Volume XLII-3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 2067-2071, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-2067-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 2067-2071, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-2067-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 Apr 2018

30 Apr 2018

A BAND SELECTION METHOD FOR HIGH PRECISION REGISTRATION OF HYPERSPECTRAL IMAGE

H. Yang and X. Li H. Yang and X. Li
  • College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China

Keywords: Hyperspectral Image, High Spatial Resolution Image, Registration, CRLB Theory, Band Selection, Algorithm

Abstract. During the registration of hyperspectral images and high spatial resolution images, too much bands in a hyperspectral image make it difficult to select bands with good registration performance. Terrible bands are possible to reduce matching speed and accuracy. To solve this problem, an algorithm based on Cram’er-Rao lower bound theory is proposed to select good matching bands in this paper. The algorithm applies the Cram’er-Rao lower bound theory to the study of registration accuracy, and selects good matching bands by CRLB parameters. Experiments show that the algorithm in this paper can choose good matching bands and provide better data for the registration of hyperspectral image and high spatial resolution image.