Emmanuel Sardis

A dataset for workflow recognition in industrial scenes

In this paper we introduce the WR (Workflow Recognition) dataset. Recorded in the production line of a major automobile manufacturer, this dataset consists of sequences that depict workers executing industrial workflows. The heavy occlusions, outliers, the visually complicated background and the human-machinery interaction are among the factors that make this dataset a very challenging testbed for computer vision and image processing algorithms. We provide the original video sequences together with event labeling, as well as feature vectors extracted through our proposed scene representation methodology, and we refer to our results so far in workflow recognition using this dataset.

A Threefold Dataset for Activity and Workflow Recognition in Complex Industrial Environments

Unlike any previous effort, the Workflow Recognition (WR) large-scale dataset is a collection of video sequences from the real industrial manufacturing environment of a major automobile manufacturer.

Social media meta-API: leveraging the content of social networks

Social Network (SN) environments are the ideal future service marketplaces. It is well known and documented that SN users are increasing at a tremendous pace. Taking advantage of these social dynamics as well as the vast volumes, of amateur content generated every second, is a major step towards creating a potentially huge market of services. In this paper, we describe the external web services that SocIoS project is researching and developing, and will support with the Social Media community. Aiming to support the end users of SNs, to enhance their transactions with more automated ways, and with the advantage for better production and performance in their workflows over SNs inputs and content, this work presents the main architecture, functionality, and benefits per external service. Finally, introduces the end user, into the new era of SNs with business applicability and better social transactions over SNs content.

iPromotion: A Cloud-Based Platform for Virtual Reality Internet Advertising

We present a large-scale platform for distributing Virtual Reality advertisements over the World Wide Web. The platform aims at receiving and transmitting large amounts of data over mobile and desktop devices in Smart City contexts, is based on a modular and distributed architecture to allow for scalability, and incorporates content-based search capabilities for Virtual Reality (VR) scenes to allow for content management. Data is stored on a cloud repository, to allow for a large amount of VR material to be kept and distributed, and follows a service-based approach of independent subsystems for the management, conversion and streaming of information. In order to function over a wide range of used end-devices, from mobile phones to high-end desktop PCs, the system is based on HTML5 technologies, and implements a remote rendering server to alleviate the computational burden on the end device. Furthermore, an extension of the MPEG-7 standard is used for the description and retrieval of 3D scenes from the cloud, and we have further ensured compliance of our system with a number of other structure and communication standards, to ensure extensibility and reusability of the sub-modules. The platform is a research work in progress: we present the subsystems already implemented, plan our next steps and describe our contributions to research.

An industrial video surveillance system for quality assurance of a manufactory assembly

In this paper, we present the research achievements of a computer vision system that surveys the behavior of workers in an industrial environment. The proposed system applies weakly supervised learning algorithms able to detect objects, then to extract the behaviors of workers with respect to the predefined assembly construction for a task and adopts adaptation mechanisms able to dynamically modified the performance of a system with respect to the environmental changes. The proposed architecture has been tested on real-life applications.

Handling multiple channel video data for personalized multimedia services: A case study on soccer games viewing

Personalization is undoubtedly present in todays pervasive and ubiquitous environments and tends to be an increasingly popular requirement in every technological aspect of the everyday life. When it comes to live multimedia services, however, there is still a lot to be done to satisfy the demanding user who wishes to view the most important parts of events that take place in parallel. In this paper, a service that allows users to personalize the provision of multimedia streaming services offered through broadcasting networks is described. The service is aimed at offering full personalization capabilities over traditionally broadcast oriented terminals such as TV sets and Set Top Boxes. Complete personalization can be achieved through analog TV or DVB broadcasts with the use of personal devices such as mobile phones by using IP connection for the return channel (RC) (DVBRC). A use case scenario featuring one example related to personalized viewing of two parallel athletic events (such as Champions League soccer matches) is described and used for the evaluation of a prototype implementation of the service.

Emergency operations support through social networking and P2P multimedia services

In this paper we investigate the requirements and propose the design of a platform that will serve emergency operations such as in cases of wildfires or road accidents. This platform will provide assistance to the rescue and the disaster relief operations through the use of social networking and P2P based multimedia streaming. The general idea is to create a platform that will facilitate the provision of an efficient communication network between the stakeholders who will be involved in such life threatening situations and of the means for having a rich, multimedia based communication for first aid and guidance. Based on the use of the proposed platform the distribution of multimedia streams can be supported through innovative techniques such as media encoding and media distribution. The matching and notification of the most appropriate volunteers can be made through the use of personal profiles and the deployment of social networking tools. The access to multimedia content can be adapted to the obstacles which are introduced through the impairment of infrastructures of services capabilities.

Biopolis, Long Term Preservation of Digital User Content

The Biopolis takes a radical approach to the long term preservation of digital user content. The system will allow Biopolis enriched User Content to be distributed and redistributed through a network of commercial and non-commercial file (Preservation Services), while ensuring a lasting relationship, between the holder and the owner of the intellectual content. Based on web and mobile technologies and using a cloud based storage system will allow the end user to maintain the time and geolocation parameter on its digital content, providing new advanced business models for e-business end users.

ESTIMATION OF FRAME SEQUENCE NOISE WITH REMOVAL OF JPEG ARTIFACTS

This paper proposes a method to remove JPEG noise artifacts from frame sequences. Using extensive experimental results we show how an online system with periodic noise estimation functionality can estimate the real frame noise even if the images are in JPEG format. We present the mathematical basis of the methodology and show in real content that we can have reliable measurements. We also present the results obtained on a real network camera and show that our method can provide a much better estimation of the noise standard deviation compared to common practice but comparable interchannel and spatial intra-channel correlation estimates. We also provide some guidelines for capturing datasets necessary to apply computer vision tasks. Our approach exploits the well known stochastic linearization phenomenon which we prove that is present in our case.

PERIKLIS - Electronic Democracy in the 21st Century

PERIKLIS platform encourages citizen participation and supports sophistication of electronic government services by leveraging the capabilities of location based services, social networks and web 2.0 technologies. In this paper a structured analysis is adopted for identifying the advantages, from the digital transformation of the government transactions and the electoral processes, exploring the notion of society members and the benefits for better life conditions through electronic transactions in a Municipality. Adopting a computing approach for e-government and voting methodologies with an easy setup and completion by its members is investigated, reviewing the availability of services through mobile and web based systems, coupled with geo location services. Furthermore, PERIKLIS proposes a high level e-governance and e-voting solution for a municipality while investigating issues that require further research for exploitation and interoperability with more than one Municipalities.