ALBERT

Description: Canopy management operations, such as shoot thinning, leaf removal, and shoot trimming, are among the most relevant agricultural practices in viticulture. However, the supervision of these tasks demands a visual inspection of the whole vineyard, which is time-consuming and laborious. The application of photogrammetric techniques to images acquired with an Unmanned Aerial Vehicle (UAV) has proved to be an efficient way to measure woody crops canopy. Consequently, the objective of this work was to determine whether the use of UAV photogrammetry allows the detection of canopy management operations. A UAV equipped with an RGB digital camera was used to acquire images with high overlap over different canopy management experiments in four vineyards with the aim of characterizing vine dimensions before and after shoot thinning, leaf removal, and shoot trimming operations. The images were processed to generate photogrammetric point clouds of every vine that were analyzed using a fully automated object-based image analysis algorithm. Two approaches were tested in the analysis of the UAV derived data: (1) to determine whether the comparison of the vine dimensions before and after the treatments allowed the detection of the canopy management operations; and (2) to study the vine dimensions after the operations and assess the possibility of detecting these operations using only the data from the flight after them. The first approach successfully detected the canopy management. Regarding the second approach, significant differences in the vine dimensions after the treatments were detected in all the experiments, and the vines under the shoot trimming treatment could be easily and accurately detected based on a fixed threshold.

Description: Remote sensing applied in the digital transformation of agriculture and, more particularly, in precision viticulture offers methods to map field spatial variability to support site-specific management strategies; these can be based on crop canopy characteristics such as the row height or vegetation cover fraction, requiring accurate three-dimensional (3D) information. To derive canopy information, a set of dense 3D point clouds was generated using photogrammetric techniques on images acquired by an RGB sensor onboard an unmanned aerial vehicle (UAV) in two testing vineyards on two different dates. In addition to the geometry, each point also stores information from the RGB color model, which was used to discriminate between vegetation and bare soil. To the best of our knowledge, the new methodology herein presented consisting of linking point clouds with their spectral information had not previously been applied to automatically estimate vine height. Therefore, the novelty of this work is based on the application of color vegetation indices in point clouds for the automatic detection and classification of points representing vegetation and the later ability to determine the height of vines using as a reference the heights of the points classified as soil. Results from on-ground measurements of the heights of individual grapevines were compared with the estimated heights from the UAV point cloud, showing high determination coefficients (R² 〉 0.87) and low root-mean-square error (0.070 m). This methodology offers new capabilities for the use of RGB sensors onboard UAV platforms as a tool for precision viticulture and digitizing applications.

Description: 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.

Description: Assessing the spatial distribution of weeds within a field is a key step to the success of site-specific weed management strategies. Centaurea diluta (knapweed) is an emerging weed that is causing a major agronomic problem in southern and central Spain because of its large size, the difficulty of controlling it, and its high competitive ability. The main objectives of this study were to examine the spatial variability of C. diluta density in two wheat fields by multivariate geostatistical methods using unmanned aerial vehicle (UAV) imagery as secondary information and to delineate potential control zones for site-specific treatments based on occurrence probability maps of weed infestation. The primary variable was obtained by grid weed density field samplings, and the secondary variables were derived from UAV imagery acquired the same day as the weed field surveys. Kriging and cokriging with UAV-derived variables that displayed a strong correlation with weed density were used to compare C. diluta density mapping performance. The accuracy of the predictions was assessed by cross-validation. Cokriging with UAV-derived secondary variables generated more accurate weed density maps with a lower RMSE compare with kriging and cokriging with RVI, NDVI, ExR, and ExR(2) (the best methods for the prediction of knapweed density). Cokriged estimates were used to generate probability maps for risk assessment when implementing site-specific weed control by indicator kriging. This multivariate geostatistical approach enabled the delineation of winter wheat fields into two zones for different prescription treatments according to the C. diluta density and the economic threshold.

Description: Significant advances in weed mapping from unmanned aerial platforms have been achieved in recent years. The detection of weed location has made possible the generation of site specific weed treatments to reduce the use of herbicides according to weed cover maps. However, the characterization of weed infestations should not be limited to the location of weed stands, but should also be able to distinguish the types of weeds to allow the best possible choice of herbicide treatment to be applied. A first step in this direction should be the discrimination between broad-leaved (dicotyledonous) and grass (monocotyledonous) weeds. Considering the advances in weed detection based on images acquired by unmanned aerial vehicles, and the ability of neural networks to solve hard classification problems in remote sensing, these technologies have been merged in this study with the aim of exploring their potential for broadleaf and grass weed detection in wide-row herbaceous crops such as sunflower and cotton. Overall accuracies of around 80% were obtained in both crops, with user accuracy for broad-leaved and grass weeds around 75% and 65%, respectively. These results confirm the potential of the presented combination of technologies for improving the characterization of different weed infestations, which would allow the generation of timely and adequate herbicide treatment maps according to groups of weeds.