Development of Registration methodology to 3-D Point Clouds in Robot Scanning

Abstract

Abstract. The problem of multi-view 3-D point clouds registration is investigated and effectively resolved by the developed methodology. A registration method is proposed to register two series of scans into an object model by using the proposed oriented-bounding-box (OBB) regional area-based descriptor. Robot 3-D scanning is often employed to generate set of point clouds of physical objects. The automated operation has to successively digitize view-dependent area-scanned point clouds from complex shaped objects by multi-view point clouds registration. To achieve this, the OBB regional area-based descriptor is employed to determine an initial transformation matrix and is then refined employing iterative closest point (ICP) algorithm. The developed method can be used to resolve the commonly encountered difficulty in accurately merging two neighbouring area-scanned images when no coordinate reference exists. The developed method has been verified through some experimental tests for its registration accuracy. Experimental results have preliminarily demonstrated the feasibility of the developed method.

3D human hands rendering by a six degrees of freedom collaborative robot and a single 2D camera

“…To create a full model of an object three different methods are typically used. The first method [20] takes multiple flat models of the object from different angles and merges them together in the correct orientation to generate the final full model. Another method [19] is to have the object held by a gripper attached to the robotic manipulator and rotated in front of the scanner to get the full object model and then remove the gripper from the model.…”