Anastasios Dimou

The Centre for Research and Technology, Hellas · Information Technologies Institute (ITI)

The present study thoroughly evaluates the most common blocking challenges faced by the federated learning (FL) ecosystem and analyzes existing state-of-the-art solutions. A system adaptation pipeline is designed to enable the integration of different AI-based tools in the FL system, while FL training is conducted under realistic conditions using a...

The planning and execution of disaster response missions are complex and multifaceted tasks that need to consider and coordinate personnel and other resources while tracking the progress of the event. Innovative technical tools can both increase situational awareness and provide an interface for information display and mission management. The FASTE...

Nowadays, the need for large amounts of carefully and complexly annotated data for the training of computer vision modules continues to grow. Furthermore, although the research community presents state of the art solutions to many problems, there exist special cases, such as the pose estimation and tracking of a glove-wearing hand, where the genera...

This paper reports the results of the 5th edition of the “Drone-vs-Bird” detection challenge, organized within the 21st International Conference on Image Analysis and Processing (ICIAP). By taking as input video samples recorded by common cameras, the aim of the challenge is to devise advanced approaches aimed at spotlighting the presence of drones...

Vehicle automation and connectivity bring new opportunities for safe and sustainable mobility in urban and highway networks. Such opportunities are however not directly associated with traffic flow improvements. Research on exploitation of connected and automated vehicles (CAVs) toward a more efficient traffic currently remains at a theoretical lev...

Celem artykułu jest przedstawienie aktualnego stanu badań realizowanych przez międzynarodowe konsorcjum w ramach projektu „FASTER — First responder Advanced technologies for Safe and efficienT Emergency Response”, który finansowany jest ze środków programu Horyzont 2020. W analizie omówiono główne cele i założenia projektu oraz zasygnalizowano tech...

Emergency first responders play an important role during search and rescue missions, by helping people and saving lives. Thus, it is important to provide them with technology that will maximize their performance and their safety on the field of action. IFAFRI, the “International Forum to Advanced First Responder Innovation” has pointed out several...

Traditional drone handheld remote controllers, although well-established and widely used, are not a particularly intuitive control method. At the same time, drone pilots normally watch the drone video feed on a smartphone or another small screen attached to the remote. This forces them to constantly shift their visual focus from the drone to the sc...

FASTER is an H2020 RIA project that develops a set of tools for enhancing the operational capacity of first responders while increasing their safety in the field. It will introduce augmented reality technologies for improved situational awareness and early risk identification and mobile and wearable technologies for better mission management and in...

Adopting effective techniques to automatically detect and identify small drones is a very compelling need for a number of different stakeholders in both the public and private sectors. This work presents three different original approaches that competed in a grand challenge on the “Drone vs. Bird” detection problem. The goal is to detect one or mor...

Integration of symbolic and sub-symbolic approaches is rapidly emerging as an Artificial Intelligence(AI) paradigm. This paper presents a proof-of-concept approach towards an unsupervised learning method, based on Restricted Boltzmann Machines (RBMs), for extracting semantic associations among prominent entities in data. Validation of the approach...

This work addresses the problem of multi-task object detection in an efficient, generic but at the same time simple way, following the recent and highly promising studies in the computer vision field, and more specifically the Region-based Convolutional Neural Network (R-CNN) approach. A flow-enhanced methodology for object detection is proposed, b...

SURVANT is an innovative video archive investigation system that aims to drastically reduce the time required to examine large amounts of video content. It can collect the videos relevant to a specific case from heterogeneous repositories in a seamless manner. SURVANT employs Deep Learning technologies to extract inter/intra-camera video analytics,...

In this work we consider UAVs as cooperative agents supporting human users in their operations. In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV. To address this in a data-driven manner, we design a data synthesis pipeline to create a...

In this paper, two novel and practical regularizing methods are proposed to improve existing neural network architectures for monocular optical flow estimation. The proposed methods aim to alleviate deficiencies of current methods, such as flow leakage across objects and motion consistency within rigid objects, by exploiting contextual information....

In this work we consider UAVs as cooperative agents supporting human users in their operations. In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV. To address this in a data-driven manner, we design a data synthesis pipeline to create a...

In recent years, numerous deep learning approaches to video super resolution have been proposed, increasing the resolution of one frame using information found in neighboring frames. Such methods either warp frames into alignment using optical flow, or else forgo warping and use optical flow as an additional network input. In this work we point out...

The Unmanned Aerial Vehicle (UAV) proliferation has raised many concerns, since their potentially malicious usage renders them as a detrimental tool for a number of illegal activities. Radar based counter-UAV applications provide a robust solution for UAV detection and classification. Most of the existing research addresses the problem of UAV class...

Usage of Unmanned Aerial Vehicles (UAVs) is growing rapidly in a wide range of consumer applications, as they prove to be both autonomous and flexible in a variety of environments and tasks. However, this versatility and ease of use also brings a rapid evolution of threats by malicious actors that can use UAVs for criminal activities, converting th...

Automatic segmentation of the hippocampus from 3D magnetic resonance imaging mostly relied on multi-atlas registration methods. In this work, we exploit recent advances in deep learning to design and implement a fully automatic segmentation method, offering both superior accuracy and fast result. The proposed method is based on deep Convolutional N...

Residual Networks (ResNets) have introduced a milestone for the Deep Learning community due to their outstanding performance in diverse applications. They enable efficient training of increasingly deep networks, reducing the training difficulty and error. The main intuition behind them is that instead of mapping the input information, they are mapp...

In this paper, a user-centric approach for video summarization is introduced. The method produces meaningful video summaries, by fusing low-level visual information, extracted by processing consecutive frames, with high-level information derived from detected events. The video summaries are presented to the user in the form of most representative f...

In this paper, an automated methodology that builds a profile for each pedestrian tracked based on its appearance, its occlusion status and the semantic information related to its position, is presented. The extracted profiles are utilized to perform context-aware tracking in multi-target tracking scenarios. A novel fusion scheme that combines the...

Online group identification is a challenging task, due to the inherent dynamic nature of groups. In this paper, a novel framework is proposed that combines the individual trajectories produced by a tracker along with a prediction of their evolution, in order to identify existing groups. In addition to the widely known criteria used in the literatur...

In this paper, a novel approximate indexing scheme for efficient content-based image search and retrieval is presented, called Multi-Sort Indexing (MSIDX). The proposed scheme analyzes high dimensional image descriptor vectors, by employing the value cardinalities of their dimensions. The dimensions value cardinalities, an inherent characteristic o...

We demonstrated a 3D holoscopic video system for 3DTV application. We showed that using a field lens and a square aperture significantly reduces the vignetting problem associated with a relay system and achieves over 95 percent fill factor. The main problem for such a relay system is the nonlinear distortion during the 3D image capturing, which can...

In this paper, re-identification techniques are exploited to add context awareness to a multi-target tracker and enhance its tracking performance, in an online manner. To achieve that, targets are labeled as independent, occluders or occluded ones, based on the completeness of their appearance information. For each category, a different tracking st...

This paper demonstrates a new approach to detecting high-level events that may be depicted in images or video frames. Given a non-annotated content item, a large number of previously trained visual concept detectors are applied to it and their responses are used for representing the content item with a model vector in a high-dimensional concept spa...

This paper presents a GPU-assisted version of the LIB-SVM library for Support Vector Machines. SVMs are par-ticularly popular for classification procedures among the re-search community, but for large training data the processing time becomes unrealistic. The modification that is proposed is porting the computation of the kernel matrix elements to...

This paper proposes the use of feature tracks for the detection of concepts in video, particularly dynamic concepts. Feature tracks are defined as sets of local interest points found in different frames of a video shot that exhibit spatio-temporal and visual continuity, defining a trajectory in the 2D+Time space. The extraction of feature tracks an...

This work examines the possibility of exploiting, for the purpose of video segmentation to scenes, semantic information coming from the analysis of the visual modality. This information, in contrast to the low-level visual features typically used in previous approaches, is obtained by application of trained visual concept detectors such as those de...

This paper presents the video retrieval engine VERGE, which combines indexing, analysis and retrieval techniques in various modalities (i.e. textual, visual and concept search). The functionalities of the search engine are demonstrated through the supported user interaction modes.

This paper builds upon previous work on local interest point detection and description to propose the extraction and representation of novel Local Invariant Feature Tracks (LIFT). These features compactly capture not only the spatial attributes of 2D local regions, as in SIFT and related techniques, but also their long-term trajectories in time. Th...

This paper provides an overview of the tasks submitted to TRECVID 2009 by ITI-CERTH. ITI-CERTH participated in the high-level feature extraction task and the search task. In the high-level feature extraction task, techniques are developed that combine motion information with existing well-performing descriptors such as SIFT and Bag-of-Words for sho...

This paper provides an overview of the tasks submitted to TRECVID 2010 by ITI-CERTH. ITI- CERTH participated in the Known-item search (KIS) and Instance search (INS) tasks, as well as in the Semantic Indexing (SIN) and the Event Detection in Internet Multimedia (MED) tasks. In the SIN task, techniques are developed, which combine motion information...

In this paper, the MKLab interactive video retrieval system is described.

This paper presents an experimental comparison of dif-ferent approaches to learning from multi-labeled video data. We compare state-of-the-art multi-label learning methods on the Mediamill Challenge dataset. We employ MPEG-7 and SIFT-based global image descriptors independently and in conjunction using variations of the stacking approach for their...

A group of four organizations from the MESH consortium (www.mesh-ip.eu) participated this year for the first time in the High Level Feature Extraction track in TRECVID. The partners were Telefónica I+D (TID, Spain), Informatics & Telematics Institute (ITI, Greece), National Technical University of Athens (NTUA, Greece) and Universidad Autónoma de M...

Abstract In this paper, we give an overview of the four tasks submitted to TRECVID 2008 by COST292. The high-level feature extraction framework comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second syste...

Several scene-change detection algorithms have been proposed in literature up to now. Most of them use fixed thresholds for the similarity metrics used to decide if there was a change or not. These thresholds are obtained by empirically or they must be calculated before the detection after the whole sequence is obtained. Performance of most scene c...