POST COMPRESSION DETECTION (PoCoDe)

摘要

Provided are examples of a detecting engine for identifying detections in compressed scene pixels. For a given compressed scene pixel having a set of M basis vector coefficients, set of N basis vectors, and code linking the M basis vector coefficients to the N basis vectors, the detecting engine reduces a spectral reference (S) to an N-dimensional spectral reference (SN) based on the set of N basis vectors. The detecting engine computes an N-dimensional spectral reference detection filter (SN*) from SN and the inverse of an N-dimensional scene covariance (CN). The detecting engine forms an M-dimensional spectral reference detection filter (SM*) from SN* based on the compression code and computes a detection filter score based on SM*. The detecting engine compares the score to a threshold and determines, based on the comparison, whether the material of interest is present in the given compressed scene pixel and is a detection.

主权项

1. A method for detecting the presence of materials of interest in a plurality of compressed scene pixels of a hyperspectral scene, the method comprising:
in a detecting engine, for a given compressed scene pixel having a set of M basis vector coefficients, a set of N basis vectors, and code linking the M basis vector coefficients to the N basis vectors, in which the value of M is less than or equal to the value of N: reducing the spectral reference (S) to an N-dimensional spectral reference (SN) based on the set of N basis vectors, the spectral reference (S) representative of a material of interest and provided to the detecting engine; computing an N-dimensional spectral reference detection filter (SN*) from the N-dimensional spectral reference (SN) and the inverse of an N-dimensional scene covariance (CN) of a hyperspectral scene in which the given compressed scene pixel is seen; forming an M-dimensional spectral reference detection filter (SM*) by selecting M elements of the N-dimensional spectral reference detection filter (SN*) based on the code of the given compressed scene pixel linking the M basis vector coefficients to the N basis vectors; computing a detection filter score for the given compressed scene pixel based on the M-dimensional spectral reference detection filter (SM*), the detection filter score being indicative of a likelihood the spectrum of the given compressed scene pixel matches the spectrum of the spectral reference (S); comparing the detection filter score to a threshold; and determining, based on the comparison, whether the material of interest is present in the given compressed scene pixel and is a detection.