点击次数：

论文类型：期刊论文

发表时间：2016-10-01

发表刊物：MEASUREMENT SCIENCE AND TECHNOLOGY

收录刊物：SCIE、EI、Scopus

卷号：27

期号：10

ISSN号：0957-0233

关键字：binocular vision calibration; stereo vision; arbitrary translations; 3D-connection

摘要：Binocular vision systems play an important role in computer vision, and high-precision system calibration is a necessary and indispensable process. In this paper, an improved calibration method for binocular stereo vision measurement systems based on arbitrary translations and 3D-connection information is proposed. First, a new method for calibrating the intrinsic parameters of binocular vision system based on two translations with an arbitrary angle difference is presented, which reduces the effect of the deviation of the motion actuator on calibration accuracy. This method is simpler and more accurate than existing active-vision calibration methods and can provide a better initial value for the determination of extrinsic parameters. Second, a 3D-connection calibration and optimization method is developed that links the information of the calibration target in different positions, further improving the accuracy of the system calibration. Calibration experiments show that the calibration error can be reduced to 0.09%, outperforming traditional methods for the experiments of this study.