Surface Reconstruction From Point Clouds

Share Presentation : Surface Reconstruction From Point Clouds

Download and Preview : Surface Reconstruction From Point Clouds

Report CopyRight/DMCA Form For : Surface Reconstruction From Point Clouds

Transcription:

Vehicle Recognition SystemGerald DalleySignal Analysis and Machine Perception LaboratoryThe Ohio State University09 May 2002.
Recognition Engine Steps Acquire range images Determine regions of interest see Kanu Local surface estimation Surface reconstruction.
Affinity measure Spectral Clustering Normalized cuts Graph matching Range Image Acquisition Model building Testing.
Local Surface Estimation What 1 Estimate the local surfacecharacteristics 2 at given locations 1 Vehicles are made up of large low order surfaces 1 Look for groups of points that imply such surfaces.
2 Our sets of range images are BIG tank from 10 views has over 220 000 range points How Local Surface Estimation Point Set Selection.
In the region of interest Collect range image points into cubic voxel bins 32x32x32mm right now Discard bins that have Too few points.
Points that do not represent a biquadratic surface well Retain only the centroids of the bins and theirsurface fits Local Surface Estimation Biquadratic Patches.
PCA Least squares biquadratic fit local coordinate system f u v a1u2 a2uv a3v2 a4u a5v a6 Surface Reconstructioncocone Mesh.
See last quarter s presentation for details on cocone Affinity Quasi Definition Affinity probability that two meshpoints were sampled from the same low order surface Why Can use grouping algorithms to segment the mesh.
to make recognition easier Our formulation Affinity Cont d Spectral Clustering Aij is block diagonal Non zero elements of the 1st.
eigenvector define a cluster Weiss Sarkar96 Aij Ayi i yi Spectral Clustering Cont d Example using our data Aij Ayi i yi 1st Cluster.
Spectral Clustering Normalized Cuts Tend to get disjoint clusters Need to balanceclustering and segmentation.
Graph Matching For each model i R For each unused object segment s For each model segment i t NULL segment Compute penalty for matching s to i t .
all previous matches made Save this match if it s better than any other Recurse to R Save the best matching of model and object segmentsfor model i.
Choose the model with the best match Graph Matching Segment Attributes Unary attributes for comparing one object segment to onemodel segment .
Segment area Mean and Gaussian Curvature from a new biquadratic fit to the voxel points participating in the Distinctiveness Binary attributes for comparing a pair of object segments to.
a pair of model segments Centroid separation Angle between normals at the centroid Further Reading Y Weiss et al Segmentation using eigenvectors a unifying view .
ICCV 975 982 1999 S Sarkar and K L Boyer Quantitative measures of change based onfeature organization eigenvalues and eigenvectors CVPR 1996 J Shi and J Malik Normalized Cuts and Image Segmentation PAMI 888 905 2000 .
CVPR 1996. J. Shi and J. Malik. â€œNormalized Cuts and Image Segmentationâ€. PAMI: 888-905, 2000. u w Voxel centroids Mesh cocone See last quarterâ€™s presentation for details on cocone qi qj pj mj nj Aij y1, where Ayi=li yi Aij y1, where Ayi=li yi 1st Cluster = ? = ?

Recent Views:

Tags:

FAMILY COMMUNICATIONS OFFICE BUSINESS INTERIOR DESIGN HOSPITALITY INTERNET SALES SOFTWARE PERFORMING ARTS CHILDREN TEENS RELIGION RADIO MULTIMEDIA LITERATURE

Surface Reconstruction From Point Clouds-ppt Download

Related Presentations