Institute of Information Theory and Automation

Methods and Algorithms for Vector and Tensor Field Image Analysis

Project leader: Prof. Ing. Jan Flusser, DrSc.
Department: ZOI
Supported by (ID): GA18-07247S
Grantor: Czech Science Foundation
Type of project: theoretical
Duration: 2018 - 2020
Publications at UTIA: list


The proposal falls into the area of computer image analysis and pattern recognition. It is focused on special type of data - multidimensional vector and tensor fields. Vector fields may describe particle velocity, optical/motion flow, image gradient, deformation/condutivity/diffusion tensors, and other phenomena. Each pixel value is a vector/tensor whose components cannot be treated independently. Many manipulations with a vector field are governed by different mathematical models than the same operations with scalar images. Existing image analysis methods cannot be readily extended to work with vector fields. The goal of the project is to develop methods and algorithms for detection, matching and tracking of patterns of interest, such as sinks, vortices, saddle points, vortex-saddle combinations, double vortices, and other specific patterns. The detection must be invariant to particular position, size and shape deformation of the pattern. The project results may find applications in mechanical engineering, fluid dynamics, medicine, computer vision, and meteorology.
Responsible for information: ZOI
Last modification: 23.12.2017
Institute of Information Theory and Automation