Power transmission line tree obstacle risk identification method based on PointNet

The invention discloses a PointNet + +-based power transmission line tree obstacle risk identification method, which comprises the following steps: firstly, determining an overhead power transmission line risk area according to a national standard and a physical model, carrying a laser radar by using an unmanned aerial vehicle, and scanning an overhead line corridor by using a LiDAR three-dimensional laser scanning technology to obtain a point cloud model of an overall environment around a power transmission line; the method comprises the steps of generating point cloud data containing coordinate position information, removing noise of the point cloud data by adopting a point cloud filtering algorithm, segmenting the whole point cloud data through point cloud processing software, respectively marking a power transmission line and a tree, segmenting according to the length of the power transmission line of 8: 1: 1, dividing a training set, a test set and a verification set, in a PointNet + + model training pro