Geodesic
Dataset and method for evaluating optical-to-sar image registration algorithms based on keypoints
Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2021), pp. 44-57.

Voir la notice de l'article provenant de la source Math-Net.Ru

Image registration is the alignment (i.e. finding a general coordinate system) of two or more images of the same scene. Complex case of this task is the multimodal image registration, for example, optical-to-SAR. The need for such registration appeared in image fusion and object detection. The research on optical-to-SAR image registration shows that there are no publicly available datasets with the enough size for debugging and testing algorithms. In many works, testing is carried out on a several pairs of images that are not always publicly available. Moreover, different works use different datasets. In this paper we present a dataset of 100 aligned optical-SAR pairs of images. Additionally, we consider methods for evaluating keypoints repeatability, the accuracy of their matching, and a method for calculating the accuracy of image registration for optical-SAR data. Using these methods, we compare the results of these methods for the classical SIFT, YAPE and Harris detectors and SIFT, ORB and SURF descriptors on the presented dataset.
Mots-clés : image registration
Keywords: repeatability of keypoints. 
@article{ITVS_2021_2_a4,
     author = {V. V. Volkov and E. A. Shvets},
     title = {Dataset and method for evaluating optical-to-sar image registration algorithms based on keypoints},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {44--57},
     publisher = {mathdoc},
     number = {2},
     year = {2021},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2021_2_a4/}
}
TY  - JOUR
AU  - V. V. Volkov
AU  - E. A. Shvets
TI  - Dataset and method for evaluating optical-to-sar image registration algorithms based on keypoints
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2021
SP  - 44
EP  - 57
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2021_2_a4/
LA  - ru
ID  - ITVS_2021_2_a4
ER  - 
%0 Journal Article
%A V. V. Volkov
%A E. A. Shvets
%T Dataset and method for evaluating optical-to-sar image registration algorithms based on keypoints
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2021
%P 44-57
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2021_2_a4/
%G ru
%F ITVS_2021_2_a4
V. V. Volkov; E. A. Shvets. Dataset and method for evaluating optical-to-sar image registration algorithms based on keypoints. Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2021), pp. 44-57. http://geodesic.mathdoc.fr/item/ITVS_2021_2_a4/