Dance Action Capture and CAD Design Based on Big Data Algorithm Optimization

The primary objective of this investigation is to refine dance motion capture and computer-aided design (CAD) processes through the utilization of big data algorithms, thereby addressing concerns related to precision and productivity in current technologies. During the data acquisition phase, suitable dance motion capture devices and CAD design tools are selected to gather authentic dance movement information and CAD specifications from dancers. Following this, the raw data undergoes preprocessing, which involves cleaning, organization, and format conversion. In the subsequent model development stage, leveraging big data algorithms alongside graph convolution networks (GCN) and other advanced techniques, an enhanced model for dance motion capture and CAD design is formulated. To validate the model's efficacy, a series of comparative experiments are devised. The experimental findings reveal that the model excels in accurately capturing dance movements, achieving an approximately 96% precision rate. Moreover, it demonstrates a capacity to rapidly generate high-calibre 3D models and exhibits remarkable adaptability to diverse dance styles. These advantages make this method have broad application prospects and potential in practical application. © 2024 U-turn Press LLC.