TY - JOUR
T1 - First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D
AU - Tong, Wai Shun
AU - Tang, Chi Keung
AU - Mordohai, Philippos
AU - Medioni, Gérard
PY - 2004/5
Y1 - 2004/5
N2 - Most computer vision applications require the reliable detection of boundaries. In the presence of outliers, missing data, orientation discontinuities, and occlusion, this problem is particularly challenging. We propose to address it by complementing the tensor voting framework, which was limited to second order properties, with first order representation and voting. First order voting fields and a mechanism to vote for 3D surface and volume boundaries and curve endpoints in 3D are defined. Boundary inference is also useful for a second difficult problem in grouping, namely, automatic scale selection. We propose an algorithm that automatically infers the smallest scale that can preserve the finest details. Our algorithm then proceeds with progressively larger scales to ensure continuity where it has not been achieved. Therefore, the proposed approach does not oversmooth features or delay the handling of boundaries and discontinuities until model misfit occurs. The interaction of smooth features, boundaries, and outliers is accommodated by the unified representation, making possible the perceptual organization of data in curves, surfaces, volumes, and their boundaries simultaneously. We present results on a variety of data sets to show the efficacy of the improved formalism.
AB - Most computer vision applications require the reliable detection of boundaries. In the presence of outliers, missing data, orientation discontinuities, and occlusion, this problem is particularly challenging. We propose to address it by complementing the tensor voting framework, which was limited to second order properties, with first order representation and voting. First order voting fields and a mechanism to vote for 3D surface and volume boundaries and curve endpoints in 3D are defined. Boundary inference is also useful for a second difficult problem in grouping, namely, automatic scale selection. We propose an algorithm that automatically infers the smallest scale that can preserve the finest details. Our algorithm then proceeds with progressively larger scales to ensure continuity where it has not been achieved. Therefore, the proposed approach does not oversmooth features or delay the handling of boundaries and discontinuities until model misfit occurs. The interaction of smooth features, boundaries, and outliers is accommodated by the unified representation, making possible the perceptual organization of data in curves, surfaces, volumes, and their boundaries simultaneously. We present results on a variety of data sets to show the efficacy of the improved formalism.
KW - 3D perceptual organization
KW - Boundary inference
KW - Discontinuities
KW - First order voting
KW - Multiscale analysis
KW - Tensor voting
UR - http://www.scopus.com/inward/record.url?scp=3042624981&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=3042624981&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2004.1273934
DO - 10.1109/TPAMI.2004.1273934
M3 - Article
C2 - 15460281
AN - SCOPUS:3042624981
SN - 0162-8828
VL - 26
SP - 594
EP - 611
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 5
ER -