ACADSTAFF UGM
| Title | : | A Comparative of SIFT and SURF Features for Stitching Aerial Images |
| Author | : |
Dr. Raden Sumiharto, S.Si., M.Kom (1) Prof. Drs. Agus Harjoko, M.Sc., Ph.D. (2) Dr. Agfianto Eko Putra, M.Si. (3) |
| Date | : | 0 2017 |
| Keyword | : | Overlap, scaling, image feature Overlap, scaling, image feature |
| Abstract | : | SIFT and SURF as feature detection methods are already widely used in various applications. Stitching of aerial images can be based on image features. This paper discusses the use of SIFT and SURF features for stitching aerial images. A number of parameters affecting the stitching algorithm are observed, such as the height of image acquisition (scale between image) and area of overlap between image. Aerial images acquired at difference altitude resulting in a different scaling and thus object resolution. Altitude difference and angle difference (due to flight control) resulting in a different overlapping area of the images to be stitched. So that both methods can be used for stitching process image aerial. The results comparison of the two methods shows that the difference in height and the area of overlap slightly (4%) and scale difference between images by 45% to 480% by SIFT and 25% to 600% by SURF is still possible to process image aerial stitching. |
| Group of Knowledge | : | Ilmu Komputer |
| Original Language | : | English |
| Level | : | Internasional |
| Status | : |
Published
|