Direction prediction method, virtual reality device and non-transitory computer readable medium

Abstract

A direction prediction method suitable for a virtual reality head-mounted device includes obtaining direction training data and adjusted direction data, where the adjusted direction data is obtained by removing a data segment from the direction training data, where the data segment corresponds to a time interval determined according to an application delay, training an initial class neural network model based on the direction training data and the adjusted direction data to obtain a trained class neural network model corresponding to the time interval, and obtaining instant direction data through a direction sensor of the virtual reality head-mounted device, and inputting the real-time direction data into the trained neural network model for outputting predicted direction data.

Description

technical field [0001] The present invention relates to a direction prediction method, a virtual reality head-mounted device, and a non-transitory computer-readable medium, and in particular, to a method for predicting the head of a user using the virtual reality head-mounted device A method for predicting the direction of movement of a part, a virtual reality headset, and a non-transitory computer-readable medium. Background technique [0002] The technology of virtual reality (VR) using a head mounted display (HDM) is developing rapidly. VR technology has been applied in various fields, from entertainment fields such as video games, navigation, virtual tours, education, and even medical fields where medical staff use HDM devices to practice or perform surgeries. [0003] VR technology uses artificial sensory simulation to induce users to perform target behaviors with minimal perception of interference. However, artificial sensory simulations may not accurately create per...

AI Technical Summary

Problems solved by technology

However, artificial sensory simulations may not be able to accurately create perceptual illusions due to motion-to-photon (MTP) delays

That is to say, since there is a time gap between the user's action and the updated image displayed on the HDM device due to the user's action, there may be a delay between the displayed image and the user's action.

And the motion photon delay may cause the user to have motion sickness

Images