Knowledge-based Incremental Bayesian Learning for Object Recognition
Gi Hyun Lim, Kun Woo Kim, Hyo-Won Suh, Il Hong Suh, Michael Beetz · Research Explorer (The University of Manchester) · 2013
Some of object recognition approaches are very effective in environments such as industrial settings, where the position and orientation of object could be controlled. However, in everyday human environments, objects are not located in the same place at all times; rather, they are cluttered in such a way that some of them are visually occluded. Thus, this paper proposes a method of robust object recognition combing ontology and probabilistic inference. The basic idea even in a human environment there is organizational principles that objects are co-occurred with their related objects. This enables a robot to recognize object dependably. To demonstrate the benefits of the proposed approach, a case study is conducted in a human working environment.