An Improved SIFT Algorithm for Monocular Vision Positioning

In view of the high real-time and accuracy requirements of the monocular hand-eye vision system in the positioning process, and in the case that the existing image matching algorithm can not meet these two requirements well at the same time, this paper improves the SIFT feature matching algorithm based on local features. First, the corner points determined in the Harris operator are used instead of the key points determined by the SIFT algorithm as feature points in the template image and the image to be matched. Then, a 32-dimensional feature description vector is constructed for each of the selected feature points through a Gaussian circular window. In the registration phase, the Euclidean distance is used as a measure function to match the 32-dimensional feature descriptors. Finally, 100 template images acquired by the monocular hand-eye vision experimental platform are used to test the matching effect of the improved SIFT algorithm, which proves that the improved algorithm has higher improvement in matching time and registration accuracy than the original algorithm. It is applicable to image registration for monocular vision positioning in industrial practice.