Research on a nonlinear spectral mixture model of hyperspectral images and its application in geological mapping
A spectral mixing model and nonlinear technology, applied in the field of spectral unmixing of hyperspectral remote sensing images, can solve problems such as low unmixing accuracy and inability to correctly reflect spectral mixing methods
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0033] ●Model derivation:
[0034] Assume that there are only two types of ground objects A and B in a certain mixed pixel ( figure 1 ), the spatial position distribution and proportion of the two kinds of ground objects are unknown, and the spectral vectors of the two kinds of ground objects are respectively m 1 and m 2 , whose abundance vectors are a 1 and a 2 , set M=[m 1 , m 2 ], a=[a 1 , a 2 ] T .
[0035] The hybrid method is divided into two categories: linear and secondary scattering:
[0036] Linear case: (a) photons are directly reflected into the sensor after incident on object A; (b) photons are directly reflected into the sensor after incident on object B.
[0037] Secondary scattering situation: The secondary impact of photons before reaching the sensor includes four situations, (c) the incident photon hits the object A, scatters to the object A and then reflects to the sensor; (d) the incident photon hits the object A , and reflect to the sensor after...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 