Power transmission line laser point cloud classification method

The invention discloses a power transmission line laser point cloud classification method, and relates to the technical field of power transmission line three-dimensional modeling. The method comprises the following steps: S1, obtaining a point cloud data set by using a laser radar, and collecting scene data of a power transmission line, thereby obtaining point cloud data of the power transmission line; and S2, constructing a PointNet + + neural network, and integrating a gradient attention module and a point attention module in the PointNet + + neural network model to obtain an improved PointNet + + neural network model. According to the method, the gradient attention module and the point attention module are integrated to the feature extraction layer of the Point Net + + network, so that finer geometric information can be captured, the local feature aggregation capability of the model is enhanced, the feature extraction efficiency of the point cloud data is improved, and the accuracy of the model in a class