Title :
Range image segmentation and fitting by residual consensus
Author :
Yu, Xinming ; Bui, T.D. ; Krzyzak, A.
Author_Institution :
Dept. of Comput. Sci., Concordia Univ., Montreal, Que., Canada
Abstract :
The authors randomly sample appropriate range image points and solve equations determined by these points for the parameters of selected primitive type. From K samples they measure residual consensus to choose one set of sample points that determines an equation having the best fit for the largest homogeneous surface patch in the current processing region. The residual consensus is measured by a compressed histogram method that works at various noise levels. The estimated surface patch is extracted out of the processing region to avoid further computation. A genetic algorithm is used to accelerate the search speed
Keywords :
genetic algorithms; image segmentation; best fit; compressed histogram; genetic algorithm; homogeneous surface patch; noise levels; processing region; range image fitting; range image points; range image segmentation; residual consensus; search speed; Computer science; Electric breakdown; Equations; Image segmentation; Least squares approximation; Least squares methods; Robustness; Sampling methods; Sorting; Surface fitting;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223208
