An effective pedestrian detection method for driver assistance system

Keun Yung Byun; Bo Sang Kim; Hyo Kak Kim; Jeong Eun Shin; Sung Jea Ko

doi:10.1109/ICCE.2012.6161841

An effective pedestrian detection method for driver assistance system

Keun Yung Byun, Bo Sang Kim, Hyo Kak Kim, Jeong Eun Shin, Sung Jea Ko

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.

Original language	English
Title of host publication	2012 IEEE International Conference on Consumer Electronics, ICCE 2012
Pages	229-230
Number of pages	2
DOIs	https://doi.org/10.1109/ICCE.2012.6161841
Publication status	Published - 2012
Event	2012 IEEE International Conference on Consumer Electronics, ICCE 2012 - Las Vegas, NV, United States Duration: 2012 Jan 13 → 2012 Jan 16

Publication series

Name	Digest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)	0747-668X

Other

Other	2012 IEEE International Conference on Consumer Electronics, ICCE 2012
Country	United States
City	Las Vegas, NV
Period	12/1/13 → 12/1/16

ASJC Scopus subject areas

Industrial and Manufacturing Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ICCE.2012.6161841

Fingerprint Dive into the research topics of 'An effective pedestrian detection method for driver assistance system'. Together they form a unique fingerprint.

Cite this

Byun, K. Y., Kim, B. S., Kim, H. K., Shin, J. E., & Ko, S. J. (2012). An effective pedestrian detection method for driver assistance system. In 2012 IEEE International Conference on Consumer Electronics, ICCE 2012 (pp. 229-230). [6161841] (Digest of Technical Papers - IEEE International Conference on Consumer Electronics). https://doi.org/10.1109/ICCE.2012.6161841

An effective pedestrian detection method for driver assistance system. / Byun, Keun Yung; Kim, Bo Sang; Kim, Hyo Kak; Shin, Jeong Eun; Ko, Sung Jea.

2012 IEEE International Conference on Consumer Electronics, ICCE 2012. 2012. p. 229-230 6161841 (Digest of Technical Papers - IEEE International Conference on Consumer Electronics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Byun, KY, Kim, BS, Kim, HK, Shin, JE & Ko, SJ 2012, An effective pedestrian detection method for driver assistance system. in 2012 IEEE International Conference on Consumer Electronics, ICCE 2012., 6161841, Digest of Technical Papers - IEEE International Conference on Consumer Electronics, pp. 229-230, 2012 IEEE International Conference on Consumer Electronics, ICCE 2012, Las Vegas, NV, United States, 12/1/13. https://doi.org/10.1109/ICCE.2012.6161841

@inproceedings{08e70a0e41904fb098a259e088731ac8,

title = "An effective pedestrian detection method for driver assistance system",

abstract = "A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.",

author = "Byun, {Keun Yung} and Kim, {Bo Sang} and Kim, {Hyo Kak} and Shin, {Jeong Eun} and Ko, {Sung Jea}",

year = "2012",

doi = "10.1109/ICCE.2012.6161841",

language = "English",

isbn = "9781457702310",

series = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

pages = "229--230",

booktitle = "2012 IEEE International Conference on Consumer Electronics, ICCE 2012",

note = "2012 IEEE International Conference on Consumer Electronics, ICCE 2012 ; Conference date: 13-01-2012 Through 16-01-2012",

}

TY - GEN

T1 - An effective pedestrian detection method for driver assistance system

AU - Byun, Keun Yung

AU - Kim, Bo Sang

AU - Kim, Hyo Kak

AU - Shin, Jeong Eun

AU - Ko, Sung Jea

PY - 2012

Y1 - 2012

N2 - A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.

AB - A driver assistance system typically adopts the wide-angle camera to obtain a wide-view image. However, the wide-angle camera often produces radial distortion. Since the conventional training-based pedestrian detection method uses distortion-free training samples, it is not suitable for distorted images. In this paper, we propose an effective pedestrian detection method that divides pedestrian training samples into several classes according to the amount of radial distortion, and trains each class separately. Likewise, a test image is divided into sub-regions and detection is performed for each sub-region separately. Experimental results show that our approach provides better performance compared to the conventional method.

UR - http://www.scopus.com/inward/record.url?scp=84863385535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863385535&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2012.6161841

DO - 10.1109/ICCE.2012.6161841

M3 - Conference contribution

AN - SCOPUS:84863385535

SN - 9781457702310

T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

SP - 229

EP - 230

BT - 2012 IEEE International Conference on Consumer Electronics, ICCE 2012

T2 - 2012 IEEE International Conference on Consumer Electronics, ICCE 2012

Y2 - 13 January 2012 through 16 January 2012

ER -