期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：2
页码：445-456
DOI：10.14257/ijsip.2016.9.2.38
出版社：SERSC
摘要：In the vision 3-D measurement field, camera calibration results directly affect the accuracy of measurement. So camera calibration method is hot spot in this field. This paper proposes a new efficient calibration method with binocular camera. First, the method uses an accurate extraction algorithm to extract the ellipse center of calibration target image. Second, the paper presents a automatic matching algorithm based RANSAC (RANSAC SAMPLE CONSENSUS), the automatic matching algorithm is simple, fast, and can complete space calibration feature points matching its image point at once. At the beginning of matching, sort calibration points in the target according to a certain sequence. The sequence of feature points extracted in the calibration image does not correspond with one of the feature points in calibration target, because of the camera distortion. But obtain the correct matching points by the RANSAC algorithm. According to the camera calibration model, use the correct matching points and obtain correct intrinsic and extrinsic parameters of each camera and the relative parameters of two cameras. Finally, through experimental verification, the results show that the calibration method is fast and robust, and has higher calibration accuracy.
关键词：Camera calibration; RANSAC algorithm; Calibration point ; correspondence
