Normal Vector Voting: Crease Detection and Curvature Estimation on Large, Noisy Meshes

Page, D. H.; Sun, Yiyong; Koschan, Andreas; Paik, Joonki; Abidi, Mongi A.

doi:10.1006/gmod.2002.0574

Cited by 107 publications

(76 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Normal vectors estimated from a local area around each 3D point into the scene are a good starting point for obtaining surfaces descriptions. Some methods, such as Page et al (2002) or Mitra & Nguyen (2003) were developed for handling noisy input data sets. The basic idea consists in analyzing each point in the local neighborhood by means of a robust estimator.…”

Section: Features Extraction Methodsmentioning

confidence: 99%

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

et al. 2012

View full text Add to dashboard Cite

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D features extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.

show abstract

Section: Features Extraction Methodsmentioning

confidence: 99%

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

et al. 2012

View full text Add to dashboard Cite

show abstract

“…An interesting new technique in limiting the ground return points is min-cut based segmentation of k-nearest neighbors graph (k-NNG) [15]. The graph is fast to compute with space partitioning, and it could have served as a basis for stoniness analysis directly e.g., by fast local principal components analysis (PCA) and local normal estimation with vector voting procedure, as in [16]. The literature focuses mostly on laser clouds of technological environment, where the problem of eliminating the canopy (noise) and finding the ground returns (a smooth technical surface) are not combined.…”

Section: Current Researchmentioning

confidence: 99%

“…Many texture recognition problems are sensitive to the raster scale used, thus we tested a combination of many scales, too. According to [16], curvature estimation on triangulated surfaces can be divided to three main approaches:…”

Section: Current Researchmentioning

confidence: 99%

Detecting Terrain Stoniness From Airborne Laser Scanning Data †

et al. 2016

View full text Add to dashboard Cite

Three methods to estimate the presence of ground surface stones from publicly available Airborne Laser Scanning (ALS) point clouds are presented. The first method approximates the local curvature by local linear multi-scale fitting, and the second method uses Discrete-Differential Gaussian curvature based on the ground surface triangulation. The third baseline method applies Laplace filtering to Digital Elevation Model (DEM) in a 2 m regular grid data. All methods produce an approximate Gaussian curvature distribution which is then vectorized and classified by logistic regression. Two training data sets consisted of 88 and 674 polygons of mass-flow deposits, respectively. The locality of the polygon samples is a sparse canopy boreal forest, where the density of ALS ground returns is sufficiently high to reveal information about terrain micro-topography. The surface stoniness of each polygon sample was categorized for supervised learning by expert observation on the site. The leave-pair-out (L2O) cross-validation of the local linear fit method results in the area under curve AUC = 0.74 and AUC = 0.85 on two data sets, respectively. This performance can be expected to suit real world applications such as detecting coarse-grained sediments for infrastructure construction. A wall-to-wall predictor based on the study was demonstrated.

show abstract

“…The mean curvature, describing insight to the degree of flatness of the surface, is applied to estimate the radius of sphere of the object at the contact area. Similar to normal vector voting (Page et al, 2001;Page et al, 2002) of curvature estimation on piecewise smooth surfaces, the mean curvature of contacted area is estimated dynamically during the haptic tool-object interaction.…”

Section: Dynamic Curvature Estimationmentioning

confidence: 99%

Realistic Haptics Interaction in Complex Virtual Environments

Chen¹

2010

Advances in Haptics

View full text Add to dashboard Cite

Normal Vector Voting: Crease Detection and Curvature Estimation on Large, Noisy Meshes

Cited by 107 publications

References 36 publications

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

Detecting Terrain Stoniness From Airborne Laser Scanning Data †

Realistic Haptics Interaction in Complex Virtual Environments

Contact Info

Product

Resources

About