Apresentando um papel de destaque no cenário nacional e internacional, o eucalipto possui rápido crescimento, alta produtividade, ampla diversidade de espécies, grande capacidade de adaptação e é aplicado em diferentes processos industriais, como por exemplo, produção de madeira, celulose e papel. No Brasil existem extensas áreas plantadas, principalmente nos estados de Minas Gerais, São Paulo e Paraná. Entretanto, eucaliptos são suscetíveis a doenças e pragas, o que pode trazer grandes prejuízo aos produtores. Tendo em vista esse contexto, surge a necessidade de detectar e diagnosticar doenças prematuramente, permitindo um combate ais eficaz e preciso a essas patologias. Visto que as plantações de eucalipto cobrem áreas muito extensas, o uso de VANTs (Veículos Aéreos Não-Tripulados) pode agilizar o processo de monitoramento, uma vez que podem sobrevoar grandes distâncias em pouco tempo. Sendo assim, esse trabalho desenvolveu um sistema de diagnóstico automático de doenças de eucalipto. Baseando-se em técnicas de detecção de ataques digitais, o diagnóstico é feito comparando assinaturas espectrais de plantas doentes com assinaturas conhecidas armazenadas em uma base de dados seguindo um modelo de assinaturas espectrais inspirado em um modelo de assinaturas de ataque. O sistema foi desenvolvido e validade utilizando dados de espectroradiômetros, apresentando precisão de até 96% em alguns casos. / Eucalyptus has played an important economic roll wordwide. It has rapid growth, high yield, wide species diversity, great adaptability and it is used in different industrial processes such as cellulose and paper production. However, Eucalyptus is susceptible to diseases and plagues, which could bring heavy damage to the plantations. In view of the importance of the production of Eucalyptus, the dimensions of the planted areas and of the possibility to increase yield, there is a need to detect and identify the pathologies effecting the trees. Since Eucalyptus plantations can cover a very extensive area, the use of UAVs (Unmanned Aerial Vehicles) can drastically speed up the process of monitoring the crop, as they can survey very large areas in very little time. Thus, this project aims to develop a system that automatically diagnoses eucalyptus diseases. Using techniques of digital intrusion detection, the diagnostic is made by comparing the spectral signature of disease plants with know signatures stored on a database following a signature model also proposed in this project. The system was developed and validated by usin data from spectroradiometers, showing a accuracies as high as 96% in some cases.

Tese de mestrado. Mestrado integrado em Engenharia Electrotécnica e de Computadores. Faculdade de Engenharia. Universidade do Porto. 2012

Philosophiae Doctor - PhD / Unmanned Aerial Vehicles (UAVs) have recently o ered signi cant technological achievements. The advancement in related applications predicts an extended need for automated data muling by UAVs, to explore high risk places, ensure e ciency and reduce the cost of various products and services. Due to advances in technology, the actual UAVs are not as expensive as they once were. On the other hand, they are limited in their ight time especially if they have to use fuel. As a result, it has recently been proposed that they could be assisted by the ground static sensors which provide information of their surroundings. Then, the UAVs need only to provide actions depending on information received from the ground sensors. In addition, UAVs need to cooperate among themselves and work together with organised ground sensors to achieve an optimal coverage. The system to handle the cooperation of UAVs, together with the ground sensors, is still an interesting research topic which would bene t both rural and urban areas. In this thesis, an e cient ground sensor network for optimal UAVs coverage is rst proposed. This is done using a clustering scheme wherein, each cluster member transmits its sensor readings to its cluster head. A more e cient routing scheme for delivering readings to cluster head(s) for collection by UAVs is also proposed. Furthermore, airborne sensor deployment models are provided for e cient data collection from a unique sensor/target. The model proposed for this consists of a scheduling technique which manages the visitation of UAVs to target. Lastly, issues relating to the interplay between both types of sensor (airborne and ground/underground) networks are addressed by proposing the optimal UAVs task allocation models; which take caters for both the ground networking and aerial deployment. Existing network and tra c engineering techniques were adopted in order to handle the internetworking of the ground sensors. UAVs deployment is addressed by adopting Operational Research techniques including dynamic assignment and scheduling models. The proposed models were validated by simulations, experiments and in some cases, formal methods used to formalise and prove the correctness of key properties.

Apresentando um papel de destaque no cenário nacional e internacional, o eucalipto possui rápido crescimento, alta produtividade, ampla diversidade de espécies, grande capacidade de adaptação e é aplicado em diferentes processos industriais, como por exemplo, produção de madeira, celulose e papel. No Brasil existem extensas áreas plantadas, principalmente nos estados de Minas Gerais, São Paulo e Paraná. Entretanto, eucaliptos são suscetíveis a doenças e pragas, o que pode trazer grandes prejuízo aos produtores. Tendo em vista esse contexto, surge a necessidade de detectar e diagnosticar doenças prematuramente, permitindo um combate ais eficaz e preciso a essas patologias. Visto que as plantações de eucalipto cobrem áreas muito extensas, o uso de VANTs (Veículos Aéreos Não-Tripulados) pode agilizar o processo de monitoramento, uma vez que podem sobrevoar grandes distâncias em pouco tempo. Sendo assim, esse trabalho desenvolveu um sistema de diagnóstico automático de doenças de eucalipto. Baseando-se em técnicas de detecção de ataques digitais, o diagnóstico é feito comparando assinaturas espectrais de plantas doentes com assinaturas conhecidas armazenadas em uma base de dados seguindo um modelo de assinaturas espectrais inspirado em um modelo de assinaturas de ataque. O sistema foi desenvolvido e validade utilizando dados de espectroradiômetros, apresentando precisão de até 96% em alguns casos. / Eucalyptus has played an important economic roll wordwide. It has rapid growth, high yield, wide species diversity, great adaptability and it is used in different industrial processes such as cellulose and paper production. However, Eucalyptus is susceptible to diseases and plagues, which could bring heavy damage to the plantations. In view of the importance of the production of Eucalyptus, the dimensions of the planted areas and of the possibility to increase yield, there is a need to detect and identify the pathologies effecting the trees. Since Eucalyptus plantations can cover a very extensive area, the use of UAVs (Unmanned Aerial Vehicles) can drastically speed up the process of monitoring the crop, as they can survey very large areas in very little time. Thus, this project aims to develop a system that automatically diagnoses eucalyptus diseases. Using techniques of digital intrusion detection, the diagnostic is made by comparing the spectral signature of disease plants with know signatures stored on a database following a signature model also proposed in this project. The system was developed and validated by usin data from spectroradiometers, showing a accuracies as high as 96% in some cases.

Using drones for cellular coverage enhancement is a recent technology that has shown a great potential in various practical scenarios. However, one of the main challenges that limits the performance of drone-enabled wireless networks is the limited flight time. In particular, due to the limited on-board battery size, the drone needs to frequently interrupt its operation and fly back to a charging station to recharge/replace its battery. In addition, the charging station might be responsible to recharge multiple drones. Given that the charging station has limited capacity, it can only serve a finite number of drones simultaneously. Hence, in order to accurately capture the influence of the battery limitation on the performance, it is required to analyze the dynamics of the time spent by the drones at the charging stations. In this thesis, we first use tools from queuing theory and stochastic geometry to study the influence of each of the charging stations limited capacity and spatial density on the performance of a drone-enabled wireless network. We then extend our work to rural areas where users are greatly impacted by low income, high cost of backhaul connectivity, and limited resources. Considering the limitation of the electricity supply scarcity in some rural regions, we investigate the possibility and performance enhancement of the deployment of renewable energy (RE) charging stations. We outline three practical scenarios, and use simulation results to demonstrate that RE charging stations can be a possible solution to address the limited on-board battery of UAVs in rural areas, specially when they can harvest and store enough energy.

Fusarium virguliforme is a soil-borne pathogen that is the causal agent of sudden death syndrome (SDS). This disease is one of the top contributors to major yield losses in soybean across the United States. Characteristic symptoms of the disease include interveinal chlorosis and/or necrosis of trifoliate leaves and defoliation. In some cases, the foliar symptoms may not be present, but yield loss still occurs. This disease is evaluated using an incidence rating, the percent of plants in the plot that are expressing symptoms, and a severity rating, using a one to nine scale based on varying levels of chlorosis, necrosis, and defoliation. Using remote sensing provides an alternate approach to identify and evaluate plant diseases. It provides a non-destructive method to assess the severity of foliar symptoms and their distribution across production fields. SDS was chosen as the disease to use for this system due to the unique disease symptomology and yield loss. In 2019 and 2020, SDS trials were established in a production field location that has a history of SDS in Valmeyer, IL. This seed treatment study had different chemicals with varying levels of efficacy against SDS. Disease ratings were collected at the first sign of symptoms, and aerial imagery was collected on the same day. There were multiple dates across both years when this data was collected. ArcGIS was used to analyze the multispectral imagery and do a plot by plot analysis for each of the plots. A regression analysis was performed to test the relationship between the foliar disease ratings and the plot data collected from the multispectral imagery. Multiple vegetation indices were tested, and the results showed that overall, in 2019, GNDVI had the strongest relationship with foliar ratings. In 2020, NDRE had the strongest overall relationship with foliar ratings. The relationship between NDVI and the ratings was the most consistent at the last rating of the season.

Unmanned Aerial Vehicles (UAVs) are increasingly becoming economical platforms for carrying a variety of sensors. Building flight plans that place sensors properly, temporally and spatially, is difficult. The goal of sensor-driven planning is to automatically generate flight plans based on desired sensor placement and temporal constraints. We propose a simple taxonomy of UAV-enabled sensors, identify a set of generic sensor tasks, and argue that many real-world tasks can be represented by the taxonomy. We present a hierarchical sensor-driven flight planning system capable of generating 2D flights that satisfy desired sensor placement and complex timing and dependency constraints. The system makes use of several well-known planning algorithms and includes a user interface. We conducted a user study to show that sensor-driven planning can be used by non-experts, that it is easier for non-experts than traditional waypoint-based planning, and that it produces better flights than waypoint-based planning. The results of our user study experiment support the claims that sensor-driven planning is usable and that it produces better flights.

No description available.

This thesis details out a system developed with objective of conducting cooperative search operation in a partially-known environment, with a human operator, and two Unmanned Aerial Vehicles (UAVs) with nadir, and front on-board cameras. The system uses two phases of flight operations, where the first phase is aimed at gathering latest overhead images of the environment using a UAV’s nadir camera. These images are used to generate and update representations of the environment including 3D reconstruction, mosaic image, occupancy image, and a network graph. During the second phase of flight operations, a human operator marks multiple areas of interest for closer inspection on the mosaic generated in previous step, displayed via a UI. These areas are used by the path planner as visitation goals. The two-step path planner, which uses network graph, utilizes the weighted-A* planning, and Travelling Salesman Problem’s solution to compute an optimal visitation plan. This visitation plan is then converted into Mission waypoints for a second UAV, and are communicated through a navigation module over a MavLink connection. A UAV flying at low altitude, executes the mission plan, and streams a live video from its front-facing camera to a ground station over a wireless network. The human operator views the video on the ground station, and uses it to locate the target object, culminating the mission. / Master of Science / This thesis details out the work focused on developing a system capable of conducting search operation in an environment where prior information has been rendered outdated, while allowing human operator, and multiple robots to cooperate for the search. The system operation is divided into two phases of flight operations, where the first operation focuses on gathering the current information using a camera equipped unmanned aircraft, while the second phase involves utilizing the human operator’s instinct to select areas of interest for a close inspection. It is followed by a flight operation using a second unmanned aircraft aimed at visiting the selected areas and gathering detailed information. The system utilizes the data acquired through first phase, and generates a detailed map of the target environment. In the second phase of flight operations, a human uses the detailed map, and marks the areas of interest by drawing over the map. This allows the human operator to guide the search operation. The path planner generates an optimal plan of visitation which is executed by the second unmanned aircraft. The aircraft streams a live video to a ground station over a wireless network, which is used by the human operator for detecting the target object’s location, concluding the search operation.

Cette thèse se focalise sur des tâches de perceptions pour des drones à voilures fixes (UAV). Lorsque la perception est la finalité, un bon modèle d'environnement couplé à la capacité de prédire l'impact de futures observations sur celui-ci est crucial. La perception active traite de l'intégration forte entre modèles de perception et processus de raisonnement, permettant au robot d'acquérir des informations pertinentes à propos du statut de la mission et de replanifier sa trajectoire de mesure en réaction à des évènements et résultats imprévisibles. Ce manuscrit décrit deux approches pour des tâches de perception active, dans deux scénarios radicalement différents. Le premier est celui de la cartographie des phénomènes météorologiques de petite échelle et fortement dynamiques, en particulier de nuages de type cumulus. L'approche présentée utilise la régression par processus Gaussien pour construire un modèle d'environnement, les hyper-paramètres étant appris en ligne. Des métriques de gain d'information sont introduites pour évaluer la qualité de futures trajectoires d'observation. Un algorithme de planification stochastique est utilisé pour optimiser une fonction d'utilité équilibrant maximisation du gain d'information avec des buts de minimisation du coût énergétique. Dans le second scénario, un UAV cartographie des champs de grandes cultures pour les besoins de l'agriculture de précision. Utilisant le résultat d'un algorithme de localisation et cartographie simultanée (SLAM), une approche nouvelle pour la construction d'un modèle d'erreurs relatives est proposée. Ce modèle est appris à partir d'attributs provenant des structures de données du SLAM, ainsi que de la topologie sous-jacente du graphe de covisibilité formé par les observations. Tous les développement ont été testés en simulation. Se focalisant sur la problématique de gestion de l'avancement tu temps et de la synchronisation de simulateurs hétérogènes dans une architecture distribuée, une solution originale basée sur une architecture décentralisée est proposée. / This thesis focuses on perception tasks for an unmanned aerial vehicle (UAV). When sensing is the finality, having a good environment model as well as being capable of predicting the impacts of future observations is crucial. Active perception deals with integrating tightly perception models in the reasoning process, enabling the robot to gain knowledge about the status of its mission and to replan its sensing trajectory to react to unforeseen events and results. This manuscript describes two approaches for active perception tasks, in two radically different settings. The first one deals with mapping highly dynamic and small scale meteorological phenomena such as cumulus clouds. The presented approach uses Gaussian Process Regression to build environment models, learning its hyperparameters online. Normalized marginal information metrics are introduced to compute the quality of future observation trajectories. A stochastic planning algorithm is used to optimize an utility measure balancing maximization of theses metrics with energetic minimization goals. The second setting revolves around mapping crop fields for precision agriculture purposes. Using the output of a monocular graph Simultaneous Localization and Mapping (SLAM) algorithm, a novel approach to building a relative error model is proposed. This model is learned both from features extracted from the SLAM algorithm’s data structures, as well as the underlying topology of the covisibility graph of the observations. All developments have been tested using realistic, distributed simulations. An analysis of the simulation issue in robotics is proposed. Focusing on the problem of managing time advancement of multiple interconnected simulators, a novel solution based on a decentralized scheme is presented.