Indoor map automatic building method and system

Abstract

The invention discloses an indoor map automatic building method and system. The system includes a data acquisition module which acquires point cloud data of indoor environment, a point cloud preprocessing module which extracts a geometric structure of the indoor environment from the point cloud data of indoor environment, a map building module which automatically builds an indoor raster map or an indoor vector map, and an output module which outputs the built map. The indoor map automatic building method and system can effectively utilize the three-dimensional point cloud data of indoor scene collected by consumption-grade RGB-D equipment to extract the geometric structure of the inside of a building by an automatic method and generate the plane raster map and the vector map of the inside of the building, which can solve the problem of conventional indoor map making, improve the efficiency of indoor mapping and reduce the cost of the indoor mapping.

Description

technical field [0001] The present invention relates to the technical field of indoor surveying and mapping, in particular to a method and system for automatically constructing indoor grid maps and vector maps based on point cloud data collected by consumer grade RGB-D sensors or LiDAR sensors. Background technique [0002] The indoor environment is the main scene of human production and life. Location-based services (Location-Based Service) for indoor environments, including but not limited to airport terminals, shopping centers, gymnasiums, art galleries, warehouses, and indoor parking lots, are currently widely used. It has become an important technical support for many emerging business service models, such as indoor navigation, target positioning, advertising and promotion, etc. The floor plan is the basis of indoor location services, and the most direct way to obtain it is to digitize architectural planning / design drawings. [0003] Due to management problems, or even...

AI Technical Summary

Problems solved by technology

The traditional method is generally in the drawing software such as commonly used AutoCAD, MicroStation and other software, and the operator manually draws the external frame and internal wall of the building according to the measurement data, which requires a lot of work and low efficiency.

Just as the aforementioned patent document with the publication number CN 104897161 A provides a method for generating a planar grid map from a scanned point cloud, but it does not involve the extraction of building structures, but only rasterizes the scanned point cloud; However, the aforementioned literature (Ochmann, S., et al. "Automatic construction of parametric building models from indoor point clouds." 2016) proposed a method for extracting building geometry and parametric modeling in an experimental environment, but The high-precision point cloud data collected by professional equipment is used, but it does not consider how to deal with the poor quality point cloud data collected by consumer equipment

[0005] To sum up, from the perspective of the development of existing technologies, how to use the low-precision data collected by consumer-grade equipment to automatically carry out indoor mapping has become an important bottleneck restricting the development of indoor location-based services. There is no method and technical solution to solve this problem. Therefore, a new and effective method for automatically building indoor maps and systematically inventing indoor maps using low-precision data collected by consumer-grade equipment is imperative. OK

Images