The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B4-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2020, 191–196, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B4-2020-191-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2020, 191–196, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B4-2020-191-2020

  24 Aug 2020

24 Aug 2020

AUTOMATIC REGISTRATION OF VECTOR DATA WITH OPTICAL IMAGES

Y. Tanguy1, J. Michel1, and G. Salgues2 Y. Tanguy et al.
  • 1Centre National d’Etudes Spatiales (CNES), 18 avenue E. Belin, Toulouse cedex 9, France
  • 2Magellium, 1, rue Ariane, 31520 Ramonville Saint Agne, France

Keywords: Optical satellite imagery, vector-to-image registration, vector conflation, feature extraction, Orfeo ToolBox

Abstract. This paper presents a method to perform automatic vector-to-image registration. The proposed method performs well on different kinds of optical satellite images from Very High Resolution (VHR, sub-meter resolution) to images in the 10/20 m resolution range. It allows to automatically register vector dataset such as urban maps (by using building layers). In contrast with existing methods, our method needs few prior-knowledge on the features to match and can therefore adapt to different landscapes.

This paper demonstrates the method robustness in several use-cases and presents the implementation which will soon be available as open-source software.