Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds.

Recent advances in Deep Learning and aerial Light Detection And Ranging (LiDAR) have offered the possibility of refining the classification and segmentation of 3D point clouds to contribute to the monitoring of complex environments. In this context, the present study focuses on developing an ordinal classification model in forest areas where LiDAR point clouds can be classified into four distinct ordinal classes: ground, low vegetation, medium vegetation, and high vegetation. To do so, an effective soft labeling technique based on a novel proposed generalized exponential function (CE-GE) is applied to the PointNet network architecture. Statistical analyses based on Kolmogorov-Smirnov and Student's t-test reveal that the CE-GE method achieves the best results for all the evaluation metrics compared to other methodologies. Regarding the confusion matrices of the best alternative conceived and the standard categorical cross-entropy method, the smoothed ordinal classification obtains a more consistent classification compared to the nominal approach. Thus, the proposed methodology significantly improves the point-by-point classification of PointNet, reducing the errors in distinguishing between the middle classes (low vegetation and medium vegetation).

Individualization of Pinus radiata Canopy from 3D UAV Dense Point Clouds Using Color Vegetation Indices.

The location of trees and the individualization of their canopies are important parameters to estimate diameter, height, and biomass, among other variables. The very high spatial resolution of UAV imagery supports these processes. A dense 3D point cloud is generated from RGB UAV images, which is used to obtain a digital elevation model (DEM). From this DEM, a canopy height model (CHM) is derived for individual tree identification. Although the results are satisfactory, the quality of this detection is reduced if the working area has a high density of vegetation. The objective of this study was to evaluate the use of color vegetation indices (CVI) in canopy individualization processes of Pinus radiata. UAV flights were carried out, and a 3D dense point cloud and an orthomosaic were obtained. Then, a CVI was applied to 3D point cloud to differentiate between vegetation and nonvegetation classes to obtain a DEM and a CHM. Subsequently, an automatic crown identification procedure was applied to the CHM. The results were evaluated by contrasting them with results of manual individual tree identification on the UAV orthomosaic and those obtained by applying a progressive triangulated irregular network to the 3D point cloud. The results obtained indicate that the color information of 3D point clouds is an alternative to support individualizing trees under conditions of high-density vegetation.

Machine Learning Methods and Synthetic Data Generation to Predict Large Wildfires.

Wildfires are becoming more frequent in different parts of the globe, and the ability to predict when and where they will occur is a complex process. Identifying wildfire events with high probability of becoming a large wildfire is an important task for supporting initial attack planning. Different methods, including those that are physics-based, statistical, and based on machine learning (ML) are used in wildfire analysis. Among the whole, those based on machine learning are relatively novel. In addition, because the number of wildfires is much greater than the number of large wildfires, the dataset to be used in a ML model is imbalanced, resulting in overfitting or underfitting the results. In this manuscript, we propose to generate synthetic data from variables of interest together with ML models for the prediction of large wildfires. Specifically, five synthetic data generation methods have been evaluated, and their results are analyzed with four ML methods. The results yield an improvement in the prediction power when synthetic data are used, offering a new method to be taken into account in Decision Support Systems (DSS) when managing wildfires.

Grape Cluster Detection Using UAV Photogrammetric Point Clouds as a Low-Cost Tool for Yield Forecasting in Vineyards.

Yield prediction is crucial for the management of harvest and scheduling wine production operations. Traditional yield prediction methods rely on manual sampling and are time-consuming, making it difficult to handle the intrinsic spatial variability of vineyards. There have been significant advances in automatic yield estimation in vineyards from on-ground imagery, but terrestrial platforms have some limitations since they can cause soil compaction and have problems on sloping and ploughed land. The analysis of photogrammetric point clouds generated with unmanned aerial vehicles (UAV) imagery has shown its potential in the characterization of woody crops, and the point color analysis has been used for the detection of flowers in almond trees. For these reasons, the main objective of this work was to develop an unsupervised and automated workflow for detection of grape clusters in red grapevine varieties using UAV photogrammetric point clouds and color indices. As leaf occlusion is recognized as a major challenge in fruit detection, the influence of partial leaf removal in the accuracy of the workflow was assessed. UAV flights were performed over two commercial vineyards with different grape varieties in 2019 and 2020, and the photogrammetric point clouds generated from these flights were analyzed using an automatic and unsupervised algorithm developed using free software. The proposed methodology achieved R2 values higher than 0.75 between the harvest weight and the projected area of the points classified as grapes in vines when partial two-sided removal treatment, and an R2 of 0.82 was achieved in one of the datasets for vines with untouched full canopy. The accuracy achieved in grape detection opens the door to yield prediction in red grape vineyards. This would allow the creation of yield estimation maps that will ease the implementation of precision viticulture practices. To the authors' knowledge, this is the first time that UAV photogrammetric point clouds have been used for grape clusters detection.

Opportunities of super high-density olive orchard to improve soil quality: Management guidelines for application of pruning residues.

Applying pruning residues in the lanes of olive groves has become a popular practice because it is economical and accrues benefits for soil and water management. This study presents an analysis of the impact of different rates of pruning residue on soil properties, in particular related with soil quality. Over 4 annual campaigns, chopped pruning residues used as a mulch were analyzed in terms of composition, coverage and moisture content to evaluate their effects on the amount of soil organic carbon (-10 cm and -20 cm) and CO2 emissions, temperature and moisture. The experiment was carried out in a super-intensive olive orchard in Cordoba (SE, Spain) and used four amounts of fresh pruning residue: 7.5 t ha⁻1(T1), 15.0 t ha⁻1 (T2) and 30.0 t ha⁻1 (T3), with a control T0 = 0.0 t ha1. Mulch mean leaf fraction was 46.0 ± 17.5% (±SD) and initial water content, 24.8 ± 8.6%. The mulching benefits for soil moisture were observed in amounts of pruning residue >7.5 t ha⁻1, which are only produced in super-intensive olive groves or in orchards with high tree densities. The low impact of the treatments on soil moisture was explained by the dramatic annual variations in residue moisture contents, caused by the regimes of high temperatures and rainfall-evapotranspiration deficits inherent to the Mediterranean Basin climate. Thus, the mulching capacity only resulted efficient when the residues were still humid in spring. In addition, 15.0 t ha⁻1 of pruning residues was the threshold to provide significant increases in soil organic carbon at depths of 0-20 cm. Thus, accumulating pruning residue in lanes at rates of over 15 t ha⁻1 (T2 and T3) is more convenient than a uniform distribution with lower amounts, due to the low mineralization rates occurring during warm seasons and the larger inputs of OM increasing the annual balance of SOC.

The Development of an Open Hardware and Software System Onboard Unmanned Aerial Vehicles to Monitor Concentrated Solar Power Plants.

Concentrated solar power (CSP) plants are increasingly gaining interest as a source of renewable energy. These plants face several technical problems and the inspection of components such as absorber tubes in parabolic trough concentrators (PTC), which are widely deployed, is necessary to guarantee plant efficiency. This article presents a system for real-time industrial inspection of CSP plants using low-cost, open-source components in conjunction with a thermographic sensor and an unmanned aerial vehicle (UAV). The system, available in open-source hardware and software, is designed to be employed independently of the type of device used for inspection (laptop, smartphone, tablet or smartglasses) and its operating system. Several UAV flight missions were programmed as follows: flight altitudes at 20, 40, 60, 80, 100 and 120 m above ground level; and three cruising speeds: 5, 7 and 10 m/s. These settings were chosen and analyzed in order to optimize inspection time. The results indicate that it is possible to perform inspections by an UAV in real time at CSP plants as a means of detecting anomalous absorber tubes and improving the effectiveness of methodologies currently being utilized. Moreover, aside from thermographic sensors, this contribution can be applied to other sensors and can be used in a broad range of applications where real-time georeferenced data visualization is necessary.

An Analysis of the Influence of Flight Parameters in the Generation of Unmanned Aerial Vehicle (UAV) Orthomosaicks to Survey Archaeological Areas.

This article describes the configuration and technical specifications of a multi-rotor unmanned aerial vehicle (UAV) using a red-green-blue (RGB) sensor for the acquisition of images needed for the production of orthomosaics to be used in archaeological applications. Several flight missions were programmed as follows: flight altitudes at 30, 40, 50, 60, 70 and 80 m above ground level; two forward and side overlap settings (80%-50% and 70%-40%); and the use, or lack thereof, of ground control points. These settings were chosen to analyze their influence on the spatial quality of orthomosaicked images processed by Inpho UASMaster (Trimble, CA, USA). Changes in illumination over the study area, its impact on flight duration, and how it relates to these settings is also considered. The combined effect of these parameters on spatial quality is presented as well, defining a ratio between ground sample distance of UAV images and expected root mean square of a UAV orthomosaick. The results indicate that a balance between all the proposed parameters is useful for optimizing mission planning and image processing, altitude above ground level (AGL) being main parameter because of its influence on root mean square error (RMSE).

Monitoring Heritage Buildings with Open Source Hardware Sensors: A Case Study of the Mosque-Cathedral of Córdoba.

A number of physical factors can adversely affect cultural heritage. Therefore, monitoring parameters involved in the deterioration process, principally temperature and relative humidity, is useful for preventive conservation. In this study, a total of 15 microclimate stations using open source hardware were developed and stationed at the Mosque-Cathedral of Córdoba, which is registered with UNESCO for its outstanding universal value, to assess the behavior of interior temperature and relative humidity in relation to exterior weather conditions, public hours and interior design. Long-term monitoring of these parameters is of interest in terms of preservation and reducing the costs of future conservation strategies. Results from monitoring are presented to demonstrate the usefulness of this system.

Spatial Quality Evaluation of Resampled Unmanned Aerial Vehicle-Imagery for Weed Mapping.

Unmanned aerial vehicles (UAVs) combined with different spectral range sensors are an emerging technology for providing early weed maps for optimizing herbicide applications. Considering that weeds, at very early phenological stages, are similar spectrally and in appearance, three major components are relevant: spatial resolution, type of sensor and classification algorithm. Resampling is a technique to create a new version of an image with a different width and/or height in pixels, and it has been used in satellite imagery with different spatial and temporal resolutions. In this paper, the efficiency of resampled-images (RS-images) created from real UAV-images (UAV-images; the UAVs were equipped with two types of sensors, i.e., visible and visible plus near-infrared spectra) captured at different altitudes is examined to test the quality of the RS-image output. The performance of the object-based-image-analysis (OBIA) implemented for the early weed mapping using different weed thresholds was also evaluated. Our results showed that resampling accurately extracted the spectral values from high spatial resolution UAV-images at an altitude of 30 m and the RS-image data at altitudes of 60 and 100 m, was able to provide accurate weed cover and herbicide application maps compared with UAV-images from real flights.

Positional quality assessment of orthophotos obtained from sensors onboard multi-rotor UAV platforms.

In this study we explored the positional quality of orthophotos obtained by an unmanned aerial vehicle (UAV). A multi-rotor UAV was used to obtain images using a vertically mounted digital camera. The flight was processed taking into account the photogrammetry workflow: perform the aerial triangulation, generate a digital surface model, orthorectify individual images and finally obtain a mosaic image or final orthophoto. The UAV orthophotos were assessed with various spatial quality tests used by national mapping agencies (NMAs). Results showed that the orthophotos satisfactorily passed the spatial quality tests and are therefore a useful tool for NMAs in their production flowchart.

Detection of Ecballium elaterium in hedgerow olive orchards using a low-cost uncrewed aerial vehicle and open-source algorithms.

BACKGROUND: Ecballium elaterium (common name: squirting cucumber) is an emerging weed problem in hedgerow or superintensive olive groves under no tillage. It colonizes the inter-row area infesting the natural or sown cover crops, and is considered a hard-to-control weed. Research in other woody crops has shown E. elaterium has a patchy distribution, which makes this weed susceptible to design a site-specific control strategy only addressed to E. elaterium patches. Therefore, the aim of this work was to develop a methodology based on the analysis of imagery acquired with an uncrewed aerial vehicle (UAV) to detect and map E. elaterium infestations in hedgerow olive orchards. RESULTS: The study was conducted in two superintensive olive orchards, and the images were taken using a UAV equipped with an RGB sensor. Flights were conducted on two dates: in May, when there were various weeds infesting the orchard, and in September, when E. elaterium was the only infesting weed. UAV-orthomosaics in the first scenario were classified using random forest models, and the orthomosaics from September with E. elaterium as the only weed, were analyzed using an unsupervised algorithm. In both cases, the overall accuracies were over 0.85, and the producer's accuracies for E. elaterium ranged between 0.74 and 1.00. CONCLUSION: These results allow the design of a site-specific and efficient herbicide control protocol which would represent a step forward in sustainable weed management. The development of these algorithms in free and open-source software fosters their application in small and medium farms. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.