Method and device for identifying false detection target based on point cloud penetrability

The invention discloses a method and a device for identifying a false detection target based on point cloud penetrability, and relates to the technical field of automatic driving. The method comprises the following steps: encoding a current frame point cloud into a two-dimensional grid; wherein the two-dimensional grid is represented by a two-dimensional array, two dimensions are the number of laser emission times of the laser radar rotating a circle and the line number of the laser radar, and elements of the two-dimensional array are used for representing the distance of points detected by the laser radar; acquiring position coordinates of the target detection frame; determining a grid area occupied by the target detection frame in the two-dimensional grid according to the position coordinates of the target detection frame; according to the distance of the points detected by the laser radar in the grid area, determining the points with no physical target in the grid area; and determining whether the target d