Samsung electronics co., ltd. (20240161314). ELECTRONIC DEVICE FOR ESTIMATING OPTICAL FLOW AND OPERATING METHOD THEREOF simplified abstract

From WikiPatents
Jump to navigation Jump to search

ELECTRONIC DEVICE FOR ESTIMATING OPTICAL FLOW AND OPERATING METHOD THEREOF

Organization Name

samsung electronics co., ltd.

Inventor(s)

Zhaohui Lv of Xi'an (CN)

Pei You of Xi'an (CN)

Penghui Sun of Xi'an (CN)

Feng Zhu of Xi'an (CN)

Ran Yang of Xi'an (CN)

Huisi Wu of Shenzhen (CN)

Wende Xie of Shenzhen (CN)

Jingyin Lin of Shenzhen (CN)

Zebin Zhao of Shenzhen (CN)

Dong Kyung Nam of Suwon-si (KR)

Jingu Heo of Suwon-si (KR)

ELECTRONIC DEVICE FOR ESTIMATING OPTICAL FLOW AND OPERATING METHOD THEREOF - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240161314 titled 'ELECTRONIC DEVICE FOR ESTIMATING OPTICAL FLOW AND OPERATING METHOD THEREOF

Simplified Explanation

The method described in the patent application involves estimating optical flow by processing two images separately and using attention feature maps. Here is a simplified explanation of the abstract:

  • Extract feature maps from the first and second images
  • Fuse row relationship information with the feature map of the first image to create a fusion attention feature map
  • Generate an attention feature map for the first image based on the fusion attention feature map and the image feature map
  • Fuse column relationship information with the attention feature map of the first image to create a fusion attention feature map for the second image
  • Generate an attention feature map for the second image based on the fusion attention feature map and the attention feature map of the first image

Potential Applications

This technology could be applied in various fields such as computer vision, autonomous vehicles, robotics, and surveillance systems.

Problems Solved

This technology helps in accurately estimating optical flow between two images, which is crucial for tasks like object tracking, motion analysis, and scene understanding.

Benefits

The method provides a more robust and accurate estimation of optical flow compared to traditional techniques. It also allows for better understanding of motion patterns in images.

Potential Commercial Applications

Potential commercial applications of this technology include video surveillance systems, drone navigation, augmented reality applications, and medical imaging.

Possible Prior Art

One possible prior art for estimating optical flow is the Lucas-Kanade method, which is a classic algorithm used for motion estimation in computer vision.

Unanswered Questions

How does this method compare to other optical flow estimation techniques in terms of accuracy and computational efficiency?

This article does not provide a direct comparison with other optical flow estimation techniques, so it is unclear how this method performs in comparison to existing methods.

Are there any limitations or constraints in the implementation of this method in real-world applications?

The article does not mention any potential limitations or constraints that may arise when implementing this method in practical scenarios, leaving this aspect unanswered.


Original Abstract Submitted

a method of estimating an optical flow includes processing, using an image processing pass, a first image and a second image separately, and estimating the optical flow based on a second image attention feature map of the first image and a second image attention feature map of the second image. the processing using the image processing pass includes extracting a feature map by encoding an image, outputting a first image fusion attention feature map by fusing row relationship information of the image with the image feature map, outputting a first image attention feature map of the image based on the first image fusion attention feature map and the image feature map, outputting a second image fusion attention feature map by fusing column relationship information of the image with the first image attention feature map, and generating a second image attention feature map of the image based on the second image fusion attention feature map and the first image attention feature map.