Occupant detection using support vector machines with a polynomial kernel function

Eduardo Atilio Destefanis; Eberhard Kienzle; Luis R. Canali

doi:10.1117/12.403659

13 October 2000 Occupant detection using support vector machines with a polynomial kernel function

Eduardo Atilio Destefanis, Eberhard Kienzle, Luis R. Canali

Proceedings Volume 4192, Intelligent Systems in Design and Manufacturing III; (2000) https://doi.org/10.1117/12.403659
Event: Intelligent Systems and Smart Manufacturing, 2000, Boston, MA, United States

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.

Citation Download Citation

Eduardo Atilio Destefanis, Eberhard Kienzle, and Luis R. Canali "Occupant detection using support vector machines with a polynomial kernel function", Proc. SPIE 4192, Intelligent Systems in Design and Manufacturing III, (13 October 2000); https://doi.org/10.1117/12.403659

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available