Transactions of Society of Automotive Engineers of Japan
Online ISSN : 1883-0811
Print ISSN : 0287-8321
ISSN-L : 0287-8321
Research Paper
Estimation of Obstacle Classification using SVM Score
Hanko YamashiroKenichi YamadaToshio Ito
Author information
JOURNAL FREE ACCESS

2010 Volume 41 Issue 2 Pages 413-418

Details
Abstract
For the realization of advanced driving support system, technologies that recognize various obstacles in the driving environment have been developing. We propose the method to recognize the obstacles (car, bike, bicycle, pedestrian) by laser radar in this paper. Many features of object classification are identified and their extraction is described. We use SVM for class classification. We classify each class by observe distance from hyper plane in time series.
Content from these authors
© 2010 Society of Automotive Engineers of Japan, Inc.
Previous article Next article
feedback
Top