远距离运动目标三维测量中图像匹配的研究

采用两个摄像机光轴平行的双目立体视觉测量系统,检测远距离运动物体的三维物体轮廓.阐述了该三维轮廓测量系统中的两个关键技术:提取出合适的图像特征;建立特征间的对应关系.将同一空间物理点在不同图像中的映象点对应起来,由此得到相应的视差图像,实现立体匹配,恢复出物体的三维轮廓.仿真实验结果表明,该三维轮廓测量方法容易实现、对硬件要求不高、精度较高和具有较高稳定性,能够满足远距离运动物体姿态和速度测量的要求.

Study on image matching of 3-D measurement system on dynamic object in long distance

The binocular stereo vision measurement system with two CCDs,where the optic axes are parallel,is presented to measure the 8D profile of dynamic object in long distance. Two key technology in the binocular stereo vision measurement system are dissertated. The first is to extract the features of two images which are separately gathered by the two CCDs. The second is to process the feature point pairs to build the corresponding relationship of different feature points of the same space point and get the disparity image. The experiment results of stereo matching and 8D profile of measured object are given, These results show that the mathematic model is simple relatively,stereo matching is easy comparatively,and the measurement is rapid. The measurement system which requires few hardware, can be realized easily, work stably, and is of high measurement precision. And the presented binocular stereo vision measurement system can be used to measure the attitude and the 3D profile of flying missile.