Support vector machine based 3D object recognition in a virtual environment

Liangyu Lei; Xiaojun Zhou

doi:10.1117/12.650273

2 December 2005 Support vector machine based 3D object recognition in a virtual environment

Liangyu Lei, Xiaojun Zhou

Proceedings Volume 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications; 60450D (2005) https://doi.org/10.1117/12.650273
Event: MIPPR 2005 SAR and Multispectral Image Processing, 2005, Wuhan, China

Abstract

Support vector machine (SVM) represent a new approach to pattern recognition and has been shown to be particularly successful in many fields. This paper presents a nonlinear SVMs based approach for 3D object recognition in a vehicular virtual experiment environment. The system outline and 3D images recognition algorithm are depicted. By simulation experiment and the comparison of the results between the recognition accuracy of SVM and BP network, we illustrate the potential of nonlinear SVMs on images classification of different objects. The excellent recognition rates achieved in the performed experiments indicate that nonlinear SVMs are well suited for 3D images recognition, especially in coping with small sample sizes. This is vital for achieving 3D object recognition and human-computer interaction rapidly and accurately in virtual experiment environment.

Citation Download Citation

Liangyu Lei and Xiaojun Zhou "Support vector machine based 3D object recognition in a virtual environment", Proc. SPIE 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications, 60450D (2 December 2005); https://doi.org/10.1117/12.650273

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