A Method of Contour Extraction of Ground Objects Based on Ground Laser Point Cloud

Abstract

The ground object contour extraction method based on the ground laser point cloud provided by the present invention introduces surface-based space measurement, which breaks through the traditional single-point measurement method, into urban measurement applications, and improves the efficiency of urban measurement. As the most important spatial entity of a city, the three-dimensional information of ground objects, especially buildings, is an important basic geographic information of the city, which has important application value. The environmental impact is small and the measurement accuracy is high, which not only improves the automation of building space data acquisition, but also the scanned point cloud can express the real three-dimensional information and detailed structure of the building in detail, and use the point cloud data to obtain accurate outline information and reconstruct The 3D model of the building has the advantages of strong interactive performance, high intelligence, high scalability, fast extraction speed, and high contour extraction accuracy.

Description

technical field [0001] The invention relates to a method for extracting the contours of ground objects from point clouds, in particular to a method for extracting contours of ground objects based on ground laser point clouds, and belongs to the technical field of contour extraction of ground objects. Background technique [0002] With the progress of society and the development of science and technology, people's cognition of their own living environment needs more accurate description and scene reconstruction, digitize the spatial information of interest and establish a database to provide services for planning management and other aspects of the real world. The growth of this demand is complementing the development of the surveying and mapping industry. After decades of development, surveying and mapping has developed from traditional surveying and mapping to digital surveying and mapping, and then to information-based surveying and mapping. The target of surveying and mapp...

AI Technical Summary

Problems solved by technology

Fourth, it has low requirements on the external environment. The 3D laser scanner itself has good stability and does not need to preset special measurement targets and marks. It can complete fast and accurate detection of target objects in complex scenes and spaces no matter in day or night. Grid scanning measurement has a wide range of applications; fifth, it can combine multi-source sensors to collect data, not only to obtain the point coordinates of the target surface, but also to collect corresponding texture and color information, so that the scanning system can obtain a more comprehensive picture of the measured object Information, the modeling results are more refined and close to the real, which improves the application value of 3D laser scanning in engineering, but there are still obvious areas for improvement in the application of 3D laser scanning to the extraction of ground object outlines;

The traditional single-point measurement method is low in efficiency and labor-intensive in collecting data, and it is difficult to reflect the three-dimensional information of the building, which does not meet the requirements of high efficiency; while the photogrammetry and remote sensing methods extract the outline of the building through satellite and aerial images. The layout of ground control points is complex and the task is heavy. The feature extraction and feature matching process of data processing requires a large amount of calculation, which takes a long time in the office and has a low degree of automation. The results cannot reflect the real 3D information and cannot meet the requirements of modern surveying and mapping;

[0007] Third, it is extremely difficult and complicated to build a general and feasible feature contour extraction in the existing technology. In the early stage, it was generally based on the measurement of a single point. Because the extraction rules are all based on manual establishment, it takes a lot of time and resources. Moreover, errors are prone to occur, resulting in poor portability; the existing technology focuses on the collection of single-point data, and the ground object contour extraction technology of ground laser point cloud is immature and cannot meet the needs of the industry. At the same time, ground laser point cloud exists Weak interactive performance, low degree of intelligence, low scalability, slow extraction speed, low extraction accuracy of ground object contours, etc.

Images