Interpretation of Industrial Scenes by Semantic Networks

An industrial vision system is presented which is designed general enough not only to recognize parts but also to evaluate their quality, inspect the environment, and control a sequence of actions for the placement of the part. The paper concentrates on the three points of segmentation, automatic construction of object models, and identification and localization of parts. It points out that due to the general approach for knowledge-based processing an expansion of the system capabilities is possible.

• Type: Conference
• Year: 1990
• Where: MVA
• Authors: Heinrich Niemann, Heinz Brünig, Richard Salzbrunn, Stefan Schröder
• Keywords: Automatic Construction, Industrial Vision, MVA 1990, MVA 2007, Object Models