Research Article
A Real-Time Optical Tracking and Measurement Processing System for Flying Targets
Algorithm 1
Multiple interest points location based on 2D contour model.
Input: 2D shape model , real-time contour with discrete sampling sets expression | Input: model interest point sets | Output: interest point sets in the real-time image | (1) // initial registration | (2) Decide whether and are mirrored or not. if mirrored, flip them. end if | (3) Compute the initial registration relationship on the hypothesis of similarity transformation, centroids | and , included angle between main axis with axis and by moment of inertia, and contour | perimeter and , so | scale /; rotation angle ; translation vector . | (4) // iterative optimization | (5) Iteration frequency . | (6) Change to according to initial registration relationship | (7) Find the nearest point pairs [4] by ass(, ) = where and are the indexes of the contour sampling | points, and size is the function for capacity computing. The distance of the nearest point pairs is computed by | (*), and the homograph is estimated with RANSAC. | (*) | (8) if or | (9) Terminate the iteration, optimized is as (**), . | (**) | (10) else , goto (7). | (11) end if |
|