Detection algorithm for road surface condition using wavelet packet transform and SVM

Author

Hun-Jun Yang ; Hyeok Jang ; Dong-Seok Jeong

Author_Institution

Electron. Eng. Multimedia Lab., Inha Univ., Incheon, South Korea

fYear

2013

Firstpage

323

Lastpage

326

Abstract

In this paper, we propose a method to detect the state of the road surface condition using wavelet and SVM(Support Vector Machine) classifier. The Road surface conditions are classified into a set of pattern states such as dry, wet, snow, ice. This approach automatically analyze road surface condition change using image processing, and does not require extra sensors. Feature extraction using wavelet transformation is classified by the SVM classifier.

Keywords

condition monitoring; feature extraction; image classification; image texture; object detection; roads; support vector machines; traffic engineering computing; wavelet transforms; SVM classifier; automatic road surface condition analysis approach; dry state; feature extraction; ice state; image processing; pattern states; road surface condition classification; road surface condition detection algorithm; snow state; support vector machine classifier; wavelet classifier; wavelet packet transformation; wet state; Feature extraction; Roads; Support vector machines; Surface waves; Wavelet packets; Support Vector Machine; Texture classification; Wavelet Packet Transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers of Computer Vision, (FCV), 2013 19th Korea-Japan Joint Workshop on

Conference_Location

Incheon

Print_ISBN

978-1-4673-5620-6

Type

conf

DOI

10.1109/FCV.2013.6485514

Filename

6485514