The Computation Reduction in Object Detection via Composite Structure of Modified Integral Images

Daeha LEE; Jaehong KIM; Ho-Hee KIM; Soon-Ja KIM

doi:10.1587/transinf.2016EDL8158

The Computation Reduction in Object Detection via Composite Structure of Modified Integral Images

Daeha LEE, Jaehong KIM, Ho-Hee KIM, Soon-Ja KIM

Full Text Views

0

Share
Cite this

Summary :

Object detection is the first step in the object recognition. According to the detection results, its following works are affected. However, object detection has a heavy resource requirement in terms of, computing power and memory. If an image is enlarged, the computational load required for object detection is also increased. An-integral-image-based method guarantees fast object detection. Once an integral image is generated, the speed of the object detection procedure remains fixed, regardless of the pattern region size. However, this becomes an even greater issue if the image is enlarged. In this paper, we propose the use of directional integral image based object detection. A directional integral image gives direction to an integral image, which can then be calculated from various directions. Furthermore, many unnecessary calculations, which typically occur when a partial integral image is used for object detection, can be avoided. Therefore, the amount of computation is reduced, compared with methods using integral images. In experiments comparing methods, the proposed method required 40% fewer computations.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.1 pp.229-233

Publication Date: 2017/01/01

Publicized: 2016/10/04

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8158

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Authors

Daeha LEE
  ETRI
Jaehong KIM
  ETRI
Ho-Hee KIM
  Kyungbook National University
Soon-Ja KIM
  Kyungbook National University

Keyword

directional integral image, integral image, composite-type directional integral image

Cite this

Copy

Daeha LEE, Jaehong KIM, Ho-Hee KIM, Soon-Ja KIM, "The Computation Reduction in Object Detection via Composite Structure of Modified Integral Images" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 1, pp. 229-233, January 2017, doi: 10.1587/transinf.2016EDL8158.
Abstract: Object detection is the first step in the object recognition. According to the detection results, its following works are affected. However, object detection has a heavy resource requirement in terms of, computing power and memory. If an image is enlarged, the computational load required for object detection is also increased. An-integral-image-based method guarantees fast object detection. Once an integral image is generated, the speed of the object detection procedure remains fixed, regardless of the pattern region size. However, this becomes an even greater issue if the image is enlarged. In this paper, we propose the use of directional integral image based object detection. A directional integral image gives direction to an integral image, which can then be calculated from various directions. Furthermore, many unnecessary calculations, which typically occur when a partial integral image is used for object detection, can be avoided. Therefore, the amount of computation is reduced, compared with methods using integral images. In experiments comparing methods, the proposed method required 40% fewer computations.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8158/_p

Copy

@ARTICLE{e100-d_1_229,
author={Daeha LEE, Jaehong KIM, Ho-Hee KIM, Soon-Ja KIM, },
journal={IEICE TRANSACTIONS on Information},
title={The Computation Reduction in Object Detection via Composite Structure of Modified Integral Images},
year={2017},
volume={E100-D},
number={1},
pages={229-233},
abstract={Object detection is the first step in the object recognition. According to the detection results, its following works are affected. However, object detection has a heavy resource requirement in terms of, computing power and memory. If an image is enlarged, the computational load required for object detection is also increased. An-integral-image-based method guarantees fast object detection. Once an integral image is generated, the speed of the object detection procedure remains fixed, regardless of the pattern region size. However, this becomes an even greater issue if the image is enlarged. In this paper, we propose the use of directional integral image based object detection. A directional integral image gives direction to an integral image, which can then be calculated from various directions. Furthermore, many unnecessary calculations, which typically occur when a partial integral image is used for object detection, can be avoided. Therefore, the amount of computation is reduced, compared with methods using integral images. In experiments comparing methods, the proposed method required 40% fewer computations.},
keywords={},
doi={10.1587/transinf.2016EDL8158},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - The Computation Reduction in Object Detection via Composite Structure of Modified Integral Images
T2 - IEICE TRANSACTIONS on Information
SP - 229
EP - 233
AU - Daeha LEE
AU - Jaehong KIM
AU - Ho-Hee KIM
AU - Soon-Ja KIM
PY - 2017
DO - 10.1587/transinf.2016EDL8158
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2017
AB - Object detection is the first step in the object recognition. According to the detection results, its following works are affected. However, object detection has a heavy resource requirement in terms of, computing power and memory. If an image is enlarged, the computational load required for object detection is also increased. An-integral-image-based method guarantees fast object detection. Once an integral image is generated, the speed of the object detection procedure remains fixed, regardless of the pattern region size. However, this becomes an even greater issue if the image is enlarged. In this paper, we propose the use of directional integral image based object detection. A directional integral image gives direction to an integral image, which can then be calculated from various directions. Furthermore, many unnecessary calculations, which typically occur when a partial integral image is used for object detection, can be avoided. Therefore, the amount of computation is reduced, compared with methods using integral images. In experiments comparing methods, the proposed method required 40% fewer computations.
ER -