An Evidential System for Color Recognition Using Multi-cameras
Résumé
Recognition is always an interesting aspect of visual processing, especially for systems that requires intuitive percep- tion like robotics or human-machine interactions. In this work, a color recognition system based on Evidence Theory is applied for a scenario of the NAO robot that recognizes the color of a requested ball. The robot employs multi-cameras to reduce uncertainties, and the Dempster-Shafer rule of combination is used to fuse information from these cameras. Experimental results validate that the proposed method outperforms the use of Fuzzy similarity with each camera, and the fusion of multi- cameras dramatically increases the recognition success rate.