Aiming at the long acquisition time of the planar in 3D laser scanning point cloud and the low accuracy of plane extraction,an algorithm for automatic and rapid recognition of the point cloud plane features based on Random Sample Consensus(RANSAC) is proposed in this paper.By improving the RANSAC method,a method based on iteration and sample points judgment optimization is proposed,which can quickly and accurately identify and extract planar features of object.Experimental results show that the algorithm can find the planar of the object effectively and accurately.