Models for crop yield estimation using multi-temporal UAV-based remote sensing imagery

使用基于多时相无人机的遥感图像进行作物产量估算的模型

• 批准号: 485917-2015
• 负责人: Wang, Jinfei
• 金额: $ 1.82万
• 依托单位: University of Western Ontario
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=585283
• 关键词: Models; crop; yield; estimation; using

Precision farming is a new agriculture management approach based on observation and measurement to respond to inter and intra-field variability in crops. Empirical crop yield estimation models have been developed using satellite remote sensing technique. However, currently, there are only very few studies on the use of Unmanned Aerial Vehicle (UAV) systems for crop yield estimation. As an innovative technology and an inexpensive and more reliable alternative to airborne and satellite remote sensing, A&L has developed hardware and software for UAV system in order to provide crop monitoring and yield prediction service for its clients. This project aims to collaborate with A&L Canada Laboratories Inc. to develop models for crop yields estimation using multi-temporal UAV-based remote sensing imagery. The objective of this project is to develop methodology/procedures for crop yield prediction using the UAV images acquired by the A&L newly developed multispectral sensor. The proposed methodology includes (1) UAV image collection, image calibration and processing; (2) mapping of canopy Nitrogen based on UAV images and plant samples, data collection on soil properties and weather conditions; (3) Development of crop yield prediction models; (4) Comparison of yield prediction results using different combinations of dates, phenological stages and different input variables. The final results and algorithms of this project will be immediately integrated into a service A&L intends to offer to the Agriculture industry in the near future. A&L will be able to generate revenue from hardware sales as well as ongoing service sales for interpretations which will be unique to their sensor technology. The research and findings will directly benefit the Canadian agricultural sector. Efficiencies found in production agriculture directly benefit not only the producers but the entire food supply chain for the domestic and export market.

精准农业是一种以观测为基础的新型农业管理方式。 对作物的田间和田内变异性作出反应。经验的作物产量估计模型已经被 利用卫星遥感技术开发的。然而，目前关于这方面的研究还很少。 利用无人驾驶飞行器(UAV)系统估计作物产量。作为一项创新技术和 A&L开发了一种廉价、更可靠的航空和卫星遥感替代方案 无人机系统的硬件和软件，以便为ITS提供作物监测和产量预测服务 客户。 该项目旨在与A&L加拿大实验室公司合作开发作物产量模型 利用基于无人机的多时相遥感图像进行估计。这个项目的目标是 开发利用A&L新近获得的无人机图像进行作物产量预测的方法/程序 开发了多光谱传感器。提出的方法包括(1)无人机图像采集、图像 (2)基于无人机图像和植物样本数据的冠层氮素制图 收集土壤性质和天气状况；(3)开发作物产量预测模型；(4) 利用不同日期、物候期和不同组合的产量预测结果的比较 输入变量。该项目的最终结果和算法将立即集成到一项服务中 A&L打算在不久的将来向农业行业提出收购要约。A&L将能够从 硬件销售以及针对其传感器的独一无二的持续服务销售 技术这项研究和发现将直接惠及加拿大农业部门。发现的效率 在生产中，农业不仅直接惠及生产者，而且直接惠及整个粮食供应链。 内外销市场。