Three-dimensional vision system for mechanical assembly/disassembly

This paper proposes a three-dimensional (3D) vision system based on range image processing for mechanical assembly and disassembly. In the field of assembly and, moreover, because of the increasing importance of recycling of industrial products, in the field of disassembly, a more flexible vision system is required. Conventional intensity image processing is not sufficient and so a 3D vision system is required. A prototype of a vision system with a high-speed range image sensor is constructed, and its robustness for assembly and disassembly is verified by experiments to detect a target region (dial of an audio amplifier) with blemishes. Shape recognition algorithms which are applicable to sparse range images of the 3D vision system are introduced. They utilize primitive surface features such as planar or cylindrical surfaces as features for model matching. Fundamental experiments show the effectiveness of the general shape recognition algorithms.