Method of boundary detection based on B-spline curve fitting

In order to enhance the tracking accuracy and efficiency of the target area in vision navigation, this paper presents a new kind of boundary extraction n algorithm. It begins preprocessing the acquisition image to get binary image, then fills binary image area based on mathematical morphology to binary image and extracts boundary with classical algorithms, fuses many boundary information into a border area, finally applied non-uniform rational B-spline interpolation method to fit curve. The presented results indicate that this algorithm can correct extract arbitrary complicated shape boundary fast, which definitely provides a better basis for the following image processing.