Enhancing pedestrian detection using optical flow for surveillance

Redwan A.K. Noaman, Mohd Alauddin Mohd Ali, Nasharuddin Zainal

Research output: Contribution to journalArticle

Abstract

Optical flow can be used to segment a moving object from its backgrounds and track it. In this paper, an Enhanced Lucas-Kanade optical flow technique was used to improve human detection in terms of speed and accuracy. We combined object segmentation output with a human detector using an optical flow algorithm. The proposed technique used the optical flow to find the area of interest to complete object segmentation and use those results as an input for the human detector. This technique has been developed to be used in surveillance systems. Our experiments indicated that the proposed method was 37% faster and 118% more accurate than the standard Felzenszwalb (PFF) detector.

Original languageEnglish
Pages (from-to)35-48
Number of pages14
JournalInternational Journal of Computational Vision and Robotics
Volume7
Issue number1-2
DOIs
Publication statusPublished - 2017

Fingerprint

Optical flows
Detectors
Experiments

Keywords

  • Gaussian filter
  • Human detection
  • Luckas-kanade
  • Optical flow
  • PFF detector

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Enhancing pedestrian detection using optical flow for surveillance. / Noaman, Redwan A.K.; Ali, Mohd Alauddin Mohd; Zainal, Nasharuddin.

In: International Journal of Computational Vision and Robotics, Vol. 7, No. 1-2, 2017, p. 35-48.

Research output: Contribution to journalArticle

@article{06d7deb019de4d169b85af1b1aef00b9,
title = "Enhancing pedestrian detection using optical flow for surveillance",
abstract = "Optical flow can be used to segment a moving object from its backgrounds and track it. In this paper, an Enhanced Lucas-Kanade optical flow technique was used to improve human detection in terms of speed and accuracy. We combined object segmentation output with a human detector using an optical flow algorithm. The proposed technique used the optical flow to find the area of interest to complete object segmentation and use those results as an input for the human detector. This technique has been developed to be used in surveillance systems. Our experiments indicated that the proposed method was 37{\%} faster and 118{\%} more accurate than the standard Felzenszwalb (PFF) detector.",
keywords = "Gaussian filter, Human detection, Luckas-kanade, Optical flow, PFF detector",
author = "Noaman, {Redwan A.K.} and Ali, {Mohd Alauddin Mohd} and Nasharuddin Zainal",
year = "2017",
doi = "10.1504/IJCVR.2017.081246",
language = "English",
volume = "7",
pages = "35--48",
journal = "International Journal of Computational Vision and Robotics",
issn = "1752-9131",
publisher = "Inderscience Enterprises Ltd",
number = "1-2",

}

TY - JOUR

T1 - Enhancing pedestrian detection using optical flow for surveillance

AU - Noaman, Redwan A.K.

AU - Ali, Mohd Alauddin Mohd

AU - Zainal, Nasharuddin

PY - 2017

Y1 - 2017

N2 - Optical flow can be used to segment a moving object from its backgrounds and track it. In this paper, an Enhanced Lucas-Kanade optical flow technique was used to improve human detection in terms of speed and accuracy. We combined object segmentation output with a human detector using an optical flow algorithm. The proposed technique used the optical flow to find the area of interest to complete object segmentation and use those results as an input for the human detector. This technique has been developed to be used in surveillance systems. Our experiments indicated that the proposed method was 37% faster and 118% more accurate than the standard Felzenszwalb (PFF) detector.

AB - Optical flow can be used to segment a moving object from its backgrounds and track it. In this paper, an Enhanced Lucas-Kanade optical flow technique was used to improve human detection in terms of speed and accuracy. We combined object segmentation output with a human detector using an optical flow algorithm. The proposed technique used the optical flow to find the area of interest to complete object segmentation and use those results as an input for the human detector. This technique has been developed to be used in surveillance systems. Our experiments indicated that the proposed method was 37% faster and 118% more accurate than the standard Felzenszwalb (PFF) detector.

KW - Gaussian filter

KW - Human detection

KW - Luckas-kanade

KW - Optical flow

KW - PFF detector

UR - http://www.scopus.com/inward/record.url?scp=85018184486&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018184486&partnerID=8YFLogxK

U2 - 10.1504/IJCVR.2017.081246

DO - 10.1504/IJCVR.2017.081246

M3 - Article

AN - SCOPUS:85018184486

VL - 7

SP - 35

EP - 48

JO - International Journal of Computational Vision and Robotics

JF - International Journal of Computational Vision and Robotics

SN - 1752-9131

IS - 1-2

ER -