Single plant vegetation extraction method based on transfer learning and Gaussian mixture model separation

The invention discloses a single-plant vegetation extraction method based on transfer learning and Gaussian mixture model separation, and the method comprises the following steps: S1, carrying out thetrunk detection based on direct-push transfer learning, so as to obtain trunk points; S2, performing nearest neighbor clustering based on the trunk point cloud to obtain an initial segmentation result; S3, determining the number of mixed components of each part in the initial segmentation by adopting principal component transformation and kernel density estimation, and realizing Gaussian mixturemodel separation based on the number of the mixed components to obtain a crown separation result; S4, over-segmentation vegetation optimization combination based on the point density gravity center iscarried out; S5, based on a vertical continuity principle, obtaining trunk point clouds corresponding to the crowns from top to bottom, and completing individual tree extraction. According to the invention, higher tree extract