Spectral feature generation using high-pass filtering for scene anomaly detection

摘要

A method of detecting an image anomaly (target) within a scene represented by image data comprises obtaining test data from a test window within the scene, combining the test data with reference data to generate combined data, then comparing the combined data with either the test data or the reference data. An improved image analyzer includes a computational unit configured to execute this method. In one example, image data is generated by a hyperspectral imager.