Indoor point cloud map generation system and indoor point cloud map generation method based on three-dimensional laser

Abstract

The invention discloses an indoor point cloud map generation system and an indoor point cloud map generation method based on three-dimensional laser. The indoor point cloud map generation system basedon three-dimensional laser comprises: a data acquisition module, wherein point cloud data is collected by a laser sensor; a data filtration module, wherein noise points and isolated points are filtered by a wave filter; a data registration module, wherein the local point cloud data is subjected to registration by using an image registration method so as to form a completed 3D point cloud map; anda data partition module, wherein the 3D point cloud map is subjected to partition by using a data partition method to obtain the point cloud collection data of different planes and different objects.According to the technical scheme of the present invention, the discrete point cloud data is converted into the complete three-dimensional point cloud map through filtering, splicing, noise reducing,matching, partition and other operations, such that the accurate indoor environment map with the complete three-dimensional structure is established, the accurate and complete map basis is provided for the subsequent navigation and positioning of the robot, and the good scalability and the good stability are provided.

Description

technical field [0001] The invention relates to indoor map generation technology, in particular to a three-dimensional laser-based indoor point cloud map generation system and method. Background technique [0002] With the improvement of various performances, service robots can complete more and more tasks in people's daily life, such as cleaning, moving objects and so on. In order to complete the task more smoothly, the robot must have a more detailed and accurate perception and understanding of the surrounding environment. [0003] Nowadays, most robots use binocular vision or two-dimensional laser point cloud maps to recognize the environment. Binocular vision is very unstable and will lead to failure in many common situations. However, the two-dimensional map only considers the environmental information of a certain height plane. Obstacles that are too high or too low cannot be avoided, so it cannot be used in complex environments. used in . Compared with traditional ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art, especially to solve the problem that the existing two-dimensional point cloud map and camera visual map have poor stability, cannot know the accurate three-dimensional structure of the surrounding environment, and cannot work when the environmental light source changes

Images