Cognitive Cameras on the Edge for Crowd Physical Distancing Monitoring in the Covid-19 Era.

With the rise of the Internet of Things (IoT) architectures and protocols, new video analytics systems and surveillance applications have been developed. In conventional systems, all the streams produced by cameras are sent to a centralized node where they can be seen by human operators whose task is to identify uncommon on abnormal situations. However, this way, much bandwidth is necessary for the system to work, and the number of necessary resources is proportional to the number of cameras and streams involved. In this paper, we propose an interesting approach to this problem: transforming any IP camera into a cognitive object. A cognitive camera (CC) can be considered a classic connected camera with onboard computational power for intelligent video processing. A CC can understand and interact with the surroundings, intelligently analyze complex scenes, and interact with the users. The IoT Edge Computing approach decreases latency in the decision-making process and consumes a tiny portion of bandwidth concerning the stream of a video, even in low resolution. CCs can help to address COVID-19. As a preventive measure, proper crowd monitoring and management systems must be installed in public places to limit sudden outbreaks and improve healthcare. The number of new infections can be significantly reduced by adopting physical distancing measures earlier. Motivated by this notion, a real-time crowd monitoring and management system for physical distance classification using CCs is proposed in this research paper. The experiment on Movidius board, an AI accelerator device, provides promising results of our proposed method in which the accuracies can achieve more than 85% from different datasets.

Automatic Stones Classification through a CNN-Based Approach.

This paper presents an automatic recognition system for classifying stones belonging to different Calabrian quarries (Southern Italy). The tool for stone recognition has been developed in the SILPI project (acronym of "Sistema per l'Identificazione di Lapidei Per Immagini"), financed by POR Calabria FESR-FSE 2014-2020. Our study is based on the Convolutional Neural Network (CNNs) that is used in literature for many different tasks such as speech recognition, neural language processing, bioinformatics, image classification and much more. In particular, we propose a two-stage hybrid approach based on the use of a model of Deep Learning (DL), in our case the CNN, in the first stage and a model of Machine Learning (ML) in the second one. In this work, we discuss a possible solution to stones classification which uses a CNN for the feature extraction phase and the Softmax or Multinomial Logistic Regression (MLR), Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Random Forest (RF) and Gaussian Naive Bayes (GNB) ML techniques in order to perform the classification phase basing our study on the approach called Transfer Learning (TL). We show the image acquisition process in order to collect adequate information for creating an opportune database of the stone typologies present in the Calabrian quarries, also performing the identification of quarries in the considered region. Finally, we show a comparison of different DL and ML combinations in our Two-Stage Hybrid Model solution.

SCARE: A Novel Switching and Collision Avoidance pRocEss for Connected Vehicles Using Virtualization and Edge Computing Paradigm.

In this paper, some collision avoidance systems based on MEC in a VANET environment are proposed and investigated. Micro services at edge are considered to support service continuity in vehicle communication and advertising. This considered system makes use of cloud and edge computing, allowing to switch communication from edge to cloud server and vice versa when possible, trying to guarantee the required constraints and balancing the communication among the servers. Simulation results were used to evaluate the performance of three considered mechanisms: the first one considering only edge with load balancing, the second one using edge/cloud switching and the third one using edge with load balancing and collision avoidance advertising.

A Proposal of a Troposphere Model in a GNSS Simulator for VANET Applications.

Vehicle positioning is becoming an important issue related to Intelligent Transportation Systems (ITSs). Novel vehicles and autonomous vehicles need to be localized under different weather conditions and it is important to have a reliable positioning system to track vehicles. Satellite navigation systems can be a key technology in providing global coverage and providing localization services through many satellite constellations such as GPS, GLONASS, Galileo and so forth. However, the modeling of positioning and localization systems under different weather conditions is not a trivial objective especially considering different factors such as receiver sensitivity, dynamic weather conditions, propagation delay and so forth. This paper focuses on the use of simulators for performing different kinds of tests on Global Navigation Satellite System (GNSS) systems in order to reduce the cost of the positioning testing under different techniques or models. Simulation driven approach, combined with some specific hardware equipment such as receivers and transmitters can characterize a more realistic scenario and the simulation can consider other aspects that could be complex to really test. In this work, the main contribution is the introduction of the Troposphere Collins model in a GNSS simulator for VANET applications, the GPS-SDR-SIM software. The use of the Collins model in the simulator allows to improve the accuracy of the simulation experiments throughout the reduction of the receiver errors.

An IoT Surveillance System Based on a Decentralised Architecture.

In the last few years, we witnessed numerous episodes of terrorist attacks and menaces in public crowded places. The necessity of better surveillance in these places pushed the development of new automated solutions to spot and notify possible menaces as fast as possible. In this work, we propose a novel approach to create a decentralized architecture to manage patrolling drones and cameras exploiting lightweight protocols used in the internet of things (IoT) domain. Through the adoption of the mist computing paradigm it is possible to give to all the object of the smart ecosystem a cognitive intelligence to speed up the recognition and analysis tasks. Distributing the intelligence among all the objects of the surveillance ecosystem allows a faster recognition and reaction to possible warning situations. The recognition of unusual objects in certain areas, e.g., airports, train stations and bus stations, has been made using computer vision algorithms. The adoption of the IoT protocols in a hierarchical architecture provides high scalability allowing an easy and painless join of other smart objects. Also a study on the soft real-time feasibility has been conducted and is herein presented.

Managing Emergency Situations in VANET Through Heterogeneous Technologies Cooperation.

Nowadays, the research on vehicular computing enhanced a very huge amount of services and protocols, aimed to vehicles security and comfort. The investigation of the IEEE802.11p, Wireless Access in Vehicular Environments (WAVE) and Dedicated Short Range Communication (DSRC) standards gave to the scientific world the chance to integrate new services, protocols, algorithms and devices inside vehicles. This opportunity attracted the attention of private/public organizations, which spent lot of resources and money to promote vehicular technologies. In this paper, the attention is focused on the design of a new approach for vehicular environments able to gather information during mobile node trips, for advising dangerous or emergency situations by exploiting on-board sensors. It is assumed that each vehicle has an integrated on-board unit composed of several sensors and Global Position System (GPS) device, able to spread alerting messages around the network, regarding warning and dangerous situations/conditions. On-board units, based on the standard communication protocols, share the collected information with the surrounding road-side units, while the sensing platform is able to recognize the environment that vehicles are passing through (obstacles, accidents, emergencies, dangerous situations, etc.). Finally, through the use of the GPS receiver, the exact location of the caught event is determined and spread along the network. In this way, if an accident occurs, the arriving cars will, probably, avoid delay and danger situations.