Publication detail

Exploiting neighbors for faster scanning window detection in images

ZEMČÍK, P. HRADIŠ, M. HEROUT, A.

Original Title

Exploiting neighbors for faster scanning window detection in images

English Title

Exploiting neighbors for faster scanning window detection in images

Type

conference paper

Language

en

Original 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.

English 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.

Keywords

real-time object detection, image features, WaldBoost

RIV year

2010

Released

13.12.2010

Publisher

Springer Verlag

Location

Sydney

ISBN

978-3-642-17690-6

Book

ACIVS 2010

Edition

Lecture Notes in Computer Science

Edition number

NEUVEDEN

Pages from

100

Pages to

111

Pages count

12

URL

Documents

BibTex


@inproceedings{BUT35132,
  author="Pavel {Zemčík} and Michal {Hradiš} and Adam {Herout}",
  title="Exploiting neighbors for faster scanning window detection in images",
  annote="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.",
  address="Springer Verlag",
  booktitle="ACIVS 2010",
  chapter="35132",
  edition="Lecture Notes in Computer Science",
  howpublished="print",
  institution="Springer Verlag",
  year="2010",
  month="december",
  pages="100--111",
  publisher="Springer Verlag",
  type="conference paper"
}