An important area in precision agriculture is related to the efficient use of chemicals applied onto fields. Efforts have been made to diminish their use, aiming at cost reduction and fewer chemical residues in the final agricultural products. The use of unmanned aerial vehicles (UAVs) presents itself as an attractive and cheap alternative for spraying pesticides and fertilizers compared to conventional mass spraying performed by ordinary manned aircraft. Besides being cheaper than manned aircraft, small UAVs are capable of performing fine-grained instead of the mass spraying. Observing this improved method, this paper reports the design of an embedded real-time UAV spraying control system supported by onboard image processing. The proposal uses a normalized difference vegetation index (NDVI) algorithm to detect the exact locations in which the chemicals are needed. Using this information, the automated spraying control system performs punctual applications while the UAV navigates over the crops. The system architecture is designed to run on low-cost hardware, which demands an efficient NDVI algorithm. The experiments were conducted using Raspberry Pi 3 as the embedded hardware. First, experiments in a laboratory were conducted in which the algorithm was proved to be correct and efficient. Then, field tests in real conditions were conducted for validation purposes. These validation tests were performed in an agronomic research station with the Raspberry hardware integrated into a UAV flying over a field of crops. The average CPU usage was about 20% while memory consumption was about 70 MB for high definition images, with 4% CPU usage and 20.3 MB RAM being observed for low-resolution images. The average current measured to execute the proposed algorithm was 0.11 A. The obtained results prove that the proposed solution is efficient in terms of processing and energy consumption when used in embedded hardware and provides measurements which are coherent with the commercial GreenSeeker equipment.

Remote biomass estimation can benefit agricultural practices in several ways, especially larger areas since it does not require local measurements. The advances of the last few decades in machine learning techniques have created new possibilities for estimating aboveground biomass. A pipeline was established from image acquisition to modelling shoot biomass of two wheat cultivars used in Southern Brazil (TBIO Toruk and BRS Parrudo). A UAV was used to acquire multispectral images with high spatial resolution to calculate vegetation indices (VIs). These VIs along with machine learning approaches are used to model the measured biomass of crops in different growth phases. To correlate the wheat images with measured shoot dry biomass, the following regression models were investigated: random forest, support vector regression, and artificial neural networks. An experiment was designed and conducted at the Agriculture Experimental Station of the Federal University of Rio Grande do Sul (EEA/UFRGS) to assess wheat growth. Variability in crop growth was created for all test areas by varying nitrogen availability. To determine shoot biomass, plants were sampled at three different crop growth stages: V6 (stage of six fully developed leaves), three nodes, and flowering. Our results indicate the importance of the radiometric calibration used. Also, the features extracted from images, such as the VIs combined with machine learning models can be used in precision agriculture for predicting the spatial variability of shoot biomass. The best model for Brazilian wheat cultivars was an artificial neural network with $R^2$ of 0.90, RMSE of 0.83t/ha, and nRMSE of 8.95%. We also found a strong correlation between ground NDVI with image-based NDVI, with an $R^2$ of 0.84.

RESUMO: Em decorrência da instabilidade da produtividade das principais culturas associada ao déficit hídrico, tem se tornado cada vez mais frequente a necessidade do uso de tecnologias como a irrigação e a agricultura de precisão (AP). O presente trabalho objetivou avaliar a variabilidade espacial da produtividade de grãos de milho e sua correlação com variáveis explicativas de planta em área irrigada. O estudo foi conduzido nas safras agrícolas 2010/2011 e 2011/2012, em área de 35ha, manejada em sistema plantio direto e irrigação por pivô central. Os componentes de produtividade e a produtividade de grãos foram avaliados seguindo uma malha amostral de 100x100m. A produtividade de grãos e a maior parte dos componentes de produtividade apresentaram baixa dispersão dos dados, condicionando a normalidade dos dados. A produtividade de grãos, mesmo com a irrigação, apresentou elevada variabilidade espacial. Na análise de trilha, verificaram-se altos coeficientes de determinação dos componentes de produtividade com a produtividade de grãos.

Biomass production and nitrogen (N) accumulated in wheat shoots may be used for quantifying optimal topdressing nitrogen doses. The objective of this study was to develop and validate models for estimating the amount of biomass and nitrogen accumulated in shoots and the N topdressing dose of maximum technical efficiency in wheat using the normalized difference vegetation index (NDVI) measured by an active optical canopy sensor. Field experiments were carried out in two years and treatments consisted of N doses applied at plant emergence and as topdressing. NDVI, shoot biomass and N accumulated in shoots at the growth stage of six fully expanded leaves and grain yield were evaluated, being determined the topdressing N dose of maximum technical efficiency (DMTE). The NDVI was positively correlated to shoot biomass and N content in shoots and models for the relationship between these variables were developed and validated. The DMTE was negatively correlated with the NDVI value evaluated at the moment of N topdressing application. Thus, NDVI evaluation by an active optical canopy sensor can be used for nitrogen fertilization in variable rate, allowing the adjustment of applied N doses in different areas within a field.

Nitrogen (N) is a dynamic element in the soil, so new nitrogen fertilization alternatives are required as a way of maximizing its efficiency. Besides, vegetation sensors are a way to assess and manage the nutritional demands of plants. This study aimed to evaluate the effect of nitrogen sources on photosynthetic pigments and their correlation with corn grain yield and dry biomass. The experiment was carried out in a randomized block design with nitrogen sources (mineral, organic and biological). Contents of chlorophyll a, b and total, as well as carotenoids, were evaluated. The chlorophyll indices evaluated by both methods were positively correlated with each other and with the grain yield per plant. Nitrogen fertilization 100 % mineral was superior, when compared to the other treatments, with increments of up to 44 %. There was a positive relationship between the methods of determining and estimating the chlorophyll contents. The grain yield per plant showed the highest values when using the 100 % mineral fertilizer source, with increments above 10 %, in relation to the other sources, spending US$ 89.77 on fertilizer and earning over US$ 538.60 on grain yield. There was a positive correlation between the photosynthetic pigments obtained by both methods and grain yield per plant. Both methods are recommended for the evaluation of chlorophyll concentrations.

RESUMO - A estimativa do potencial produtivo da cultura do milho ao longo do ciclo de desenvolvimento é uma das novas práticas agrícolas que vêm sendo utilizadas para qualificar o manejo da cultura. Neste sentido, destaca-se a inserção de sensores de vegetação, com a finalidade de realizar o monitoramento do desenvolvimento e da condição nutricional da cultura ao longo do seu ciclo. O objetivo do presente trabalho foi determinar os limites críticos do Índice de vegetação por diferença normalizada (NDVI) para a determinação de classes de potencial produtivo do milho em diferentes estádios fenológicos, utilizando sensor óptico ativo de vegetação (Greenseeker). O experimento foi conduzido na EEA/UFRGS, durante a safra agrícola 2013/2014. Os tratamentos consistiram de diferentes épocas de dessecação da aveia branca (Avena sativa L.) antes da semeadura da cultura do milho. As avaliações com o sensor óptico ativo foram realizadas nos estádios fenológicos V3, V5, V6, V7 e V8. Os resultados mostraram que o NDVI medido pelo sensor Greenseeker foi eficiente na predição da produtividade de milho em diferentes estádios fenológicos. Os limites críticos de NDVI, os quais correspondem a diferentes classes de potencial produtivo, podem ser identificados de maneira rápida e precisa entre os estádios fenológicos V3 a V8 e esta informação pode ser empregada para a adubação nitrogenada em taxa variável de acordo com o potencial produtivo estimado. Palavras-chave: Greenseeker, índice de vegetação, Zea mays, NDVI. CRITICAL LIMITS OF NDVI FOR YIELD POTENTIAL ESTIMATION IN MAIZE ABSTRACT - The estimation of grain yield potential of maize along the growth cycle is one of new agricultural practices that have been used to qualify crop management. In this sense, the use of vegetation sensors can be highlighted, in order to carry out the monitoring of plant development and nutritional condition throughout its development. The objective of this study was to indicate NDVI critical limits for determining grain yield potential classes of maize in different growth stages using an active optical vegetation sensor (Greenseeker). The experiment was carried out in the 2013/14 growing season, in Eldorado do Sul, State of Rio Grande do Sul, southern Brazil. Treatments consisted of different dissecation timing of oat (Avena sativa L.) before corn sowing. Evaluations with the active optical sensor were done at growth stages V3, V5, V6, V7, and V8. Results showed that NDVI measured by the sensor Greenseeker was efficient in identifying maize grain productivity at different growth stages. NDVI critical limits that correspond to different yield potential levels in maize can be quickly and precisely identified between V3 and V8 growth stages and this information can be used for site-specific nitrogen fertilization according to the estimated yield potential. Keywords: Greenseeker, vegetation index, Zea mays, NDVI.