This paper presents a method for computation of two-dimensional motion vector fields from an image sequence. The magnitudes from a set of spatio-temporal quadrature filters are combined into a tensor description. The shape of the tensors describe locally the structure of the spatio-temporal neighbourhood and provides information about local velocity and if true flow or only normal flow is present. It is shown how normal flow estimates are combined into a true flow using linear filtering on this tensor field description.<>
Estimation of motion vector fields using tensor field filtering
Proceedings of 1st International Conference on Image Processing ; 2 ; 237-241 vol.2
1994-01-01
433738 byte
Conference paper
Electronic Resource
English
Estimation of Motion Vector Fields using Tensor Field Filtering
British Library Conference Proceedings | 1994
|Dense Motion Field Estimation using Spatial Filtering and Quasi Eigenfunction approximations
British Library Conference Proceedings | 2005
|Research issues in vector and tensor field visualization
IEEE | 1994
|Motion estimation and vector splines
IEEE | 1994
|