An adaptive subdivision method for surface-fitting from sampled data
SIGGRAPH '86 Proceedings of the 13th annual conference on Computer graphics and interactive techniques
Segmentation through Variable-Order Surface Fitting
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
Neural networks and the bias/variance dilemma
Neural Computation
A Pyramidal Data Structure for Triangle-Based Surface Description
IEEE Computer Graphics and Applications
A Minimum-Variance Adaptive Surface Mesh
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
| Hi-index | 0.00 |
This paper describes a new class of adaptive mesh surface for terrain analysis. The novelty of the contribution resides in the control of the mesh. We use a variance-bias criterion to select the optimal areas for the triangular facets of the mesh. In this way the mesh adapts itself to offer the best tradeoff between increasing the facet area to minimise the noise variance and deccreasing the facet area to minimise the bias of the fitted facet parameters. We provide a illustration of the effectiveness of the new mesh control methodology for the case where the faces of the mesh represent planar patches. The piecewise planar mesh is shown to be effective in the modelling of an area of complex terrain structure in Southern England.