Abstract:
An apparatus and method for generating synthetic training data for motion recognition. The method includes generating a three-dimensional (3D) human body model in real time according to motion of a human body, converting volume data of the 3D human body model into a 3D linear structure and extracting skeletal joint information, generating a data set of a human body image and skeletal joint information by rendering the 3D human body model and the skeletal joint information, and providing the data set of the image and the skeletal joint information as synthetic training data for motion recognition.
Abstract:
Disclosed is a method that performs a user modeling operation based on usage history data of a specific function which is provided or executed by a user terminal, and enables the user modeling result to be applied to various services. The method matches a user with a specific class, based on usage history data of various functions collected by a user terminal, and provides a user-based service suitable for the specific class.