Real-time estimation method of the number of pedestrians in video sequences

Sayaka Kuriyama; Go Hasegawa; Hirotaka Nakano

doi:10.1109/ICDT.2009.19

Real-time estimation method of the number of pedestrians in video sequences

Sayaka Kuriyama, Go Hasegawa, Hirotaka Nakano

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In a ubiquitous network society, information on mobile nodes such as pedestrians with cell phones in a target region is useful for network configuration, communication control, and so on. In this paper, we propose a novel method to estimate in real time the number of pedestrians in video sequences using a stationary camera. The proposed method extracts moving regions from video frame grabs using background difference and frame difference, and estimates the number of pedestrians based on the size of the moving region using a conversion function constructed based on prior learning. We evaluate the effectiveness of the proposed method by comparing the estimated values with the actual values, and show that the estimation error of the number of pedestrians is smaller than 0.1 in approximately 50% of frames, and that the mean absolute error is 0.37.

Original language	English
Title of host publication	Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009
Pages	65-70
Number of pages	6
DOIs	https://doi.org/10.1109/ICDT.2009.19
Publication status	Published - 2009 Nov 20
Externally published	Yes
Event	2009 4th International Conference on Digital Telecommunications, ICDT 2009 - Colmar, France Duration: 2009 Jul 20 → 2009 Jul 25

Publication series

Name	Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009

Conference

Conference	2009 4th International Conference on Digital Telecommunications, ICDT 2009
Country	France
City	Colmar
Period	09/7/20 → 09/7/25

Keywords

Background difference
Component
Frame difference
Stationary camera
Ubiquitous networks
Video sequences

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICDT.2009.19

Fingerprint Dive into the research topics of 'Real-time estimation method of the number of pedestrians in video sequences'. Together they form a unique fingerprint.

Cite this

Real-time estimation method of the number of pedestrians in video sequences. / Kuriyama, Sayaka; Hasegawa, Go; Nakano, Hirotaka.

Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009. 2009. p. 65-70 5205233 (Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kuriyama, S, Hasegawa, G & Nakano, H 2009, Real-time estimation method of the number of pedestrians in video sequences. in Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009., 5205233, Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009, pp. 65-70, 2009 4th International Conference on Digital Telecommunications, ICDT 2009, Colmar, France, 09/7/20. https://doi.org/10.1109/ICDT.2009.19

@inproceedings{664e51e70f4848d1af22249102cc4230,

title = "Real-time estimation method of the number of pedestrians in video sequences",

abstract = "In a ubiquitous network society, information on mobile nodes such as pedestrians with cell phones in a target region is useful for network configuration, communication control, and so on. In this paper, we propose a novel method to estimate in real time the number of pedestrians in video sequences using a stationary camera. The proposed method extracts moving regions from video frame grabs using background difference and frame difference, and estimates the number of pedestrians based on the size of the moving region using a conversion function constructed based on prior learning. We evaluate the effectiveness of the proposed method by comparing the estimated values with the actual values, and show that the estimation error of the number of pedestrians is smaller than 0.1 in approximately 50% of frames, and that the mean absolute error is 0.37.",

keywords = "Background difference, Component, Frame difference, Stationary camera, Ubiquitous networks, Video sequences",

author = "Sayaka Kuriyama and Go Hasegawa and Hirotaka Nakano",

year = "2009",

month = nov,

day = "20",

doi = "10.1109/ICDT.2009.19",

language = "English",

isbn = "9780769536958",

series = "Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009",

pages = "65--70",

booktitle = "Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009",

note = "2009 4th International Conference on Digital Telecommunications, ICDT 2009 ; Conference date: 20-07-2009 Through 25-07-2009",

}

TY - GEN

T1 - Real-time estimation method of the number of pedestrians in video sequences

AU - Kuriyama, Sayaka

AU - Hasegawa, Go

AU - Nakano, Hirotaka

PY - 2009/11/20

Y1 - 2009/11/20

N2 - In a ubiquitous network society, information on mobile nodes such as pedestrians with cell phones in a target region is useful for network configuration, communication control, and so on. In this paper, we propose a novel method to estimate in real time the number of pedestrians in video sequences using a stationary camera. The proposed method extracts moving regions from video frame grabs using background difference and frame difference, and estimates the number of pedestrians based on the size of the moving region using a conversion function constructed based on prior learning. We evaluate the effectiveness of the proposed method by comparing the estimated values with the actual values, and show that the estimation error of the number of pedestrians is smaller than 0.1 in approximately 50% of frames, and that the mean absolute error is 0.37.

AB - In a ubiquitous network society, information on mobile nodes such as pedestrians with cell phones in a target region is useful for network configuration, communication control, and so on. In this paper, we propose a novel method to estimate in real time the number of pedestrians in video sequences using a stationary camera. The proposed method extracts moving regions from video frame grabs using background difference and frame difference, and estimates the number of pedestrians based on the size of the moving region using a conversion function constructed based on prior learning. We evaluate the effectiveness of the proposed method by comparing the estimated values with the actual values, and show that the estimation error of the number of pedestrians is smaller than 0.1 in approximately 50% of frames, and that the mean absolute error is 0.37.

KW - Background difference

KW - Component

KW - Frame difference

KW - Stationary camera

KW - Ubiquitous networks

KW - Video sequences

UR - http://www.scopus.com/inward/record.url?scp=70449595617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449595617&partnerID=8YFLogxK

U2 - 10.1109/ICDT.2009.19

DO - 10.1109/ICDT.2009.19

M3 - Conference contribution

AN - SCOPUS:70449595617

SN - 9780769536958

T3 - Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009

SP - 65

EP - 70

BT - Proceedings - 2009 4th International Conference on Digital Telecommunications, ICDT 2009

T2 - 2009 4th International Conference on Digital Telecommunications, ICDT 2009

Y2 - 20 July 2009 through 25 July 2009

ER -