In this paper, we propose an algorithm to construct 3-D surface model from
a set of range data, based on non-uniform rational B-splines (NURBS) surfac
e-fitting technique. It is assumed that the range data is initially unorgan
ized and scattered 3-D points, while their connectivity is also unknown. Th
e proposed algorithm consists of three stages: initial model approximation
employing K-means clustering, hierarchical decomposition of the initial mod
el, and construction of NURBS surface patch network. The initial model is a
pproximated by both polyhedral and triangular model. Then, the initial mode
l is represented by a hierarchical graph, which is efficiently used to cons
truct the G(1) continuous NURBS patch network of the whole object, Experime
nts are carried out on synthetic and real range data to evaluate the perfor
mance of the proposed algorithm. It is shown that the initial model as well
as the NURBS patch network are constructed automatically with tolerable co
mputation. The modeling error of the NURBS model is reduced to 10%, compare
d with the initial mesh model.