Night vision pedestrian detection based on adaptive preprocessing using near infrared camera

Tae Young Han; Byung Cheol Song

doi:10.1109/ICCE-Asia.2016.7804763

Night vision pedestrian detection based on adaptive preprocessing using near infrared camera

Tae Young Han, Byung Cheol Song

Inha University

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

20 Scopus citations

Abstract

Performance of computer vision algorithm for pedestrian detection decrease in case of night vision system. Since intensity of luminance at night is extremely low compare to daytime, even human visibility cannot recognize object properly at night. Most recent generation of night vision system have researched using near infrared camera to settle the problem, but it still have poor visibility and application. This paper describes a night vision pedestrian detection for AEB (Automatic Emergency Braking) system using near infrared camera. ACF (Aggregated Channel Features) and AdaBoost algorithm are employed to discriminate pedestrians reflected by infrared. Most significant contribution of this paper is adaptive preprocessing to enhance contrast of pedestrians. Implementation have been done on both desktop and embedded board. With improved pedestrian detection performance, our approach allow drivers to avoid potential collisions effectively.

Original language	English
Title of host publication	2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509027439
DOIs	https://doi.org/10.1109/ICCE-Asia.2016.7804763
State	Published - 3 Jan 2017
Event	2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016 - Seoul, Korea, Republic of Duration: 26 Oct 2016 → 28 Oct 2016

Publication series

Name	2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016

Conference

Conference	2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016
Country/Territory	Korea, Republic of
City	Seoul
Period	26/10/16 → 28/10/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

ACF
Contrast enhancement
NIR camera
Pedestrian detection

Access to Document

10.1109/ICCE-Asia.2016.7804763

Cite this

Han, T. Y., & Song, B. C. (2017). Night vision pedestrian detection based on adaptive preprocessing using near infrared camera. In 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016 Article 7804763 (2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Asia.2016.7804763

@inproceedings{8ad95ec463ad48a1bc0b7d9b702f133c,

title = "Night vision pedestrian detection based on adaptive preprocessing using near infrared camera",

abstract = "Performance of computer vision algorithm for pedestrian detection decrease in case of night vision system. Since intensity of luminance at night is extremely low compare to daytime, even human visibility cannot recognize object properly at night. Most recent generation of night vision system have researched using near infrared camera to settle the problem, but it still have poor visibility and application. This paper describes a night vision pedestrian detection for AEB (Automatic Emergency Braking) system using near infrared camera. ACF (Aggregated Channel Features) and AdaBoost algorithm are employed to discriminate pedestrians reflected by infrared. Most significant contribution of this paper is adaptive preprocessing to enhance contrast of pedestrians. Implementation have been done on both desktop and embedded board. With improved pedestrian detection performance, our approach allow drivers to avoid potential collisions effectively.",

keywords = "ACF, Contrast enhancement, NIR camera, Pedestrian detection",

author = "Han, {Tae Young} and Song, {Byung Cheol}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016 ; Conference date: 26-10-2016 Through 28-10-2016",

year = "2017",

month = jan,

day = "3",

doi = "10.1109/ICCE-Asia.2016.7804763",

language = "English",

series = "2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016",

address = "United States",

}

Han, TY & Song, BC 2017, Night vision pedestrian detection based on adaptive preprocessing using near infrared camera. in 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016., 7804763, 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016, Seoul, Korea, Republic of, 26/10/16. https://doi.org/10.1109/ICCE-Asia.2016.7804763

Night vision pedestrian detection based on adaptive preprocessing using near infrared camera. / Han, Tae Young; Song, Byung Cheol.
2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7804763 (2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016).

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

TY - GEN

T1 - Night vision pedestrian detection based on adaptive preprocessing using near infrared camera

AU - Han, Tae Young

AU - Song, Byung Cheol

PY - 2017/1/3

Y1 - 2017/1/3

N2 - Performance of computer vision algorithm for pedestrian detection decrease in case of night vision system. Since intensity of luminance at night is extremely low compare to daytime, even human visibility cannot recognize object properly at night. Most recent generation of night vision system have researched using near infrared camera to settle the problem, but it still have poor visibility and application. This paper describes a night vision pedestrian detection for AEB (Automatic Emergency Braking) system using near infrared camera. ACF (Aggregated Channel Features) and AdaBoost algorithm are employed to discriminate pedestrians reflected by infrared. Most significant contribution of this paper is adaptive preprocessing to enhance contrast of pedestrians. Implementation have been done on both desktop and embedded board. With improved pedestrian detection performance, our approach allow drivers to avoid potential collisions effectively.

AB - Performance of computer vision algorithm for pedestrian detection decrease in case of night vision system. Since intensity of luminance at night is extremely low compare to daytime, even human visibility cannot recognize object properly at night. Most recent generation of night vision system have researched using near infrared camera to settle the problem, but it still have poor visibility and application. This paper describes a night vision pedestrian detection for AEB (Automatic Emergency Braking) system using near infrared camera. ACF (Aggregated Channel Features) and AdaBoost algorithm are employed to discriminate pedestrians reflected by infrared. Most significant contribution of this paper is adaptive preprocessing to enhance contrast of pedestrians. Implementation have been done on both desktop and embedded board. With improved pedestrian detection performance, our approach allow drivers to avoid potential collisions effectively.

KW - ACF

KW - Contrast enhancement

KW - NIR camera

KW - Pedestrian detection

UR - http://www.scopus.com/inward/record.url?scp=85011116125&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Asia.2016.7804763

DO - 10.1109/ICCE-Asia.2016.7804763

M3 - Conference contribution

AN - SCOPUS:85011116125

T3 - 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016

BT - 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016

Y2 - 26 October 2016 through 28 October 2016

ER -

Han TY, Song BC. Night vision pedestrian detection based on adaptive preprocessing using near infrared camera. In 2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7804763. (2016 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2016). doi: 10.1109/ICCE-Asia.2016.7804763

Night vision pedestrian detection based on adaptive preprocessing using near infrared camera

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this