The objective of FitOptiVis is to develop a cross-domain approach for smart integration of image- and video-processing pipelines for CPS covering a reference architecture, supported by low-power, high-performance, smart devices, and by methods and tools for combined design-time and run-time multi-objective optimisation within system and environment constraints.

Graded properties are ubiquitous in human discourse and reasoning. They are characterized by the fact that they may apply with different intensity to different objects. Typical examples are vague properties (e.g.

Objects moving fast with respect to the camera appear blurred when observed. Surprisingly this common phenomenon has not yet been considered and analyzed by the computer vision community. It is the blur that encodes information about the object motion properties. Instead of considering blur as a nuisance, the project proposes to take it as a cue for detection and tracking of fast moving objects.

The goal of the project is to establish the research cooperation between the mutually complementary Taiwan and Czech research teams. The research is oriented to the development and verification of a new data mining technique based on probabilistic compositional models, the theory of which was developed by the Czech partner in the last decade.

The goal of the project is to develop new methods for colour image acquisition and processing and to apply the results of this research in selected practical applications. The project is aimed at colour image with high colour resolution, with up to several tens colour components.

The topic of this project is to develop efficient algorithms for robust image description and for recovering a clear image from its degraded version.

This project is focused on systematic experimental investigation and theoretical description of nucleation and propagation of martensitic phase transformation via localized inhomogeneities in NiTi shape memory alloys, so-called transformation bands.