Title :
A fast edge detection method based on the correlation of moving images and its application
Author :
Que, Da-shun ; Lu, Ling ; Wang, Hong ; Song, Xiao-dong
Author_Institution :
Sch. of Inf. Eng., Wuhan Univ. of Technol., China
Abstract :
Edge detection is one of the most important aspects of image processing. In the paper, a method of edge parameters extraction based on the vertical template in the Sobel operator is studied, combining the inter-frames correlation of the target and background in image series. This method can decrease the superfluous pixels of background and increase the processing speed of edge detection. An experiment is illustrated, which shows the effectiveness of this method and the high speed of the processing. The technology can be applied to some real-time systems such as movement detection and automatic vehicle identification.
Keywords :
edge detection; image motion analysis; image sequences; Sobel operator; automatic vehicle identification; edge parameters extraction; fast edge detection method; image series; inter-frames correlation; movement detection; moving images correlation; Computer vision; Humans; Image edge detection; Image processing; Machine vision; Parameter extraction; Pixel; Real time systems; Road vehicles; Vehicle detection;
Conference_Titel :
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7508-4
DOI :
10.1109/ICMLC.2002.1175429
