Emotion interaction based Peking Opera teaching system

Abstract

A Peking Opera teaching system based on somatosensory interaction, including a data acquisition module, a data processing module and a user interface interaction module. The data acquisition module obtains the user's joint information and sound data through the somatosensory interaction device; the data processing module realizes the user's logical control of the system Display the user model synchronized with the user's actions, perform matching and feedback between the Peking Opera standard model and the user model, obtain user voice data, and perform matching and feedback between the standard singing voice and the user's audio; the user interface interaction module performs the operation interface through the recognition of user gestures Display and switching, Peking Opera teaching video display, action performance evaluation display and audio scoring display. The Beijing opera teaching system of the present invention operates through somatosensory operation throughout, has a high recognition rate, and does not need a keyboard or a mouse as inputs. The user model has a high synchronization rate with the actual user posture, and there is no jitter, frame skipping phenomenon, and it is not affected by the hardware limitation of sensory capture and the environmental noise during bone tracking.

Description

technical field [0001] The invention relates to the field of somatosensory interaction, in particular to a Beijing opera teaching system based on somatosensory interaction. Background technique [0002] Peking Opera is the quintessence of China and represents the traditional culture of the Chinese nation. It is of far-reaching significance to inherit and carry forward Peking Opera. However, the teaching process of Peking Opera is relatively complicated. Each link of singing, reciting, sitting, and playing requires corresponding special teaching steps. Many factors lead to the high cost of teaching Peking Opera, which is not conducive to the inheritance and development of traditional culture such as Peking Opera in the younger generation. [0003] The Peking Opera teaching system is mainly divided into two parts: body posture teaching and singing tone teaching. The related technologies mainly include 3D model rendering and smoothing technology, gesture recognition technology...

AI Technical Summary

Problems solved by technology

[0004] The amount of data per second of the existing skeletal joint point capture technology is constant. When the user’s limbs move too fast, the received skeletal joint point data jumps greatly in the three-dimensional space, and some model rendering and smoothing algorithms cannot quickly Handle this well, resulting in stiff model motion or frame skipping

The main disadvantage of existing gesture recognition algorithms is that the recognition success rate and accuracy are low. When the user's gestures are too complex or have a high similarity, the existing algorithms cannot distinguish the differences between different gestures and accurately identify different complex gestures. High-degree gestures, thus increasing the difficulty of the user's somatosensory operation

At present, the mainstream audio matching technology is mainly based on frequency matching, and the energy processing of the user's voice is less, while the user's audio quality is determined by both frequency and energy, and the lack of energy processing reduces the accuracy of matching.

In addition, the existing technology cannot filter the environmental noise well, so the matching result is easily affected by the environment, and cannot truly reflect the user's singing level

Images