Samsung electronics co., ltd. (20240331176). METHOD AND ELECTRONIC DEVICE FOR DETERMINING DEPTH INFORMATION OF OBJECTS IN A SCENE simplified abstract

From WikiPatents
Revision as of 15:49, 4 October 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

METHOD AND ELECTRONIC DEVICE FOR DETERMINING DEPTH INFORMATION OF OBJECTS IN A SCENE

Organization Name

samsung electronics co., ltd.

Inventor(s)

Akshat Ramachandran of Bengaluru (IN)

Ankit Dhiman of Bengaluru (IN)

Basavaraja Shanthappa Vandrotti of Bengaluru (IN)

Jooyoung Kim of Suwon-si (KR)

Lokesh Rayasandra Boregowda of Bengaluru (IN)

METHOD AND ELECTRONIC DEVICE FOR DETERMINING DEPTH INFORMATION OF OBJECTS IN A SCENE - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240331176 titled 'METHOD AND ELECTRONIC DEVICE FOR DETERMINING DEPTH INFORMATION OF OBJECTS IN A SCENE

Simplified Explanation

This patent application describes a method for determining depth information of objects in a scene by combining RGB images and depth images.

  • Using an RGB camera to generate RGB images with a high pixel density.
  • Using a depth camera to generate a depth image with a lower pixel density.
  • Creating an attention map from the RGB images.
  • Merging the RGB images and the depth image to generate a merged image.
  • Calculating an uncertainty score for each pixel in the merged image.
  • Setting a threshold based on the uncertainty score.
  • Determining depth values for pixels exceeding the threshold.
  • Applying the depth values to the merged image to generate the scene with depth information.

Key Features and Innovation

  • Integration of RGB and depth images for depth information.
  • Attention map generation to focus on important areas.
  • Uncertainty score calculation for accurate depth determination.
  • Threshold setting to filter out uncertain depth values.

Potential Applications

This technology can be used in various fields such as:

  • Augmented reality
  • Robotics
  • Autonomous vehicles
  • Medical imaging

Problems Solved

  • Accurate depth information extraction from scenes.
  • Improved object recognition and tracking.
  • Enhanced spatial awareness in various applications.

Benefits

  • Enhanced depth perception in visual systems.
  • Improved decision-making in autonomous systems.
  • Enhanced user experience in augmented reality applications.

Commercial Applications

Title: Depth Information Integration Technology for Enhanced Visual Systems This technology can be utilized in industries such as:

  • Gaming
  • Surveillance
  • Industrial automation
  • Virtual reality

Questions about Depth Information Integration Technology

What are the key advantages of combining RGB and depth images for depth information?

By combining RGB and depth images, the system can provide more accurate depth information, enabling better object recognition and tracking.

How does the uncertainty score help in determining depth values for pixels in the merged image?

The uncertainty score helps filter out unreliable depth values, ensuring that only accurate depth information is used in the final scene generation.


Original Abstract Submitted

a method for determining depth information of objects in a scene, includes: generating rgb images having a first pixel density using an rgb camera; generating a depth image having a second pixel density using a depth camera, the second pixel density being lower than the first pixel density; generating an attention map using the rgb images with a high pixel density; merging the rgb images and the depth image to generate a merged image; determining an uncertainty score of each pixel of a plurality of pixels in the merged image; determining a threshold for the uncertainty score based on a level of uncertainty in the plurality of pixels; determining a depth value for each pixel of the plurality of pixels exceeding the threshold of the uncertainty score; applying the depth value of each pixel of the plurality of pixels in the merged image; and generating the scene with the depth information based on the depth value.