Building R, Room 120
Department Informatik, University of Hamburg
Vogt-Koelln-Str. 30 Hamburg
Phone: +49 (40) 42883-2580
Email: terzic somewhere-at informatik.uni-hamburg.de

• Research interests
• Projects
• Publications
• Videos
• BV Übung

I have moved to the Vision Lab at the University of Algarve.

Research Interests

Scene Interpretation

• middle-layer in a scene interpretation system
• use of reasoning and context in computer vision
• detection of spatiotemporal occurrences
• classification and categorisation

3D Segmentation and Analysis

• N-dimensional image processing algorithms
• industrial applications of 3D image analysis
• medical imaging
• 3D visualisation

Other

• neural networks
• cognitive science
• autonomous vehicle navigation
• knowledge representation

Projects

Cognitive and Flexible Learning System Operating Robust Interpretation of Extended Real Scenes by Multi-sensors Datafusion

Oct 2009 - Feb 2011

Co-FRIEND aims to design a framework for understanding human activities in real environments, through an artificial cognitive vision system, identifying objects and events, and extracting sense from scene observation. It will manage uncertainty and change, and will create analysis meaning.

E-Training for Interpreting Images of Man-Made Scenes

Apr 2006 - Sep 2009

The aim of this project is to advance the state of the art of cognitive systems by developing a methodology for autonomous and continuous learning. The project will concentrate on structural learning, where relations between components and compositional hierarchies play a central role in object categorization. Such learning is particularly relevant for the interpretation of man-made objects, hence the project will use the recognition of buildings in outdoor scenes as its exemplary application domain.

3D Analysis of Medium Density Fibreboards

2005

The aim of this project is to develop methods for analysing 3D tomography images of medium density fibreboards (MDF), a material made of wood commonly used in the industry. The tasks include the segmentation of individual fibres, finding the contact surface between the fibres, determining the amount of adhesive resin, calculating the lumen volume and visualising the results.

Cognitive Vision

Oct 2003 - Dec 2004

The objective of this project is to provide the methods and techniques that enable construction of vision systems that can perform task oriented categorization and recognition of objects and events in the context of an embodied agent. The functionality will enable construction of mobile agents that can interpret the action of humans and interact with the environment for tasks such as fetch and delivery of objects in a realistic domestic setting.

Videos

Facade Segmentation

Segmentation

A video showing the combination of several low-level segmenters using a probabilistic high-level model provided by the Bayesian Compositional Hierarchy. The best combination of regions from the evidence soup is selected and classified based on a set of valid facade models. Done together with Arne Kreutzmann

3D Wood Segmentation

Fibre - Resin

Two videos showing the segmentation of wood fibres. The first video shows the fibre segmentation process, starting with noise removal, following up with lumen detection and finally showing a detected fibre. The second video shows the detection of the adhesive resin.

Interpreting Table Scenes

Tracking - Interpretation

Two videos showing the interpretation process on table-setting scenes. The first video shows the tracking and object detection module which provides evidence. The second video shows a part of the interpretation process using the KONWERK tool and the final interpretation. Done together with Lothar Hotz

BV Übungen

Die Bilder für die Übungsaufgaben für die Vorlesung "Bildverarbeitung" von Prof. Neumann finden Sie hier:

Blatt 1, Aufgabe 2: Bayer filter image

Blatt 3, Aufgabe 4: Salt'n'peppa