Real-time detection of crossing pedestrians for traffic-adaptive signal control

Vignesh Bhuvaneshwar; Pitu Mirchandani

Real-time detection of crossing pedestrians for traffic-adaptive signal control

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

Abstract

In this paper we propose an approach to detect and count pedestrians at an intersection, in real-time, using a fixed camera. After identifying moving objects in sequential images via motion segmentation, median filtering and erosion/dilation operations are performed to suppress noise. Connected component extraction is then employed to extract and label the moving objects in the image. The binary foreground region of each component is projected onto the axis perpendicular to its major axis to obtain a vertical projection histogram from which shadows can be detected, extracted and suppressed. Information about the size and coordinates of each component is then utilized to compute the number of people in the scene.

Original language	English (US)
Title of host publication	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Pages	309-313
Number of pages	5
State	Published - 2004
Externally published	Yes
Event	Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 - Washington, DC, United States Duration: Oct 3 2004 → Oct 6 2004

Other

Other	Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004
Country/Territory	United States
City	Washington, DC
Period	10/3/04 → 10/6/04

Keywords

Connected component extraction
Pedestrian detection
Projection histogram

ASJC Scopus subject areas

General Engineering

Cite this

@inproceedings{5dc8bd23f4214c41ae93d3c5585b8b64,

title = "Real-time detection of crossing pedestrians for traffic-adaptive signal control",

abstract = "In this paper we propose an approach to detect and count pedestrians at an intersection, in real-time, using a fixed camera. After identifying moving objects in sequential images via motion segmentation, median filtering and erosion/dilation operations are performed to suppress noise. Connected component extraction is then employed to extract and label the moving objects in the image. The binary foreground region of each component is projected onto the axis perpendicular to its major axis to obtain a vertical projection histogram from which shadows can be detected, extracted and suppressed. Information about the size and coordinates of each component is then utilized to compute the number of people in the scene.",

keywords = "Connected component extraction, Pedestrian detection, Projection histogram",

author = "Vignesh Bhuvaneshwar and Pitu Mirchandani",

year = "2004",

language = "English (US)",

pages = "309--313",

booktitle = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

note = "Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 ; Conference date: 03-10-2004 Through 06-10-2004",

}

TY - GEN

T1 - Real-time detection of crossing pedestrians for traffic-adaptive signal control

AU - Bhuvaneshwar, Vignesh

AU - Mirchandani, Pitu

PY - 2004

Y1 - 2004

N2 - In this paper we propose an approach to detect and count pedestrians at an intersection, in real-time, using a fixed camera. After identifying moving objects in sequential images via motion segmentation, median filtering and erosion/dilation operations are performed to suppress noise. Connected component extraction is then employed to extract and label the moving objects in the image. The binary foreground region of each component is projected onto the axis perpendicular to its major axis to obtain a vertical projection histogram from which shadows can be detected, extracted and suppressed. Information about the size and coordinates of each component is then utilized to compute the number of people in the scene.

AB - In this paper we propose an approach to detect and count pedestrians at an intersection, in real-time, using a fixed camera. After identifying moving objects in sequential images via motion segmentation, median filtering and erosion/dilation operations are performed to suppress noise. Connected component extraction is then employed to extract and label the moving objects in the image. The binary foreground region of each component is projected onto the axis perpendicular to its major axis to obtain a vertical projection histogram from which shadows can be detected, extracted and suppressed. Information about the size and coordinates of each component is then utilized to compute the number of people in the scene.

KW - Connected component extraction

KW - Pedestrian detection

KW - Projection histogram

UR - http://www.scopus.com/inward/record.url?scp=13344284584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13344284584&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:13344284584

SP - 309

EP - 313

BT - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

T2 - Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004

Y2 - 3 October 2004 through 6 October 2004

ER -

Real-time detection of crossing pedestrians for traffic-adaptive signal control

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this