A hybrid modeling method of Chinese ancient architecture
Wu Guo, Yunyi Zhang, Dongfeng Han, Wenhui Li · 2008
In this paper, we present a hybrid of graph-based and neural network modeling system of Chinese Ancient Pagoda (CAP). To implement the pagoda modeling system, we have built a basic element model library of pagoda by L system and a corresponding feature library. Feature points have been detected by our feature points extraction algorithm. After the Feature Segment Graph (FSG) is transformed into representation vectors, and these vectors are presented to the neural network which classifies them into feature classes. Once the feature information is detected, a virtual assembly process ensures the coherent architecture styles of CAP. The most important characteristic of this method is realistic modeling and rapid generating, so it can be applied to promising applications in entertainment industry.