Towards a non-contact driver-vehicle interface

Gordon McAllister; Stephen J. McKenna; Ian W. Ricketts

doi:10.1109/ITSC.2000.881018

Towards a non-contact driver-vehicle interface

Gordon McAllister
, Stephen J. McKenna
, Ian W. Ricketts

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

7 Citations (Scopus)

Abstract

A novel, non-contact, pointing interface is being developed for the control of non-safety critical systems inside a vehicle with the aims of improving safety, decreasing manufacturing cost and improving the ease of driver migration between different cars. A driver operates the interface via an on-screen cursor using pointing gestures to be identified by a computer vision system. This paper describes the vision subsystem responsible for detection and tracking of the driver's hands. To be robust, it must detect and track under varying lighting conditions with no prior assumptions concerning the colour of the hands or clothing. Adaptive foreground and background models are used for segmentation and a robust geometrical hand model is employed for tracking. The system is demonstrated working at speeds close to real-time on a standard PC using image sequences captured inside a car

Original language	English
Title of host publication	2000 IEEE Intelligent Transportation Systems proceedings
Publisher	IEEE
Pages	58-63
Number of pages	6
ISBN (Print)	0780359712
DOIs	https://doi.org/10.1109/ITSC.2000.881018
Publication status	Published - 2000
Event	Intelligent Transportation Systems, 2000 - The Ritz Carlton Hotel, Dearborn, MI, United States Duration: 1 Oct 2000 → 3 Oct 2000

Conference

Conference	Intelligent Transportation Systems, 2000
Country/Territory	United States
City	Dearborn, MI
Period	1/10/00 → 3/10/00

Access to Document

10.1109/ITSC.2000.881018

Cite this

@inproceedings{dc42b61d661346639e1c6549bb1eaa9e,

title = "Towards a non-contact driver-vehicle interface",

abstract = "A novel, non-contact, pointing interface is being developed for the control of non-safety critical systems inside a vehicle with the aims of improving safety, decreasing manufacturing cost and improving the ease of driver migration between different cars. A driver operates the interface via an on-screen cursor using pointing gestures to be identified by a computer vision system. This paper describes the vision subsystem responsible for detection and tracking of the driver's hands. To be robust, it must detect and track under varying lighting conditions with no prior assumptions concerning the colour of the hands or clothing. Adaptive foreground and background models are used for segmentation and a robust geometrical hand model is employed for tracking. The system is demonstrated working at speeds close to real-time on a standard PC using image sequences captured inside a car ",

author = "Gordon McAllister and McKenna, \{Stephen J.\} and Ricketts, \{Ian W.\}",

year = "2000",

doi = "10.1109/ITSC.2000.881018",

language = "English",

isbn = " 0780359712 ",

pages = "58--63",

booktitle = "2000 IEEE Intelligent Transportation Systems proceedings",

publisher = "IEEE",

note = "Intelligent Transportation Systems, 2000 ; Conference date: 01-10-2000 Through 03-10-2000",

}

TY - GEN

T1 - Towards a non-contact driver-vehicle interface

AU - McAllister, Gordon

AU - McKenna, Stephen J.

AU - Ricketts, Ian W.

PY - 2000

Y1 - 2000

N2 - A novel, non-contact, pointing interface is being developed for the control of non-safety critical systems inside a vehicle with the aims of improving safety, decreasing manufacturing cost and improving the ease of driver migration between different cars. A driver operates the interface via an on-screen cursor using pointing gestures to be identified by a computer vision system. This paper describes the vision subsystem responsible for detection and tracking of the driver's hands. To be robust, it must detect and track under varying lighting conditions with no prior assumptions concerning the colour of the hands or clothing. Adaptive foreground and background models are used for segmentation and a robust geometrical hand model is employed for tracking. The system is demonstrated working at speeds close to real-time on a standard PC using image sequences captured inside a car

AB - A novel, non-contact, pointing interface is being developed for the control of non-safety critical systems inside a vehicle with the aims of improving safety, decreasing manufacturing cost and improving the ease of driver migration between different cars. A driver operates the interface via an on-screen cursor using pointing gestures to be identified by a computer vision system. This paper describes the vision subsystem responsible for detection and tracking of the driver's hands. To be robust, it must detect and track under varying lighting conditions with no prior assumptions concerning the colour of the hands or clothing. Adaptive foreground and background models are used for segmentation and a robust geometrical hand model is employed for tracking. The system is demonstrated working at speeds close to real-time on a standard PC using image sequences captured inside a car

U2 - 10.1109/ITSC.2000.881018

DO - 10.1109/ITSC.2000.881018

M3 - Conference contribution

SN - 0780359712

SP - 58

EP - 63

BT - 2000 IEEE Intelligent Transportation Systems proceedings

PB - IEEE

T2 - Intelligent Transportation Systems, 2000

Y2 - 1 October 2000 through 3 October 2000

ER -

Towards a non-contact driver-vehicle interface

Abstract

Conference

Access to Document

Fingerprint

Cite this