MUSESUAN 2014 Abstracts


Full Papers
Paper Nr: 3
Title:

MOSAIC - Multimodal Analytics for the Protection of Critical Assets

Authors:

Atta Badii, Marco Tiemann, Richard Adderley, Patrick Seidler, Rubén Heras Evangelio, Tobias Senst, Thomas Sikora, Luca Panattoni, Matteo Raffaelli, Matthew Cappel-Porter, Zsolt L. Husz, Thomas Hecker and Ines Peters

Abstract: This paper presents an overview of the MOSAIC architecture and the validated Demonstrator resulting from an EU-co-funded research project concerned with the development of an advanced system for the use and integration of multimodal analytics for the protection of critical assets. The paper motivates the MOSAIC vision and describes the major components of the integrated solution; including the ontological framework, the data representation, text mining, data mining, video analytics, social network analysis and decision support. In the descriptions of these components, it is illustrated how MOSAIC can be used to improve the protection of critical assets without necessitating data gathering that goes beyond what is already currently being gathered by relevant security organisations such as police forces by improving data analytics techniques, integration of analysis outputs and decision support mechanisms.

Paper Nr: 5
Title:

A Multi-configuration Part-based Person Detector

Authors:

Alvaro Garcia-Martin, Ruben Heras Evangelio and Thomas Sikora

Abstract: People detection is a task that has generated a great interest in the computer vision and specially in the surveillance community. One of the main problems of this task in crowded scenarios is the high number of occlusions deriving from persons appearing in groups. In this paper, we address this problem by combining individual body part detectors in a statistical driven way in order to be able to detect persons even in case of failure of any detection of the body parts, i.e., we propose a generic scheme to deal with partial occlusions. We demonstrate the validity of our approach and compare it with other state of the art approaches on several public datasets. In our experiments we consider sequences with different complexities in terms of occupation and therefore with different number of people present in the scene, in order to highlight the benefits and difficulties of the approaches considered for evaluation. The results show that our approach improves the results provided by state of the art approaches specially in the case of crowded scenes.

Paper Nr: 7
Title:

GIS-supported People Tracking Re-acquisition in a Multi-camera Environment

Authors:

Anastasios Dimou, Vasileios Lovatsis, Andreas Papadakis, Stelios Pantelopoulos and Petros Daras

Abstract: Modern surveillance systems consist of multiple, geographically dispersed cameras, increasing the technical and scalability challenges for person re-identification. In this context, the use of geographical information to boost the effectiveness of a state-of-the-art re-identification algorithm has been implemented and evaluated, by leveraging the prediction of an event evolution. It is argued that the estimation of possible target trajectories can limit the footage search space and allow focused application of the re-identification algorithm. This is reflected in performance, effectiveness and scalability. The parametrization of the interesting footage reduction mechanism allows using different profiles and a flexible trade-off between performance and robustness. Our work is verified and evaluated in a well known benchmark dataset for re-identification and a real-world dataset created in the framework of the EU-project ADVISE.

Short Papers
Paper Nr: 4
Title:

Data Integration, Semantic Data Representation and Decision Support for Situational Awareness in Protection of Critical Assets

Authors:

Atta Badii, Marco Tiemann and Daniel Thiemert

Abstract: This paper presents the design and development of a system for data integration, data representation, situational awareness and decision support that has been developed in the EC-co-funded research project MOSAIC. The paper motivates the architecture and describes the data representation model and the developed system components. It discusses the approach for improved situational awareness and decision support as a novel integration of systems developed under the MOSAIC project as deployed for the protection of critical assets as a demonstrator.

Paper Nr: 6
Title:

Multimedia Analysis of Video Sources

Authors:

Juan Arraiza Irujo, Montse Cuadros, Naiara Aginako, Matteo Raffaelli, Olga Kaehm, Naser Damer and Joao P. Neto

Abstract: Law Enforcement Agencies (LEAs) spend increasing efforts and resources on monitoring open sources, searching for suspicious behaviours and crime clues. The task of efficiently and effectively monitoring open sources is strongly linked to the capability of automatically retrieving and analyzing multimedia data. This paper presents a multimodal analytics system, created in cooperation with European LEAs. In particular it is described how the video analytics subsystem produces a workflow of multimedia data analysis processes. After a first analysis of video files, images are extracted in order to perform image comparison, classification and face recognition. In addition, audio content is extracted to perform speaker recognition and multilingual analysis of text transcripts. The integration of multimedia analysis results allows LEAs to extract pertinent knowledge from the gathered information.