Colour Hue and Texture Evaluation for 3D Symbolization of Indoor Environments Using RGB-D Data

In this work an evaluation procedure of the use of colour hue and texture for 3D symbolization of indoor environments using RGB-D data is presented. The main characteristics of the proposed method involve RGB-D cameras to collect colour and depth data and the evaluation of the visual variables colour hue and texture combined with visual aspects such as lighting and camera configuration for the symbolization of 3D indoor environments. High quality coloured point clouds of indoor environments are obtained with the Kinect sensor and then registered and processed in order to create 3D models. These sets of point clouds can be detected, recognized and classified under one of the three following main categories: ceiling, wall or floor. After classification is done, the resulting point clouds are properly treated as 3D triangular meshes in the MeshLab software. These meshes are then filtered to form complete surfaces which are then refined before being considered for visual variable application. We evaluated the proposed method on several indoor environments to show that it efficiently combines the colour and depth data obtained from RGB-D cameras with different parameters defined for the visual variables colour hue and texture for 3D symbolization of indoor environments.