近景摄影测量中编码标志点解码方法研究

Research on Decode Algorithm of Coded Targets in Close-Range Photogrammetry

在近景摄影测量过程中,为提高特征点物体的精准匹配,降低匹配难度,对图像进行预处理,根据圆形标志点的几何特征识别标志点,用椭圆拟合法求解圆形标志点的圆心,并根据灰度变化寻找编码带的解码起点,利用环形编码带的圆心角进行解码。实验结果表明,该算法抵抗噪声能力强,圆形标志点圆心求解可达亚像素精度,解码正确率高。

In close-range photogrammetry process,feature on the object surface is not enough to match the target from images taken from different angles.The artificial targets are usually used to improve the accuracy of the feature recognition and reduce the difficulty of the feature matching.Then,the image is preprocessed,and the targets are recognized according to the geometric characteristics of the round mark points,and the ellipse fitting method is used to solve the center of the circle mark point.And then,the decoding starting point of the coding band is searched according to the gray jumping,and the decoding is carried out by using the center angle of the ring coding band.The experimental results show that the algorithm has strong anti-noise ability,and the center of the circle mark can be reached to sub-pixel accuracy,and the decoding accuracy is high too.