Quantifying Citrus Tree Health Using True Color UAV Images

The Combined Use of UAV-Based RGB and DEM Images for the Detection and Delineation of Orange Tree Crowns with Mask R-CNN: An Approach of Labeling and Unified Framework

In this study, we used images obtained by Unmanned Aerial Vehicles (UAV) and an instance segmentation model based on deep learning (Mask R-CNN) to evaluate the ability to detect and delineate canopies in high density orange plantations. The main objective of the work was to evaluate the improvement acquired by the segmentation model when integrating the Canopy Height Model (CHM) as a fourth band to the images. Two models were evaluated, one with RGB images and the other with RGB + CHM images, and the results indicated that the model with combined images presents better results (overall accuracy from 90.42% to 97.01%). In addition to the comparison, this work suggests a more efficient ground truth mapping method and proposes a methodology for mosaicking the results by Mask R-CNN on remotely sensed images.

Meta-analysis of Unmanned Aerial Vehicle (UAV) Imagery for Agro-environmental Monitoring Using Machine Learning and Statistical Models

Unmanned Aerial Vehicle (UAV) imaging systems have recently gained significant attention from researchers and practitioners as a cost-effective means for agro-environmental applications. In particular, machine learning algorithms have been applied to UAV-based remote sensing data for enhancing the UAV capabilities of various applications. This systematic review was performed on studies through a statistical meta-analysis of UAV applications along with machine learning algorithms in agro-environmental monitoring. For this purpose, a total number of 163 peer-reviewed articles published in 13 high-impact remote sensing journals over the past 20 years were reviewed focusing on several features, including study area, application, sensor type, platform type, and spatial resolution. The meta-analysis revealed that 62% and 38% of the studies applied regression and classification models, respectively. Visible sensor technology was the most frequently used sensor with the highest overall accuracy among classification articles. Regarding regression models, linear regression and random forest were the most frequently applied models in UAV remote sensing imagery processing. Finally, the results of this study confirm that applying machine learning approaches on UAV imagery produces fast and reliable results. Agriculture, forestry, and grassland mapping were found as the top three UAV applications in this review, in 42%, 22%, and 8% of the studies, respectively.

Detection of Citrus Huanglongbing Based on Multi-Input Neural Network Model of UAV Hyperspectral Remote Sensing

Citrus is an important cash crop in the world, and huanglongbing (HLB) is a destructive disease in the citrus industry. To efficiently detect the degree of HLB stress on large-scale orchard citrus trees, an UAV (Uncrewed Aerial Vehicle) hyperspectral remote sensing tool is used for HLB rapid detection. A Cubert S185 (Airborne Hyperspectral camera) was mounted on the UAV of DJI Matrice 600 Pro to capture the hyperspectral remote sensing images; and a ASD Handheld2 (spectrometer) was used to verify the effectiveness of the remote sensing data. Correlation-proven UAV hyperspectral remote sensing data were used, and canopy spectral samples based on single pixels were extracted for processing and analysis. The feature bands extracted by the genetic algorithm (GA) of the improved selection operator were 468 nm, 504 nm, 512 nm, 516 nm, 528 nm, 536 nm, 632 nm, 680 nm, 688 nm, and 852 nm for the HLB detection. The proposed HLB detection methods (based on the multi-feature fusion of vegetation index) and canopy spectral feature parameters constructed (based on the feature band in stacked autoencoder (SAE) neural network) have a classification accuracy of 99.33% and a loss of 0.0783 for the training set, and a classification accuracy of 99.72% and a loss of 0.0585 for the validation set. This performance is higher than that based on the full-band AutoEncoder neural network. The field-testing results show that the model could effectively detect the HLB plants and output the distribution of the disease in the canopy, thus judging the plant disease level in a large area efficiently.

A Pilot Study to Estimate Forage Mass from Unmanned Aerial Vehicles in a Semi-Arid Rangeland

The application of unmanned aerial vehicles (UAVs) in the monitoring and management of rangelands has exponentially increased in recent years due to the miniaturization of sensors, ability to capture imagery with high spatial resolution, lower altitude platforms, and the ease of flying UAVs in remote environments. The aim of this research was to develop a method to estimate forage mass in rangelands using high-resolution imagery derived from the UAV using a South Texas pasture as a pilot site. The specific objectives of this research were to (1) evaluate the feasibility of quantifying forage mass in semi-arid rangelands using a double sampling technique with high-resolution imagery and (2) to compare the effect of altitude on forage mass estimation. Orthoimagery and digital surface models (DSM) with a resolution <1.5 cm were acquired with an UAV at altitudes of 30, 40, and 50 m above ground level (AGL) in Duval County, Texas. Field forage mass data were regressed on volumes obtained from a DSM. Our results show that volumes estimated with UAV data and forage mass as measured in the field have a significant relationship at all flight altitudes with best results at 30-m AGL (r2 = 0.65) and 50-m AGL (r2 = 0.63). Furthermore, the use of UAVs would allow one to collect a large number of samples using a non-destructive method to estimate available forage for grazing animals.