基于控制点鲁棒提取的视觉成像畸变校正方法

基于控制点的摄像机视觉成像畸变校正过程中,控制点自动提取困难且误差较大,因此难以实现动态图像的在线准确校正.针对目前控制点提取校正方法的局限性,提出了基于鲁棒性好的控制点匹配提取校正方法.该方法在实现控制点的自动、精确、鲁棒提取的基础上,建立畸变图像与原始图像的最优次数多项式映射模型,并结合双线性插值运算对图像进行校正.该校正算法应用结果表明:该方法在图像识别系统中实现了快速、精确的图像畸变校正,校正误差为0.037像素.

Anamorphic Visual Image Rectification Method Based on Robust Pick-up of Control Points

It is hard to rectify accurately the dynamic images online because of the big errors resulting from the difficult automatic pick-up of control points in the rectification process of unavoidable anamorphic images by camera.Taking account of the limitation of existing pick-up methods,an approach to well-matched high robust pick-up of control points was proposed for the rectification,which can implement the automatic,accurate and robust pick-up of control points through developing a polynomial mapping model wi...