Granted Patent B2

US 12,462,338 · App. 17/429,950 · Granted Nov 4, 2025

Inventor: Jinfeng Liu (Guangdong, CN)

Assignee: TCL China Star Optoelectronics Technology Co., Ltd.

G06T3/4053G06T3/4023

Abstract

Claims (54)

1 . A super-resolution image reconstruction method, comprising:

S 1 , collecting an original image to be reconstructed, the original image comprising a plurality of pixels arranged in an array; wherein each row of pixels comprises a plurality of row pixel groups composed of continuous pixels, and each column of pixels comprises a plurality of column pixel groups composed of continuous pixels;

S 2 , obtaining, according to visible relationship between pixels in each of the plurality of row pixel groups, gray scale values corresponding to newly added row pixels between two adjacent pixels in each row of pixels, and determining, according to visible relationship between pixels in each of the plurality of column pixel groups, gray scale values corresponding to newly added column pixels between two adjacent pixels in each column of pixels;

S 3 , determining, according to the newly added row pixels and the newly added column pixels, a gray scale value corresponding to a newly added central pixel in a surrounding area composed of newly added row pixels between two adjacent pixels in two adjacent rows and newly added column pixels between two adjacent pixels in two adjacent columns; wherein the two adjacent pixels in the two adjacent rows and the two adjacent pixels in the two adjacent columns overlap with each other; and

S 4 , inserting the newly added row pixels between two adjacent pixels in each row of pixels, inserting the newly added column pixels between adjacent two pixels in each column of pixels, and inserting the central pixel in the surrounding area composed of the newly added row pixels and the newly added column pixels, in order to obtain a super-resolution image reconstructed corresponding to the original image;

wherein the step S 2 of obtaining, according to the visible relationship between the pixels in each of the plurality of row pixel groups, the gray scale values corresponding to the newly added row pixels between the two adjacent pixels in each row of pixels, specifically comprises:

S 21 , determining, according to a gray scale value of each pixel and a row position of each pixel in a pixel row, at least one visible row pixel of each pixel in a row pixel group; wherein each pixel and the at least one the visible row pixel corresponding to each pixel satisfy a preset visible condition; and

S 22 , according to the gray scale value and the row position of each pixel, and a gray scale value and a row position of the at least one visible row pixel corresponding to each pixel, obtaining a gray scale value corresponding to a newly added row pixel of any row position between two adjacent pixels in each row of pixels;

wherein in the step S 21 , the preset visible condition comprises: gray scale values of pixels located between the row position of each pixel and the row position of the at least one visible row pixel corresponding to each pixel are all less than the gray scale value of each pixel and the gray scale value of each visible row pixel.

2 . The super-resolution image reconstruction method according to claim 1 , wherein the step S 22 specifically comprises:

S 221 , according to the gray scale value and the row position of each pixel, and the gray scale value and the row position of the at least one visible row pixel corresponding to each pixel, establishing a visible function relationship between each pixel and each corresponding visible row pixel, respectively;

S 222 , selecting, according to the visible function relationship between each pixel and each corresponding visible row pixel, a visible function relationship associated with two adjacent pixels in each row of pixels; wherein the visible function relationship associated with the two adjacent pixels is a visible function relationship that has an intersection with row positions between the two adjacent pixels; and

S 223 , obtaining the gray scale value corresponding to the newly added row pixel at any row position between the two adjacent pixels according to the visible function relationship associated with the two adjacent pixels.

3 . The super-resolution image reconstruction method according to claim 2 , wherein the step S 223 specifically comprises:

according to any row position between the two adjacent pixels, and all the visible function relationships associated with the two adjacent pixels, obtaining a plurality of initial gray scale values corresponding to the newly added row pixel at any row position; and

using an average value of the plurality of initial gray scale values as the gray scale value corresponding to the newly added row pixel at any row position.

4 . The super-resolution image reconstruction method according to claim 1 , wherein the step S 3 specifically comprises:

S 31 , selecting the two adjacent pixels in the two adjacent rows and the two adjacent pixels in the two adjacent columns that overlap each other; and

S 32 , using an average value of gray scale values of newly added row pixels between the two adjacent pixels in the two adjacent rows and gray scale values of the newly added column pixels between the two adjacent pixels in the two adjacent columns as the gray scale value corresponding to the newly added central pixel.

5 . The super-resolution image reconstruction method according to claim 1 , wherein a number of the newly added row pixels inserted between the two adjacent pixels of each row of pixels is the same, and a number of the newly added column pixels inserted between the two adjacent pixels is the same.

6 . A super-resolution image reconstruction method, comprising:

S 1 , collecting an original image to be reconstructed, the original image comprising a plurality of pixels arranged in an array; wherein each row of pixels comprises a plurality of row pixel groups composed of continuous pixels, and each column of pixels comprises a plurality of column pixel groups composed of continuous pixels;

S 2 , obtaining, according to visible relationship between pixels in each of the plurality of row pixel groups, gray scale values corresponding to newly added row pixels between two adjacent pixels in each row of pixels, and determining, according to visible relationship between pixels in each of the plurality of column pixel groups, gray scale values corresponding to newly added column pixels between two adjacent pixels in each column of pixels;

S 3 , determining, according to the newly added row pixels and the newly added column pixels, a gray scale value corresponding to a newly added central pixel in a surrounding area composed of newly added row pixels between two adjacent pixels in two adjacent rows and newly added column pixels between two adjacent pixels in two adjacent columns; wherein the two adjacent pixels in the two adjacent rows and the two adjacent pixels in the two adjacent columns overlap with each other; and

S 4 , inserting the newly added row pixels between two adjacent pixels in each row of pixels, inserting the newly added column pixels between adjacent two pixels in each column of pixels, and inserting the central pixel in the surrounding area composed of the newly added row pixels and the newly added column pixels, in order to obtain a super-resolution image reconstructed corresponding to the original image;

wherein the step S 2 of determining, according to the visible relationship between the pixels in each of the plurality of column pixel groups, the gray scale values corresponding to the newly added column pixels between the two adjacent pixels in each column of pixels, specifically comprises:

S 21 ′, determining, according to a gray scale value of each pixel and a column position of each pixel in a pixel column, at least one visible column pixel of each pixel in a column pixel group; wherein each pixel and the at least one visible column pixel corresponding to each pixel satisfy a preset visible condition; and

S 22 ′, according to the gray scale value and the column position of each pixel, and a gray scale value and a column position of the at least one visible column pixel corresponding to each pixel, obtaining a gray scale value corresponding to a newly added column pixel at any column position between two adjacent pixels in each column of pixels;

wherein in the step S 21 ′, the preset visible condition comprises: gray scale values of pixels between the column position of each pixel and the column position of the at least one column pixel corresponding to each pixel are all less than the gray scale value of each pixel and the gray scale value of each visible column pixel.

7 . The super-resolution image reconstruction method according to claim 6 , wherein the step S 22 ′ specifically comprises:

S 221 ′, according to the gray scale value and the column position of each pixel, and the gray scale value and the column position of the visible column pixel corresponding to each pixel, establishing a visible function relationship between each pixel and each corresponding visible column pixel, respectively;

S 222 ′, selecting, according to the visible function relationship between each pixel and each corresponding visible column pixel, a visible function relationship associated with two adjacent pixels in each column of pixels; wherein the visible function relationship associated with the two adjacent pixels is a visible function relationship that has an intersection with column positions between the two adjacent pixels; and

S 223 ′, obtaining the gray scale value corresponding to the newly added column pixel at any column position between the adjacent two pixels according to the visible function relationship associated with the two adjacent pixels.

8 . The super-resolution image reconstruction method according to claim 7 , wherein the step S 223 ′ specifically comprises:

according to any column position between the two adjacent pixels and all the visible function relationships associated with the two adjacent pixels, obtaining a plurality of initial gray scale values corresponding to the newly added column pixel at any column position; and

using an average value of the plurality of initial gray scale values as the gray scale value corresponding to the newly added column pixel at any column position.

9 . A super-resolution image reconstruction device, comprising:

a collection module configured to collect an original image to be reconstructed, the original image comprising a plurality of pixels arranged in an array; wherein each row of pixels comprises a plurality of row pixel groups composed of continuous pixels, and each column of pixels comprises a plurality of column pixel groups composed of continuous pixels;

a newly added row and column pixel module configured to obtain, according to visible relationship between pixels in each of the plurality of row pixel groups, gray scale values corresponding to newly added row pixels between two adjacent pixels in each row of pixels, and determine, according to visible relationship between pixels in each of the plurality of column pixel groups, gray scale values corresponding to newly added column pixels between two adjacent pixels in each column of pixels;

a newly added central pixel module configured to determine, according to the newly added row pixels and the newly added column pixels, a gray scale value corresponding to a newly added central pixel in a surrounding area composed of newly added row pixels between two adjacent pixels in two adjacent rows and newly added column pixels between two adjacent pixels in two adjacent columns; wherein the two adjacent pixels in the two adjacent rows and the two adjacent pixels in the two adjacent columns overlap with each other; and

an insertion module configured to insert the newly added row pixels between two adjacent pixels in each row of pixels, insert the newly added column pixels between adjacent two pixels in each column of pixels, and insert the central pixel in the surrounding area composed of the newly added row pixels and the newly added column pixels, in order to obtain a super-resolution image reconstructed corresponding to the original image;

wherein the newly added row and column pixel module specifically comprises:

a row pixel visible relationship unit configured to determine, according to a gray scale value of each pixel and a row position of each pixel in a pixel row, at least one visible row pixel of each pixel in a row pixel group; wherein each pixel and the at least one the visible row pixel corresponding to each pixel satisfy a preset visible condition; and

a newly added row pixel gray scale value acquisition unit configured to obtain a gray scale value corresponding to a newly added row pixel of any row position between two adjacent pixels in each row of pixels, according to the gray scale value and the row position of each pixel, and a gray scale value and a row position of the at least one visible row pixel corresponding to each pixel;

wherein the newly added row pixel gray scale value acquisition unit is specifically configured to:

according to the gray scale value and the row position of each pixel, and the gray scale value and the row position of the at least one visible row pixel corresponding to each pixel, establish a visible function relationship between each pixel and each corresponding visible row pixel, respectively;

select, according to the visible function relationship between each pixel and each corresponding visible row pixel, a visible function relationship associated with two adjacent pixels in each row of pixels; wherein the visible function relationship associated with the two adjacent pixels is a visible function relationship that has an intersection with row positions between the two adjacent pixels; and

obtain the gray scale value corresponding to the newly added row pixel at any row position between the two adjacent pixels according to the visible function relationship associated with the two adjacent pixels

wherein the newly added row pixel gray scale value acquisition unit specifically configured to obtain the gray scale value corresponding to the newly added row pixel at any row position between the two adjacent pixels according to the visible function relationship associated with the two adjacent pixels further comprises:

according to any row position between the two adjacent pixels, and all the visible function relationships associated with the two adjacent pixels, obtaining a plurality of initial gray scale values corresponding to the newly added row pixel at any row position; and

using an average value of the plurality of initial gray scale values as the gray scale value corresponding to the newly added row pixel at any row position.

10 . The super-resolution image reconstruction device according to claim 9 , wherein the newly added central pixel module is specifically configured to:

select the two adjacent pixels in the two adjacent rows and the two adjacent pixels in the two adjacent columns that overlap each other; and

use an average value of gray scale values of newly added row pixels between the two adjacent pixels in the two adjacent rows and gray scale values of the newly added column pixels between the two adjacent pixels in the two adjacent columns as the gray scale value corresponding to the newly added central pixel.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (29)