摘要：An automatic 3D semantic annotation algorithm is proposed based on the associated scene between models. This algorithm uses the semantic context of 3D models to annotate the non-annotated nodes in terms of the annotated nodes. Firstly, this algorithm abstracts the extensible 3D (X3D) scene into the X3D conventional scene tree, transforming the conventional scene tree into an in-line node scene tree. Additionally, the algorithm uses the X3D ontology for semantic reasoning between the scene and the models. Lastly, the algorithm annotates the model files automatically. This study analyses the time and space complexity of the algorithm. Experimental results confirm that this algorithm improves not only the annotation validity but also the retrieval performance.
