In-Field Estimation of Orange Number and Size by 3D Laser Scanning

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

In precision viticulture, the intra-field spatial variability characterization is a crucial step to efficiently use natural resources by lowering the environmental impact. In recent years, technologies such as Unmanned Aerial Vehicles (UAVs), Mobile Laser Scanners (MLS), multispectral sensors, Mobile Apps (MA) and Structure from Motion (SfM) techniques enabled the possibility to characterize this variability with low efforts. The study aims to evaluate, compare and cross-validate the potentiality and the limits of several tools (UAV, MA, MLS) to assess the vine canopy size parameters (thickness, height, volume) by processing 3D point clouds. Three trials were carried out to test the different tools in a vineyard located in the Chianti Classico area (Tuscany, Italy). Each test was made of a UAV flight, an MLS scanning over the vineyard and a MA acquisition over 48 geo-referenced vines. The Leaf Area Index (LAI) were also assessed and taken as reference value. The results showed that the analyzed tools were able to correctly discriminate between zones with different canopy size characteristics. In particular, the R2 between the canopy volumes acquired with the different tools was higher than 0.7, being the highest value of R2 = 0.78 with a RMSE = 0.057 m3 for the UAV vs. MLS comparison. The highest correlations were found between the height data, being the highest value of R2 = 0.86 with a RMSE = 0.105 m for the MA vs. MLS comparison. For the thickness data, the correlations were weaker, being the lowest value of R2 = 0.48 with a RMSE = 0.052 m for the UAV vs. MLS comparison. The correlation between the LAI and the canopy volumes was moderately strong for all the tools with the highest value of R2 = 0.74 for the LAI vs. V_MLS data and the lowest value of R2 = 0.69 for the LAI vs. V_UAV data.

Photogrammetry (SfM) vs. Terrestrial Laser Scanning (TLS) for Archaeological Excavations: Mosaic of Cantillana (Spain) as a Case Study

The discovery of a Roman mosaic from the 2nd century AD in Cantillana (Seville) generated interest and the need for exhaustive documentation, so that it could be recreated with real measurements in a 3D model, not only to obtain an exact replica, but with the intention of analyzing and studying the behavior of two main geomatics techniques. Thus, the objective of this study was the comparative analysis of both techniques: near object photogrammetry by SfM and terrestrial laser scanner or TLS. The aim of this comparison was to assess the use of both techniques in archaeological excavations. Special attention was paid to the accuracy and precision of measurements and models, especially in altimetry. Mosaics are frequently relocated from their original location to be exhibited in museums or for restoration work, after which they are returned to their original place. Therefore, the altimetric situation is of special relevance. To analyze the accuracy and errors of each technique, a total station was used to establish the real values of the ground control points (GCP) on which the comparisons of both methods were to be made. It can be concluded that the SfM technique was the most accurate and least limiting for use in semi-buried archaeological excavations. This manuscript opens new perspectives for the use of SfM-based photogrammetry in archaeological excavations.

Tree Crowns Segmentation and Classification in Overlapping Orchards Based on Satellite Images and Unsupervised Learning Algorithms

Smart agriculture is a new concept that combines agriculture and new technologies to improve the yield's quality and quantity as well as facilitate many tasks for farmers in managing orchards. An essential factor in smart agriculture is tree crown segmentation, which helps farmers automatically monitor their orchards and get information about each tree. However, one of the main problems, in this case, is when the trees are close to each other, which means that it would be difficult for the algorithm to delineate the crowns correctly. This paper used satellite images and machine learning algorithms to segment and classify trees in overlapping orchards. The data used are images from the Moroccan Mohammed VI satellite, and the study region is the OUARGHA citrus orchard located in Morocco. Our approach starts by segmenting the rows inside the parcel and finding all the trees there, getting their canopies, and classifying them by size. In general, the model inputs the parcel's image and other field measurements to classify the trees into three classes: missing/weak, normal, or big. Finally, the results are visualized in a map containing all the trees with their classes. For the results, we obtained a score of 0.93 F-measure in rows segmentation. Additionally, several field comparisons were performed to validate the classification, dozens of trees were compared and the results were very good. This paper aims to help farmers to quickly and automatically classify trees by crown size, even if there are overlapping orchards, in order to easily monitor each tree's health and understand the tree's distribution in the field.

Spatially variable pesticide application in olive groves: Evaluation of potential pesticide-savings through stochastic spatial simulation algorithms

Site-specific management using spatial crown volume characterization can greatly reduce the amount of pesticides applied in agricultural treatments performed with air-assisted sprayers, while helping farmers achieve the European legislation on safe use of pesticides. Nevertheless, variable rate treatments in olive groves have received little attention. Thus, field research was conducted in a 20.6-ha traditional olive grove. Two attributes of the trees - tree crown volume (V) and tree projected area - were determined, using 67 samples for V and all trees of the field (1433) for tree projected area. Spatial continuity of both attributes was modelled with exponential variograms. To gain a measure of local uncertainty, stochastic simulation algorithms were applied. One hundred simulated images were obtained for tree projected area using direct sequential simulation. Tree projected area simulations were used to improve spatial prediction of V, more difficult and more expensive to obtain, taking advantage of the high linear correlation between both variables (r_xy = 0.72,p < 0.001). Thus, direct sequential cosimulation was employed to predict the spatial distribution of V, obtaining 100 geostatistical realizations of V. In order to estimate the potential reduction of pesticide use in the farm with variable rate treatments, two cut-off values of V were considered (50 and 100 m³_{crown volume}). Local uncertainty, understood as the probability of each tree belonging to a given crown volume interval was determined. Probability maps were further transformed to morphological maps and finally to variable prescription maps. Two scenarios with 2 and 3 management zones (MZs) were obtained. In comparison with a conventional phytosanitary application, the variable rate treatments could reduce the pesticide amounts by 21.3% with 2 MZs, and by 38% with 3 MZs. The joint use of V and tree projected area in stochastic sequential simulation algorithms has shown to be useful to determine MZs in olive groves.

Apple Shape Detection Based on Geometric and Radiometric Features Using a LiDAR Laser Scanner

Yield monitoring systems in fruit production mostly rely on color features, making the discrimination of fruits challenging due to varying light conditions. The implementation of geometric and radiometric features in three-dimensional space (3D) analysis can alleviate such difficulties improving the fruit detection. In this study, a light detection and range (LiDAR) system was used to scan apple trees before (TL) and after defoliation (TD) four times during seasonal tree growth. An apple detection method based on calibrated apparent backscattered reflectance intensity (RToF) and geometric features, capturing linearity (L) and curvature (C) derived from the LiDAR 3D point cloud, is proposed. The iterative discretion of apple class from leaves and woody parts was obtained at RToF > 76.1%, L < 15.5%, and C > 73.2%. The position of fruit centers in TL and in TD was compared, showing a root mean square error (RMSE) of 5.7%. The diameter of apples estimated from the foliated trees was related to the reference values based on the perimeter of the fruits, revealing an adjusted coefficient of determination (R2adj) of 0.95 and RMSE of 9.5% at DAFB120. When comparing the results obtained on foliated and defoliated tree’s data, the estimated number of fruit’s on foliated trees at DAFB42, DAFB70, DAFB104, and DAFB120 88.6%, 85.4%, 88.5%, and 94.8% of the ground truth values, respectively. The algorithm resulted in maximum values of 88.2% precision, 91.0% recall, and 89.5 F1 score at DAFB120. The results point to the high capacity of LiDAR variables [RToF, C, L] to localize fruit and estimate its size by means of remote sensing.

Assessing the Orange Tree Crown Volumes Using Google Maps as a Low-Cost Photogrammetric Alternative

The accurate assessment of tree crowns is important for agriculture, for example, to adjust spraying rates, to adjust irrigation rates or even to estimate biomass. Among the available methodologies, there are the traditional methods that estimate with a three-dimensional approximation figure, the HDS (High Definition Survey), or TLS (Terrestrial Laser Scanning) based on LiDAR technology, the aerial photogrammetry that has re-emerged with unmanned aerial vehicles (UAVs), as they are considered low cost. There are situations where either the cost or location does not allow for modern methods and prices such as HDS or the use of UAVs. This study proposes, as an alternative methodology, the evaluation of images extracted from Google Maps (GM) for the calculation of tree crown volume. For this purpose, measurements were taken on orange trees in the south of Spain using the four methods mentioned above to evaluate the suitability, accuracy, and limitations of GM. Using the HDS method as a reference, the photogrammetric method with UAV images has shown an average error of 10%, GM has obtained approximately 50%, while the traditional methods, in our case considering ellipsoids, have obtained 100% error. Therefore, the results with GM are encouraging and open new perspectives for the estimation of tree crown volumes at low cost compared to HDS, and without geographical flight restrictions like those of UAVs.