Publication Details

Exploiting neighbors for faster scanning window detection in images

ZEMČÍK Pavel, HRADIŠ Michal and HEROUT Adam. Exploiting neighbors for faster scanning window detection in images. In: ACIVS 2010. Lecture Notes in Computer Science, vol. 6475. Sydney: Springer Verlag, 2010, p. 12. ISBN 978-3-642-17690-6.
Czech title
Využití sousedů pro rachlejší detekci objektů v obraze
Type
conference paper
Language
english
Authors
URL
Keywords

real-time object detection, image features, WaldBoost

Abstract

Detection of objects through scanning windows is widely used and accepted method. The detectors traditionally do not make use of information that is shared between neighboring image positions although this fact means that the traditional solutions are not optimal. Addressing this, we propose an efficient and computationally inexpensive approach how to exploit the shared information and thus increase speed of detection. The main idea is to predict responses of the classifier in neighbor windows close to the ones already evaluated and skip such positions where the prediction is confident enough. In order to predict the responses, the proposed algorithm builds a new classifier which reuses the set of image features already exploited. The results show that the proposed approach can reduce scanning time up to four times with only minor increase of error rate. On the presented examples it is shown that, it is possible to reach less than one feature computed on average per single image position. The paper presents the algorithm itself and also results of experiments on several data sets and with different types of image features.

Published
2010
Pages
12
Proceedings
ACIVS 2010
Series
Lecture Notes in Computer Science
Volume
6475
Conference
Advanced Concepts for Intelligent Vision Systems 2010, Sydney, Australia, AU
ISBN
978-3-642-17690-6
Publisher
Springer Verlag
Place
Sydney, AU
BibTeX
@INPROCEEDINGS{FITPUB9410,
   author = "Pavel Zem\v{c}\'{i}k and Michal Hradi\v{s} and Adam Herout",
   title = "Exploiting neighbors for faster scanning window detection in images",
   pages = 12,
   booktitle = "ACIVS 2010",
   series = "Lecture Notes in Computer Science",
   volume = 6475,
   year = 2010,
   location = "Sydney, AU",
   publisher = "Springer Verlag",
   ISBN = "978-3-642-17690-6",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9410"
}
Files
Back to top