18072974. APPARATUS AND METHOD WITH OBJECT POSTURE ESTIMATING simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

From WikiPatents
Jump to navigation Jump to search

APPARATUS AND METHOD WITH OBJECT POSTURE ESTIMATING

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Weiming Li of Beijing (CN)

Qiang Wang of Beijing (CN)

HYUN SUNG Chang of Suwon-si (KR)

JIYEON Kim of Suwon-si (KR)

SUNGHOON Hong of Suwon-si (KR)

Bao He of Beijing (CN)

APPARATUS AND METHOD WITH OBJECT POSTURE ESTIMATING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18072974 titled 'APPARATUS AND METHOD WITH OBJECT POSTURE ESTIMATING

Simplified Explanation

The patent application describes an apparatus and method for estimating the posture of an object in an image. Here is a simplified explanation of the abstract:

  • The method involves analyzing an image to determine key points, which are specific features or landmarks in the image.
  • A key point feature map is then used to modify the key point information, potentially enhancing the accuracy or reliability of the key points.
  • Based on the modified key point information, the method estimates the posture of the object in the image, which refers to the position, orientation, and shape of the object.

Potential applications of this technology:

  • Object recognition and tracking: The method can be used to accurately estimate the posture of objects in images, enabling better object recognition and tracking systems.
  • Augmented reality: By estimating the posture of objects in real-time, this technology can enhance augmented reality applications by precisely overlaying virtual objects onto the real world.
  • Robotics: The method can be applied in robotics to estimate the posture of objects in the robot's environment, allowing for more precise manipulation and interaction.

Problems solved by this technology:

  • Estimating the posture of objects in images can be challenging due to variations in lighting, perspective, and occlusions. This method addresses these challenges by using key point information and a key point feature map to improve accuracy.
  • Traditional methods for estimating object posture may require complex algorithms or extensive computational resources. This method provides a more efficient and effective approach.

Benefits of this technology:

  • Improved accuracy: By using modified key point information, the method can enhance the accuracy of estimating object posture in images.
  • Efficiency: The method provides a more efficient solution compared to traditional methods, reducing computational requirements and processing time.
  • Versatility: The technology can be applied to various fields such as computer vision, robotics, and augmented reality, offering a wide range of potential applications.


Original Abstract Submitted

An apparatus and method of estimating an object posture are provided. A method includes determining key point information in an image to be processed, determining modified key point information based on a key point feature map corresponding to the key point information, and estimating an object posture of an object in the image to be processed, based on the modified key point information.