tailieunhanh - Machine Vision - David Vernon Part 11

Tham khảo tài liệu 'machine vision - david vernon part 11', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Introduction to image understanding to determine . Thus to determine Vt and vr and hence z we exploit the value of V1 the orthogonal component of velocity computed at an earlier stage. This can be accomplished directly by solving the attendant system of equations or by a geometrical construction. In the solution by geometrical construction V is determined from the intersection of three straight lines derived from Vĩ for which all terms are known V1- which was computed previously and the position of the FOE. First Vĩ defines the first line of the construction refer to Figure . Second the position of the FOE defines the direction of Vt since ft is parallel to the line joining the FOE and the point x J in question. Thus the second line is parallel to ft and passes through the point given by Vr see Figure . The coordinates of the FOE are given by XFOE yFOE where JFx Wy and wz are the known velocities of the camera in the X- y- and z-directions respectively. Finally we note again that V is also given by the sum of the orthogonal component and the tangential component of velocity v vx 1 T Since these two vectors are orthogonal to one another and since is known this relationship defines a third line through the point given by f1 and normal to the direction of VHence V is given by the intersection of the second and the third lines see Figure . In the simpler case of translatory motion along the optic axis Ỡ is equal to Figure Computation of true velocity V from V1 Vtvr at a point p on a zero-crossing contour. 238 Visual processes zero and the translational component of velocity reduces to Vt x Di-D2 y Di-D2 z z while the rotational component vr is now zero. Computing V in this manner and in particular computing Vs- using image differences errors can still be recorded in the final flow. A significant improvement can be achieved by performing a contour-to-contour matching between successive frames along the direction of the flow vectors tuning the length .