Point cloud road surface extraction method and device based on normal vector histogram threshold segmentation

The invention discloses a point cloud road surface extraction method based on normal vector histogram threshold segmentation, and the method comprises the steps: obtaining vehicle-mounted laser point cloud data of different urban areas, the point cloud data being recorded in the form of points, and the points comprising elevations; performing preprocessing based on the point cloud data, wherein the preprocessing comprises segmentation processing and filtering processing; obtaining a normal vector of each point based on a local plane fitting formula; decomposing the normal vector under a space rectangular coordinate system by taking the starting point of the normal vector as the origin of coordinates to obtain length components lnx, lny and lnz along the X-axis direction, the Y-axis direction and the Z-axis direction; the lnx, the lny and the lnz serve as feature values respectively and are converted into component histograms; based on the component histogram, obtaining three groups of candidate road surface p