Airborne laser point cloud classification method based on high-order conditional random field

Abstract

The invention provides an airborne laser point cloud classification method based on a high-order conditional random field. The airborne laser point cloud classification method specifically comprises the following steps: (1) point cloud segmentation based on DBSCAN clustering; (2) point cloud over-segmentation based on the K-means cluster; (3) construction of a point set adjacency relation based onthe Meanshift clustering; and (4) construction of a point cloud classification method of a high-order conditional random field based on the multi-level point set. The method has the advantages that:(1) a multi-layer clustering point set structure construction method is provided, and a connection relation between point sets is constructed by introducing a Meanshift point set cluster constrained by category labels, so that the categories of the point sets can be classified more accurately; (2) a multi-level point set of the non-linear point cloud number can be adaptively constructed, and information such as the structure and the shape of a point cloud target can be more completely represented; and (3) a CRF model is constructed by taking the point set as a first-order item, and higher efficiency and a classification effect are achieved, so that a higher framework is integrated, and a better effect is obtained.

Description

technical field [0001] The invention relates to an airborne laser point cloud classification method based on high-order conditional random fields, and belongs to the technical field of architectural model measurement and construction. Background technique [0002] With the rapid development of lidar sensors, 3D point cloud data has been widely used in many fields, such as autonomous driving, smart cities, and surveying and mapping remote sensing. However, 3D point cloud classification is an important step in the application of point cloud data, so it is of great significance to point classification in outdoor scenes. At present, point cloud classification can be divided into two ways: single point-based point cloud classification and object-based point cloud classification. Point cloud classification based on single points is mainly through neighborhood selection, feature extraction, feature selection and classifier classification of single points of point clouds. For examp...

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to overcome the defects in the above-mentioned existing point cloud classification methods, and propose an ALS point cloud classification algorithm based on object-based multi-layer clustering and high-order conditional random fields, so as to solve the problem of low accuracy of single point classification in existing methods and the calculation Large amount of problems; solve the poor adaptability of target shape and size based on template segmentation, poor segmentation robustness caused by region growth-based seed point selection and regional discrimination conditions, and inability to effectively segment based on a single clustering algorithm; at the same time solve problems based on When a single point set is classified, the constraint relationship between point sets is lost and the topological relationship between point sets is not fully represented based on the second-order conditional random field.

Images