중첩 영역 추정을 통한 파노라마 영상 생성

The panorama is a good alternative to overcome narrow FOV under study in robot vision, stereo camera and panorama imageregistration and modeling. The panorama can materialize view with angles wider than human view and provide realistic spacewhich make feeling of being on the scene based on realism. If we use all correspondence, it is too difficult to find strongfeatures and correspondences and assume accurate homography matrix in geographic changes in images as load of calculationincreases. Accordingly, we used SURF algorithm to estimate overlapping areas with high similarity by comparing andanalyzing the input images’histograms and to detect features. And we solved the problem of input order so we can makepanorama by input images without order.