A Real-Time Motion Capture System with Multiple Camera Fusion
ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Quality Control Schemes for Industrial Production by Workers' Motion Capture
AINAW '08 Proceedings of the 22nd International Conference on Advanced Information Networking and Applications - Workshops
Dynamic context capture and distributed video arrays for intelligent spaces
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hi-index | 0.00 |
In quality control of industrial products, it is very important that not only qualities of materials and parts, design, but also a manufacturing work accords to instruction manuals for manufacturing process. Generally, most assembly process such as assembly line and cell production system have processes in everywhere to confirm quality and work in former processes. However, there are some cases that are difficult to be confirmed in later processes. For example, to fix a part by some screws, it is desirable to drive in diagonal order little by little. However, it is not easy to detect in appearance in case of this desirable procedure is violated. Therefore, we are developing a system to improve quality of industrial products. This system deals manufacturing processes as context, and grasp manufacturing process, recognizes context by tracing motions of worker's arm/hand by using terrestrial magnetism sensors and accelerometers. As a prototype of this system, we developed a system that judges attaching process of a particular part is correctly done or not in an accrual vehicle assemble factory. In this paper, we describe outline of the prototype of our workers' motion trace system and algorithms for judgment, and its evaluation.