Title :
Passing car identification using Hough data verification
Author :
Ueno, K. ; Yamaguchi, Jun
Author_Institution :
Fac. of Eng., Kagawa Univ., Takamatsu, Japan
Abstract :
In this study, the authors proposed Hough data verification to identify a 3D object image in view point change of the camera. In the method, we pay attention to a distribution pattern of Hough data. A positional relationship of the peaks as Hough data shows tendency to be kept, in case of camera shooting condition change. The object identification method based on a distinction of the peak distribution pattern by Matched filter. In the paper, using the method, the authors describe on identification of a passing car shot from beside car. To decrease the misunderstanding, a peak distribution is made from the edge image without wheel area. We performed an identification experiment using the passing car images. As a result, high identification rate was obtained.
Keywords :
Hough transforms; automobiles; edge detection; matched filters; object detection; 3D object image identification; Hough data distribution pattern; Hough data verification; camera shooting condition; camera view point change; edge image; matched filter; object identification method; passing car image identification rate; passing car shot identification; peak distribution pattern; peak positional relationship; Cameras; Correlation; Image edge detection; Matched filters; Object recognition; Tires; Transforms; Hough transform; Matched filter; Passing car identification; Pattern matching;
Conference_Titel :
Frontiers of Computer Vision, (FCV), 2013 19th Korea-Japan Joint Workshop on
Conference_Location :
Incheon
Print_ISBN :
978-1-4673-5620-6
DOI :
10.1109/FCV.2013.6485484