Abstract
Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. State-of-the-art methods show good performance in a wide range of situations, but systematically fail when facing more challenging scenarios. Lately, a number of image processing modules inspired in biological models of the human visual system have been explored in different areas of application. This paper proposes a bio-inspired boosting method to address the problem of unsupervised segmentation of moving objects in video that shows the ability to overcome some of the limitations of widely used state-of-the-art methods. An exhaustive set of experiments was conducted and a detailed analysis of the results, using different metrics, revealed that this boosting is more significant when challenging scenarios are faced and state-of-the-art methods tend to fail.

Abstract
Over the last decade noticeable progress has occurred in automated computer interpretation of visual information. Computers running artificial intelligence algorithms are growingly capable of extracting perceptual and semantic information from images, and registering it as metadata. There is also a growing body of manually produced image annotation data. All of this data is of great importance for scientific purposes as well as for commercial applications. Optimizing the usefulness of this, manually or automatically produced, information implies its precise and adequate expression at its different logical levels, making it easily accessible, manipulable and shareable. It also implies the development of associated manipulating tools. However, the expression and manipulation of computer vision results has received less attention than the actual extraction of such results. Hence, it has experienced a smaller advance. Existing metadata tools are poorly structured, in logical terms, as they intermix the declaration of visual detections with that of the observed entities, events and comprising context. This poor structuring renders such tools rigid, limited and cumbersome to use. Moreover, they are unprepared to deal with more advanced situations, such as the coherent expression of the information extracted from, or annotated onto, multi-view video resources. The work here presented comprises the specification of an advanced XML based syntax for the expression and processing of Computer Vision relevant metadata. This proposal takes inspiration from the natural cognition process for the adequate expression of the information, with a particular focus on scenarios of varying numbers of sensory devices, notably, multi-view video.

Abstract
Tracking objects in video is a very challenging research topic, particularly when people in groups are tracked, with partial and full occlusions and group dynamics being common difficulties. Hence, its necessary to deal with group tracking, formation and separation, while assuring the overall consistency of the individuals. This paper proposes enhancements to a group management and tracking algorithm that receives information of the persons in the scene, detects the existing groups and keeps track of the persons that belong to it. Since input information for group management algorithms is typically provided by a tracking algorithm and it is affected by noise, mechanisms for handling such noisy input tracking information were also successfully included. Performed experiments demonstrated that the described algorithm outperformed state-of-the-art approaches.

Abstract
The ocean and the Blue Economy are increasingly top priorities worldwide. The immense ocean territory in the planet and its huge associated economical potential is envisioned to increase the activity at the ocean in the forthcoming years. The support of these activities, and the convergence to the Internet of Things paradigm, will demand wireless and mobile communications to connect humans and systems at remote ocean areas. Currently, there is no communications solution enabling cost-effective broadband Internet access at remote ocean areas in alternative to expensive, narrowband satellite communications. This paper presents the maritime communications solution being developed in the BLUECOM+ project. The BLUECOM+ solution enables cost-effective broadband Internet access at remote ocean areas using standard wireless access technologies, e.g., GPRS/UMTS/LTE and Wi-Fi. Its novelty lies on the joint use of TV white spaces for long range radio communications, tethered balloons for lifting communications nodes high above the ocean surface, multi-hop relaying techniques for radio range extension, and standard access networks at the ocean. Simulation results prove it is possible to reach radio ranges beyond 100 km and bitrates in excess of 3 Mbit/s using a two-hop land-sea communications chain.

Abstract
In wireless power transfer systems, if the driver is not capable of dynamically adapt its own switching frequency, small environmental changes or even slight deviations in circuit parameters may prevent the complete system from working properly when the optimal resonance frequency moves towards new values. In this paper, we propose an adaptive system suitable for underwater wireless applications in sea water. The output voltage is regulated using the wireless power link, avoiding the need for additional wireless interfaces. Our complete system includes the power driver, coupling coils, rectifier, and two micro-controllers. The regulation is accomplished by digital load modulation, observable at the input by means of current sensing at the power supply. Experimental results demonstrate a class-D driver with a series-series resonant topology working in saline water, delivering power between 1.6 and 2.4 W. The regulated voltage is 7.5 V with error less than 7.2 % in the load range of 30 to 37 Omega and 6 to 10 V power supply variation. The switching frequency is adjusted within the range of 7 kHz deviation (-7%).

Abstract
This work presents a new topology for the matching networks of an underwater wireless power transfer system. A class-D driver is used in resonance at fundamental and third harmonic frequencies. The double resonance helps reducing the reverse voltage stress at the diode rectifier. We present the analytical derivation of the proposed network and demonstrate the design procedure with an example. We also show that additional degrees of freedom can be acquired with the proposed topology, which improves the design space for time-varying operation conditions of our application, such as the load changing when a battery is being recharged. The performance of our topology is compared to most conventional approaches, such as the series-series and series-parallel networks, revealing a good compromise between power delivery and efficiency across a wide load range.