Crop Height Monitoring Using a Consumer-Grade Camera and UAV Technology

Abstract

Recent advances in the ability to capture high spatial resolution images by unmanned aerial vehicles (UAVs) have shown the potential of this technology for a wide range of application including exploring the effects of different external stimuli when monitoring environmental and structural variables. In this paper, we show the application of UAV technology for crop height monitoring and modelling to provide quantitative crop growth data and demonstrate the remote sensing and photogrammetric capabilities of the technology to the farming industry. This study was carried out in a field trial involving a combination of six wheat varieties and three different fungicide treatments. The UAV imagery of the field trial site was captured on five occasions throughout crop development. These were used to create digital surface models from which crop surface models (CSMs) were extracted for the cropped areas. Crop heights are estimated from the photogrammetric derived CSMs and are compared against the reference heights captured using Real-Time Kinematic Global Navigation Satellite System (GNSS) to validate the CSMs. Furthermore, crop growth differences among varieties are analysed; and crop height correlations with grain yield as well as with independently estimated vegetation indices are evaluated. These evaluations show that the technology is suitable (with average bias range 2-10 cm depending on wind conditions relative to GNSS height) and has potential for quantitative and qualitative monitoring of canopy and/or crop height and growth. Keywords Crop monitoring • Crop surface model • Digital surface model • Low-cost sensor system • Unmanned aerial vehicles • UAV in agriculture Zusammenfassung Überwachung von Getreidehöhen mit einer handelsüblichen Kamera und UAV Technologie. Jüngste Fortschritte bei der Erfassung von Bildern mit hoher Auflösung durch unbemannte Luftfahrzeuge (Unmanned Aerial Vehicles, UAV) haben das Potenzial dieser Technologie für einen breiten Anwendungsbereich aufgezeigt, einschließlich der Untersuchung der Auswirkungen verschiedener externer Reize bei der Überwachung von Umgebungs-und Strukturvariablen. In diesem Artikel zeigen wir die Anwendung der UAV-Technologie zur Überwachung und Modellierung von Getreidehöhen, um quantitative Getreidewachstumshöhen bereitzustellen und die Fernerkundungs-und photogrammetrische Fähigkeiten der Technologie für die Landwirtschaft zu demonstrieren. Diese Studie wurde in einem Feldversuch mit einer Kombination von sechs Weizensorten und drei verschiedenen Pilzbehandlungen durchgeführt. Die UAV-Bilder des Feldversuchsgeländes wurden während der gesamten Ernteentwicklung fünfmal aufgenommen. Diese Bilder wurden verwendet, um digitale Oberflächenmodelle (Digital Surface Models-DSMs) zu erstellen, aus denen Getreideoberflächenmodelle (Crop Surface Models-CSMs) für die Versuchsflächen extrahiert wurden. Die Erntehöhen werden aus den photogrammetrisch abgeleiteten CSMs geschätzt DGPF

Opportunities and challenges in phenotyping row crops using drone‐based RGB imaging

“…In this approach, one DSM is subtracted from another to obtain height for any one flight date (Figure 3B). The ground DSM is captured from a flight completed before the crops are growing, while the flight DSM captures the plant canopies on the day of interest (Acorsi et al., 2019; Belton et al., 2019; Chu et al., 2018). This method relies on accurate flight paths, DSM registration, and high DSM resolution for accuracy (Table 1).…”

Field Phenomics: Will It Enable Crop Improvement?

“…RGB digital cameras are probably the primary tool for plant phenotyping imagery (especially from UAVs), because of their ready availability and low price, flexibility in application, and, for UAV operation, potentially low mass. Additionally, a major advantage of RGB imaging is the high resolution now available in consumer-grade cameras [87], and, rather obviously, that the visible spectrum enables humans to easily label features of interest and train object detection algorithms [88].…”

Estimation of plant height and yield based on UAV imagery in faba bean (Vicia faba L.)

“…RGB camera [ 22 , 23 ], multispectral or hyperspectral camera [ 24 ], lidar [ 25 , 26 ] and ultrasonic sensors [ 27 , 28 ] have been applied on the UAV platform. These high-throughput phenotyping platforms have been implemented in many crops such as maize [ 29 , 30 ], wheat [ 31 , 32 ], rice [ 33 , 34 ], sorghum [ 35 , 36 ], soybean [ 37 ] in terms of plant height study. However, there was no report for faba bean.…”