Share Email Print

Proceedings Paper

Occupant detection using support vector machines with a polynomial kernel function
Author(s): Eduardo Atilio Destefanis; Eberhard Kienzle; Luis R. Canali
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The use of air bags in the presence of bad passenger and baby seat positions in car seats can injure or kill these individuals in case of an accident when this device is inflated. A proposed solution is the use of range sensors to detect passenger and baby seat risky positions. Such sensors allow the Airbag inflation to be controlled. This work is concerned with the application of different classification schemes to a real world problem and the optimization of a sensor as a function of the classification performance. The sensor is constructed using a new technology which is called Photo-Mixer-Device (PMD). A systematic analysis of the occupant detection problem was made using real and virtual environments. The challenge is to find the best sensor geometry and to adapt a classification scheme under the current technological constraints. Passenger head position detection is also a desirable issue. A couple of classifiers have been used into a simple configuration to reach this goal. Experiences and results are described.

Paper Details

Date Published: 13 October 2000
PDF: 8 pages
Proc. SPIE 4192, Intelligent Systems in Design and Manufacturing III, (13 October 2000); doi: 10.1117/12.403659
Show Author Affiliations
Eduardo Atilio Destefanis, Univ. Tecnologica Nacional (Argentina)
Eberhard Kienzle, Fachhochschule fuer Technik Esslingen (Germany)
Luis R. Canali, Univ. Tecnologica Nacional (Argentina)

Published in SPIE Proceedings Vol. 4192:
Intelligent Systems in Design and Manufacturing III
Bhaskaran Gopalakrishnan; Angappa Gunasekaran, Editor(s)

© SPIE. Terms of Use
Back to Top