1 - Judging whether multiple silhouettes can come from the same object.
D. Jacobs et P. Belhumeur et I. H. Jermyn. Dans Int. Workshop on Visual Form, Springer-Verlag Lecture Notes in Computer Science 2059, Capri, Italie, mai 2001.
@INPROCEEDINGS{IJ01b,
|
| author |
= |
{Jacobs, D. and Belhumeur, P. and Jermyn, I. H.}, |
| title |
= |
{Judging whether multiple silhouettes can come from the same object}, |
| year |
= |
{2001}, |
| month |
= |
{mai}, |
| booktitle |
= |
{Int. Workshop on Visual Form, Springer-Verlag Lecture Notes in Computer Science 2059}, |
| address |
= |
{Capri, Italie}, |
| pdf |
= |
{http://www-sop.inria.fr/members/Ian.Jermyn/publications/Jacobs01iwvf.pdf}, |
| keyword |
= |
{} |
| } |
Abstract :
We consider the problem of recognizing an object from its
silhouette. We focus on the case in which the camera translates, and
rotates about a known axis parallel to the image, such as when a mo-
bile robot explores an environment. In this case we present an algorithm
for determining whether a new silhouette could come from the same ob-
ject that produced two previously seen silhouettes. In a basic case, when
cross-sections of each silhouette are single line segments, we can check
for consistency between three silhouettes using linear programming. This
provides the basis for methods that handle more complex cases. We show
many experiments that demonstrate the performance of these methods
when there is noise, some deviation from the assumptions of the algo-
rithms, and partial occlusion. Previous work has addressed the problem
of precisely reconstructing an object using many silhouettes taken under
controlled conditions. Our work shows that recognition can be performed
without complete reconstruction, so that a small number of images can
be used, with viewpoints that are only partly constrained. |
|
haut de la page
Rapport d'activité 2011
bibtex
