DocumentCode :
3572827
Title :
A vision positioning method for the opening of railway oil tank wagon based on shape matching
Author :
Xuezhi Xiang ; Changyun Ge ; Rino, Fidiniaina ; Lei Zhang ; Yulong Qiao
Author_Institution :
Sch. of Inf. & Commun. Eng., Harbin Eng. Univ., Harbin, China
fYear :
2014
Firstpage :
1970
Lastpage :
1973
Abstract :
The opening positioning for railway oil tank wagon using machine vision technology is an effective way to load petroleum automatically. To overcome the adverse effects produced by illumination changes, various types of railway tank wagon and various positions of camera, a shape matching positioning method is proposed in this paper. Due to the shape of the opening of railway tank wagon is a standard geometry, the edge of the opening can be extracted from a standard image so that the shape of the opening can be described by shape fitting method, which is used as standard template of image recognition, then contour normalized correlation is employed to search the object in the image. To improve flexibility, scalable template is used so that various types opening image of railway tank wagon can be processed by the proposed method. To gain a speed-up, image pyramid is applied to reduce calculation amount. The experiments show that the proposed method fully meets the requirements of practical industrial applications.
Keywords :
cameras; computer vision; edge detection; image matching; railway rolling stock; shape recognition; calculation amount; camera position; contour normalized correlation; image pyramid; image recognition; load petroleum; machine vision technology; opening positioning; railway oil tank wagon; railway tank wagon; scalable template; shape fitting method; shape matching positioning method; standard geometry; vision positioning method; Fitting; Fuel storage; Image edge detection; Lighting; Rail transportation; Shape; Standards; big crane tube; machine vision; railway oil tank wagon; shape matching; vision positioning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control and Automation (WCICA), 2014 11th World Congress on
Type :
conf
DOI :
10.1109/WCICA.2014.7053023
Filename :
7053023
Link To Document :
بازگشت