Building elevation extraction method based on building outer contour lines and laser-point cloud

Abstract

The invention provides a building elevation extraction method based on building outer contour lines and a laser point cloud. The building elevation extraction method includes the following steps that the outer contour lines of a building are obtained; a ground plane, namely an XY plane, is selected and used as a projection plane, projections of the outer contour lines on the XY plane are shown as multiple line segments which are from P1, P2 to Pn, and a buffering region is selected; whether laser points in a three-dimensional panoramic picture are in the buffering region is judged, and therefore all the laser points in the buffering region are obtained; and a filtering algorithm is used, all the laser points in the buffering region are subjected to denoising processing, and then building elevations are generated according to the laser points and the outer contour lines of the building. Through the building elevation extraction method based on the building outer contour lines and the laser point cloud, the defects in the prior art are overcome, the building elevations can be generated automatically or semi-automatically, a streetscape data production cycle and a digital city production cycle are greatly shortened, and the building elevation extraction method based on the building outer contour lines and the laser point cloud has very high economic value and very high social value.

Description

technical field [0001] The invention relates to a method for automatically extracting the facade of a building based on the outline of the building and a three-dimensional laser point cloud, belonging to the field of surveying and mapping information. Background technique [0002] Street view service is a new bright spot in the development of digital cities at present, and it is a hotspot on the Internet and the development direction of map services. [0003] Street view services are inseparable from the support of data. Currently, in the process of collecting street view data, 3D laser point cloud data and panoramic image data are collected at the same time. The three-dimensional laser point cloud is the high-precision three-dimensional coordinates of the surface of the object, and the coordinates and feature information of the ground object can be directly obtained through the point cloud. However, the 3D laser point cloud is only raw data, not the result data required by...

AI Technical Summary

Problems solved by technology

[0005] Due to the large amount of data obtained from street view data collection, and the traditional production of building facades basically relies on manual labor and low automation, the cost of street view data production is very high, which is not conducive to the promotion and application of street view services