20240031678. POSE TRACKING FOR ROLLING SHUTTER CAMERA simplified abstract (Unknown Organization)

From WikiPatents
Jump to navigation Jump to search

POSE TRACKING FOR ROLLING SHUTTER CAMERA

Organization Name

Unknown Organization

Inventor(s)

Georg Halmetschlager-funek of Vienna (AT)

Jeroen Hol of Hengelo (NL)

Matthias Kalkgruber of Vienna (AT)

Nikolaj Kuntner of Vienna (AT)

Daniel Wolf of Modling (AT)

POSE TRACKING FOR ROLLING SHUTTER CAMERA - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240031678 titled 'POSE TRACKING FOR ROLLING SHUTTER CAMERA

Simplified Explanation

The abstract describes a method and apparatus for tracking poses of a rolling-shutter camera in an augmented reality (AR) system. The method involves using camera information and inertial sensor readings from an inertial measurement unit (IMU) to estimate the pose of the camera at a reference line. The relative pose changes at scanlines can then be calculated using the inertial sensor data. The estimated reference pose of the camera is further refined based on visual information from the camera, the relative pose changes, and the optimized reference line pose of a previous image. The estimate of the scanline poses can be updated using the relative pose changes obtained in the earlier steps.

  • The invention is a method and apparatus for tracking poses of a rolling-shutter camera in an AR system.
  • It uses camera information and inertial sensor readings from an IMU to estimate the camera's pose at a reference line.
  • Relative pose changes at scanlines can be calculated using the inertial sensor data.
  • The estimated reference pose of the camera is refined based on visual information from the camera, relative pose changes, and the optimized reference line pose of a previous image.
  • The estimate of the scanline poses can be updated using the relative pose changes obtained earlier.

Potential applications of this technology:

  • Augmented reality systems: The method and apparatus can be used in AR systems to accurately track the poses of rolling-shutter cameras, enhancing the overall AR experience.
  • Virtual reality systems: The technology can also be applied in virtual reality systems to improve the tracking of rolling-shutter cameras, providing more immersive VR experiences.
  • Robotics: The method and apparatus can be utilized in robotics applications where accurate pose tracking of rolling-shutter cameras is required, such as in autonomous navigation or object recognition tasks.

Problems solved by this technology:

  • Rolling-shutter camera pose tracking: The invention addresses the challenge of accurately tracking the poses of rolling-shutter cameras in AR systems, which can be affected by the rolling shutter effect and motion blur.
  • Inertial sensor integration: By combining camera information with inertial sensor readings from an IMU, the technology solves the problem of integrating these different data sources to estimate the camera's pose accurately.
  • Refinement of pose estimation: The method improves the accuracy of pose estimation by refining the estimated reference pose using visual information from the camera, relative pose changes, and the optimized reference line pose of a previous image.

Benefits of this technology:

  • Enhanced AR experience: By accurately tracking the poses of rolling-shutter cameras, the technology improves the alignment of virtual objects with the real world, resulting in a more seamless and immersive AR experience.
  • Improved VR immersion: In virtual reality systems, the accurate tracking of rolling-shutter camera poses enhances the realism and immersion of the virtual environment, providing users with a more engaging VR experience.
  • Precise robotics applications: The technology enables precise pose tracking of rolling-shutter cameras in robotics applications, contributing to more accurate navigation, object recognition, and other tasks that rely on camera pose information.


Original Abstract Submitted

a method and apparatus of tracking poses of a rolling-shutter camera in an augmented reality (ar) system is provided. the method and apparatus use camera information and inertial sensor readings from inertial measurement unit (imu) to estimate the pose of the camera at a reference line. thereafter, relative pose changes at scanlines may be calculated using the inertial sensor data. the estimated reference pose of the camera is then further refined based on the visual information from the camera, the relative pose changes and the optimized reference line pose of a previous image. thereafter, the estimate of the scanline poses may be updated using the relative pose changes obtained in the earlier steps.