Automatic registration of multiple range views based on feature matching and feature-depth correspondences

Previous works that employed an automatic registration of multiple range views resorted to the use of corresponding 3D matching points in order to compute relative orientations. False 3D matches were detected by verifying their compliance with the parameteres of the orientation's mathematical model computed in 3D space. In this research we introduce a new method to detect correct 3D matches. This method employs first the removal of the false 2D matches. Subsequently, 3D matches are detected by using the one to one correspondences provided by the scanning device between the 3D points and their corresponding 2D image projections. Due to its ability to detect the matching points in a fast manner, our method is suited for applications characterized by a 3D fast reconstruction demand. Experimental results with real object demonstrate the effectiveness of our method.