Segmentation for Range Image Based on Snake Active Contour Model
Mei Zhang, Wen Jing Hua, Peng Xing Xing · International Journal of Signal Processing Image Processing and Pattern Recognition · 2016
Range image segmentation is one of the most common problem in the field of computer vision. In view of the defect about traditional range image segmentation methods, this paper introduces a new range image segmentation method based on snake active contour model (SCAM). First, this paper expresses the snake active contour model in the form of parameters, and illustrates the contour line data points inside and outside of the movement and pseudo code description of the motion of a point algorithm; then constructs energy function, pushing the Euler equation and discretization; finally gets the results by Cholesky decomposition. Numerical experiment results show that the method is accurate and efficient, of good effect and the segmentation results are consistent with human subjective visual perception.