A. Neubeck, und L. Van Gool. Proceedings of the 18th International Conference on Pattern Recognition - Volume 03, Seite 850--855. Washington, DC, USA, IEEE Computer Society, (2006)
DOI: 10.1109/ICPR.2006.479
Zusammenfassung
In this work we scrutinize a low level computer vision task - non-maximum suppression (NMS) - which is a crucial preprocessing step in many computer vision applications. Especially in real time scenarios, efficient algorithms for such preprocessing algorithms, which operate on the full image resolution, are important. In the case of NMS, it seems that merely the straightforward implementation or slight improvements are known. We show that these are far from being optimal, and derive several algorithms ranging from easy-to-implement to highly-efficient.
%0 Conference Paper
%1 Neubeck:2006:ENS:1170749.1172615
%A Neubeck, Alexander
%A Van Gool, Luc
%B Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
%C Washington, DC, USA
%D 2006
%I IEEE Computer Society
%K fast feature non-maximum suppression
%P 850--855
%R 10.1109/ICPR.2006.479
%T Efficient Non-Maximum Suppression
%U http://dx.doi.org/10.1109/ICPR.2006.479
%X In this work we scrutinize a low level computer vision task - non-maximum suppression (NMS) - which is a crucial preprocessing step in many computer vision applications. Especially in real time scenarios, efficient algorithms for such preprocessing algorithms, which operate on the full image resolution, are important. In the case of NMS, it seems that merely the straightforward implementation or slight improvements are known. We show that these are far from being optimal, and derive several algorithms ranging from easy-to-implement to highly-efficient.
%@ 0-7695-2521-0
@inproceedings{Neubeck:2006:ENS:1170749.1172615,
abstract = {In this work we scrutinize a low level computer vision task - non-maximum suppression (NMS) - which is a crucial preprocessing step in many computer vision applications. Especially in real time scenarios, efficient algorithms for such preprocessing algorithms, which operate on the full image resolution, are important. In the case of NMS, it seems that merely the straightforward implementation or slight improvements are known. We show that these are far from being optimal, and derive several algorithms ranging from easy-to-implement to highly-efficient.},
acmid = {1172615},
added-at = {2012-11-11T16:12:58.000+0100},
address = {Washington, DC, USA},
author = {Neubeck, Alexander and Van Gool, Luc},
biburl = {https://www.bibsonomy.org/bibtex/288351d0936ce0f665f0b46d596b8c8bd/daill},
booktitle = {Proceedings of the 18th International Conference on Pattern Recognition - Volume 03},
description = {Efficient Non-Maximum Suppression},
doi = {10.1109/ICPR.2006.479},
interhash = {26735a78327c91a46179d3135123a285},
intrahash = {88351d0936ce0f665f0b46d596b8c8bd},
isbn = {0-7695-2521-0},
keywords = {fast feature non-maximum suppression},
numpages = {6},
pages = {850--855},
publisher = {IEEE Computer Society},
series = {ICPR '06},
timestamp = {2012-11-11T16:12:58.000+0100},
title = {Efficient Non-Maximum Suppression},
url = {http://dx.doi.org/10.1109/ICPR.2006.479},
year = 2006
}