Robust people counting system based on sensor fusion

Byoung Kyu Dan, You Sun Kim, Suryanto, June Young Jung, Sung-Jea Ko

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

This paper presents a novel robust people counting system based on fusing the depth and vision data. Conventional algorithms utilize the monoscopic or stereoscopic vision data to count people. However, these vision-based people counting methods often fail due to occasional illumination change and crowded environment. In the proposed algorithm, both the top-view vision and depth images are captured by a video-plus-depth camera mounted on the ceiling. The depth image is first processed by a morphological operator to alleviate depth artifacts such as the optical noise and lost data. Then the human object is extracted using a human model from the preprocessed depth image. Finally, the trajectory of the detected object is established by applying the bidirectional matching algorithm. Experimental results show that the proposed algorithm achieves over 98% accuracy in various testing environments.

Original languageEnglish
Article number6311350
Pages (from-to)1013-1021
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume58
Issue number3
DOIs
Publication statusPublished - 2012 Oct 16

Fingerprint

Fusion reactions
Sensors
Ceilings
Lighting
Cameras
Trajectories
Testing

Keywords

  • depthcamera
  • object detection
  • people counting
  • sensor fusing
  • Surveillance system

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Robust people counting system based on sensor fusion. / Dan, Byoung Kyu; Kim, You Sun; Suryanto; Jung, June Young; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 58, No. 3, 6311350, 16.10.2012, p. 1013-1021.

Research output: Contribution to journalArticle

Dan, Byoung Kyu ; Kim, You Sun ; Suryanto ; Jung, June Young ; Ko, Sung-Jea. / Robust people counting system based on sensor fusion. In: IEEE Transactions on Consumer Electronics. 2012 ; Vol. 58, No. 3. pp. 1013-1021.
@article{f65855cca3ed4cae8c55770ca32d40d3,
title = "Robust people counting system based on sensor fusion",
abstract = "This paper presents a novel robust people counting system based on fusing the depth and vision data. Conventional algorithms utilize the monoscopic or stereoscopic vision data to count people. However, these vision-based people counting methods often fail due to occasional illumination change and crowded environment. In the proposed algorithm, both the top-view vision and depth images are captured by a video-plus-depth camera mounted on the ceiling. The depth image is first processed by a morphological operator to alleviate depth artifacts such as the optical noise and lost data. Then the human object is extracted using a human model from the preprocessed depth image. Finally, the trajectory of the detected object is established by applying the bidirectional matching algorithm. Experimental results show that the proposed algorithm achieves over 98{\%} accuracy in various testing environments.",
keywords = "depthcamera, object detection, people counting, sensor fusing, Surveillance system",
author = "Dan, {Byoung Kyu} and Kim, {You Sun} and Suryanto and Jung, {June Young} and Sung-Jea Ko",
year = "2012",
month = "10",
day = "16",
doi = "10.1109/TCE.2012.6311350",
language = "English",
volume = "58",
pages = "1013--1021",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Robust people counting system based on sensor fusion

AU - Dan, Byoung Kyu

AU - Kim, You Sun

AU - Suryanto,

AU - Jung, June Young

AU - Ko, Sung-Jea

PY - 2012/10/16

Y1 - 2012/10/16

N2 - This paper presents a novel robust people counting system based on fusing the depth and vision data. Conventional algorithms utilize the monoscopic or stereoscopic vision data to count people. However, these vision-based people counting methods often fail due to occasional illumination change and crowded environment. In the proposed algorithm, both the top-view vision and depth images are captured by a video-plus-depth camera mounted on the ceiling. The depth image is first processed by a morphological operator to alleviate depth artifacts such as the optical noise and lost data. Then the human object is extracted using a human model from the preprocessed depth image. Finally, the trajectory of the detected object is established by applying the bidirectional matching algorithm. Experimental results show that the proposed algorithm achieves over 98% accuracy in various testing environments.

AB - This paper presents a novel robust people counting system based on fusing the depth and vision data. Conventional algorithms utilize the monoscopic or stereoscopic vision data to count people. However, these vision-based people counting methods often fail due to occasional illumination change and crowded environment. In the proposed algorithm, both the top-view vision and depth images are captured by a video-plus-depth camera mounted on the ceiling. The depth image is first processed by a morphological operator to alleviate depth artifacts such as the optical noise and lost data. Then the human object is extracted using a human model from the preprocessed depth image. Finally, the trajectory of the detected object is established by applying the bidirectional matching algorithm. Experimental results show that the proposed algorithm achieves over 98% accuracy in various testing environments.

KW - depthcamera

KW - object detection

KW - people counting

KW - sensor fusing

KW - Surveillance system

UR - http://www.scopus.com/inward/record.url?scp=84867327772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867327772&partnerID=8YFLogxK

U2 - 10.1109/TCE.2012.6311350

DO - 10.1109/TCE.2012.6311350

M3 - Article

AN - SCOPUS:84867327772

VL - 58

SP - 1013

EP - 1021

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 3

M1 - 6311350

ER -