A 3D digital content intelligent production cloud platform based on motion capture big data

Abstract

The invention discloses a three-dimensional digital content intelligent production cloud platform based on motion capture big data. The platform comprises a three-dimensional data acquisition unit, a three-dimensional data cloud storage unit and a three-dimensional digital content cloud computing unit. The three-dimensional data acquisition unit is used for acquiring data. The three-dimensional data cloud storage unit is used for storing and reading the three-dimensional data at a cloud side. The three-dimensional digital content cloud computing unit intelligently generates the required three-dimensional digital content through a cloud side server parallel computing processor. The platform has excellent compatibility and has high matching speed and high accuracy of the three-dimensional model data and the three-dimensional motion data and can be adaptive to any forms of three-dimensional motion capture systems so that the three-dimensional digital content production threshold can be reduced, and users can fully schedule the client side module to acquire the same quality of three-dimensional digital content and the same user experience by using the technology in the webpage and APP.

Description

technical field [0001] The invention belongs to the technical field of intelligent production of three-dimensional digital content, in particular to a cloud platform for intelligent production of three-dimensional digital content based on motion capture big data. Background technique [0002] With the rapid development of computer technology and people's higher pursuit of quality of life, more 3D digital products have entered people's daily life. In the entertainment industry, high-tech 3D animation film and television and film special effects production are becoming more and more popular and sought after by the market. Every year, the global investment in the 3D animation industry reaches tens of billions of dollars. At the same time, in the application of technologies such as virtual reality, augmented reality, and naked-eye 3D, people have more and more requirements for 3D digital content. However, the production of 3D digital content must be manually produced by profess...

AI Technical Summary

Problems solved by technology

However, when the object is continuously changing, it may produce confusing and occluded target points. This is also the defect of the current optical motion capture compared to other methods, and it needs to be corrected manually.

[0005] On the 3D motion database, there are only a few motion databases including Carnegie Mellon University. The stored motion data is not only small in number and simple in motion, but also classified according to motion, which can only be used for research and is difficult to use directly. in commercial animation

[0006] At present, the benchmark software system in the field of 3D digital content is Autodesk's MotionBuilder abroad. When using the above software, it is necessary to manually match the performer's skeleton with the character's skeleton. At the same time, Motionbuilder needs to adopt the standard human skeleton structure defined by Autodesk itself. Many animation characters are different from the human skeleton structure defined by Motionbuilder, and Motionbuilder cannot perform human motion matching and motion driving

In action matching and action driving, a common problem is the action "going through" and "sliding step"

Images