17826251. APPRATUS AND METHOD WITH 3D MODELING simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

APPRATUS AND METHOD WITH 3D MODELING

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Jiyeon Kim of Yongin-si (KR)

APPRATUS AND METHOD WITH 3D MODELING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17826251 titled 'APPRATUS AND METHOD WITH 3D MODELING

Simplified Explanation

The abstract describes a method for three-dimensional modeling using a processor. Here are the key points:

  • The method determines the type of movement of an object detected in an image based on the variability of its position and shape.
  • The object is segmented into smaller chunks, each representing a unit of movement, based on the determined type of movement.
  • The determined type of movement is corrected by analyzing the change in position of feature points within the object.
  • The state of the movement of the object is determined based on the corrected type of movement.
  • The pose of the sensor is corrected based on the state of the object.
  • The pose for each chunk of the object is updated based on the determined state of the object and the corrected pose of the sensor.

Potential Applications

  • Three-dimensional modeling and reconstruction of objects or scenes.
  • Augmented reality applications.
  • Robotics and autonomous systems.
  • Virtual reality and gaming.

Problems Solved

  • Accurate and efficient three-dimensional modeling of objects with varying shapes and movements.
  • Improved tracking and understanding of object movements in images.
  • Enhanced sensor pose correction for more accurate modeling.

Benefits

  • Improved accuracy and realism in three-dimensional modeling.
  • Better understanding and tracking of object movements.
  • Enhanced capabilities for augmented reality and virtual reality applications.
  • Improved performance and efficiency in robotics and autonomous systems.


Original Abstract Submitted

A processor-implemented method with three-dimensional (3D) modeling includes: determining a type of movement of an object detected in an image received from a sensor, based on a variability of a position of the object and a variability of a shape of the object; segmenting the object into one or more chunks each corresponding to a unit of movement, based on the determined type of movement; correcting the determined type of movement based on a change in position of one or more feature points of the one or more chunks of the object in the image; determining a state of the movement of the object based on the corrected type of the movement of the object; correcting a pose of the sensor based on a state of the object; and updating a pose for each of the one or more chunks of the object based on the determined state of the object and the corrected pose of the sensor.