Boaz B. Tulu , Fitsum Teshome , Yiannis Ampatzidis , Niguss Solomon Hailegnaw , Haimanote K Bayabil","doi":"10.1016/j.softx.2025.102083","DOIUrl":null,"url":null,"abstract":"<div><div>Unmanned Aerial Vehicles (UAVs) equipped with thermal and multispectral imaging capabilities, which offer high spatial and temporal resolutions, are becoming increasingly valuable for timely crop monitoring and informed decision-making in precision agriculture. However, processing and extracting useful information from UAV images is often complex, time-consuming, and requires specialized software, which limits its broader adoption for practical field implementations. To address these challenges, the Agriculture Sensing and Artificial Intelligence (AgriSenAI), a user-friendly Python-based desktop application, was developed to automate processing and information extraction from UAV-acquired thermal and multispectral imagery. AgriSenAI was developed by integrating advanced image processing with geospatial analysis to streamline field and plot extraction, plant canopy detection, noise removal, and extraction of information at pixel, plot, and field scales. The application was designed and tested using UAV-based thermal and multispectral imagery collected daily for three years from a research field at the University of Florida's Tropical Research and Education Center in Homestead, Florida. The research field consisted of 12 plots of green beans and 12 plots of sweet corn. The processing time and accuracy of AgriSenAI were evaluated. Results showed that AgriSenAI had a very high level of accuracy in extracting pixel values and significantly reduced processing time and costs compared with traditional approaches involving commercial software. The streamlined AgriSenAI workflow produced reliable canopy temperature information and vegetation indices, demonstrating the capacity to handle large-scale datasets and enhance precision agriculture through improved efficiency and accuracy in remote sensing data processing and information extraction, which could potentially be used to inform timely and data-driven crop management decisions.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"30 ","pages":"Article 102083"},"PeriodicalIF":2.4000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SoftwareX","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352711025000500","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

Unmanned Aerial Vehicles (UAVs) equipped with thermal and multispectral imaging capabilities, which offer high spatial and temporal resolutions, are becoming increasingly valuable for timely crop monitoring and informed decision-making in precision agriculture. However, processing and extracting useful information from UAV images is often complex, time-consuming, and requires specialized software, which limits its broader adoption for practical field implementations. To address these challenges, the Agriculture Sensing and Artificial Intelligence (AgriSenAI), a user-friendly Python-based desktop application, was developed to automate processing and information extraction from UAV-acquired thermal and multispectral imagery. AgriSenAI was developed by integrating advanced image processing with geospatial analysis to streamline field and plot extraction, plant canopy detection, noise removal, and extraction of information at pixel, plot, and field scales. The application was designed and tested using UAV-based thermal and multispectral imagery collected daily for three years from a research field at the University of Florida's Tropical Research and Education Center in Homestead, Florida. The research field consisted of 12 plots of green beans and 12 plots of sweet corn. The processing time and accuracy of AgriSenAI were evaluated. Results showed that AgriSenAI had a very high level of accuracy in extracting pixel values and significantly reduced processing time and costs compared with traditional approaches involving commercial software. The streamlined AgriSenAI workflow produced reliable canopy temperature information and vegetation indices, demonstrating the capacity to handle large-scale datasets and enhance precision agriculture through improved efficiency and accuracy in remote sensing data processing and information extraction, which could potentially be used to inform timely and data-driven crop management decisions.

查看原文本刊更多论文

AgriSenAI：用于精准农业的无人机热成像和多光谱图像处理自动化

配备热成像和多光谱成像能力的无人机（uav）提供高空间和时间分辨率，在精准农业中对作物进行及时监测和知情决策变得越来越有价值。然而，从无人机图像中处理和提取有用的信息通常是复杂的，耗时的，并且需要专门的软件，这限制了它在实际领域实现的广泛采用。为了应对这些挑战，开发了农业传感和人工智能（AgriSenAI），这是一个用户友好的基于python的桌面应用程序，用于自动处理和从无人机获取的热图像和多光谱图像中提取信息。AgriSenAI将先进的图像处理与地理空间分析相结合，简化了田地和地块的提取、植物冠层检测、噪声去除以及像素、地块和田地尺度的信息提取。该应用程序的设计和测试使用了基于无人机的热图像和多光谱图像，这些图像每天从佛罗里达州霍姆斯特德的佛罗里达大学热带研究和教育中心的一个研究领域收集，持续了三年。研究区包括12块四季豆和12块甜玉米。对AgriSenAI的处理时间和精度进行了评价。结果表明，AgriSenAI在提取像素值方面具有很高的精度，与使用商业软件的传统方法相比，显著降低了处理时间和成本。简化的AgriSenAI工作流程产生了可靠的冠层温度信息和植被指数，展示了处理大规模数据集的能力，并通过提高遥感数据处理和信息提取的效率和准确性来增强精准农业，这可能被用于及时和数据驱动的作物管理决策。

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

SoftwareX COMPUTER SCIENCE, SOFTWARE ENGINEERING-

CiteScore

5.50

自引率

2.90%

发文量

184

审稿时长

9 weeks

期刊介绍： SoftwareX aims to acknowledge the impact of software on today''s research practice, and on new scientific discoveries in almost all research domains. SoftwareX also aims to stress the importance of the software developers who are, in part, responsible for this impact. To this end, SoftwareX aims to support publication of research software in such a way that: The software is given a stamp of scientific relevance, and provided with a peer-reviewed recognition of scientific impact; The software developers are given the credits they deserve; The software is citable, allowing traditional metrics of scientific excellence to apply; The academic career paths of software developers are supported rather than hindered; The software is publicly available for inspection, validation, and re-use. Above all, SoftwareX aims to inform researchers about software applications, tools and libraries with a (proven) potential to impact the process of scientific discovery in various domains. The journal is multidisciplinary and accepts submissions from within and across subject domains such as those represented within the broad thematic areas below: Mathematical and Physical Sciences; Environmental Sciences; Medical and Biological Sciences; Humanities, Arts and Social Sciences. Originating from these broad thematic areas, the journal also welcomes submissions of software that works in cross cutting thematic areas, such as citizen science, cybersecurity, digital economy, energy, global resource stewardship, health and wellbeing, etcetera. SoftwareX specifically aims to accept submissions representing domain-independent software that may impact more than one research domain.