Bursaphelenchus xylophilus disease change detection method based on hyperspectral image outlier detection

The invention relates to the technical field of pine wood nematode disease detection, in particular to a pine wood nematode disease detection method based on hyperspectral image outlier detection. The method comprises the following steps: acquiring a hyperspectral image; searching natural nearest neighbors of all sample points by using a natural neighbor search algorithm; dividing the neighbors into natural dense neighbors and natural sparse neighbors; calculating a density turning degree and a neighborhood turning degree; calculating the lesion turning degree of each sample point; and selecting a sample point with the maximum lesion turning degree as a lesion sample point, and taking a natural sparse neighbor of the lesion sample point as the lesion sample point. According to the method, the sample points of the pine wood nematode disease can be effectively detected by adopting a highlight image outlier detection technology, and the problems of low efficiency, high hysteresis and high cost of manual detectio