US Patent Application 18312448. TRACKING ALGORITHM FOR CONTINUOUS AR EXPERIENCES simplified abstract
Contents
TRACKING ALGORITHM FOR CONTINUOUS AR EXPERIENCES
Organization Name
Inventor(s)
Luca Ballan of San Jose CA (US)
Mahesh Ramachandran of Dublin CA (US)
Qiyue Zhang of Cupertino CA (US)
Konstantine Nicholas John Tsotsos of Corte Madera CA (US)
TRACKING ALGORITHM FOR CONTINUOUS AR EXPERIENCES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18312448 titled 'TRACKING ALGORITHM FOR CONTINUOUS AR EXPERIENCES
Simplified Explanation
The patent application describes a tracking system and algorithms for providing a continuous augmented reality (AR) experience without the need for resetting.
- The system uses an AR headset with a camera and an inertial measurement unit (IMU) to track the position and orientation of the headset in its environment.
- Motion sensor data from the IMU is combined with image data from the camera to create a device pose.
- When a reset occurs, a six-degrees-of-freedom (6DoF) algorithm supports the pose until re-initialization is completed.
- A neural network is used to correct for IMU integration drifts in the 6DoF algorithm.
- The IMU-based 6DoF algorithm utilizes the device's past motion to predict its future motion.
Original Abstract Submitted
A tracking system and associated algorithms are disclosed that can provide a user with a continuous, reset-free augmented reality (AR) experience. When the user wears an AR headset equipped with a camera and an inertial measurement unit (IMU), motion sensor data from the IMU can be combined with image data from the camera to create a device pose, representing a position and an orientation of the headset relative to its environment. In some implementations, when a reset occurs, a six-degrees-of-freedom (6DoF) algorithm can be configured to support the pose until a re-initialization is completed. In some implementations, a neural network can be used to correct for IMU integration drifts in the 6DoF algorithm. In some implementations, the IMU-based 6DoF uses a neural network that exploits the device's past motion to infer its future motion.
