Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
ZEMČÍK, P. HRADIŠ, M. HEROUT, A.
Originální název
Exploiting neighbors for faster scanning window detection in images
Typ
článek ve sborníku mimo WoS a Scopus
Jazyk
angličtina
Originální abstrakt
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.
Klíčová slova
real-time object detection, image features, WaldBoost
Autoři
ZEMČÍK, P.; HRADIŠ, M.; HEROUT, A.
Rok RIV
2010
Vydáno
13. 12. 2010
Nakladatel
Springer Verlag
Místo
Sydney
ISBN
978-3-642-17690-6
Kniha
ACIVS 2010
Edice
Lecture Notes in Computer Science
Strany od
100
Strany do
111
Strany počet
12
URL
https://www.fit.vut.cz/research/publication/9410/
BibTex
@inproceedings{BUT35132, author="Pavel {Zemčík} and Michal {Hradiš} and Adam {Herout}", title="Exploiting neighbors for faster scanning window detection in images", booktitle="ACIVS 2010", year="2010", series="Lecture Notes in Computer Science", volume="6475", pages="100--111", publisher="Springer Verlag", address="Sydney", isbn="978-3-642-17690-6", url="https://www.fit.vut.cz/research/publication/9410/" }