The epipolar line calculation unit (26) calculates an epipolar line, of a prescribed image, that should pass through a prescribed feature point.

An epipolar geometry of the captured images can be determined.

The images can be rectified to parallelize epipolar lines of the epipolar geometry.

Epipolar geometry describes the mapping relationship between the two images.

Each line in the virtual image is reconstructed from a line set of the epipolar image.

The epipolar geometry constraint may further be combined with local, heuristic constraints or robust statistical methods.

Coupled use of two or more devices enables automated range computation without the need for subsequent epipolar rectification.

The offset epipolar image includes a plurality of line sets, each such line set incorporating one scanning line from each of the discrete video images.

The homologous epipolar lines are superposed, so we have solved the problem of epipolar geometry.

This relationship is based on the parallax motion of points with respect to an arbitrary planar surface, and does not involve epipolar geometry.

The image position (14) on the second epipolar line (9b) for which the measure of agreement is greatest is determined.

The underlying geometry that describes the relationship between both cameras is known as the epipolar geometry.

The epipolar geometry for the point correspondence having a minimum median error is selected as the 2D view geometry of the scene.

A three-dimensional measurement method three-dimensionally restores an edge having a cross angle close to parallel to an epipolar line.

Improvements in both accuracy and performance in computing optical flow are achieved utilizing the epipolar geometry constraint.