DocumentCode :
532293
Title :
Study on multi-object and multi-type fusion location of vehicle license plate
Author :
Fang, Peiyu ; Song, Shuguang ; Wang, Mei
Author_Institution :
Dept. of Inf. Eng., Yantai Vocational Coll., Yantai, China
Volume :
7
fYear :
2010
fDate :
22-24 Oct. 2010
Abstract :
For the problem of object location under complex environment, especially for unknown object-quantity and object-type, a fusion vehicle license plate(VLP) location method with object authenticity confirmation is presented. Firstly, every region related to multi-type object color is marked in the same gray-level image by multi-value processing. Secondly, vertical edge operator is used to extract object. Thirdly, each kind of possible object is detected by the feature fusing color and edge. At last, object authenticity confirmation method is designed to throw off false alarm. The experiments on 2000 Chinese automobile RGB real color images taken from traffic stations under various conditions show that the correct location rate is over 99 percent.
Keywords :
edge detection; feature extraction; image colour analysis; object detection; sensor fusion; traffic engineering computing; Chinese automobile RGB real color images; edge detection; feature fusing color; fusion vehicle license plate location method; gray-level image; multiobject fusion location; multitype fusion location; multitype object color; multivalue processing; object authenticity confirmation method; object extraction; object location; vertical edge operator; License plate location; fusion; multi-object; multi-type; object authenticity confirmation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
Type :
conf
DOI :
10.1109/ICCASM.2010.5620286
Filename :
5620286
Link To Document :
بازگشت