Title :
Road Region Detection in Video System
Author :
Chi Jian-nan ; Zhou Nan-nan ; Zhang Peng-yi ; Zheng Si-yi
Author_Institution :
Inf. Eng. Sch., Univ. of Sci. & Technol. Beijing, Beijing, China
Abstract :
In this paper, image multi-scale edge detection based on anti-symmetrical wavelet is given detailed in theory. Namely convolution operation property which anti-symmetrical wavelet transform bears is deduced, and function of which anti-symmetrical biorthogonal wavelet transform works as differential operator is analyzed. Algorithm of wavelet decomposition in which multi-scale edge can be detected is put forward. Based on above, a road region detection method in video system is put forward. Using multi-scale edge image of anti-symmetrical wavelet decomposition region growth is applied to identify road area roughly. Then borderline of road is extracted using Hough transformation and road region is defined finally. Experimental results indicate that the method presented in the paper is effective.
Keywords :
Hough transforms; convolution; edge detection; feature extraction; roads; video signal processing; wavelet transforms; Hough transformation; antisymmetrical biorthogonal wavelet transform; convolution operation property; differential operator; image multiscale edge detection; region growth; road region detection method; video system; wavelet decomposition; Convolution; Data mining; Image edge detection; Image segmentation; Intelligent systems; Pattern recognition; Roads; Video surveillance; Wavelet analysis; Wavelet transforms; Hough transformation; Multi-scale edge detection; Region growing; Road region detection; Symmetrical biorthogonal wavelet;
Conference_Titel :
Intelligent Systems, 2009. GCIS '09. WRI Global Congress on
Conference_Location :
Xiamen
Print_ISBN :
978-0-7695-3571-5
DOI :
10.1109/GCIS.2009.339
