Automatic segmentation method for indoor room point cloud

Abstract

The invention discloses an automatic segmentation method for indoor room point cloud, and the method comprises the steps that: the ceiling point cloud data in the collected multi-room point cloud data is firstly determined; and one room generally corresponds to one ceiling, therefore, the multi-room point cloud data can be accurately segmented into the point cloud data of the single room according to the determined ceiling point cloud data, and the point cloud data of the single room obtained after segmentation can be directly used for an existing model reconstruction algorithm. The problem that in the prior art, collected point cloud data of multiple rooms in a building are difficult to apply to an existing model reconstruction algorithm based on a single room is solved. 本发明公开了一种室内房间点云的自动分割方法，所述方法通过首先确定采集到的多房间点云数据中的天花板点云数据，由于一个房间通常对应一个天花板，因此根据确定天花板点云数据可以准确地将多房间点云数据分割成单个房间的点云数据，分割后得到的单个房间点云数据即可直接于现有的模型重建算法，解决了现有技术中采集到的建筑室内多个房间的点云数据，难以应用于现有的基于单个房间的模型重建算法的问题。