A pedestrian detection system accelerated by kernelized proposals

Jeonghyun Baek; Junhyuk Hyun; Euntai Kim

doi:10.1109/TITS.2019.2904836

A pedestrian detection system accelerated by kernelized proposals

Jeonghyun Baek, Junhyuk Hyun, Euntai Kim

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

When pedestrian detection (PD) is implemented on a central processing unit (CPU), performing real-time processing using a classical sliding window is difficult. Therefore, an efficient proposal generation method is required. A new generation method, named additive kernel binarized normed gradient (AKBING), is proposed herein, and this method is applied to the PD for real-time implementation on a CPU. The AKBING is based on an additive kernel support vector machine (AKSVM) and is implemented using the binarized normed gradient. The proposed PD can operate in real time because all AKSVM computations are approximated via simple atomic operations. In the suggested kernelized proposal method, the popular features and a classifier are combined, and the method is tested on a Caltech Pedestrian dataset and KITTI dataset. The experimental results show that the detection system with the proposed method improved the speed with minor degradation in detection accuracy.

Original language	English
Article number	8681730
Pages (from-to)	1216-1228
Number of pages	13
Journal	IEEE Transactions on Intelligent Transportation Systems
Volume	21
Issue number	3
DOIs	https://doi.org/10.1109/TITS.2019.2904836
Publication status	Published - 2020 Mar

Bibliographical note

Funding Information:
Manuscript received March 25, 2018; revised November 29, 2018; accepted February 16, 2019. Date of publication April 4, 2019; date of current version February 28, 2020. This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under Grant NRF-2016R1A2A2A05005301. The Associate Editor for this paper was N. Zheng. (Corresponding author: Euntai Kim.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, South Korea (e-mail: etkim@yonsei.ac.kr). Digital Object Identifier 10.1109/TITS.2019.2904836

Publisher Copyright:
© 2000-2011 IEEE.

All Science Journal Classification (ASJC) codes

Automotive Engineering
Mechanical Engineering
Computer Science Applications

Access to Document

10.1109/TITS.2019.2904836

Cite this

@article{d9cfdf627a2f4af787ca8277cfd42d5a,

title = "A pedestrian detection system accelerated by kernelized proposals",

abstract = "When pedestrian detection (PD) is implemented on a central processing unit (CPU), performing real-time processing using a classical sliding window is difficult. Therefore, an efficient proposal generation method is required. A new generation method, named additive kernel binarized normed gradient (AKBING), is proposed herein, and this method is applied to the PD for real-time implementation on a CPU. The AKBING is based on an additive kernel support vector machine (AKSVM) and is implemented using the binarized normed gradient. The proposed PD can operate in real time because all AKSVM computations are approximated via simple atomic operations. In the suggested kernelized proposal method, the popular features and a classifier are combined, and the method is tested on a Caltech Pedestrian dataset and KITTI dataset. The experimental results show that the detection system with the proposed method improved the speed with minor degradation in detection accuracy.",

author = "Jeonghyun Baek and Junhyuk Hyun and Euntai Kim",

note = "Funding Information: Manuscript received March 25, 2018; revised November 29, 2018; accepted February 16, 2019. Date of publication April 4, 2019; date of current version February 28, 2020. This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under Grant NRF-2016R1A2A2A05005301. The Associate Editor for this paper was N. Zheng. (Corresponding author: Euntai Kim.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, South Korea (e-mail: etkim@yonsei.ac.kr). Digital Object Identifier 10.1109/TITS.2019.2904836 Publisher Copyright: {\textcopyright} 2000-2011 IEEE.",

year = "2020",

month = mar,

doi = "10.1109/TITS.2019.2904836",

language = "English",

volume = "21",

pages = "1216--1228",

journal = "IEEE Transactions on Intelligent Transportation Systems",

issn = "1524-9050",

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

number = "3",

}

TY - JOUR

T1 - A pedestrian detection system accelerated by kernelized proposals

AU - Baek, Jeonghyun

AU - Hyun, Junhyuk

AU - Kim, Euntai

N1 - Funding Information: Manuscript received March 25, 2018; revised November 29, 2018; accepted February 16, 2019. Date of publication April 4, 2019; date of current version February 28, 2020. This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under Grant NRF-2016R1A2A2A05005301. The Associate Editor for this paper was N. Zheng. (Corresponding author: Euntai Kim.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, South Korea (e-mail: etkim@yonsei.ac.kr). Digital Object Identifier 10.1109/TITS.2019.2904836 Publisher Copyright: © 2000-2011 IEEE.

PY - 2020/3

Y1 - 2020/3

N2 - When pedestrian detection (PD) is implemented on a central processing unit (CPU), performing real-time processing using a classical sliding window is difficult. Therefore, an efficient proposal generation method is required. A new generation method, named additive kernel binarized normed gradient (AKBING), is proposed herein, and this method is applied to the PD for real-time implementation on a CPU. The AKBING is based on an additive kernel support vector machine (AKSVM) and is implemented using the binarized normed gradient. The proposed PD can operate in real time because all AKSVM computations are approximated via simple atomic operations. In the suggested kernelized proposal method, the popular features and a classifier are combined, and the method is tested on a Caltech Pedestrian dataset and KITTI dataset. The experimental results show that the detection system with the proposed method improved the speed with minor degradation in detection accuracy.

AB - When pedestrian detection (PD) is implemented on a central processing unit (CPU), performing real-time processing using a classical sliding window is difficult. Therefore, an efficient proposal generation method is required. A new generation method, named additive kernel binarized normed gradient (AKBING), is proposed herein, and this method is applied to the PD for real-time implementation on a CPU. The AKBING is based on an additive kernel support vector machine (AKSVM) and is implemented using the binarized normed gradient. The proposed PD can operate in real time because all AKSVM computations are approximated via simple atomic operations. In the suggested kernelized proposal method, the popular features and a classifier are combined, and the method is tested on a Caltech Pedestrian dataset and KITTI dataset. The experimental results show that the detection system with the proposed method improved the speed with minor degradation in detection accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85081140805&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081140805&partnerID=8YFLogxK

U2 - 10.1109/TITS.2019.2904836

DO - 10.1109/TITS.2019.2904836

M3 - Article

AN - SCOPUS:85081140805

SN - 1524-9050

VL - 21

SP - 1216

EP - 1228

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

IS - 3

M1 - 8681730

ER -

A pedestrian detection system accelerated by kernelized proposals

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this