提出了一种采用ORB算法匹配运动物体的特征点,实现目标物体在线三维测量的方法。仅将一固定的正弦光栅投影到匀速运动待测量物体,使用CCD等时间间隔拍照,获取物体的五帧变形条纹图并提取出背景光场。借助ORB算法对物体的背景光场进行特征点匹配,得到后四帧图像中的物体相对于第一帧的位移量。从而利用图像裁剪的方法获得一组等相移量的变形条纹图,即可采用等步相移算法重构出物体的三维面形。实验验证了该方法的可行性,适用于在线三维测量。

An on-line three-dimensional (3D) measuring method based on oriented FAST and rotated BRIEF (ORB) algorithm is proposed to match feature points of moving objects. Only a fixed sinusoidal grating is projected onto the measured object with uniform motion, and the CCD is used to take photos at equal time intervals to obtain the five deformed patterns on the object and extract the background patterns respectively. With the aid of the ORB feature points matching algorithm on the background patterns, the displacement of the object in the last four frames relative to the first frame can be obtained. So a group of deformed patterns with the same shifting phase can be cut out. And then the 3D surface shape of the object can be reconstructed successfully with an equal phase-shifting algorithm. The experimental results show the feasibility of the proposed method. And it is suitable for on-line 3D measurement.