摘要

Stable and efficient extracting the centre of laser stripe in image is a challenging computer vision problem. Existing methods are mainly based on the Gaussian and parabola distribution of laser stripe. However, the new beam-shaping technology is developed to make the light intensity of laser stripes with a uniformly distribution instead of Gaussian distribution. This paper proposes a fast and robust algorithm for laser stripe centre extraction based on Legendre moment theory. The proposed method can be summarized as follows: first, an ideal one-dimensional light intensity model of laser stripe is given based on the uniformly distribution; second, a closed-form solution for extracting the centre from every transversal section of laser stripe is derived based on conservation laws of Legendre moment; finally, a smoothing spline algorithm is used to eliminate noise as well as maintain the original features of the centre points. The experimental results show that the method has good robustness and accuracy.