Distributed Events Analysis Research GroupHead of department- Tamás Szirányi
Secretary- Monika Barti
 Address: 1111 Budapest, Kende u. 13-17.Room number: K 413Phone: +36 1 279 6132, +36 1 279 6247E-mail: bartiEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
Generic information
Description
The goal of the DEVA group is the interpretation and organization of information coming from dis-tributed sensors. Sensors can be dynamic or static imaging devices or other multimedia sources. By spatio-temporal analysis of information we recog-nize and classify events. These events are e.g. unusual motion patterns, behavior change in time series, voice patterns, or words different from the usual ones. We place special emphasis on machine learning, data mining, human perception, geomet-rical optics, optimization methods and variational analysis in areas such as image and video process-ing, biometrical identification, connections with sensor networks and computer graphics.
Research Areas
• Ontology based classification and indexing of multimedia events
• Recognition and tracking of biometric features
• Energy based image and video segmentation
• Stochastic models and learning methods for event analysis
• Automatic camera registration, event matching of multiple views, optics-oriented image understand-ing
• Self organizing distributed sensor-networks and related calculations, operation optimization
• Cognitive vision problems in visibility, compression, recognition, visualization of artistic effects
• Detection and removal of artifacts from still images: shadow regions, reflections, undesired objects
More information:
Staff- Csaba Benedek
- Attila Börcs
 Address: 1111 Budapest, Kende u. 13-17.Room number: K405E-mail: borcsEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
- László Rajmund Havasi
- Miklós Homolya
- Oszkár Józsa
- Anita Keszler
- Ákos Kiss
 Address: 1111 Budapest, Kende u. 13-17.Room number: K409-412Phone: +36 1 279-6106E-mail: kiss.akosEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
- Andrea Kovács
 Address: 1111 Budapest, Kende u. 13-17.Room number: K409-412Phone: +36 1 279 6106E-mail: andrea.kovacsEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
- Levente Attila Kovács
- Judit Megyery
Address: 1111 Budapest, Kende u. 13-17.Room number: K 124Phone: +36 1 279 6214, +36 1 209 6001Fax: +36-1-386-9378E-mail: megyeryEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
- Dömötör László Molnár
- Dinh Bao Nguyen
- Szilárd Szalai
Address: 1111 Budapest, Kende u. 13-17.Room number: K 409-412E-mail: szalaiEZT_TOROLJE_KI@EZT_TOROLJE_KIsztaki.hu
- Ákos Utasi
- Anikó Vágvölgyi
2012.- Building Development Monitoring in Multitemporal Remotely Sensed Image Pairs with Stochastic Birth-Death Dynamics
 Authors: Benedek, Csaba; Descombes, Xavier; Zerubia, JosianeDate: 2012. 01. 01.Download article: [94]
2011.- Analysis of Solder Paste Scooping with Hierarchical Point Processes
- Orthogonality based stopping condition for iterative image deconvolution methods.
- A 3-D Marked Point Process Model for Multi-View People Detection
- Interactive Search and Result Visualization for Content Based Retrieval
- Improved Force Field for Vector Field Convolution Method
- Detection of Soldering Defects in Printed Circuit Boards with Hierarchical Marked Point Processes
2010.- Building detection in a single remotely sensed image with a point process of rectangles.
Authors: Benedek, Csaba; Descombes, Xavier; Zerubia, JosianeDate: 2010. 08.Download article: [pdf]
- Trainable blotch detection on high resolution archive films minimizing the human interaction
- Detection of unusual optical flow patterns by multilevel hidden Markov models.
- A statistical method for object localization in multi-camera tracking.
2009.- VISRET - a content based annotation, retrieval and visualization toolchain.
- Extraction, categorization and unusual motion signaling of small moving objects.
- Seamless NPR video painting.
- Change detection in optical aerial images by a multilayer conditional mixed Markov model.
- Detection of object motion regions in aerial image pairs with a multilayer Markovian model.
2008.- Behavior and event detection for annotation and surveillance.
- Bayesian foreground and shadow detection in uncertain frame rate surveillance videos.
2007.- Video camera registration using accumulated co-motion maps.
- Detection of gait characteristics for scene registration in video surveillance system.
- Focus area extraction by blind deconvolution for defining regions of interest.
- Stochastic view registration of overlapping cameras based on arbitrary motion.
- Painterly effects rendering with focus based level of detail.
- Study on color space selection for detecting cast shadows in video surveillance.
Date: 2007.
2006.- Estimation of the vanishing point in camera-mirror scenes using from video
- Higher order symmetry for non-linear classification of human walk detection
- Markovian framework for foreground-background-shadow separation of real world video scenes
2005.- Relative focus map estimation using blind deconvolution
|
Departments 
Magyar
