Search

National and international Vitis variety catalogues can be used as image datasets for computer vision in viticulture. These databases archive ampelographic features and phenology of several grape varieties and plant structures images (e.g. leaf, bunch, shoots). Although these archives represent a potential database for computer vision in viticulture, plant structure images are acquired singularly and mostly not directly in the vineyard. Localization computer vision models would take advantage of multiple objects in the same image, allowing more efficient training. The present images and labels dataset was designed to overcome such limitations and provide suitable images for multiple cluster identification in white grape varieties. A group of 373 images were acquired from later view in vertical shoot position vineyards in six different Italian locations at different phenological stages. Images were then labelled in YOLO labelling format. The dataset was made available both in terms of images and labels. The real number of bunches counted in the field, and the number of bunches visible in the image (not covered by other vine structures) was recorded for a group of images in this dataset.

The famous empirical model for the horizontal force estimation of farm implements was issued by the American Society of Agricultural Biological Engineers (ASABE). It relies on information on soil texture through its soil texture adjustment parameter, which is called the Fi -parameter. The Fi-parameter is not measurable, and the geometry of the plow through the machine parameter values are not measurable; however, the tillage speed, implement width, and tillage depth are measurable. In this study, the Fi-parameter was calibrated using a regression technique based on a soil texture norm that combines the sand, silt, and clay contents of a soil with R2 of 0.703. A feed-forward artificial neural network (ANN) with a backpropagation algorithm for training purposes was established to estimate the modified values of the horizontal force based on four inputs: working field criterion, soil texture norm, initial soil moisture content, and the horizontal force (which was estimated by the ASABE standard using the new—Fi-parameter). Our developed ANN model had high values for the coefficient of determination (R2) and their values in the training, testing, and validation stages were 0.8286, 0.8175, and 0.8515, respectively that demonstrated the applicability for the prediction of the modified horizontal forces. An Excel spreadsheet was created using the weights of the established ANN model to estimate the values of the horizontal force of specific tillage implements, such as a disk, chisel, or moldboard plows. The Excel spreadsheet was tested using data for a moldboard plow; in addition, a good prediction of the required horizontal force with a percentage error of 10% was achieved. The developed Excel spreadsheet contributed toward a numerical method that can be used by agricultural engineers in the future. Furthermore, we also concluded that the equations presented in this study can be formulated by any of computer language to create a simulation program to predict the horizontal force requirements of a tillage implement.

Aim: The recent availability of Sentinel-2 satellites has led to an increasing interest in their use in viticulture. The aim of this short communication is to determine performance and limitation of a Sentinel-2 vegetation index in precision viticulture applications, in terms of correlation and variability assessment, compared to the same vegetation index derived from an unmanned aerial vehicle (UAV). Normalised difference vegetation index (NDVI) was used as reference vegetation index. Methods and Results: UAV and Sentinel-2 vegetation indices were acquired for 30 vineyard blocks located in the south of France without inter-row grass. From the UAV imagery, the vegetation index was calculated using both a mixed pixels approach (both vine and inter-row) and from pure vine-only pixels. In addition, the vine projected area data were extracted using a support vector machine algorithm for vineyard segmentation. The vegetation index was obtained from Sentinel-2 imagery obtained at approximately the same time as the UAV imagery. The Sentinel-2 images used a mixed pixel approach as pixel size is greater than the row width. The correlation between these three layers and the Sentinel-2 derived vegetation indices were calculated, considering spatial autocorrelation correction for the significance test. The Gini coefficient was used to estimate variability detected by each sensor at the within-field scale. The effects of block border and dimension on correlations were estimated. Conclusions: The comparison between Sentinel-2 and UAV vegetation index showed an increase in correlation when border pixels were removed. Block dimensions did not affect the significance of correlation unless blocks were < 0.5 ha. Below this threshold, the correlation was non-significant in most cases. Sentinel-2 acquired data were strongly correlated with UAV-acquired data at both the field (R2 = 0.87) and sub-field scale (R2 = 0.84). In terms of variability detected, Sentinel-2 proved to be able to detect the same amount of variability as the UAV mixed pixel vegetation index. Significance and impact of the study: This study showed at which field conditions the Sentinel-2 vegetation index can be used instead of UAV-acquired images when high spatial resolution (vine-specific) management is not needed and the vineyard is characterised by no inter-row grass. This type of information may help growers to choose the most appropriate information sources to detect variability according to their vineyard characteristics.

Over the last few years, several Convolutional Neural Networks for object detection have been proposed, characterised by different accuracy and speed. In viticulture, yield estimation and prediction is used for efficient crop management, taking advantage of precision viticulture techniques. Convolutional Neural Networks for object detection represent an alternative methodology for grape yield estimation, which usually relies on manual harvesting of sample plants. In this paper, six versions of the You Only Look Once (YOLO) object detection algorithm (YOLOv3, YOLOv3-tiny, YOLOv4, YOLOv4-tiny, YOLOv5x, and YOLOv5s) were evaluated for real-time bunch detection and counting in grapes. White grape varieties were chosen for this study, as the identification of white berries on a leaf background is trickier than red berries. YOLO models were trained using a heterogeneous dataset populated by images retrieved from open datasets and acquired on the field in several illumination conditions, background, and growth stages. Results have shown that YOLOv5x and YOLOv4 achieved an F1-score of 0.76 and 0.77, respectively, with a detection speed of 31 and 32 FPS. Differently, YOLO5s and YOLOv4-tiny achieved an F1-score of 0.76 and 0.69, respectively, with a detection speed of 61 and 196 FPS. The final YOLOv5x model for bunch number, obtained considering bunch occlusion, was able to estimate the number of bunches per plant with an average error of 13.3% per vine. The best combination of accuracy and speed was achieved by YOLOv4-tiny, which should be considered for real-time grape yield estimation, while YOLOv3 was affected by a False Positive–False Negative compensation, which decreased the RMSE.

Defining the most profitable remote sensing platforms is a difficult decision-making process, as it requires agronomic and economic considerations. In this paper, the price and profitability of three levels of remote sensing platforms were evaluated to define a decision-making process. Prices of satellite, plane and UAV-acquired vegetation indices were collected in Italy during 2020 and compared to the economic benefits resulting from variable rate nitrogen application, according to a bibliographic meta-analysis performed on grains. The quality comparison of these three technologies was performed considering the error propagation in the NDVI formula. The errors of the single bands were used to assess the optical properties of the sensors. Results showed that medium-resolution satellite data with good optical properties could be profitably used for variable rate nitrogen applications starting from 2.5 hectares, in case of medium resolution with good optical properties. High-resolution satellites with lower optical quality were profitable starting from 13.2 hectares, while very high-resolution satellites with good optical properties could be profitably used starting from 76.8 hectares. Plane-acquired images, which have good optical properties, were profitable starting from 66.4 hectares. Additionally, a reference model for satellite image price is proposed.

Sensor applications are impacting the everyday objects that enhance human life quality. In this special issue, the main objective was to address recent advances of sensor applications in agriculture covering a wide range of topics in this field. A total of 14 articles were published in this special issue where nine of them were research articles, two review articles and two technical notes. The main topics were soil and plant sensing, farm management and post-harvest application. Soil-sensing topics include monitoring soil moisture content, drain pipes and topsoil movement during the harrowing process while plant-sensing topics include evaluating spray drift in vineyards, thermography applications for winter wheat and tree health assessment and remote-sensing applications as well. Furthermore, farm management contributions include food systems digitalization and using archived data from plowing operations, and one article in post-harvest application in sunflower seeds.

Harrowing is a process that reduces the size of soil clods and prepares the field for seeding. Rotary harrows are a common piece of equipment in North Italy that consists of teeth rotating around a vertical axis with a processing depth of 5−15 cm. In this study, the topsoil movement in terms of distance and direction were estimated at different rotary harrow working conditions. A total of eight tests was performed using two forward speeds of 1 and 3 km/h, two working depths of 6 and 10 cm and two levelling bar positions of 0 and 10 cm from the ground. In order to simulate and follow topsoil movement, Radio-Frequency Identification (RFID) tags were inserted into cork stoppers and distributed in a regular pattern over the soil. Tags were distributed in six lines along the working width and repeated in three rows for each test: a total number of 144 tags was tracked. Results showed that there were no significant differences between the performed tests, on the other hand the reported tests highlight the effectiveness of the RFID monitoring approach.