A Method of Hyperspectral Mixed Pixel Decomposition Based on Compressed Sensing
A technology of mixed pixel decomposition and compressed sensing, which is applied in the field of hyperspectral remote sensing and compressed sensing, and can solve the problem of slow decomposition of mixed pixels
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0048] Specific embodiment 1: A method for decomposing hyperspectral mixed pixels based on compressed sensing described in this embodiment, the method is:
[0049] Step 1: Input the observation matrix Φ and the compressed observation matrix Y, and use the compressed sensing theory to establish a spectral mixing model:
[0050] Y=ΦX T = Φ(AS) T (1)
[0051] Φ∈R M×N is an M×N observation matrix, R is a real number,
[0052] X∈R L×N is an L×N mixed pixel spectral matrix,
[0053] Y∈R M×L is a compressed observation matrix of M×L,
[0054] S∈R P×N is a P×N endmember abundance matrix,
[0055] A∈R L×P is the endmember spectral matrix of L×P,
[0056] Step 2, initialization, randomly select an endmember spectral matrix A as the estimated value of the endmember spectral matrix A and is a matrix of L×P,
[0057] Let the estimated value of the endmember abundance matrix S be:
[0058] S ^ = 0 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


