基于坐标变换的快速高精度图像拼接算法

Rapid and High-precision Image Mosaicing Algorithm Based on Coordinate Transformation

该文提出了一种能实现较大零件几何量高精度视觉综合测量的图像拼接方法,首先视觉系统按一定的轨迹路径依次移位采像获取高分辨率、小视场的影像序列,并对采集图像应用向后映射法实现归一化焦平面重采样以消除影像畸变,再利用位姿变换关系实现图像序列的精确配准,从而获得高分辨率、大视场的完整成像。该拼接算法不依赖于待拼接图像的特征信息,适用面广且拼接精度高,实验结果表明,该算法具有较好的应用价值。

In allusion to the high-precision geometric measurement of larger parts geometrical metrology,a image mosaic algorithm is introduced into the vision measurement in this paper. Firstly,the visual acquisition system moves a- long the planned trajectory path and grabbes the high-resolution,small-viewing field image sequence successively. And then a backward mapping algorithm is adopt to convert the above-mentioned images into the normalized focal plane in order to eliminate the image distortion. Finally,with the aid of pose transformation relations,the mapping images are precisely tiled into a larger field of view image. This image mosaicing algorithm has high mosaic accuracy and is applicable to a wide range of applications due to it does not depend on characteristics information of the image to be mosaic. Experimental results show that the algorithm has better application value.