Special Session for EU Projects: 16 July, 09:25-11:45
This year we will have a special session (16.July.2015, organised by the LASIE Project) of invited talks by relevant EU projects.
We have invited presentations related to EU-funded projects especially in the areas of security, crime prevention, imaging systems and applications, social impact of such technologies and any other relevant fields. These projects will be able to disseminate their objectives and results through oral presentations, posters and demonstrations.
Please contact Dr Apostolos Axenopoulos for further details on the arrangements.
PARIS will define and demonstrate a methodological approach for the development of surveillance infrastructure which enforces the right of citizens for privacy, justice and freedom and takes into account the evolving nature of such rights, e.g. aspects that are acceptable today might not be acceptable in the future, and the social and ethical nature of such rights, e.g. perception of such rights varies.
The methodological approach will be based on two pillars, first a theoretical framework for balancing surveillance and privacy/data protection which fully integrates the concept of accountability, and secondly an associated process for the design of surveillance systems which takes from the start privacy (i.e. Privacy-by-Design) and accountability (i.e. Accountability-by-Design).
The theoretical framework will first be defined in a generic way and guidelines will be provided to define specialized conceptual frameworks (e.g. for a given country), which are called SALT frameworks (Social / ethicAl / Legal / Technological). Examples of SALT frameworks will be provided. The case of SALT frameworks interplay (i.e. exchanging surveillance data) will be analysed. A framework management tool will be developed (1) to allow for the creation and edition of a conceptual framework and (2) to subsequently act as a reference to surveillance system designers.
A SALT compliant design process will then be defined, i.e. surveillance and privacy balance according to the specialized framework will be ensured through the process. Two use case will be demonstrated, one based on video search technology which focuses on the archived data, and one based on biometrics technology which focuses on embedded systems sensor like data. The two use cases will used different SALT frameworks. The resulting methodology will be promoted through associations and standardization bodies.
The project is 36-months long and has received funding from the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement number 312504.
Martin Boyer: is working as research engineer at AIT. He graduated in electronics from FH Technikum Wien in 2003. During 2002 and 2003 he developed digital filter and data transmission systems to measure the state of power-grid overhead and underground cables. From 2003 to 2006 he worked as a software developer in the field of engine control units especially improving adaptive cruise control systems and contributing to a patent in the field of injector drift compensation. From November 2006 he worked as a software architect on research projects with the Austrian national railways in the field of track geometry and applied geodesy. He joined AIT in 2011 as research engineer in the area of video and security technology with a strong focus on distributed computation of video processing tasks. The resulting system is utilized in multiple projects, among others as base for the video processing of ABC systems in the FastPass project, as well a use case demonstration in the PARIS project.
Stephan Veigl: has an MSc in Computer Science from Vienna University of Technology. He is a software engineer at AIT focusing on modern concepts and architectures for video and image processing. Mr. Veigl has researched and implemented tracking algorithms for embedded systems as well as desktop computers. Currently, he is working on the software design of a modular, service based video analytics system capable of processing both, offline and live data. This system is utilized in multiple projects, among others as base for the video processing of ABC systems in the FastPass project, as well a use case demonstration in the PARIS project.
Petty Crimes (also known as Volume Crime) take place on a daily basis affecting citizens, local communities, business owners and infrastructure owners. Petty Crime incidents such as theft, criminal damage and anti-social behaviour are on the rise in Europe due to the economic crisis and in turn incidents adversely impact the local socioeconomic environment.
The P-REACT project will design and develop a low cost surveillance platform that will detect Petty Crime incidents. The solution will encompass intelligent video and audio sensors to detect petty crime incidents, a cloud based monitoring, alert detection and storage platform. Technology trends in computer vision, motion detection, video retrieval, semantic video analysis and cloud technology will be exploited.
The solution will focus on connecting citizens, business owners, infrastructure owners and security and law enforcement personnel so that Petty Crime incidents can be effectively dealt with and prevented in the future.
The project will ensure that legal, ethical and end user needs are properly balanced and addressed ensuring a 'Privacy-by-design' solution approach.
Juan Arraiza: Staff Researcher at Vicomtech, leader of security related R&D projects and Project Coordinator of the FP7 P-REACT project. He graduated in Computer Science from Deusto University in 1997. After a MPhil in Software Engineering at Deusto University (1998-1999) he first worked at PricewaterhouseCoopers as an E-Business consultant (1999-2000) and then he moved to Thomson Reuters Aranzadi where he worked as software engineer, then as project manager, and finally as the manager of the Project Management Office (2000-2012). Juan is PMP certified since 2005 and he is currently working on his PhD thesis in Project Management.
"3D-Forensics - Mobile high-resolution 3D-Scanner and 3D data analysis for forensic evidence" is co-funded by the European Union under the Seventh Framework Programme for research and technological development. The project is focussed on improving both the workflow of capturing and also analysing footwear and tyre impressions left at crime scenes. The data capturing methodology is based on optical 3D scanning by projection of fringe patterns onto a surface implemented in a compact, handheld scanner device for direct use at crime scenes. The scanner is combined with new analysis tools that support the determination of class and identification characteristics of footwear and tyre impressions out of the digital 3D data and comparison between impressions. The project has seven European partners including police forensic experts from the Netherlands. It started in May 2013 and will be completed in August 2015. The prototypes are being tested at the moment. The presentation will present the project's approach, foreseen advantages and the actual hard and software development results.
Stephen Crabbe is the Managing Director of Crabbe Consulting Ltd (CCLD). CCLD works at the interfaces between end users, researchers and industry to support international cooperative Research, Development and Innovation (RD&I) often with European funding, particularly in connection with security challenges facing society. He has over 18 years initiating, managing and researching and developing in such projects. In the area of forensics, previous projects have included the development of a police database to identify and link missing persons and unidentified bodies at an international level. He obtained his undergraduate degree in Laws from University College London and a postgraduate diploma in vocational training for the Bar from BPP University College of Professional Studies.
Current video-surveillance systems in urban scenarios are very limited and only consist in a presentation of the visual information captured by the visual sensors network, not oriented to end-users, that limiting thus the capacity to help and prevent the criminal activity. Furthermore, the visual-surveillance systems usually do not have any automatic process to store the more relevant evidences to be used in the legal punitive process of the criminals. The SmartPrevent project focuses on the detection and prevention of frequent petty crimes that are of high impact to local communities and citizens in urban scenarios, considered to be a low-cost video-surveillance system oriented to end-users.
SmartPrevent proposes to address this challenge by:
Víctor Fernández-Carbajales Cañete holds a degree in Electronic Engineering from the Autonomic University of Madrid (2004) and he doing his PhD in Computer and Telecommunication Engineering in the University of Madrid. In 2004, he joined the Video Processing and Understanding Lab (VPU Lab) at Universidad Autónoma de Madrid, a research group focused on digital image processing theory, methods and applications aimed for video sequence analysis and visual content adaptation.
He is currently R&D Project Manager in Treelogic and Head of Computer Vision Team. He has a wide experience in R&D projects related to a range of technologies, although he is specialized in video-surveillance systems, low-level video processing, semantics and personalization technologies. In an industrial domain, he is responsible for several projects on applications of video processing methods and behavioural modelling to prevent adverse and risky events.
As a technical manager, he is been leading several European projects focused on computer vision in the following topics:
- Studying the characteristics of frequent criminal activities in real urban scenarios including typical variations and unanticipated criminal situations.
- Developing a low-cost adaptive video-surveillance system in order to detect and prevent criminal activities.
- Building a video-surveillance system as punitive tool in order to store the most relevant evidences of the detected criminal activities.
CogLaboration (FP7-287888): focused in the object transfer procedure between a robot and a human, considered to be a key aspect to be addressed to provide successful and efficient robotic assistance to humans.
SmartPrevent (FP7-606952): focuses on the detection and prevention of frequent petty crimes with high impact to local communities and citizens in urban scenarios, considered to be a low-cost video-surveillance system oriented to end-users.
SAFEROADAS (E!-8217): Its objective is the creation of a new tool for automation traffic management, based on the already existing camera infrastructure, with the purpose of improving the current capacities
Finally, his research interests are focused in the analysis of video sequences for the video surveillance (moving object extraction, object tracking and recognition, event detection, ...), real time video processing, scene understanding in complex environments and the using of the visual attention in this environment.
The LASIE project aims to design and implement an open and expandable framework that will significantly increase the efficiency of current investigation practices, by providing an automated initial analysis of the vast amounts of heterogeneous forensic data that analysts have to cope with. The framework will be able to handle forensic data that have been acquired from a variety of different sources including CCTV surveillance content, confiscated desktops and hard disks, mobile devices, Internet, social networks, handwritten and calligraphic documents. The LASIE framework will be able to: (i) extract evidence from the available data (text, images, video, audio and biometric information in multiple formats), (ii) perform inferences based on the evidence, (iii) guide the investigation process through the incorporation of recommendation functionality, and (iv) interact with the user through an efficient and user-friendly interface. The overall process will be performed under the condition that all legal and ethical restrictions are satisfied and the computed data can be presented as evidence in European courts of law.
LASIE is a project funded by the European Commission. This project is receiving funding from the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement nr. 607480
Petros Daras PhD, MSc, SMIEEE, is a Senior Researcher Grade B (Associate Professor) and Chair of the Visual Computing Lab. He received the Diploma in Electrical and Computer Engineering, the MSc and the Ph.D. degrees in Electrical and Computer Engineering all from the Aristotle University of Thessaloniki, Greece in 1999, 2002 and 2005, respectively. His main research interests include visual content processing, multimedia indexing, search engines, recommendation algorithms and relevance feedback. His involvement with those research areas has led to the co-authoring of more than 150 papers in refereed journals and international conferences. Dr Daras has been involved in more than 20 projects, funded by the EC and the Greek Ministry of Research and Technology. Among them, he is the Technical Manager of the EC projects LASIE, ADVISE, VICTORY and I-SEARCH. Dr. Daras is a Senior member of IEEE. He regularly acts as a reviewer for the European Commission and the GSRT.
Apostolos Axenopoulos PhD, MSc, works as an Associate Researcher at the Information Technologies Institute (CERTH/ITI), since November 2003. He received the Diploma in Electrical and Computer Engineering (2003) and the MSc degree in Advanced Computing Systems (2008) from the Aristotle University of Thessaloniki and his Ph.D. degree in Electrical and Computer Engineering (2014) from the University of Thessaly. He has participated in more than 10 projects, funded by the EC and the Greek Ministry of Research and Technology. His main research interests include multimedia processing, computer vision and pattern recognition. He has published more than 30 papers in refereed journals, book chapters and international conferences, and he is a reviewer for several journals and conferences. He is also a Member IEEE.