Hyperspectral image dimension reduction system and method
OwnerIan S. Robinsoninventor
Life of this patent
Estimating the term…
Abstract
Provided is a method of hyperspectral image dimension reduction. The method includes receiving a hyperspectral image having a plurality of pixels. A set of basis vectors is established at least in part with respect to the spectral vectors of the initial hyperspectral image. For each pixel of the hyperspectral image, the spectral vector is read and decomposed, i.e. unmixed, with the basis vector set to provide at least a reduced dimension vector for each pixel. Collectively the reduced dimension vectors for each pixel represent the dimensionally reduced image. A system operable to perform the method is also provided.
Claims19
1-33. (canceled)
A method of hyperspectral image dimension reduction, comprising:
- receiving a hyperspectral image having a plurality of pixels;
- establishing a basis vector (BV) set;
- for each of the plurality of pixels:
- reading a spectral vector from a subject pixel;
- unmixing the spectral vector with the BV set resulting in a set of alpha coefficients not constrained in value, a reduced dimension vector of the subject pixel being composed of the set of alpha coefficients;
- and
- providing a dimension reduced image including the reduced dimension vectors for each pixel.
A method of hyperspectral image dimension reduction, comprising:
- receiving a hyperspectral image having a plurality of pixels;
- establishing, incrementally, a basis vector (BV) set having a pre-determined maximum number of members, such that members of the BV set having lesser residual vector magnitudes are replaced by basis vectors from pixels yielding greater residual vector magnitudes;
- for each of the plurality of pixels:
- reading a spectral vector from the pixel;
- and
- unmixing the spectral vector with the BV set to provide a reduced dimension vector for the pixel and the residual vector magnitude for the pixel;
- and
- providing a dimension reduced image comprising the reduced dimension vectors for each pixel.
A system for hyperspectral image dimension reduction, comprising:
- one or more processors configured to:
- receive a hyperspectral image having a plurality of pixels;
- establish a basis vector (BV) set;
- for each of the plurality of pixels:
- read a spectral vector from a subject pixel;
- unmix the spectral vector with the BV set resulting in a set of alpha coefficients not constrained in value, a reduced dimension vector of the subject pixel being composed of the set of alpha coefficients;
- and
- provide a dimension reduced image including the reduced dimension vectors for each pixel.
A system for hyperspectral image dimension reduction, comprising:
- one or more processors configured to:
- receive a hyperspectral image having a plurality of pixels;
- establish, incrementally, a basis vector (BV) set having a pre-determined maximum number of members, such that members of the BV set having lesser residual vector magnitudes are replaced by basis vectors from pixels yielding greater residual vector magnitude;
- for each of the plurality of pixels:
- read a spectral vector from the pixel;
- and
- unmix the spectral vector with the BV set to provide a reduced dimension vector for the pixel and the residual vector magnitude for the pixel;
- and
- provide a dimension reduced image comprising the reduced dimension vectors for each pixel.
Dependencies are inferred from the claim text.