Welcome to Box Dimensions
Project Home Page. Here we present
a completely automatic approach for realtime
computation of boxes
dimensions from single perspective projection
images. Given a picture
of a box, acquired with a camera whose intrinsic
parameters are known,
the dimensions of the box are computed from the
extracted box
silhouette and the projection of two parallel
laser beams on one of its
visible faces. We demonstrate the proposed
approach by building a
prototype of a scanner for computing box
dimensions and using it to
automatically compute the dimensions of several
boxes. The main
contributions of this research include:
 An algorithm for
computing the dimensions of boxes in a
completely automatic way in
realtime;
 An algorithm for extracting box silhouettes
in the presence of
partial occlusion of the box edges;
 A statistical model for detecting background
pixels under different
lighting conditions, for use with a moving
camera; and
 An efficient voting scheme for identifying
approximately collinear
line segments using a Hough Transform.
This project
was developed by me
under
supervision of professor Manuel
Menezes
de
Oliveira
Neto, Ph.D., and contribution of professor
Roberto
da Silva, Ph.D.
Here
you find:
 A copy of the
SIGGRAPH'2006 sketch;
 A link to the Pattern Recognition paper;
 A link to the Computational Statistics and
Data Analysis paper;
 A copy of the JBCS paper;
 A copy of the CTD'2007 paper;
 A copy of the SIBGRAPI'2005 paper;

A
copy
of
my
master's
thesis
(in
Portuguese);
and

A
video
illustrating
the
use
of
our
scanner.

SIGGRAPH Sketch 



Leandro
A.
F.
Fernandes, Manuel M. Oliveira. A
scanner
for
computing
box
dimensions
in
real
time. ACM SIGGRAPH
2006 Conference Abstracts and Applications,
July, 2006.
Available in the conference CDROM (ISBN
1595933662). [DOI
Bookmark] [Sketch]
[Video
(AVI)] [Video
(WMV)]


top 


Journal Papers 



Leandro
A.
F.
Fernandes, Manuel M. Oliveira, Roberto da
Silva. Uncertainty
propagation:
avoiding the expensive sampling process for
realtime
imagebased measurements. Computational
Statistics and
Data Analysis (CSDA), Elsevier, 52:7,
2008. pp. 38523876. [DOI
Bookmark]




Leandro
A.
F.
Fernandes, Manuel M. Oliveira. Realtime
line detection
through an improved Hough transform voting
scheme. Pattern
Recognition
(PR), Elsevier, 41:1, 2008. pp.
299314. [DOI
Bookmark]
[Corrigendum]
[Project Page]




Leandro
A.
F.
Fernandes, Manuel M. Oliveira, Roberto da
Silva, Gustavo J.
Crespo. A
fast
and
accurate
approach
for
computing
the
dimensions
of
boxes
from single
perspective images. Journal of
the Brazilian Computer
Society (JBCS), 12:2, 2006. pp.
1930. [Paper]
[DOI
Bookmark]


top 


Conference Paper 



Leandro
A.
F.
Fernandes, Manuel M. Oliveira. Um
método
projetivo para
cálculo de dimensões de caixas
em tempo real. Proceedings
of
27th
Brazilian
Computer
Society
Conference
(CSBC
2007), XX
Theses and Dissertations Contest (CTD), Rio de
Janeiro, Brazil, 2007,
pp. 20332037. (in Portuguese) [Paper]

Dissertation
Winner 




Leandro
A.
F.
Fernandes, Manuel M. Oliveira, Roberto da
Silva, Gustavo J.
Crespo. Computing
box
dimensions
from
single
perspective
images
in
real
time. Proceedings
of
XVIII
Brazilian
Symposium
on Computer Graphics and Image Processing
(SIBGRAPI 2005), Natal, Brazil, 2005.
pp. 155162. [DOI
Bookmark] [Paper]

Top Three
 CG Papers 


top 


Conference Poster 



Leandro
A. F.
Fernandes, Manuel M. Oliveira. An
imagebased approach for
computing box dimensions in real time. Workshop
of Theses
and Dissertations of XX
SIBGRAPI, October, 2007.
Available
in the conference CDROM (ISBN 8576691493). 

top 


Master's Thesis 



Um
método
projetivo para
cálculo de dimensões de caixas
em tempo real. Master's
Thesis under supervision of professor
Manuel Menezes de
Oliveira Neto, Ph.D. PPGCUFRGS, January, 2006,
126 pages. (in
Portuguese) [Manuscript]

Dissertation
Winner
XX Brazilian
Computer
Society's
Master Theses Contest (CTD
2007, Certificate)
27th Brazilian Computer Society
Conference (CSBC)



top 


