Visual tracking strategies for intelligent vehicle-highway systems

Christopher E. Smith; Nikolaos P. Papanikolopoulos; Scott A. Brandt; Charles Richards

doi:10.1117/12.198923

Visual tracking strategies for intelligent vehicle-highway systems

Christopher E. Smith, Nikolaos P. Papanikolopoulos, Scott A. Brandt, Charles Richards

Computer Science and Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

The complexity and congestion of current transportation systems often produce traffic situations that jeopardize the safety of the people involved. These situations vary from maintaining a safe distance behind a leading vehicle to safely allowing a pedestrian to cross a busy street. Environmental sensing plays a critical role in virtually all of these situations. Of the sensors available, vision sensors provide information that is richer and more complete than other sensors, making them a logical choice for a multisensor transportation system. In this paper we present robust techniques for intelligent vehicle-highway applications where computer vision plays a crucial role. In particular, we demonstrate that the Controlled Active Vision framework¹ can be utilized to provide a visual sensing modality to a traffic advisory system in order to increase the overall safety margin in a variety of common traffic situations. We have selected two application examples, vehicle tracking and pedestrian tracking, to demonstrate that the framework can provide precisely the type of information required to effectively manage the given situation.

Original language	English (US)
Pages (from-to)	234-245
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2344
DOIs	https://doi.org/10.1117/12.198923
State	Published - Dec 29 1994
Event	Intelligent Vehicle Highway Systems 1994 - Boston, United States Duration: Oct 31 1994 → Nov 4 1994

Bibliographical note

Funding Information:
This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-O1, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota.

Funding Information:
This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota.

Publisher Copyright:
© 1994 SPIE. All rights reserved.

Keywords

Detection
Intelligent vehicle-highway systems
Optical flow
Pedestrian control
Visual tracking

Publisher link

10.1117/12.198923

Find It

Find It at U of M Libraries

Cite this

@article{80b197cb2aa24fe3ac78e99e25fc61fa,

title = "Visual tracking strategies for intelligent vehicle-highway systems",

abstract = "The complexity and congestion of current transportation systems often produce traffic situations that jeopardize the safety of the people involved. These situations vary from maintaining a safe distance behind a leading vehicle to safely allowing a pedestrian to cross a busy street. Environmental sensing plays a critical role in virtually all of these situations. Of the sensors available, vision sensors provide information that is richer and more complete than other sensors, making them a logical choice for a multisensor transportation system. In this paper we present robust techniques for intelligent vehicle-highway applications where computer vision plays a crucial role. In particular, we demonstrate that the Controlled Active Vision framework1 can be utilized to provide a visual sensing modality to a traffic advisory system in order to increase the overall safety margin in a variety of common traffic situations. We have selected two application examples, vehicle tracking and pedestrian tracking, to demonstrate that the framework can provide precisely the type of information required to effectively manage the given situation.",

keywords = "Detection, Intelligent vehicle-highway systems, Optical flow, Pedestrian control, Visual tracking",

author = "Smith, {Christopher E.} and Papanikolopoulos, {Nikolaos P.} and Brandt, {Scott A.} and Charles Richards",

note = "Funding Information: This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-O1, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota. Funding Information: This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota. Publisher Copyright: {\textcopyright} 1994 SPIE. All rights reserved.; Intelligent Vehicle Highway Systems 1994 ; Conference date: 31-10-1994 Through 04-11-1994",

year = "1994",

month = dec,

day = "29",

doi = "10.1117/12.198923",

language = "English (US)",

volume = "2344",

pages = "234--245",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Visual tracking strategies for intelligent vehicle-highway systems

AU - Smith, Christopher E.

AU - Papanikolopoulos, Nikolaos P.

AU - Brandt, Scott A.

AU - Richards, Charles

N1 - Funding Information: This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-O1, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota. Funding Information: This work has been supported by the Department of Energy (Sandia National Laboratories) through Contract #AC-3752D, the National Science Foundation through Contract #IRI-9410003, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the 3M Corporation, the Graduate School of the University of Minnesota, and the Department of Computer Science of the University of Minnesota. Publisher Copyright: © 1994 SPIE. All rights reserved.

PY - 1994/12/29

Y1 - 1994/12/29

N2 - The complexity and congestion of current transportation systems often produce traffic situations that jeopardize the safety of the people involved. These situations vary from maintaining a safe distance behind a leading vehicle to safely allowing a pedestrian to cross a busy street. Environmental sensing plays a critical role in virtually all of these situations. Of the sensors available, vision sensors provide information that is richer and more complete than other sensors, making them a logical choice for a multisensor transportation system. In this paper we present robust techniques for intelligent vehicle-highway applications where computer vision plays a crucial role. In particular, we demonstrate that the Controlled Active Vision framework1 can be utilized to provide a visual sensing modality to a traffic advisory system in order to increase the overall safety margin in a variety of common traffic situations. We have selected two application examples, vehicle tracking and pedestrian tracking, to demonstrate that the framework can provide precisely the type of information required to effectively manage the given situation.

AB - The complexity and congestion of current transportation systems often produce traffic situations that jeopardize the safety of the people involved. These situations vary from maintaining a safe distance behind a leading vehicle to safely allowing a pedestrian to cross a busy street. Environmental sensing plays a critical role in virtually all of these situations. Of the sensors available, vision sensors provide information that is richer and more complete than other sensors, making them a logical choice for a multisensor transportation system. In this paper we present robust techniques for intelligent vehicle-highway applications where computer vision plays a crucial role. In particular, we demonstrate that the Controlled Active Vision framework1 can be utilized to provide a visual sensing modality to a traffic advisory system in order to increase the overall safety margin in a variety of common traffic situations. We have selected two application examples, vehicle tracking and pedestrian tracking, to demonstrate that the framework can provide precisely the type of information required to effectively manage the given situation.

KW - Detection

KW - Intelligent vehicle-highway systems

KW - Optical flow

KW - Pedestrian control

KW - Visual tracking

UR - http://www.scopus.com/inward/record.url?scp=84878220144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878220144&partnerID=8YFLogxK

U2 - 10.1117/12.198923

DO - 10.1117/12.198923

M3 - Conference article

AN - SCOPUS:84878220144

SN - 0277-786X

VL - 2344

SP - 234

EP - 245

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Intelligent Vehicle Highway Systems 1994

Y2 - 31 October 1994 through 4 November 1994

ER -

Visual tracking strategies for intelligent vehicle-highway systems

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this