Title :
Approach of vehicle segmentation based on texture character
Author_Institution :
Sch. of Civil Eng., Guangzhou Univ., Guangzhou
Abstract :
Moving vehicles segmentation is the key step of traffic parameters detection by video. The cast shadow of vehicle run with it, so it is difficult to segment the moving vehicle accurately and effectively. The paper discover the difference between the road and vehicle in texture, and propose a method of detection and removing vehicle shadow. First of all, road background is set up according to the serial images. Then according to the comparative result of the texture vectograph of background and the present frame image, judge whether it is vehicle or not. Morphological filters are carried on to reject isolated points and remedy the inside cavity, in the last the vehicle is segmented with vehicle segmentation masks. The experiments show that the method has a good adaptability and effectually.
Keywords :
image segmentation; image texture; traffic information systems; morphological filter; texture character; texture vectograph; traffic parameters; vehicle segmentation; Civil engineering; Filters; Image segmentation; Road vehicles; Vehicle detection; Cast Shadow; Mmorphological Filter; Texture Character;
Conference_Titel :
Control Conference, 2008. CCC 2008. 27th Chinese
Conference_Location :
Kunming
Print_ISBN :
978-7-900719-70-6
Electronic_ISBN :
978-7-900719-70-6
DOI :
10.1109/CHICC.2008.4605841