Door and Window Detection in 3D Point Cloud of Indoor Scenes

This paper proposes a 3D-2D-3D algorithm for doors and windows detection in 3D indoor environment of point cloud data.Firstly,by setting up a virtual camera in the middle of this 3D environment,a set of pictures are taken from different angles by rotating the camera,so that corresponding 2D images can be generated.Next,these images are used to detect and identify the positions of doors and windows in the space.To obtain point cloud data containing the doors and windows position information,the 2D information are then mapped back to the origin 3D point cloud environment.Finally,by processing the contour lines and crossing points,the features of doors and windows through the position information are optimized.The experimental results show that this“global-local”approach is efficient when detecting and identifying the location of doors and windows in 3D point cloud environment.