Building detection method based on laser radar point cloud and near-infrared image

Abstract

The invention discloses a building detection method based on a laser radar point cloud and a near-infrared image. The method comprises the steps: obtaining an ortho-image with a near-infrared band andthe laser radar point cloud, and carrying out the registration and fusion of the ortho-image and the laser radar point cloud; calculating a normalized difference vegetation index NDVI of each laser point after fusion, and completing vegetation identification based on the NDVI and a support vector machine classifier; as for non-vegetation laser points, completing building recognition through a neighbor search algorithm and a height threshold value; as for the building laser points, extracting roof seed points and candidate facade points, and obtaining a roof point group based on a single building according to the roof seed points; estimating the vertical facade of the building based on the roof point group of each building; estimating a vertical facade based on the candidate facade points,and performing fine extraction of the facade points; and completing the detection of the three-dimensional building through the roof points and the facade points obtained through fine extraction. Thedetection precision of the building is effectively improved, and the high detail level of the building model can be ensured.

Description

technical field [0001] The invention relates to the technical field of three-dimensional extraction of remote sensing ground objects, in particular to a building detection method based on laser radar point clouds and near-infrared images. Background technique [0002] Building detection using remote sensing data has good applications in various fields such as urban planning, real estate and land use analysis. Conceptually, building detection is a classification problem that requires separating buildings from other objects such as vehicles, ground (roads, lawns) and vegetation (trees and shrubs). Existing building detection algorithms can be divided into three categories according to the different input data. [0003] The first is an aerial image-based method, which uses pixel-based and object-based image segmentation methods to extract buildings. Heterogeneous pixel-based methods, whether using supervised or unsupervised learning, have the advantage of always low complexit...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a building detection method based on lidar point cloud and near-infrared images to solve the problem of high misclassification rate between buildings and trees in areas with high vegetation coverage and lack of building scanning in the prior art Point-level high-precision detection methods can effectively improve the detection accuracy of buildings

Images