Method to improve efficiency of human detection using scalemap

Guntae Bae, Sooyeong Kwak, Hyeran Byun, Daeyong Park

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

An efficient method is introduced for detecting humans in surveillance video. The method improves the performance of multiscale human detection through the use of a scalemap, and does not require knowledge of the camera parameters or the use of additional devices. A scalemap is a map that links each position in the observed image to the optimal detection scale. The proposed method efficiently reduces the computational costs by estimating the scale of interest and the region of interest based on the scalemap, while maintaining the accuracy of the detection. It is experimentally shown through an experiment that the proposed method can improve both the accuracy and the efficiency of real-world surveillance videos.

Original languageEnglish
Pages (from-to)265-267
Number of pages3
JournalElectronics Letters
Volume50
Issue number4
DOIs
Publication statusPublished - 2014 Feb 13

Fingerprint

Cameras
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Bae, Guntae ; Kwak, Sooyeong ; Byun, Hyeran ; Park, Daeyong. / Method to improve efficiency of human detection using scalemap. In: Electronics Letters. 2014 ; Vol. 50, No. 4. pp. 265-267.
@article{bfbee89142484271a1ca970679928192,
title = "Method to improve efficiency of human detection using scalemap",
abstract = "An efficient method is introduced for detecting humans in surveillance video. The method improves the performance of multiscale human detection through the use of a scalemap, and does not require knowledge of the camera parameters or the use of additional devices. A scalemap is a map that links each position in the observed image to the optimal detection scale. The proposed method efficiently reduces the computational costs by estimating the scale of interest and the region of interest based on the scalemap, while maintaining the accuracy of the detection. It is experimentally shown through an experiment that the proposed method can improve both the accuracy and the efficiency of real-world surveillance videos.",
author = "Guntae Bae and Sooyeong Kwak and Hyeran Byun and Daeyong Park",
year = "2014",
month = "2",
day = "13",
doi = "10.1049/el.2013.3588",
language = "English",
volume = "50",
pages = "265--267",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "4",

}

Method to improve efficiency of human detection using scalemap. / Bae, Guntae; Kwak, Sooyeong; Byun, Hyeran; Park, Daeyong.

In: Electronics Letters, Vol. 50, No. 4, 13.02.2014, p. 265-267.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Method to improve efficiency of human detection using scalemap

AU - Bae, Guntae

AU - Kwak, Sooyeong

AU - Byun, Hyeran

AU - Park, Daeyong

PY - 2014/2/13

Y1 - 2014/2/13

N2 - An efficient method is introduced for detecting humans in surveillance video. The method improves the performance of multiscale human detection through the use of a scalemap, and does not require knowledge of the camera parameters or the use of additional devices. A scalemap is a map that links each position in the observed image to the optimal detection scale. The proposed method efficiently reduces the computational costs by estimating the scale of interest and the region of interest based on the scalemap, while maintaining the accuracy of the detection. It is experimentally shown through an experiment that the proposed method can improve both the accuracy and the efficiency of real-world surveillance videos.

AB - An efficient method is introduced for detecting humans in surveillance video. The method improves the performance of multiscale human detection through the use of a scalemap, and does not require knowledge of the camera parameters or the use of additional devices. A scalemap is a map that links each position in the observed image to the optimal detection scale. The proposed method efficiently reduces the computational costs by estimating the scale of interest and the region of interest based on the scalemap, while maintaining the accuracy of the detection. It is experimentally shown through an experiment that the proposed method can improve both the accuracy and the efficiency of real-world surveillance videos.

UR - http://www.scopus.com/inward/record.url?scp=84894069093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894069093&partnerID=8YFLogxK

U2 - 10.1049/el.2013.3588

DO - 10.1049/el.2013.3588

M3 - Article

VL - 50

SP - 265

EP - 267

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 4

ER -