Abstract

Abstract
This study explored the viability of out-the-box, pre-trained ConvNet models as a tool to generate features for large-scale classification tasks. A juxtaposition with generative methods for vocabulary generation was drawn. Both methods were chosen in an attempt to integrate other datasets (transfer learning) and unlabelled data, respectively. Both methods were used together, studying the viability of a ConvNet model to estimate category labels of unlabelled images. All experiments pertaining to this study were carried out over a two-class set, later expanded into a 5-category dataset. The pre-trained models used were obtained from the Caffe Model Zoo. The study showed that the pre-trained model achieved best results for the binary dataset, with an accuracy of 0.945. However, for the 5-class dataset, generative vocabularies outperformed the ConvNet (0.91 vs. 0.861). Furthermore, when replacing labelled images with unlabelled ones during training, acceptable accuracy scores were obtained (as high as 0.903). Additionally, it was observed that linear kernels perform particularly well when utilized with generative models. This was especially relevant when compared to ConvNets, which require days of training even when utilizing multiple GPUs for computations.

Abstract
Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. The best solutions are, in general, computationally heavy preventing their use in real-time applications. This research addresses this problem by proposing a robust and computationally efficient method, BMOG, that significantly boosts the performance of the widely used MOG2 method. The complexity of BMOG is kept low, proving its suitability for real-time applications. The proposed solution explores a novel classification mechanism that combines color space discrimination capabilities with hysteresis and a dynamic learning rate for background model update.

Abstract
FLEXUS unmanned surface vehicle was designed in the context of the Internet of Moving Things. This small catamaran weights less than 15kg and is less than 1m long, making it a very convenient vehicle with reduced logistics needs for operations in real outdoor environments. The present paper describes the resulting system both in terms of design and performances. Based on the requirements for this project, the subsystems composing the vehicle are described. Results obtained from experiments conducted in outdoor conditions have successfully validated this design and are presented in this paper.

Abstract
Enterprise Wi-Fi networks have been increasingly considering energy efficiency. In this paper, we present the Wi-Green project wherein we are investigating new techniques and innovative solutions that will allow the minimization of the energy consumption in Wi-Fi networks. In Wi-Green we will consider an enterprise network, in which there is equipment from different vendors, with different ages and different consumption profiles.

Abstract
This paper focus on the use of unmanned aerial vehicle teams for performing cooperative perception using Data Distribution Service (DDS) Network. We develop a DDS framework to manage the incoming and out bounding network traffic of multiple types of data that is exchanged inside the UAV network. Experimental results both in laboratory and in actual flight are presented to help characterize the proposed system solution.