A COMPARISON OF ARTIFICIAL NEURAL NETWORK AND HOMOTOPY CONTINUATION IN 3D INTERIOR BUILDING MODELLING

Abstract. Indoor surveying is currently based on laser scanning technology, which is time-consuming and costly. A construction model depends on complex calculations which need to manage a large number of measured points. This is suitable for the detailed geometrical models utilized for representation, yet excessively overstated when a simple model including walls, floors, roofs, entryways, and windows is required, such a basic model being a key for efficient network analysis such as shortest path finding. To reduce the time and cost of the indoor building data acquisition process, the Trimble LaserAce 1000 range finder is used. A comparison of neural network and a combined method of interval analysis and homotopy continuation in 3D interior building modelling for calibration of inaccurate surveying equipment is presented. We will present the interval valued homotopy model of the measurement of horizontal angles by the magnetometer component of the rangefinder. This model blends interval analysis and homotopy continuation. The results prove that homotopies give the best results both in terms of RMSE and the L_∞ metric.