Welcome to Journal of Graphics share: 
Journal of Graphics

Journal of Graphics

Previous Articles     Next Articles

Reconstruction of Triangle Mesh for Unorganized Point Cloud Data with Reconstruction of Triangle Mesh for Unorganized Point Cloud Data with 

Abstract: An approach based on the self-organizing feature map (SOFM) neural network has#br# been developed to reconstruct Delaunay triangle mesh for the unorganized measured point cloud.#br# However the approach suffers from approximation and boundary problems. A triangle mesh model#br# with high approximation precision is proposed in order to reduce the approximation error and#br# boundary error. First all the neurons of the mesh model are trained directly over the unorganized#br# point cloud. Next the neuron location weights of the mesh model are adjusted along the normal#br# vectors of the mesh vertices. Last only the boundary neurons of the mesh model undergo training#br# by the boundary points of the measured point cloud. As a result of applying the proposed mesh#br# model, the boundary error is greatly reduced and the mesh is drawn toward the sampled object#br# with higher precision comparing with the original SOFM training algorithm. The feasibility of the#br# developed mesh model is demonstrated on two examples.#br# Key words: reverse engineering; triangle mesh; neural network; approximation error;#br# boundary error; unorganized point cloud   

  • Online:2015-04-30 Published:2015-03-30

PDF (PC)

207

Abstract: An approach based on the self-organizing feature map (SOFM) neural network has
been developed to reconstruct Delaunay triangle mesh for the unorganized measured point cloud.
However the approach suffers from approximation and boundary problems. A triangle mesh model
with high approximation precision is proposed in order to reduce the approximation error and
boundary error. First all the neurons of the mesh model are trained directly over the unorganized
point cloud. Next the neuron location weights of the mesh model are adjusted along the normal
vectors of the mesh vertices. Last only the boundary neurons of the mesh model undergo training
by the boundary points of the measured point cloud. As a result of applying the proposed mesh
model, the boundary error is greatly reduced and the mesh is drawn toward the sampled object
with higher precision comparing with the original SOFM training algorithm. The feasibility of the
developed mesh model is demonstrated on two examples.

Key words: reverse engineering, triangle mesh, neural network, approximation error;
boundary error, unorganized point cloud