Paper Info
Title
A 3D model perceptual feature metric based on global height field.
Abstract
Human visual attention system tends to be attracted to perceptual feature points on 3D model surfaces. However, purely geometric-based feature metrics may be insufficient to extract perceptual features, because they tend to detect local structure details. Intuitively, the perceptual importance degree of vertex is associated with the height of its geometry position between original model and a datum plane. So, we propose a novel and straightforward method to extract perceptually important points based on global height field. Firstly, we construct spectral domain using Laplace---Beltrami operator, and we perform spectral synthesis to reconstruct a rough approximation of the original model by adopting low-frequency coefficients, and make it as the 3D datum plane. Then, to build global height field, we calculate the Euclidean distance between vertex geometry position on original surface and the one on 3D datum plane. Finally, we set a threshold to extract perceptual feature vertices. We implement our technique on several 3D mesh models and compare our algorithm to six state-of-the-art interest points detection approaches. Experimental results demonstrate that our algorithm can accurately capture perceptually important points on arbitrary topology 3D model.
Year
DOI
Venue
2016
10.1007/s00371-015-1199-3
The Visual Computer
Keywords
Field
DocType
Perceptual feature points metric, Human visual attention, Global height field, Spectral method
Computer vision,Datum reference,Height field,Polygon mesh,Vertex (geometry),Computer science,Euclidean distance,Operator (computer programming),Artificial intelligence,Spectral method,Perception
Journal
Volume
Issue
ISSN
32
9
1432-2315
Citations 
PageRank 
References 
2
0.38
22
Authors
6
Name
Order
Citations
PageRank
Yihui Guo120.72
Shujin Lin2777.74
Zhuo Su310222.32
Xiaonan Luo469792.76
Ruomei Wang53520.82
Kang Yang698.81