Inovação tecnológica de boas práticas agrícolas e a informática na gestão agropecuária

This study aims to develop innovative proposals for production agriculture management and plans to build a participatory model, through the digital inclusion of members of the family farm gathered in a cooperative venture seeking to establish new environmental management efficiency for household production. The first part of the hypothesis assumes that a major obstacle to the insertion of small family farms into the markets is skilled labor, human capital. A training model has been developed for traceability and tracking activities on family farms, based on the atemoya culture. The second hypothesis predicts that it is possible to create a model that is scientifically supported by widely accepted rules derived from GlobalGAP standard certification, a global benchmark for good agricultural practices. Using these rules the model seeks to achieve the traceability of agricultural products and operations from the preservation of identity information within the production chain. The results obtained by the computerized system confirmed the presented hypotheses by demonstrating that technological innovation through intensive communication and information technologies education as well as other associated forms are important drivers of regional development, especially if implemented through a digital inclusion project using the state program Infocentros Access São Paulo.

Planificación de trayectorias bi-objetivo en robótica aérea para agricultura de precisión

Este trabajo presenta las experiencias y resultados obtenidos al aplicar tecnicas de planificacion de trayectorias para vehıculos aereos no tripulados con el objetivo doble de tomar imagenes aereas de alta resolucion para realizar mosaicos de cultivos asi como recoger los datos recopilados por motas o sistemas sensoriales inalambricos con capacidad de crear y gestionar redes. Dichas redes son utilizadas para la monitorizacion y evaluacion de tendencias en variables como la temperatura o humedad.

Sistema de aconselhamento de aplicação de produtos fitofarmacêuticos

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Desenvolvimento de um sistema computacional para tratamento de dados meteorológicos no setor de agroenergia

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Toward Multi-Scale Object-Based Data Fusion

This paper proposes a new methodology for object based 2-D data fu- sion, with a multiscale character. This methodology is intended to be use in agriculture, specifically in the characterization of the water status of different crops, so as to have an appropriate water management at a farm-holding scale. As a first approach to its evaluation, vegetation cover vigor data has been integrated with texture data. For this purpose, NDVI maps have been calculated using a multispectral image and Lacunarity maps from the panchromatic image. Preliminary results show this methodology is viable in the integration and management of large volumes of data, which characterize the behavior of agricultural covers at farm-holding scale.

A waypoint-based mission planner for a farmland coverage with an aerial robot - a precision farming tool

Remote sensing (RS) with aerial robots is becoming more usual in every day time in Precision Agriculture (PA) practices, do to their advantages over conventional methods. Usually, available commercial platforms providing off-the-shelf waypoint navigation are adopted to perform visual surveys over crop fields, with the purpose to acquire specific image samples. The way in which a waypoint list is computed and dispatched to the aerial robot when mapping non empty agricultural workspaces has not been yet discussed. In this paper we propose an offline mission planner approach that computes an efficient coverage path subject to some constraints by decomposing the environment approximately into cells. Therefore, the aim of this work is contributing with a feasible waypoints-based tool to support PA practices

Grapevine Yield and Leaf Area Estimation Using Supervised Classification Methodology on RGB Images Taken under Field Conditions

The aim of this research was to implement a methodology through the generation of a supervised classifier based on the Mahalanobis distance to characterize the grapevine canopy and assess leaf area and yield using RGB images. The method automatically processes sets of images, and calculates the areas (number of pixels) corresponding to seven different classes (Grapes, Wood, Background, and four classes of Leaf, of increasing leaf age). Each one is initialized by the user, who selects a set of representative pixels for every class in order to induce the clustering around them. The proposed methodology was evaluated with 70 grapevine (V. vinifera L. cv. Tempranillo) images, acquired in a commercial vineyard located in La Rioja (Spain), after several defoliation and de-fruiting events on 10 vines, with a conventional RGB camera and no artificial illumination. The segmentation results showed a performance of 92% for leaves and 98% for clusters, and allowed to assess the grapevine’s leaf area and yield with R2 values of 0.81 (p < 0.001) and 0.73 (p = 0.002), respectively. This methodology, which operates with a simple image acquisition setup and guarantees the right number and kind of pixel classes, has shown to be suitable and robust enough to provide valuable information for vineyard management.

Tractor PT: A traction prediction software for agricultural tractor

Traction prediction modelling, a key factor in farm tractor design, has been driven by the need to find the answer to this question without having to build physical prototypes. A wide range of theories and their respective algorithms can be used in such predictions. The “Tractors and Tillage” research team at the Polytechnic University of Madrid, which engages, among others, in traction prediction for farm tractors, has developed a series of programs based on the cone index as the parameter representative of the terrain. With the software introduced in the present paper, written in Visual Basic, slip can be predicted in two- and four-wheel drive tractors using any one of four models. It includes databases for tractors, front tyres, rear tyres and working conditions (soil cone index and drawbar pull exerted). The results can be exported in spreadsheet format.

SIMLIDAR Simulation of LiDAR performance in artificially simulate orchards

SIMLIDAR is an application developed in Cþþ that generates an artificial orchard using a Lindenmayer system. The application simulates the lateral interaction between the artificial orchard and a laser scanner or LIDAR (Light Detection and Ranging). To best highlight the unique qualities of the LIDAR simulation, this work focuses on apple trees without leaves, i.e. the woody structure. The objective is to simulate a terrestrial laser sensor (LIDAR) when applied to different artificially created orchards and compare the simulated characteristics of trees with the parameters obtained with the LIDAR. The scanner is mounted on a virtual tractor and measures the distance between the origin of the laser beam and the nearby plant object. This measurement is taken with an angular scan in a plane which is perpendicular to the route of the virtual tractor. SIMLIDAR determines the distance measured in a bi-dimensional matrix N M, where N is the number of angular scans and M is the number of steps in the tractor route. In order to test the data and performance of SIMLIDAR, the simulation has been applied to 42 different artificial orchards. After previously defining and calculating two vegetative parameters (wood area and wood projected area) of the simulated trees, a good correlation (R2 ¼ 0.70e0.80) was found between these characteristics and the wood area detected (impacted) by the laser beam. The designed software can be valuable in horticulture for estimating biomass and optimising the pesticide treatments that are performed in winter.

Rediseño del marco de siembra en el cultivo de maíz forrajero

El marco de siembra tradicional del maíz forrajero está condicionado por el ancho de las ruedas del tractor, en el cual la separación entre filas de siembra es cinco veces la separación entre plantas, lo que genera una baja competencia con malas hierbas ya que el cultivo tarda mucho tiempo en cubrir completamente el suelo. Los nuevos prototipos de micromáquinas que se están diseñando para los tratamientos herbicidas de post-emergencia en maíz facilitarían la modificación del marco de siembra. El objetivo de este ensayo ha sido comprobar la eficacia de nuevos marcos de siembra de maíz forrajero, habiéndose estudiado su respuesta en Madrid y Copenhague.

Risk analysis for UAV safe operations: a rationalization for an agricultural environment

The road to the automation of the agricultural processes passes through the safe operation of the autonomous vehicles. This requirement is a fact in ground mobile units, but it still has not well defined for the aerial robots (UAVs) mainly because the normative and legislation are quite diffuse or even inexistent. Therefore, to define a common and global policy is the challenge to tackle. This characterization has to be addressed from the field experience. Accordingly, this paper presents the work done in this direction, based on the analysis of the most common sources of hazards when using UAV's for agricultural tasks. The work, based on the ISO 31000 normative, has been carried out by applying a three-step structure that integrates the identification, assessment and reduction procedures. The present paper exposes how this method has been applied to analyze previous accidents and malfunctions during UAV operations in order to obtain real failure causes. It has allowed highlighting common risks and hazardous sources and proposing specific guards and safety measures for the agricultural context.

Automatic detection of crop rows in maize fields with high weeds pressure

This paper proposes a new method, oriented to crop row detection in images from maize fields with high weed pressure. The vision system is designed to be installed onboard a mobile agricultural vehicle, i.e. submitted to gyros, vibrations and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of three main processes: image segmentation, double thresholding, based on the Otsu’s method, and crop row detection. Image segmentation is based on the application of a vegetation index, the double thresholding achieves the separation between weeds and crops and the crop row detection applies least squares linear regression for line adjustment. Crop and weed separation becomes effective and the crop row detection can be favorably compared against the classical approach based on the Hough transform. Both gain effectiveness and accuracy thanks to the double thresholding that makes the main finding of the paper.

Crop row detection in maize fields inspired on the human visual perception

This paper proposes a new method, oriented to image real-time processing, for identifying crop rows in maize fields in the images. The vision system is designed to be installed onboard a mobile agricultural vehicle, that is, submitted to gyros, vibrations, and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of two main processes: image segmentation and crop row detection. The first one applies a threshold to separate green plants or pixels (crops and weeds) from the rest (soil, stones, and others). It is based on a fuzzy clustering process, which allows obtaining the threshold to be applied during the normal operation process. The crop row detection applies a method based on image perspective projection that searches for maximum accumulation of segmented green pixels along straight alignments. They determine the expected crop lines in the images. The method is robust enough to work under the above-mentioned undesired effects. It is favorably compared against the well-tested Hough transformation for line detection.

Anàlisi i disseny eCommerce : Productes de Casa, venda de productes de la agricultura catalana

El projecte que és trobarà a continuació consisteix en l’anàlisi i desenvolupament d’una aplicació web orientada al comerç electrònic per un client que distribueix productes relacionats amb l’agricultura catalana. Aquest client ens planteja una idea respecte al model de negoci, i ens demana la realització tant de la part de Programació, com la part de documentació necessària per que pugui ser fàcil de mantenir en futures versions del software i tindre un bon punt de partida per a futures versions.