Review on unmanned aerial vehicles, remote sensors, imagery processing, and their applications in agriculture

Abstract

Unmanned aerial vehicles (UAV) and the sensors they can be equipped with are becoming more technologically advanced and common place within the agricultural industry. The output analyses from UAV captured data helps drive decisions for improving input efficiency in agricultural systems, which can result in maximum return on investment and reduced environmental impact. Advances in UAV technologies provides producers with options for assessment of crucial factors impacting crop yield and quality including crop water status and nutrient stress, competition from weeds, insects, and pathogens, and soil characteristics and precision field maps. Thus, integrating UAV technologies as a component of production agriculture enables producers to identify and locate problem areas in their fields in near real time and take corrective actions once these areas are verified. UAV technologies also offers researchers with a non-destructive, objective manner for obtaining phenotypic measurements such as height assessment, biomass estimation, canopy reflectance, and abiotic and biotic stress tolerance, which can greatly expedite field data collection for advancing germplasm with desired agronomic traits. This review covers more than a hundred articles that were obtained from the existing literature and illustrates common UAV types, common sensor types, imagery processing options, and their practical application and pitfalls in the modern agricultural industry.Abbreviations: CWSI, crop water stress index; LiDAR, light detecting and ranging; NDVI, normalized difference vegetation index; RENDVI, red edge normalized difference vegetation index; UAV, unmanned aerial vehicle.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Agronomic and efficacy evaluations of oxathiapiprolin as a soybean seed treatment

“…These visual data are subjective and are prone to human error as data are typically collected by different individuals at different timepoints. The use of unmanned aerial vehicles (UAV) equipped with spectral sensors has resulted in improvement in precision for growers and other agricultural businesses (Maes & Steppe, 2019; Milics et al., 2019; Olson & Anderson, 2021). Measurement quality, geospatial linkage, increased throughput, and an ability to make many measurements at greater temporal density have driven adoption of the technology.…”

“…Image analysis techniques have been developed for converting a digital image into numerical phenotypic trait data (Daponte et al., 2019; Lee & Lee, 2011; Narayanan et al., 2019; Olson & Anderson, 2021; Zhao et al., 2018). A technology commonly used for the detection and quantification of objects within imagery is computer vision and machine learning; an artificial intelligence system that can train a computer to measure and quantify differences in plant growth characteristics (Olson & Anderson, 2021; Rehman et al., 2019; Tian et al., 2019). Fusing the high throughput data collection abilities of UAV with sensitive detection approaches in computer vision and machine learning enables phenotypes to be rapidly collected and quantified with a high level of accuracy.…”

How Can Unmanned Aerial Vehicles Be Used for Detecting Weeds in Agricultural Fields?

“…Contrarily, manned aircraft can cover broad areas but are prohibitively expensive. Handheld sensors are very accurate; yet, when compared to aerial remote sensing, their coverage area is incredibly limited [21]. [25] Clouds, Aerosols, Vapors, Ice, and Snow: CAVIS.…”

“…Furthermore, dif satellites offer some advantages and disadvantages of its features (Table manned aircraft can cover broad areas but are prohibitively expensive. Han are very accurate; yet, when compared to aerial remote sensing, their co incredibly limited [21].…”

UAVs for Vegetation Monitoring: Overview and Recent Scientific Contributions

“…In addition, the UAV-based digital images can be an efficient alternative to data collected with manual fieldwork, which is often arduous, involves destructive sampling, and may provide inconsistent and subjective information. As a result of these strengths, the UAVs are becoming very suitable platforms for agroforestry applications [4,5], such as vegetation characterization and mapping [6], land management [7], environmental monitoring [8], and especially to address diverse precision agriculture objectives [9] and plant phenotypic characterization in breeding programs [10,11].…”