101 - New Prospects in Line Detection by Dynamic Programming. N. Merlet et J. Zerubia. IEEE Trans. Pattern Analysis and Machine Intelligence, 18(4): pages 426-431, avril 1996. Mots-clés : Line detection, dynamic programming, energy minimization, curvature, satellite images.
@ARTICLE{MerletPAMI96,
|
author |
= |
{Merlet, N. and Zerubia, J.}, |
title |
= |
{New Prospects in Line Detection by Dynamic Programming}, |
year |
= |
{1996}, |
month |
= |
{avril}, |
journal |
= |
{IEEE Trans. Pattern Analysis and Machine Intelligence}, |
volume |
= |
{18}, |
number |
= |
{4}, |
pages |
= |
{426-431}, |
url |
= |
{http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=10562&arnumber=491623&count=15&index=6}, |
keyword |
= |
{Line detection, dynamic programming, energy minimization, curvature, satellite images} |
} |
Abstract :
The detection of lines in satellite images has drawn a lot of attention within the last 15 years. Problems of resolution, noise, and image understanding are involved, and one of the best methods developed so far is the F* algorithm of Fischler, which achieves robustness, rightness, and rapidity. Like other methods of dynamic programming, it consists of defining a cost which depends on local information; then a summation-minimization process in the image is performed. We present herein a mathematical formalization of the F* algorithm, which allows us to extend the cost both to cliques of more than two points (to deal with the contrast), and to neighborhoods of size larger than one (to take into account the curvature). Thus, all the needed information (contrast, grey-level, curvature) is synthesized in a unique cost function defined on the digital original image. This cost is used to detect roads and valleys in satellite images (SPOT). |
|