作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (24): 179-181. doi: 10.3969/j.issn.1000-3428.2009.24.059

• 人工智能及识别技术 • 上一篇    下一篇

基于分割区间LS-SVM的摄像机标定

刘 胜,傅荟璇,王宇超   

  1. (哈尔滨工程大学自动化学院,哈尔滨 150001)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-12-20 发布日期:2009-12-20

Camera Calibration Based on Divided Region LS-SVM

LIU Sheng, FU Hui-xuan, WANG Yu-chao   

  1. (College of Automatization, Harbin Engineering University, Harbin 150001)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-12-20 Published:2009-12-20

摘要: 利用最小二乘支持向量机(LS-SVM)可以不考虑摄像机具体的内部参数和外部参数实现摄像机的标定。由于镜头的畸变主要由径向畸变引起,根据摄像机畸变特点对畸变区域进行划分,提出一种基于分割区间LS-SVM的摄像机标定法,对不同的畸变区域进行单独处理。该方法与BP神经网络和基本LS-SVM预测结果对比表明,分割区间LS-SVM摄像机标定法误差小、速度快、标定精度高。

关键词: 摄像机标定, 最小二乘支持向量机, 分隔区间, 计算机视觉, BP神经网络

Abstract: By using Least Squares Support Vector Machines(LS-SVM), it need not consider internal and external parameters to achieve the camera calibration. Because the lens distortion is mostly caused by radial distortion, according to the camera distortion characteristic, it divides the distortion region. A new method of camera calibration based on divided region LS-SVM is proposed, and the distortion of different regions deals with separately. The comparison with other methods including BP Neural Network(BPNN) and LS-SVM shows that the calibration accuracy is improved by using the divided LS-SVM method, and the speed is higher.

Key words: camera calibration, Least Squares Support Vector Machines(LS-SVM), divided region, computer vision, BP Neural Network(BPNN)

中图分类号: