Road Surface Texture Recognition Method Research Based on Wavelet Packet HMM

Author

Li Hong ; Lin Jun ; Feng Yanhui

Author_Institution

Coll. of Instrum. & Electr. Eng., Jilin Univ., Changchun

Volume

2

fYear

2009

fDate

22-24 Jan. 2009

Firstpage

362

Lastpage

365

Abstract

Wavelet packet analysis method is appropriate to process nature texture signal and a hidden Markov model has good learning interpretability and needs only small training samples. A wavelet packet-HMM-based method on road surface state recognition was proposed. The wavelet packet analysis was adapted to extract characteristic entropies from the image signals. Thus, four kinds of data on road surface were trained respectively to get the HMM to identify road surface states. The result of experiments shows that the means is effective.

Keywords

automated highways; entropy; feature extraction; hidden Markov models; image recognition; image texture; learning (artificial intelligence); meteorology; road accidents; road traffic; wavelet transforms; HMM; ITS; entropy; feature extraction; hidden Markov model; machine learning; meteorology; road surface texture recognition method; traffic accident; wavelet packet analysis; Hidden Markov models; Image analysis; Image texture analysis; Roads; Signal analysis; Signal processing; Surface texture; Surface waves; Wavelet analysis; Wavelet packets; Wavelet packet HMM; meteorology; road surface; texture recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Engineering and Technology, 2009. ICCET '09. International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4244-3334-6

Type

conf

DOI

10.1109/ICCET.2009.234

Filename

4769623