以特征点对应技术为基础的摄影测量术有着广泛应用,但存在着测量数据稀疏的缺陷,对此提出了SFS(Shape from shading)与特征点技术相结合的方法,加密插值点,解决复杂表面形状测量问题。首先设计了用于测量的摄像系统,然后讨论了图像平面的剖分算法,最后给出SFS与特征点技术结合的有限单元形式,并设计了多重网格加速求解算法。算例表明,该方法效果令人满意。
A B-spline active contour model based on finite element method is presented, into which the advantages of a B-spline active contour attributing to its fewer parameters and its smoothness is built accompanied with reduced computational complexity and better numerical stability resulted from the finite element method. In this model, a cubic B-spline segment is taken as an element, and the finite element method is adopted to solve the energy minimization problem of the B-spline active contour, thus to implement image segmentation. Experiment results verify that this method is efficient for B-spline active contour, which attains stable, accurate and faster convergence.