DCETE 2018 Abstracts


Full Papers
Paper Nr: 2
Title:

Scene Understanding for Parking Space Management

Authors:

Daniele Di Mauro

Abstract: Smart cities is one of the new frontier of the Computer Vision community. The major part of world-wide population moved to urban areas, after such process many issues of major cities have worsened, e.g. air pollution, traffic, security. The increase of security cameras and the improvements of Computer Vision algorithm can be a good solution for many of those problems. Park Smart s.r.l., a company located in Catania, believes that Computer Vision can be the answer for parking space management. Their aim is to help private companies and public administrations to manage free entry parking areas, as well closed ones, in order to offer better services to the final customer i.e. the drivers and to increase the revenue per stall for public administrations. The architecture of the system follow the Edge Computing design which brings the Computer Vision computation close to the parking area. The main problem the company has to face is to find a fast way to deploy working solutions, lowering the labeling effort to the minimum, across different scene, cities, parking areas. During the three years of doctoral studies we have tried to solve the problem through the use of various methods such as Semi-Supervised Learning, Counting and Scene Adaptation through Image Classification, Object Detection and Semantic Segmentation.

Paper Nr: 3
Title:

Dynamic Key Distribution for Secure Group Communications in Constrained Environments

Authors:

Tobias Guggemos

Abstract: Group communication -- especially in form of multicast -- is a famous communication pattern in constrained networks, e.g. in the Internet of Things (IoT), Wireless Sensor Networks (WSN) or Device to Device (D2D) communication. However, it comes with mandatory management overhead during the life-cycle of a group, which is usually favored due to the potential energy savings ones the connection is set up. The management paradigm worsens, if the connection within and the management of the group has to be secure and in turn requires security management. Security and cryptography, however, need special attention when used in constrained environments. The proposed thesis will connect group management, group communication and security management and apply them to constrained environments.

Paper Nr: 4
Title:

Multi-sensor Data Fusion for Wearable Devices

Authors:

Tiziana Rotondo

Abstract: The real time information comes from multiple sources such as wearable sensors, audio signals, GPS, etc. The idea of multi-sensor data fusion is to combine the data coming from different sensors to provide more accurate information than that a single sensor alone. To contribute to ongoing research in this area, the goal of my research is to build a shared representation between data coming from different domains, such as images, signal audio, heart rate, acceleration, etc., in order to predict daily activities. In the state of the art, these arguments are treated individually. Many papers, such as (Lan et al., 2014; Ma et al., 2016) et al., predict daily activity from video or static image. Others, such as (Ngiam et al., 2011; Srivastava and Salakhutdinov, 2014) et al., build a shared representation then rebuild the inputs or rebuild a missing modality, or (Nakamura et al., 2017) classifies from multimodal data.