Hyperspectral image isolation anomaly detection method based on nearest neighbor distance

The invention discloses a hyperspectral image isolation anomaly detection method based on a nearest neighbor distance. The method comprises the following steps: acquiring three-dimensional hyperspectral remote sensing data; converting the data into two-dimensional hyperspectral remote sensing data; calculating an effective spectral index ESI according to all wave band data, and screening an effective wave band set; in any wave band of the effective wave band set, calculating a background-target distinguishing index, and screening an effective wave band subset; the method comprises the following steps: randomly selecting a plurality of pixels as a training set, making a plurality of hyper-spheres by taking all pixels in the training set as circle centers and Euclidean distances from the pixels to nearest neighbor pixels as radiuses, calculating abnormal scores of the pixels to be detected in each group of hyper-sphere sets according to the hyper-sphere sets, and carrying out mean value calculation to obtain a