3D vision sensing for improved pedestrian safety

Grant Grubb; Alexander Zelinsky; Lars Nilsson; Magnus Rilbe

3D vision sensing for improved pedestrian safety

Grant Grubb^*
, Alexander Zelinsky
, Lars Nilsson
, Magnus Rilbe

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

99 Citations (Scopus)

Abstract

Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive Pedestrian Protection Systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5% and 0.4% respectively.

Original language	English
Pages	19-24
Number of pages	6
Publication status	Published - 2004
Event	2004 IEEE Intelligent Vehicles Symposium - Parma, Italy Duration: 14 Jun 2004 → 17 Jun 2004

Conference

Conference	2004 IEEE Intelligent Vehicles Symposium
Country/Territory	Italy
City	Parma
Period	14/06/04 → 17/06/04

Cite this

@conference{1bd80361a911438db4fa9449aa61aaea,

title = "3D vision sensing for improved pedestrian safety",

abstract = "Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive Pedestrian Protection Systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5\% and 0.4\% respectively.",

author = "Grant Grubb and Alexander Zelinsky and Lars Nilsson and Magnus Rilbe",

year = "2004",

language = "English",

pages = "19--24",

note = "2004 IEEE Intelligent Vehicles Symposium ; Conference date: 14-06-2004 Through 17-06-2004",

}

TY - CONF

T1 - 3D vision sensing for improved pedestrian safety

AU - Grubb, Grant

AU - Zelinsky, Alexander

AU - Nilsson, Lars

AU - Rilbe, Magnus

PY - 2004

Y1 - 2004

N2 - Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive Pedestrian Protection Systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5% and 0.4% respectively.

AB - Pedestrian-vehicle accidents account for the second largest source of automotive related fatality and injury worldwide. This paper presents a system which detects and tracks pedestrians in realtime for use with automotive Pedestrian Protection Systems (PPS) aimed at reducing such pedestrian-vehicle related injury. The system is based on a passive stereo vision configuration which segments a scene into 3D objects, classifies each object as pedestrian/non-pedestrian and finally tracks the pedestrian in 3D. Our system was implemented and tested on a Volvo test vehicle. Strong results for the system were obtained over a range of simple and complex environments, with average positive and false positive detection rates of 83.5% and 0.4% respectively.

UR - https://www.scopus.com/pages/publications/4544319826

M3 - Paper

AN - SCOPUS:4544319826

SP - 19

EP - 24

T2 - 2004 IEEE Intelligent Vehicles Symposium

Y2 - 14 June 2004 through 17 June 2004

ER -

3D vision sensing for improved pedestrian safety

Abstract

Conference

Other files and links

Fingerprint

Cite this