Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector Machine

Jeonghyun Baek, Jisu Kim, Euntai Kim

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

For reliable driving assistance or automated driving, pedestrian detection must be robust and performed in real time. In pedestrian detection, a linear support vector machine (linSVM) is popularly used as a classifier but exhibits degraded performance due to the multipostures of pedestrians. Kernel SVM (KSVM) could be a better choice for pedestrian detection, but it has a disadvantage in that it requires too much more computation than linSVM. In this paper, the cascade implementation of the additive KSVM (AKSVM) is proposed for the application of pedestrian detection. AKSVM avoids kernel expansion by using lookup tables, and it is implemented in cascade form, thereby speeding up pedestrian detection. The cascade implementation is trained by a genetic algorithm such that the computation time is minimized, whereas the detection accuracy is maximized. In experiments, the proposed method is tested with the INRIA dataset. The experimental results indicate that the proposed method has better detection accuracy and reduced computation time compared with conventional methods.

Original languageEnglish
Article number7552553
Pages (from-to)902-916
Number of pages15
JournalIEEE Transactions on Intelligent Transportation Systems
Volume18
Issue number4
DOIs
Publication statusPublished - 2017 Apr 1

Fingerprint

Support vector machines
Table lookup
Classifiers
Genetic algorithms
Experiments

All Science Journal Classification (ASJC) codes

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Cite this

@article{fc96f0d147aa42c79bb696d476af9795,
title = "Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector Machine",
abstract = "For reliable driving assistance or automated driving, pedestrian detection must be robust and performed in real time. In pedestrian detection, a linear support vector machine (linSVM) is popularly used as a classifier but exhibits degraded performance due to the multipostures of pedestrians. Kernel SVM (KSVM) could be a better choice for pedestrian detection, but it has a disadvantage in that it requires too much more computation than linSVM. In this paper, the cascade implementation of the additive KSVM (AKSVM) is proposed for the application of pedestrian detection. AKSVM avoids kernel expansion by using lookup tables, and it is implemented in cascade form, thereby speeding up pedestrian detection. The cascade implementation is trained by a genetic algorithm such that the computation time is minimized, whereas the detection accuracy is maximized. In experiments, the proposed method is tested with the INRIA dataset. The experimental results indicate that the proposed method has better detection accuracy and reduced computation time compared with conventional methods.",
author = "Jeonghyun Baek and Jisu Kim and Euntai Kim",
year = "2017",
month = "4",
day = "1",
doi = "10.1109/TITS.2016.2594816",
language = "English",
volume = "18",
pages = "902--916",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector Machine. / Baek, Jeonghyun; Kim, Jisu; Kim, Euntai.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 18, No. 4, 7552553, 01.04.2017, p. 902-916.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector Machine

AU - Baek, Jeonghyun

AU - Kim, Jisu

AU - Kim, Euntai

PY - 2017/4/1

Y1 - 2017/4/1

N2 - For reliable driving assistance or automated driving, pedestrian detection must be robust and performed in real time. In pedestrian detection, a linear support vector machine (linSVM) is popularly used as a classifier but exhibits degraded performance due to the multipostures of pedestrians. Kernel SVM (KSVM) could be a better choice for pedestrian detection, but it has a disadvantage in that it requires too much more computation than linSVM. In this paper, the cascade implementation of the additive KSVM (AKSVM) is proposed for the application of pedestrian detection. AKSVM avoids kernel expansion by using lookup tables, and it is implemented in cascade form, thereby speeding up pedestrian detection. The cascade implementation is trained by a genetic algorithm such that the computation time is minimized, whereas the detection accuracy is maximized. In experiments, the proposed method is tested with the INRIA dataset. The experimental results indicate that the proposed method has better detection accuracy and reduced computation time compared with conventional methods.

AB - For reliable driving assistance or automated driving, pedestrian detection must be robust and performed in real time. In pedestrian detection, a linear support vector machine (linSVM) is popularly used as a classifier but exhibits degraded performance due to the multipostures of pedestrians. Kernel SVM (KSVM) could be a better choice for pedestrian detection, but it has a disadvantage in that it requires too much more computation than linSVM. In this paper, the cascade implementation of the additive KSVM (AKSVM) is proposed for the application of pedestrian detection. AKSVM avoids kernel expansion by using lookup tables, and it is implemented in cascade form, thereby speeding up pedestrian detection. The cascade implementation is trained by a genetic algorithm such that the computation time is minimized, whereas the detection accuracy is maximized. In experiments, the proposed method is tested with the INRIA dataset. The experimental results indicate that the proposed method has better detection accuracy and reduced computation time compared with conventional methods.

UR - http://www.scopus.com/inward/record.url?scp=84983672185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983672185&partnerID=8YFLogxK

U2 - 10.1109/TITS.2016.2594816

DO - 10.1109/TITS.2016.2594816

M3 - Article

VL - 18

SP - 902

EP - 916

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 4

M1 - 7552553

ER -