出版社：Faculty of Humanities, Kaunas University of Technology
其他摘要：Creation of the big aerial images out of several smaller fragments is investigated in this paper. Proposed technique for the fully automated stitching of the overlapping two-dimensional photomap images. Technique is based on the detection of the general features in the overlapping image areas. Suggested to perform feature detection when overlapping is bigger than 50%. Proven that accurate and reliable stitching of images with unknown content is possible only when fragment overlapping is multiple. In this case it is mandatory to detect image’s corner points. Corner point quantity must be controlled by changing the value of the threshold function. Corner points in the images can be detected using Harris-Plessey method supplemented with the predictive threshold function. Feasibility of the proposed method is proven by experiment. Ill. 5, bibl. 9 (in English; summaries in English, Russian and Lithuanian).
