An outline for an intelligent system performing peg-in-hole actions with flexible objects
ICIRA'11 Proceedings of the 4th international conference on Intelligent Robotics and Applications - Volume Part II
| Hi-index | 0.00 |
Active 3D acquisition setups currently capture 3D data from a single viewpoint. We propose a system that supports the effective use of multiple structured light modules placed around the object of interest. We show how oppositely positioned modules could work together and how we can avoid those parts of the background that unnecessarily take up computation time. Key to the setup is having the structured light patterns masked outside the outlines of the object to be captured. This is done very fast, so that the system can be used for motion capture. Only off-the-shelf hardware is required.