Abstract
The effective monitoring and maintenance of power lines are becoming increasingly important due to a global growing dependence on electricity. The costs and risks associated with the traditional foot patrol and helicopter-based inspections can be reduced by using UAVs with the appropriate sensors. However, this implies developing algorithms to make the power line inspection process reliable and autonomous. In order to overcome the limitations of visual methods in the presence of poor light and noisy backgrounds, we propose to address the problem of power line detection and modeling based on LiDAR. The PL2DM, Power Line LiDAR-based Detection and Modeling, is a novel approach to detect power lines. Its basis is a scan-by-scan adaptive neighbor minimalist comparison for all the points in a point cloud. The power line final model is obtained by matching and grouping several line segments, using their collinearity properties. Horizontally, the power lines are modeled as a straight line, and vertically as a catenary curve. Using a real dataset, the algorithm showed promising results both in terms of outputs and processing time, adding real-time object-based perception capabilities for other layers of processing.

Abstract
The project Viable Alternative Mine Operating System ('VAMOS') develops a novel underwater mining technique for extracting inland mineral deposits in flooded open-cut mines. From a floating launch and recovery vessel a remotely-operated underwater mining vehicle with a roadheader cutting machine is deployed. The cut material is transported to the surface via a flexible riser hose. Since there is no direct intervisibility between the operator and the mining machine, the data of the sensor systems can only be perceived via a computer interface. Therefore, part of the efforts in the project focus on enhancing the situational awareness of the operator by providing a 3D model of the mine combined with representations of the mining equipment and sensor data. We present a method how a positioning and navigation system, perception system and mapping system can be used to create a replica of the physical system and mine environment in Virtual Reality (VR) in order to assist remote control. This approach is beneficial because it allows visualizing different sensor information and data in a consistent interface, and enables showing the complete context of the mining site even if only part of the mine is currently observed by surveying equipment. We demonstrate how the system is used during tele-operation and show results achieved during the field trials of the complete system in Silvermines, Ireland.

Abstract
This work addresses a hyperspectral imaging system for maritime surveillance using unmanned aerial vehicles. The objective was to detect the presence of vessels using purely spatial and spectral hyperspectral information. To accomplish this objective, we implemented a novel 3-D convolutional neural network approach and compared against two implementations of other state-of-the-art methods: spectral angle mapper and hyperspectral derivative anomaly detection. The hyperspectral imaging system was developed during the SUNNY project, and the methods were tested using data collected during the project final demonstration, in Sao Jacinto Air Force Base, Aveiro (Portugal). The obtained results show that a 3-D CNN is able to improve the recall value, depending on the class, by an interval between 27% minimum, to a maximum of over 40%, when compared to spectral angle mapper and hyperspectral derivative anomaly detection approaches. Proving that 3-D CNN deep learning techniques that combine spectral and spatial information can be used to improve the detection of targets classification accuracy in hyperspectral imaging unmanned aerial vehicles maritime surveillance applications.

Abstract
The importance of planktonic microbial communities is well acknowledged, since they are fundamental for several natural processes of aquatic ecosystems. Microorganisms naturally control the flux of nutrients, and also degrade and recycle anthropogenic organic and inorganic contaminants. Nevertheless, climate change effects and/or the runoff of nutrients/pollutants can affect the equilibrium of natural microbial communities influencing the occurrence of microbial pathogens and/or microbial toxin producers, which can compromise ecosystem environmental status. Therefore, improved microbial plankton monitoring is essential to better understand how these communities respond to environmental shifts. The study of marine microbial communities typically involves highly cost and time-consuming sampling procedures, which can limit the frequency of sampling and data availability. In this context, we developed and validated an in situ autonomous biosampler (IS-ABS) able to collect/concentrate in situ planktonic communities of different size fractions (targeting prokaryotes and unicellular eukaryotes) for posterior genomic, metagenomic, and/or transcriptomic analysis at a home laboratory. The IS-ABS field prototype is a small size and compact system able to operate up to 150 m depth. Water is pumped by a micropump (TCS MG2000) through a hydraulic circuit that allows in situ filtration of environmental water in one or more Sterivex filters placed in a filter cartridge. The IS-ABS also includes an application to program sampling definitions, allowing pre-setting configuration of the sampling. The efficiency of the IS-ABS was tested against traditional laboratory filtration standardized protocols. Results showed a good performance in terms of DNA recovery, as well as prokaryotic (16S rDNA) and eukaryotic (18S rDNA) community diversity analysis, using either methodologies. The IS-ABS automates the process of collecting environmental DNA, and is suitable for integration in water observation systems, what will contribute to substantially increase biological surveillances. Also, the use of highly sensitive genomic approaches allows a further study of the diversity and functions of whole or specific microbial communities.

Abstract
The growing dependence of modern-day societies on electricity increases the importance of effective monitoring and maintenance of power lines. Endowing UAVs with the appropriate sensors for inspecting power lines, the costs and risks associated with the traditional foot patrol and helicopter-based inspections can be reduced. However, this implies the development of algorithms to make the inspection process reliable and autonomous. Visual methods are usually applied to locate the power lines and their components, but poor light conditions or a background rich in edges may compromise their results. To overcome those limitations, we propose to address the problem of power line detection and modeling based on LiDAR. A novel approach to the power line detection was developed, the PL2DM -Power Line LiDAR-based Detection and Modeling. It is based in a scan-by-scan adaptive neighbor minimalist comparison for all the points in a point cloud. The power line final model is obtained by matching and grouping several line segments, using their collinearity properties. Horizontally, the power lines are modeled as a straight line, and vertically as a catenary curve. The algorithm was validated with a real dataset, showing promising results both in terms of outputs and processing time, adding real-time object-based perception capabilities for other layers of processing.

Abstract
Zooplankton plays a key -role on Earth's ecosystem, emerging in the oceans and rivers in great quantities and diversity, making it an important and rather common topic on scientific studies. Given the numbers of different species it is not only necessary to study their numbers but also their classification. In this paper a possible solution for the zooplankton in situ detection and classification problem in real-time is proposed using a portable deep learning approach based on Convolutional Neural Networks deployed on INESC TEC's MarinEye system. For detection a Single Shot Detection model with MobileNet was used, and ZooplanktoNet for classification. System portability is guaranteed with the use of MovidiusTMNeural Compute Stick as the deep learning motor.