Search

The details presented in this article revolve around a sophisticated monitoring framework equipped with knowledge representation and computer vision capabilities, that aims to provide innovative solutions and support services in the healthcare sector, with a focus on clinical and non-clinical rehabilitation and care environments for people with mobility problems. In contemporary pervasive systems most modern virtual agents have specific reactions when interacting with humans and usually lack extended dialogue and cognitive competences. The presented tool aims to provide natural human-computer multi-modal interaction via exploitation of state-of-the-art technologies in computer vision, speech recognition and synthesis, knowledge representation, sensor data analysis, and by leveraging prior clinical knowledge and patient history through an intelligent, ontology-driven, dialogue manager with reasoning capabilities, which can also access a web search and retrieval engine module. The framework’s main contribution lies in its versatility to combine different technologies, while its inherent capability to monitor patient behaviour allows doctors and caregivers to spend less time collecting patient-related information and focus on healthcare. Moreover, by capitalising on voice, sensor and camera data, it may bolster patients’ confidence levels and encourage them to naturally interact with the virtual agent, drastically improving their moral during a recuperation process.

In this article, the problem of real-time robot exploration and map building (active SLAM) is considered. A single stereo vision camera is exploited by a fully autonomous robot to navigate, localiz...

Surveillance systems currently deploy a variety of devices that can capture visual content (such as CCTV, body-worn cameras, and smartphone cameras), thus rendering the monitoring of the video footage obtained from multiple such devices a complex task. This becomes especially challenging when monitoring social events that involve large crowds, particularly when there is a risk of crowd violence. This paper presents and demonstrates a crowd violence detection system that can process, analyze, and alert the potential stakeholders when violence-related content is identified in crowd-based video footage. Based on deep neural networks, the proposed end-to-end framework utilizes a 3D Convolutional Neural Network (CNN) to deal with the (near) real-time analysis of video streams and video files for crowd violence detection. The framework is trained, evaluated, and demonstrated using the most recent dataset related to crowd-violence, namely the Violent Flows dataset. The presented framework is provided as a standalone application for desktop environments and can analyze video streams and video files.

Social media play an important role in the daily life of people around the globe and users have emerged as an active part of news distribution as well as production. The threatening pandemic of COVID-19 has been the lead subject in online discussions and posts, resulting to large amounts of related social media data, which can be utilised to reinforce the crisis management in several ways. Towards this direction, we propose a novel framework to collect, analyse, and visualise Twitter posts, which has been tailored to specifically monitor the virus spread in severely affected Italy. We present and evaluate a deep learning localisation technique that geotags posts based on the locations mentioned in their text, a face detection algorithm to estimate the number of people appearing in posted images, and a community detection approach to identify communities of Twitter users. Moreover, we propose further analysis of the collected posts to predict their reliability and to detect trending topics and events. Finally, we demonstrate an online platform that comprises an interactive map to display and filter analysed posts, utilising the outcome of the localisation technique, and a visual analytics dashboard that visualises the results of the topic, community, and event detection methodologies.

Recently, research endeavors have shown the potentiality of Cycle-Consistent Adversarial Networks (CycleGAN) in style transfer. In Cycle-Consistent Adversarial Networks, the consistency loss is introduced to measure the difference between the original images and the reconstructed in both directions, forward and backward. In this work, the combination of Cycle-Consistent Adversarial Networks with Fast and Adaptive Bidimensional Empirical Mode Decomposition (FABEMD) is proposed to perform style transfer on images. In the proposed approach the cycle-consistency loss is modified to include the differences between the extracted Intrinsic Mode Functions (BIMFs) images. Instead of an estimation of pixel-to-pixel difference between the produced and input images, the FABEMD is applied and the extracted BIMFs are involved in the computation of the total cycle loss. This method enriches the computation of the total loss in a content-to-content and style-to-style comparison by connecting the spatial information to the frequency components. The experimental results reveal that the proposed method is efficient and produces qualitative results comparable to state-of-the-art methods.

In what has arguably been one of the most troubling periods of recent medical history, with a global pandemic emphasising the importance of staying healthy, innovative tools that shelter patient well-being gain momentum. In that view, a framework is proposed that leverages multimodal data, namely inertial and depth sensor-originating data, can be integrated in health care-oriented platforms, and tackles the crucial task of human action recognition (HAR). To analyse person movement and consequently assess the patient’s condition, an effective methodology is presented that is two-fold: initially, Kinect-based action representations are constructed from handcrafted 3DHOG depth features and the descriptive power of a Fisher encoding scheme. This is complemented by wearable sensor data analysis, using time domain features and then boosted by exploring fusion strategies of minimum expense. Finally, an extended experimental process reveals competitive results in a well-known benchmark dataset and indicates the applicability of our methodology for HAR.

Current technology in imaging sensors offers a wide variety of information that can be extracted from an observed scene. Acquired images from different sensor modalities exhibit diverse characteristics such as type of degradation; salient features etc. and can be particularly beneficial in surveillance systems. Such representative sensory systems include infrared and thermal imaging cameras, which can operate beyond the visual spectrum providing functionality under any environmental conditions. Multi-sensor information is jointly combined to pro- vide an enhanced representation, particularly utile in automated surveillance systems such as monitoring robotics. In this chapter, a surveillance framework based on a fusion model is presented in order to enhance the capabilities of unmanned vehicles for monitoring critical infrastructures. The fusion scheme multiplexes the acquired repre- sentations from different modalities by applying an image decomposition algorithm and combining the resulted sub-signals via metric optimization. Subsequently, the fused representations are fed into an identification module in order to recognize the detected instances and improve eventually the surveillance of the required area. The proposed framework adopts recent advancements in object detection for optimal identification by deploying a deep learning model properly trained with fused data. Initial results indicate that the overall scheme can accurately identify the objects of interest by processing the enhanced representations of the fusion scheme. Considering that the overall processing time and the resource requirements are kept in low levels, the framework can be integrated in an automated surveillance system comprised by unmanned vehicles.

This works focuses on examining the performance of the Single Shot Detector (SSD) model in resource restricted systems where maintaining the power of the full model comprises a significant prerequisite. The proposed SSD variations examine the behavior of lighter versions of SSD while propose measures to limit the unavoidable performance shortage. The outcomes of the conducted research demonstrate a remarkable trade-off between performance losses, speed improvement and the required resource reservation. Thus, the experimental results evidence the efficiency of the presented SSD alterations towards accomplishing higher frame rates and retaining the performance of the original model.

Nowadays, the visual information captured by CCTV surveillance and body worn cameras is continuously increasing. Such visual information is often used for security purposes, such as the recognition of suspicious activities, including potential crime- and terrorism-related activities and violent behaviours. To this end, specific tools have been developed in order to provide law enforcement with better investigation capabilities and to improve their crime and terrorism detection and prevention strategies. This work proposes a novel framework for recognising abnormal activities where the continuous recognition of such activities in visual streams is carried out using state-of-the-art deep learning techniques. Specifically, the proposed method is based on an adaptable (near) real-time image processing strategy followed by the widely used 3D convolution architecture. The proposed framework is evaluated using the publicly available diverse dataset VIRAT for activity detection and recognition in outdoor environments. Taking into account the non-batch image processing and the advantage of 3D convolution approaches, the proposed method achieves satisfactory results on the recognition of human-centred activities and vehicle actions in (near) real time.

Cross-border crime utilizes recent advanced systems to perform their illegal activities. Innovative sensory systems and specialized equipment are examples that were used for trafficking of human and of various illicit materials. The increasing challenges that border personnel must resolve require the usage of recent technological advances as well. Thus, the utilization of pioneer technologies seems imperative to precede technologically organized crime. Towards this objective, the introduction of unmanned vehicles (UxV) and the advances of relevant sub-systems have created a new solution to fight cross-border crime. Utilizing a combination of UxVs enriched with enhanced detection capabilities comprises an effective solution. The chapter will introduce and present the capability of an autonomous navigation system by exploiting swarm intelligence principles towards simplifying the overall operation. Computer vision advances and semantic enrichment of the acquired information are incorporated to deliver cutting-edge technologies. The described architecture and services can provide a complete solution for optimal border surveillance and increased situation awareness.

The Verifiability Approach is a lie detection method based on the insight that truth-tellers provide precise details whereas liars sometimes remain vague to avoid being exposed. We provide a-game-theoretic analysis of a speaker who wants to be acquitted and an investigator who prefers to find out the truth. The investigator can verify the speaker’s statement at some cost; verification gets more reliable the more details are provided. If, after a falsified statement, the investigator convicts, an additional obstruction penalty is imposed. We derive all the equilibria of the game and thereby the conditions under which the investigator can infer additional information from the speaker's statement at face value. Strategic information revelation by the speaker and verification by the investigator then necessarily work in tandem. Improvements in reliability result in more valuable (strategic) information transmission, whereas a harsher obstruction penalty does not as soon as a lower limit is met.

This open access book is about public open spaces, about people, and about the relationship between them and the role of technology in this relationship. It is about different approaches, methods, empirical studies, and concerns about a phenomenon that is increasingly being in the centre of sciences and strategies – the penetration of digital technologies in the urban space. As the main outcome of the CyberParks Project, this book aims at fostering the understanding about the current and future interactions of the nexus people, public spaces and technology. It addresses a wide range of challenges and multidisciplinary perspectives on emerging phenomena related to the penetration of technology in people’s lifestyles - affecting therefore the whole society, and with this, the production and use of public spaces. Cyberparks coined the term cyberpark to describe the mediated public space, that emerging type of urban spaces where nature and cybertechnologies blend together to generate hybrid experiences and enhance quality of life.

The introduction of Unmanned vehicles (UxVs) in the recent years has created a new security field that can use them as both a potential threat as well as new technological weapons against those threats. Dealing with these issues from the counter-threat perspective, the proposed architecture project focuses on designing and developing a complete system which utilizes the capabilities of multiple UxVs for surveillance objectives in different operational environments. Utilizing a combination of diverse UxVs equipped with various sensors, the developed architecture involves the detection and the characterization of threats based on both visual and thermal data. The identification of objects is enriched with additional information extracted from other sensors such as radars and RF sensors to secure the efficiency of the overall system. The current prototype displays diverse interoperability concerning the multiple visual sources that feed the system with the required optical data. Novel detection models identify the necessary threats while this information is enriched with higher-level semantic representations. Finally, the operator is informed properly according to the visual identification modules and the outcomes of the UxVs operations. The system can provide optimal surveillance capacities to the relevant authorities towards an increased situational awareness.

If last century’s conception of open public space was understood as a performance stage where individuals could negotiate and establish relationships not only amongst them but also with elements of spatial manifestation demonstrating the significance of some visual, most times, qualities, a contemporary observer will probably not make this link.

In recent years, mobile devices have become very popular communication tools that provide access to information and communication, influence people’s social behaviour and change patterns of their everyday activities. The use of communication technologies in public open spaces has become significant for the outdoor experiences of people and the relationship between users and technologically mediated outdoor activities. More specifically, wireless digital cultures not only influence spatial layout, infrastructure systems and moving patterns, but also require ICT-based placemaking strategies. This is often not considered sufficiently during the physical design stage. It is important to consider a space appropriation approach to the use of digital technologies in public spaces, based on user requirements and the local context. This is demonstrated with a case study of the Gardens at new waterfront of Thessaloniki, Greece. In this project space analysis and users’ questionnaires were applied to relate digital space to the reality of the physical landscape as a first stage in the design process. This approach has wider implications for successful place making strategies. This chapter considers the possibilities of extensive outdoor use of digital media technologies in traditional forms of spatial experiences. It proposes that the new digital layer overlaying the physical space should first be methodologically explored in a way that could advance understanding of the extent to which immaterial networks and relationships can affect material planning and design dimensions.

Oil spill is considered one of the main threats to marine and coastal environments. Efficient monitoring and early identification of oil slicks are vital for the corresponding authorities to react expediently, confine the environmental pollution and avoid further damage. Synthetic aperture radar (SAR) sensors are commonly used for this objective due to their capability for operating efficiently regardless of the weather and illumination conditions. Black spots probably related to oil spills can be clearly captured by SAR sensors, yet their discrimination from look-alikes poses a challenging objective. A variety of different methods have been proposed to automatically detect and classify these dark spots. Most of them employ custom-made datasets posing results as non-comparable. Moreover, in most cases, a single label is assigned to the entire SAR image resulting in a difficulties when manipulating complex scenarios or extracting further information from the depicted content. To overcome these limitations, semantic segmentation with deep convolutional neural networks (DCNNs) is proposed as an efficient approach. Moreover, a publicly available SAR image dataset is introduced, aiming to consist a benchmark for future oil spill detection methods. The presented dataset is employed to review the performance of well-known DCNN segmentation models in the specific task. DeepLabv3+ presented the best performance, in terms of test set accuracy and related inference time. Furthermore, the complex nature of the specific problem, especially due to the challenging task of discriminating oil spills and look-alikes is discussed and illustrated, utilizing the introduced dataset. Results imply that DCNN segmentation models, trained and evaluated on the provided dataset, can be utilized to implement efficient oil spill detectors. Current work is expected to contribute significantly to the future research activity regarding oil spill identification and SAR image processing.

Oil spills pose a major threat of the oceanic and coastal environments, hence, an automatic detection and a continuous monitoring system comprises an appealing option for minimizing the response time of relevant operations. Numerous efforts have been conducted towards such solutions by exploiting a variety of sensing systems such as satellite Synthetic Aperture Radar (SAR) which can identify oil spills over sea surfaces in any environmental conditions and operational time. Such approaches include the use of artificial neural networks which effectively identify the polluted areas. Considering their remarkable abilities in many applications, deep Convolutional Neural Networks (DCNN) could surpass limitations and performances of previously proposed methods. This paper describes the application of an approach that combines the merits of a DCNN with SAR imagery in order to provide a fully automated oil spill identification system. The model semantically segments the input SAR images into multiple areas of interest. The deployed DCNN was trained using multiple SAR images acquired from the Sentinel-1 satellite provided by ESA and based on EMSA records for maritime pollution events. Experiments on such challenging benchmark datasets for such an abstract problem demonstrate that the algorithm can accurately identify oil spills leading to an effective detection solution.

Cellular Automata (CAs) are computational models that can capture the essential features of systems in which global behavior emerges from the collective effect of simple components, which interact locally. During the last decades, CAs have been extensively used for mimicking several natural processes and systems to find fine solutions in many complex hard to solve computer science and engineering problems. Among them, the shortest path problem is one of the most pronounced and highly studied problems that scientists have been trying to tackle by using a plethora of methodologies and even unconventional approaches. The proposed solutions are mainly justified by their ability to provide a correct solution in a better time complexity than the renowned Dijkstra’s algorithm. Although there is a wide variety regarding the algorithmic complexity of the algorithms suggested, spanning from simplistic graph traversal algorithms to complex nature inspired and bio-mimicking algorithms, in this chapter we focus on the successful application of CAs to shortest path problem as found in various diverse disciplines like computer science, swarm robotics, computer networks, decision science and biomimicking of biological organisms’ behaviour. In particular, an introduction on the first CA-based algorithm tackling the shortest path problem is provided in detail. After the short presentation of shortest path algorithms arriving from the relaxization of the CAs principles, the application of the CA-based shortest path definition on the coordinated motion of swarm robotics is also introduced. Moreover, the CA based application of shortest path finding in computer networks is presented in brief. Finally, a CA that models exactly the behavior of a biological organism, namely the Physarum’s behavior, finding the minimum-length path between two points in a labyrinth is given. The CA-based model results are found in very good agreement with the computation results produced by the in-vivo experiments especially when combined with truly parallel implementations of this CA in a Field Programmable Gate Array (FPGA) and on a Graphical Processing Unit (GPU). The presented implementations succeed to take advantage of the CA’s inherit parallelism and significantly improve the performance of the CA algorithm when compared with software in terms of computational speed and power consumption.

A Cellular Automaton-based technique suitable for solving the path planning problem in a distributed robot team is outlined. Real-time path planning is a challenging task that has many applications in the fields of artificial intelligence, moving robots, virtual reality, and agent behavior simulation. The problem refers to finding a collision-free path for autonomous robots between two specified positions in a configuration area. The complexity of the problem increases in systems of multiple robots. More specifically, some distance should be covered by each robot in an unknown environment, avoiding obstacles found on its route to the destination. On the other hand, all robots must adjust their actions in order to keep their initial team formation immutable. Two different formations were tested in order to study the efficiency and the flexibility of the proposed method. Using different formations, the proposed technique could find applications to image processing tasks, swarm intelligence, etc. Furthermore, the presented Cellular Automaton (CA) method was implemented and tested in a real system using three autonomous mobile minirobots called E-pucks. Experimental results indicate that accurate collision-free paths could be created with low computational cost. Additionally, cooperation tasks could be achieved using minimal hardware resources, even in systems with low-cost robots.

Creating collision-free trajectories for mobile robots, known as the path planning problem, is considered to be one of the basic problems in robotics. In case of multiple robotic systems, the complexity of such systems increases proportionally with the number of robots, due to the fact that all robots must act as one unit to complete one composite task, such as retaining a specific formation. The proposed path planner employs a combination of Cellular Automata (CA) and Ant Colony Optimization (ACO) techniques in order to create collision-free trajectories for every robot of a team while their formation is kept immutable. The method reacts with obstacle distribution changes and therefore can be used in dynamical or unknown environments, without the need of a priori knowledge of the space. The team is divided into subgroups and all the desired pathways are created with the combined use of a CA path planner and an ACO algorithm. In case of lack of pheromones, paths are created using the CA path planner. Compared to other methods, the proposed method can create accurate collision-free paths in real time with low complexity while the implemented system is completely autonomous. A simulation environment was created to test the effectiveness of the applied CA rules and ACO principles. Moreover, the proposed method was implemented in a system using a real world simulation environment, called Webots. The CA and ACO combined algorithm was applied to a team of multiple simulated robots without the interference of a central control. Simulation and experimental results indicate that accurate collision free paths could be created with low complexity, confirming the robustness of the method.

In this chapter, a unified architecture is proposed for a robot team in order to accomplish several tasks based on the application of an enhanced Cellular Automata (CA) path planner. The presented path planner can produce adequate collision-free pathways with minimum hardware resources and low complexity levels. During the course of a robot team to its final destination, dynamic obstacles are detected and avoided in real time as well as coordinated movements are executed by applying cooperations in order to maintain the team’s initial formation. The inherit parallelism and simplicity of CA result in a path planner that requires low computational resources and thus, its implementation in miniature robots is straightforward. Cooperations are limited to a minimum so that further resource reduction can be achieved. For this purpose, the basic fundamentals of another artificial intelligence method, namely Ant Colonies Optimization (ACO) technique, were applied. The entire robot team is divided into equally numbered subgroups and an ACO algorithm is applied to reduce the complexity. As each robot moves towards to its final position, it creates a trail of an evaporated substance, called “pheromone”. The “pheromone” and its quantity are detected by the following robots and thus, every robot is absolved by the necessity of continuous communication with its neighbors. The total complexity of the presented architecture results to a possible implementation using a team of miniature robots where all available resources are exploited.

During the last years, several methods have been applied to tackle the image resizing problem. Most of these methods are derived from image interpolation techniques for image enlargement. Among them, the edge-directed interpolation methods succeed to preserve the edges of the low resolution image and produce crisper results compared to the space invariantmodels. In this chapter, we present an edge-directed method which exploits the simplicity and the inherent parallelism of the Cellular Automata (CA) computational tool to generate high resolution images from low resolution acquired images. This task is accomplished with the help of the Canny Edge Detector so as to discriminate the edge regions from the homogenous ones. Moreover, appropriate CA states and transition rules were designed to evolve the CA, which, eventually, attempt to enhance the quality of the edge areas. The orientation of the edge cells are considered in order to preserve effectively the edges of the initial image. The presented experimental results in terms of PSNR values and processing time demonstrate the effectiveness of the proposed method when compared to well-known methods as well as its suitability, especially for systems with low requirements specifications when further image processing is required.

A new method for fusing a scene of two or more different exposed images is proposed. The process of Fast and Adaptive Bidimensional Empirical mode Decomposition is adopted in order to decompose the illumination component of the input images in their Intrinsic Mode Functions (IMFs). The features of each image can then be detected by applying local energy operators within the IMFs and the final fused image is derived as a collection of features from the input images. Finally, the color information is selected from the “best exposed” pixels of the input sequence. Experimental results show that this method captures all the features from the input images while the fused images display uniform pixel values in the entire image region.

This paper introduces a novel image resizing method for both color and grayscale images. The method could be beneficial in applications where time and quality of the processed images are crucial. The basic idea of the proposed method relies on preserving the edges by partitioning the digital images into homogenous and edge areas during the enlargement process. In addition, the basic fundamentals of Cellular Automata were adopted in order to achieve better performance both in terms of processing time as well as in image quality. By creating appropriate transition rules, the direction of the edges is considered so that every unknown pixel is processed based on its neighbors in order to preserve the quality of the edges. Results demonstrate that the proposed method improves the subjective quality of the enlarged images over conventional resizing methods while keeping the required processing time in low levels.

One of the major tasks in the field of robotics is the path planning problem. In systems consisted of numerous robots, the creation of collision free trajectories becomes even more complex. Such robotic teams must avoid all detected obstacles while further tasks must be achieved such as forming specific patterns. In this paper, a Cellular Automaton (CA) based path planner and its implementation in a real cooperative robot team are presented. All robots must cover the same distance avoiding all detected obstacles while their formation is kept immutable. Due to its simplicity, the method has low computational load and therefore further applications could be applied. On the other hand, miniature robots can cooperate in order to perform area measurements, simultaneous localization and mapping (SLAM), panoramic images and so on. One of the most interesting cooperation aspects is the usage of multiple digital cameras, usually found with low resolutions. In order to process accurately all the acquired images taken from every robot, image interpolation algorithms could be applied as a preprocessing stage. Consequently, the inherent parallelism and the fundamental features of CA were also used to achieve the desired resolution enhancement. Final results indicate that both the CA based path planner and the image resolution enhancement could be executed concurrently using the resources of each mini robot, confirming their low requirements of computational resources.

The settlement of the collision-free path planning problem is considered as a complicated objective and is of vital importance in systems comprising one or multiple robots. In multi-robots systems, the path planning problem is based on cooperation. In such systems, the robots dynamically exchange roles in order to complete complex tasks, such as moving in different formations. In this paper, a Cellular Automaton algorithm for solving the path planning problem in a multi-agent system is presented. Moreover, robots must cooperate to keep their initial formation if an unexpected event in the environment takes place. The proposed method was implemented in a real time system of three autonomous mobile robots. Simulation results and the results obtained from this system demonstrate the effectiveness of the method and its robustness.

This work presents a spatio-temporal activity detection and recognition framework for untrimmed surveillance videos consisting of a three-step pipeline: object detection, tracking, and activity recognition. The framework relies on the YOLO v4 architecture for object detection, Euclidean distance for tracking, while the activity recognizer uses a 3D Convolutional Deep learning architecture employing spatio-temporal boundaries and addressing it as multi-label classification. The evaluation experiments on the VIRAT dataset achieve accurate detections of the temporal boundaries and recognitions of activities in untrimmed videos, with better performance for the multi-label compared to the multi-class activity recognition.

Oil spill pollution comprises a significant threat of the oceanic and coastal ecosystems. A continuous monitoring framework with automatic detection capabilities could be valuable as an early warning system so as to minimize the response time of the authorities and prevent any environmental disaster. The usage of Synthetic Aperture Radar (SAR) data acquired from satellites have received a considerable attention in remote sensing and image analysis applications for disaster management, due to the wide area coverage and the all-weather capabilities. Over the past few years, multiple solutions have been proposed to identify oil spills over the sea surface by processing SAR images. In addition, deep convolutional neural networks (DCNN) have shown remarkable results in a wide variety of image analysis applications and could be deployed to overcome the performance of previously proposed methods. This paper describes the development of an image analysis approach utilizing the benefits of a deep CNN combined with SAR imagery to establish an early warning system for oil spill pollution identification. SAR images are semantically segmented into multiple areas of interest including oil spill, look-alikes, land areas, sea surface and ships.The model was trained and tested using multiple SAR images, acquired from the Copernicus Open Access Hub and manually annotated. The dataset is a result of Sentinel-1 missions and EMSA records for relative pollution events. The conducted experiments demonstrate that the deployed DCNN model can accurately discriminate oil spills from other instances providing the relevant authorities a valuable tool to manage the upcoming disaster effectively.

This work examines violence detection in video scenes of crowds and proposes a crowd violence detection framework based on a 3D convolutional deep learning architecture, the 3D-ResNet model with 50 layers. The proposed framework is evaluated on the Violent Flows dataset against several state-of-the-art approaches and achieves higher accuracy values in almost all cases, while also performing the violence detection activities in (near) real-time.