This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
How Far 3D Shapes Can Be Understood from 2D Silhouettes
February 1995 (vol. 17 no. 2)
pp. 188-195
ASCII Text
x 
 
Aldo Laurentini, "How Far 3D Shapes Can Be Understood from 2D Silhouettes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 188-195, February, 1995.
 
 
BibTex
x
 
@article{ 10.1109/34.368170,
author = {Aldo Laurentini},
title = {How Far 3D Shapes Can Be Understood from 2D Silhouettes},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {17},
number = {2},
issn = {0162-8828},
year = {1995},
pages = {188-195},
doi = {http://doi.ieeecomputersociety.org/10.1109/34.368170},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
TI - How Far 3D Shapes Can Be Understood from 2D Silhouettes
IS - 2
SN - 0162-8828
SP188
EP195
EPD - 188-195
A1 - Aldo Laurentini,
PY - 1995
KW - Computer vision
KW - 3D object reconstruction
KW - 2D images
KW - volume intersection
KW - shape from silhouettes
KW - visual hull.
VL - 17
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 

Abstract— Each 2D silhouette of a 3D unknown object O constrains O inside the volume obtained by back-projecting the silhouette from the corresponding viewpoint. A set of silhouettes specifies a boundary volume R, obtained by intersecting the volumes due to each silhouette. R more or less closely approximates O, depending on the viewpoints and the object itself. This approach to the reconstruction of 3D objects is usually referred to as volume intersection. This correspondence addresses the problem of inferring the shape of the unknown object O from the reconstructed object R. For doing this, we divide the points of the surface of R into hard points, which belong to the surface of any possible object originating R, and soft points, which may or may not belong to O. We consider two cases: In the first case R is the closest approximation of O which can be obtained from its silhouettes, i.e., its visual hull; in the second case, R is a generic reconstructed object. In both cases we supply necessary and sufficient conditions for a point to be hard and give rules for computing the hard surfaces.

[1] Y.C. Kim and J.K. Aggarwal,“Rectangular parallelepiped coding for solid modeling,” Int’l J. Robotics Automation, vol. 1, pp. 77-85, 1986.
[2] C. Chien and J.K. Aggarwal,“Model reconstruction and shape recognition from occluding contours,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 11, pp. 372-389, 1989.
[3] Lavakusa,A.K. Pujazi,, and P.G. Reddy,“Linear octrees by volume intersection,” Computer Vision Graphics Image Process, vol. 45, pp. 371-379, 1989.
[4] S. Srivastava and N. Ahuia,“An algorithm for generatng octrees from object silhouettes in perspective views,” Proc. IEEE Workshop Computer Vision,Miami Beach, Fla., pp. 363-365, Nov. 1987.
[5] N. Ahuja and J. Veenstra,“Generating octrees from object silhouettes in orthographic views,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 11, pp. 137-149, 1989.
[6] T.H. Hong and M. Schneier,“Describing a robot’s workspace using a sequence of views from a moving camera,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 7, pp. 721-726, 1985.
[7] K. Shanmukh and A.K. Pujari,“Volume intersection with optimal set of directions,” Pattern Recognition Letters, vol. 12, pp. 165-170, 1991.
[8] W.N. Martin and J.K. Aggarwal,“Volumetric description of objects from multiple views,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 5, pp. 150-158, 1983.
[9] P. Srinivasan,S. Fukusa,, and S. Azimoto.,“Computational geometric methods in volumetric intersection for 3D reconstruction,” Pattern Recognition, vol. 23, pp. 843-857, 1990.
[10] M. Potemesil,“Generating octree models of 3D objects from their silhouettes in a sequence of images,” Computer Vision Graphics and Image Process., vol. 40, pp. 1-29, 1987.
[11] H. Noborio,P. Liang,, and S. Hackwood,“Construction of the octree approximating three-dimensional objects by using multiple views,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 10, pp. 769-782, 1988.
[12] C.H. Chien and J.K. Aggarwal,“Volume/surface octrees for the representation of three-dimensional objects,” Computer Vision, Graphics and Image Processing, vol. 36, pp. 100-113, 1986.
[13] Lavakusha,A.K. Pujazi,, and P.G. Reddy.,“Volume intersection algorithms with changing directions of views,” Proc. MIV-89,Tokyo, pp. 309-314, 1989.
[14] A. Laurentini,“The visual hull of solids of revolution,” Proc. 11th IAPR Int’l Conf. on Pattern Recognition, The Hague, the Netherlands, pp. 720-724, 1992.
[15] A. Laurentini,“The visual hull concept for silhouette-based image understanding,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 16, pp. 150-162, 1994.
[16] F.P. Preparata and M.I. Shamos, Computational Geometry. Springer-Verlag, 1985.
[17] A. Laurentini,“Theoretical capabilities and limits of the volume intersection technique,” Int. Rept. L292, 1992.

Index Terms:
Computer vision, 3D object reconstruction, 2D images, volume intersection, shape from silhouettes, visual hull.
Citation:
Aldo Laurentini, "How Far 3D Shapes Can Be Understood from 2D Silhouettes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 188-195, Feb. 1995, doi:10.1109/34.368170
Usage of this product signifies your acceptance of the Terms of Use.