Construction method and system for two-dimensional and three-dimensional joint model of indoor environment

Abstract

The invention discloses a construction method and system for a two-dimensional and three-dimensional joint model of an indoor environment. The method comprises: obtaining two-dimensional laser scanning data output by a two-dimensional laser scanning instrument arranged in a horizontal direction, and constructing a two-dimensional grid map; performing platform six-degree-of-freedom pose estimation according to data output by an inertial sensing unit and the two-dimensional grid map with an extended Kalman filtering method; obtaining two-dimensional laser scanning data output by two two-dimensional laser scanning instruments with bottoms mounted in a vertical direction, and constructing three-dimensional point cloud data of the indoor environment; registering the three-dimensional point cloud data to be a three-dimensional map by taking a platform six-degree-of-freedom pose estimation result as an initial rotary translation matrix; and performing closed-loop detection of the two-dimensional grid map by adopting a closed-loop detection principle in two-dimensional grid map construction, and obtaining globally optimized two-dimensional grid map and three-dimensional map through platform pose adjustment, thereby achieving an effect of efficiently and accurately constructing two-dimensional and three-dimensional maps.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of synchronous positioning and map creation, and in particular to a method and system for building a combined two-dimensional and three-dimensional model of an indoor environment. Background technique [0002] Driven by the huge application demands of digital cities, emergency response simulation and training, and digital cultural heritage, especially in typical applications such as anti-terrorism, fire protection, and smart buildings, the 3D model of the indoor environment is an indispensable basic data. Different from the outdoor environment, the indoor environment has the characteristics of close distance, multiple corners, easy occlusion, complex lighting, and lack of absolute positioning. It is a challenging subject to efficiently and accurately obtain 3D information of the indoor environment. The currently commonly used solution is based on static laser scanners for multi-site mea...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to propose a method for building a two-dimensional and three-dimensional joint model of an indoor environment, aiming at accurately constructing a two-dimensional grid map of the indoor environment and providing a corresponding three-dimensional point cloud model to solve the problems of the prior art The efficiency of the static scanning scheme is low. When the mobile platform moves in the three-dimensional space, the exploration ability of the three-dimensional space is limited, and it is impossible to provide an efficient and accurate three-dimensional model of the indoor environment.

Images