CN111277780B - Method and device for improving frame interpolation effect - Google Patents

Method and device for improving frame interpolation effect Download PDF

Info

Publication number
CN111277780B
CN111277780B CN201811473025.8A CN201811473025A CN111277780B CN 111277780 B CN111277780 B CN 111277780B CN 201811473025 A CN201811473025 A CN 201811473025A CN 111277780 B CN111277780 B CN 111277780B
Authority
CN
China
Prior art keywords
interpolation
pixel
frame
frame image
quality
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811473025.8A
Other languages
Chinese (zh)
Other versions
CN111277780A (en
Inventor
肖宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201811473025.8A priority Critical patent/CN111277780B/en
Publication of CN111277780A publication Critical patent/CN111277780A/en
Application granted granted Critical
Publication of CN111277780B publication Critical patent/CN111277780B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
    • H04N7/0135—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level involving interpolation processes

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Television Systems (AREA)

Abstract

The present disclosure relates to a method and apparatus for improving an effect of frame interpolation. The method comprises the following steps: determining an interpolation frame image between two adjacent original frames of images based on an optical flow frame interpolation method; judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not; updating the interpolated frame image when the interpolation frame quality of the interpolated frame image does not meet a criterion. The method and the device can improve the interpolation frame quality of the interpolation frame image obtained based on the optical flow interpolation frame method, and effectively improve the watching experience of a user on the high-frame-rate video obtained after the interpolation frame.

Description

Method and device for improving frame interpolation effect
Technical Field
The present disclosure relates to the field of video processing, and in particular, to a method and an apparatus for improving an interpolation effect.
Background
The video frame rate enhancement is a video post-processing method for converting a low frame rate video into a high frame rate video, and is characterized in that an interpolation frame image is determined by utilizing the time domain correlation between adjacent frame original images, and then the interpolation frame image is inserted between the adjacent frame original images so as to achieve the purpose of increasing the frame rate. For example, the video frame rate is increased from 30fps (Frames per Second) to 60 fps. The higher the video frame rate, the smoother the motion in the video picture, and the better the user viewing experience.
The currently common video frame rate enhancement method is an optical flow interpolation frame method based on optical flow, and generates an interpolated frame image between adjacent frame original images by calculating the optical flow between the adjacent frame original images in a video. In practical application, because it cannot be ensured whether the optical flow between the original images of the adjacent frames is accurate, a phenomenon that the viewing experience of a user is affected, such as object edge breakage, may occur in a high-frame-rate video after optical flow interpolation.
Therefore, a method for improving the effect of frame interpolation is needed.
Disclosure of Invention
In view of the above, the present disclosure provides a method and an apparatus for improving an interpolation effect, which are used to improve the interpolation quality of an interpolated frame image obtained based on an optical flow interpolation method, so as to improve the viewing experience of a user on a high frame rate video obtained after interpolation.
According to a first aspect of the present disclosure, there is provided a method for improving frame interpolation effect, including: determining an interpolation frame image between two adjacent original frames of images based on an optical flow frame interpolation method; judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not; updating the interpolated frame image when the interpolation frame quality of the interpolated frame image does not meet a criterion.
In one possible implementation, the determining whether the interpolation frame quality of the interpolation frame image meets a standard includes: judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights of the interpolation pixel points corresponding to a plurality of mapping pixel points in the two adjacent original frames of images.
In a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of an interpolation pixel point in the interpolation frame image includes: determining a first number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent frame original images are all smaller than a first threshold value; when the first number is larger than a second threshold, it is determined that the interpolation frame quality of the interpolation frame image does not meet.
In a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of an interpolation pixel point in the interpolation frame image includes: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one of the two adjacent original frames of images and the pixel quality of the interpolation pixel point in the interpolation frame image.
In a possible implementation manner, determining whether the interpolation frame quality of the interpolation frame image meets the standard according to the optical flow value of a pixel point in at least one of the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image includes: determining a second number corresponding to a first type of pixel points included in at least one frame of original image in the two adjacent frames of original images, wherein optical flow values corresponding to the first type of pixel points are greater than a third threshold value; determining a third number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent frame original images are all smaller than a first threshold value; when the second number is greater than a fourth threshold and the third number is greater than a fifth threshold, determining that the interpolation frame quality of the interpolation frame image does not meet.
In a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of an interpolation pixel point in the interpolation frame image includes: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image.
In a possible implementation manner, determining whether the interpolation frame quality of the interpolation frame image meets the standard according to the optical flow consistency between the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image includes: determining a fourth number corresponding to a second type of pixel point included in at least one frame of original image in the two adjacent frames of original images, wherein the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent frames of original images do not have optical flow consistency; determining a fifth number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent original frames of images are all smaller than a first threshold value; when the fourth number is greater than a sixth threshold and the fifth number is greater than a seventh threshold, determining that the interpolation frame quality of the interpolated frame image does not meet.
In a possible implementation manner, the two adjacent frames of original images are a t-th frame of original image and a t + 1-th frame of original image; the second-class pixel points and the second-class pixel points have no optical flow consistency between the mapping pixel points in the original image of the adjacent frame, and the method comprises at least one of the following steps: the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold; the second type pixel points are located in a t +1 th frame original image, and the difference of optical flow absolute values between backward optical flows of the second type pixel points and forward optical flows of mapping pixel points of the second type pixel points in the t th frame original image is larger than the eighth threshold.
In one possible implementation, updating the interpolated frame image when the interpolated frame image has an interpolated frame quality that does not meet a criterion includes: and re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other frame interpolation methods except the optical flow frame interpolation method.
In one possible implementation manner, the method further includes: and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
In one possible implementation, determining an interpolated frame image between two adjacent original frames based on an optical flow interpolation method includes: based on an optical flow frame interpolation method, aiming at any interpolation pixel point in the interpolation frame image, determining a plurality of mapping pixel points of the interpolation pixel point in the two adjacent original frames of images; determining the weight corresponding to any mapping pixel point in the plurality of mapping pixel points; and determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
According to a second aspect of the present disclosure, there is provided an apparatus for improving an effect of frame interpolation, comprising: the determination module is used for determining an interpolation frame image between two adjacent original frames of images based on an optical flow frame interpolation method; the judging module is used for judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not; an updating module for updating the interpolated frame image when an interpolation frame quality of the interpolated frame image does not meet a criterion.
In a possible implementation manner, the determining module is specifically configured to: judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights of the interpolation pixel points corresponding to a plurality of mapping pixel points in the two adjacent original frames of images.
In one possible implementation manner, the determining module includes: the first determining submodule is used for determining a first number corresponding to a first type of interpolation pixel points included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel points in the two adjacent original frames of images are all smaller than a first threshold value; a second determination sub-module for determining that the interpolation frame quality of the interpolation frame image does not meet when the first number is larger than a second threshold.
In a possible implementation manner, the determining module is specifically configured to: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one of the two adjacent original frames of images and the pixel quality of the interpolation pixel point in the interpolation frame image.
In one possible implementation manner, the determining module includes: a third determining sub-module, configured to determine, for at least one original image of the two adjacent original images, a second number corresponding to a first type of pixel point included in the at least one original image, where an optical flow value corresponding to the first type of pixel point is greater than a third threshold; a fourth determining submodule, configured to determine a third number corresponding to a first type of interpolation pixel point included in the interpolated frame image, where weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent original frames of images are all smaller than a first threshold; a fifth determination sub-module configured to determine that the interpolation frame quality of the interpolated frame image does not meet when the second number is greater than a fourth threshold and the third number is greater than a fifth threshold.
In a possible implementation manner, the determining module is specifically configured to: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image.
In one possible implementation manner, the determining module includes: a sixth determining submodule, configured to determine, for at least one original image of the two adjacent original images, a fourth number corresponding to a second type of pixel point included in the at least one original image, where the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent original image do not have optical flow consistency; a seventh determining submodule, configured to determine a fifth number corresponding to a first type of interpolation pixel included in the interpolation frame image, where weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel in the two adjacent original frames of images are all smaller than a first threshold; an eighth determination submodule configured to determine that the interpolation frame quality of the interpolation frame image does not meet when the fourth number is larger than a sixth threshold and the fifth number is larger than a seventh threshold.
In a possible implementation manner, the two adjacent frames of original images are a t-th frame of original image and a t + 1-th frame of original image; the second-class pixel points and the second-class pixel points have no optical flow consistency between the mapping pixel points in the original image of the adjacent frame, and the method comprises at least one of the following steps: the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold; the second type pixel points are located in a t +1 th frame original image, and the difference of optical flow absolute values between backward optical flows of the second type pixel points and forward optical flows of mapping pixel points of the second type pixel points in the t th frame original image is larger than the eighth threshold.
In a possible implementation manner, the update module is specifically configured to: and re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other frame interpolation methods except the optical flow frame interpolation method.
In one possible implementation, the update module is further configured to: and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
In one possible implementation, the determining module includes: a ninth determining submodule, configured to determine, based on an optical flow frame interpolation method, for any interpolation pixel in the interpolation frame image, multiple mapping pixels of the interpolation pixel in the two adjacent original images; a tenth determining submodule, configured to determine a weight corresponding to any one of the plurality of mapping pixel points; and the eleventh determining submodule is used for determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
According to a third aspect of the present disclosure, there is provided an apparatus for improving an effect of frame interpolation, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the method for improving the effect of frame interpolation according to the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method for improving the effect of frame insertion according to the first aspect.
After the interpolation frame image between two adjacent original images is determined based on the optical flow interpolation frame method, whether the interpolation frame quality of the interpolation frame image reaches the standard or not is judged, and when the interpolation frame quality of the interpolation frame image does not reach the standard, the interpolation frame image is updated, so that the interpolation frame quality of the interpolation frame image obtained based on the optical flow interpolation frame method can be improved, and the watching experience of a user on a high-frame-rate video obtained after frame interpolation is effectively improved.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flowchart illustrating a method for improving frame interpolation according to an embodiment of the disclosure;
FIG. 2 is a schematic diagram illustrating an optical flow interpolation-based method for determining an interpolated frame image between two adjacent original frames according to an embodiment of the disclosure;
FIG. 3 is a diagram illustrating a method for improving the effect of frame interpolation according to an embodiment of the disclosure;
fig. 4 is a schematic structural diagram illustrating an apparatus for improving an effect of frame interpolation according to an embodiment of the disclosure;
fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. As will be appreciated by those skilled in the art, and/or represents at least one of the connected objects.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
Fig. 1 is a flowchart illustrating a method for improving an effect of frame interpolation according to an embodiment of the disclosure. As shown in fig. 1, the method may include:
in step S11, an interpolated frame image between two adjacent original frames is determined based on the optical flow interpolation method.
In step S12, it is determined whether the interpolation frame quality of the interpolation frame image meets the standard.
In step S13, when the interpolation frame quality of the interpolation frame image does not meet the criterion, the interpolation frame image is updated.
In one possible implementation, determining an interpolated frame image between two adjacent original frames based on an optical flow interpolation method includes: based on an optical flow frame interpolation method, aiming at any interpolation pixel point in an interpolation frame image, determining a plurality of mapping pixel points of the interpolation pixel point in two adjacent original frames of images; determining the weight corresponding to any mapping pixel point in a plurality of mapping pixel points; and determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
Fig. 2 is a schematic diagram illustrating an optical flow frame interpolation-based method for determining an interpolated frame image between two adjacent original frames according to an embodiment of the disclosure.
As shown in fig. 2, based on the optical flow frame interpolation method, a t +0.5 th frame interpolated frame image between a t +1 th frame original image and a t +1 th frame original image is determined, that is, a pixel value corresponding to any interpolated pixel point in the t +0.5 th frame interpolated frame image is determined.
Determining a pixel value corresponding to an interpolation pixel point (i, j) in the t +0.5 th frame interpolation frame image, specifically:
firstly, aiming at an interpolation pixel point (i, j) in an interpolation frame image in a t +0.5 th frame, determining a first mapping point (a, b) of the interpolation pixel point (i, j) in the t +1 th frame original image according to a forward optical flow of the pixel point (i, j) in the t +0.5 th frame original image; determining a second mapping point (c, d) of the interpolation pixel point (i, j) in the t frame original image according to the backward optical flow of the pixel point (i, j) in the t frame original image; determining a third mapping point (e, f) of the interpolation pixel point (i, j) in the t frame original image according to the backward optical flow of the pixel point (i, j) in the t +1 frame original image; determining a fourth mapping point (g, h) of the interpolation pixel point (i, j) in the t +1 frame original image according to the forward optical flow of the pixel point (i, j) in the t +1 frame original image;
next, the weight w corresponding to the first mapping point (a, b) is determined1The weight w corresponding to the second mapping point (c, d)2The weight w corresponding to the third mapping point (e, f)3The weight w corresponding to the fourth mapping point (g, h)4；
Finally, the pixel value corresponding to the interpolation pixel point (i, j) is determined according to the weighted average algorithm
Figure BDA0001891470660000081
Figure BDA0001891470660000082
Wherein the content of the first and second substances,
Figure BDA0001891470660000083
the pixel value corresponding to the first mapping point (a, b),
Figure BDA0001891470660000084
the pixel value corresponding to the second mapping point (c, d),
Figure BDA0001891470660000085
the pixel value corresponding to the third mapping point (e, f),
Figure BDA0001891470660000086
the pixel value corresponding to the fourth mapping point (g, h).
After the interpolation frame image between two adjacent original images is determined based on the optical flow interpolation method, whether the optical flow between the two adjacent original images is accurate cannot be determined, so that whether the interpolation frame quality of the interpolation frame image meets the standard or not needs to be judged in order to ensure that the interpolation frame image can meet the watching requirement of a user.
In one possible implementation, the determining whether the interpolation frame quality of the interpolation frame image meets a standard includes: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of the interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights corresponding to a plurality of mapping pixel points of the interpolation pixel points in two adjacent original frames of images.
The larger the weight corresponding to the mapping pixel point of the interpolation pixel point in the original image of the adjacent frame is, the higher the pixel quality of the interpolation pixel point is obtained based on the optical flow method. The pixel quality of the interpolation pixel points in the interpolation frame image is judged according to the weight corresponding to the mapping point, the interpolation pixel points with the pixel quality not up to the standard in the interpolation frame image can be determined, and whether the interpolation frame image up to the standard is judged effectively.
Fig. 3 is a schematic diagram illustrating a method for improving an effect of frame interpolation according to an embodiment of the disclosure.
As shown in fig. 3, the determination of whether the interpolation frame quality of the interpolation frame image meets the standard according to at least the pixel quality of the interpolation pixel in the interpolation frame image includes, but is not limited to, the following three ways.
The first method comprises the following steps:
in a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of the interpolation pixel point in the interpolation frame image includes: determining a first number corresponding to a first type of interpolation pixel point in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in two adjacent frame original images are all smaller than a first threshold value; when the first number is larger than a second threshold, it is determined that the interpolation frame quality of the interpolation frame image does not meet.
And determining a plurality of mapping points of the interpolation pixel point in the adjacent two frames of original images aiming at any interpolation pixel point in the interpolation frame image, determining the weight corresponding to any mapping point in the plurality of mapping points, and determining the interpolation pixel point as a first type of interpolation pixel point when the weights of the plurality of mapping points are all smaller than a first threshold value.
When the weights corresponding to the plurality of mapping points of the interpolation pixel point in the two adjacent frames of original images are all smaller than the first threshold, the pixel value corresponding to the interpolation pixel point obtained according to the weights corresponding to the plurality of mapping points is inaccurate, that is, the pixel quality of the interpolation pixel point does not reach the standard. The specific value of the first threshold is not limited in this disclosure.
The method comprises the steps of determining a first number corresponding to a first type of pixel points included in an interpolated frame image, and determining that the interpolated frame quality of the interpolated frame image does not meet the standard when the first number is larger than a second threshold, namely when the number of interpolated pixel points with unqualified pixel quality is larger than the second threshold. The specific value of the second threshold is not limited in this disclosure.
For example, the first number of interpolation pixel points of the first type included in the interpolation frame image is N, the second threshold value is N, and when N > N, it may be determined that the interpolation frame quality of the interpolation frame image does not meet the standard.
In an example, the value of the second threshold n may be a first preset proportion of the total number of pixels in the interpolated frame image. For example, if the number of rows of pixels in the interpolated frame image is x, the number of columns in the interpolated frame image is y, and the first predetermined ratio is α, the value of the second threshold n may be α × x × y.
And the second method comprises the following steps:
in a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of the interpolation pixel point in the interpolation frame image includes: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one frame of original image in the two adjacent frames of original images and the pixel quality of the interpolation pixel point in the interpolation frame image.
The larger the optical flow value of a pixel point in an original image is, the larger the motion of a feature point corresponding to the pixel point in an adjacent frame image is, and based on the optical flow value, it is difficult to find a feature point matched with the pixel point in the adjacent frame original image, that is, the optical flow value is inaccurate and cannot be effectively applied to an optical flow frame interpolation process. By comprehensively considering the optical flow values of the pixel points in the original image and the pixel quality of the interpolation pixel points in the interpolation frame image, whether the interpolation frame image obtained based on the optical flow interpolation method reaches the standard or not can be more accurately judged.
In a possible implementation manner, determining whether the interpolation frame quality of the interpolation frame image meets the standard according to the optical flow value of a pixel point in at least one of the two adjacent original frames and the pixel quality of the interpolation pixel point in the interpolation frame image includes: determining a second number corresponding to a first type of pixel points included in at least one frame of original image aiming at least one frame of original image in two adjacent frames of original images, wherein the optical flow value corresponding to the first type of pixel points is greater than a third threshold value; determining a third number corresponding to a first type of interpolation pixel point in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in two adjacent frame original images are all smaller than a first threshold value; when the second number is greater than a fourth threshold value and the third number is greater than a fifth threshold value, it is determined that the interpolation frame quality of the interpolation frame image does not meet.
In an example, after a t +0.5 th frame interpolated frame image between a t frame original image and a t +1 th frame original image is determined based on an optical flow interpolation frame method, a forward optical flow value corresponding to any pixel point in the t frame original image is determined, and a pixel point of which the forward optical flow value is greater than a third threshold value is determined as a first-class pixel point.
For example, if the forward optical flow corresponding to the pixel point (i, j) in the original image of the t-th frame is (2,3), the forward optical flow value corresponding to the pixel point (i, j) is (2,3)
Figure BDA0001891470660000101
In an example, after the t +0.5 th frame interpolated frame image between the t +1 th frame original image and the t +1 th frame original image is determined based on an optical flow interpolation method, whether a backward optical flow value corresponding to any pixel point in the t +1 th frame original image is greater than a third threshold value or not is determined, and a pixel point of which the backward optical flow value is greater than the third threshold value is determined as a first-class pixel point.
For example, if the forward optical flow corresponding to the pixel point (i, j) in the t +1 th frame of the original image is (-4, -3), the forward optical flow value corresponding to the pixel point (i, j) is
Figure BDA0001891470660000102
When the optical flow value of the pixel point is greater than the third threshold, the pixel point can be considered as a pixel point corresponding to the fast motion feature point, that is, the first-class pixel points are all pixel points corresponding to the fast motion feature point. Because the characteristic points move quickly, the first-class pixel points are difficult to find the correct mapping points in the original images of the adjacent frames, namely, the optical flow values corresponding to the first-class pixel points are inaccurate. The specific value of the third threshold is not limited in this disclosure.
And determining a second number corresponding to the first type of pixel points in at least one of the two adjacent frames of original images, namely determining a second number corresponding to pixel points with inaccurate optical flow values. And determining a third number corresponding to the first type of pixel points in the interpolated frame image between the two adjacent frames of original images determined based on the optical flow method, namely determining the third number corresponding to the interpolated pixel points with unqualified pixel quality.
When the second number is greater than the fourth threshold and the third number is greater than the fifth threshold, that is, when the number of pixels whose optical flow values are inaccurate is greater than the fourth threshold and the number of interpolation pixels whose pixel quality does not meet the standard is greater than the fifth threshold, it may be determined that the interpolation frame quality of the interpolation frame image does not meet the standard. The specific values of the fourth threshold and the fifth threshold are not limited in the present disclosure.
For example, the second number of the first type of pixel point correspondences included in at least one of the two adjacent original images is M, the first number of the first type of interpolation pixel point correspondences included in the interpolation frame image between the two adjacent original images is N, the fourth threshold is M, the fifth threshold is N ', and when M > M and N > N', it may be determined that the interpolation frame quality of the interpolation frame image does not meet the standard.
In an example, the value of the fourth threshold m may be a second preset proportion of the total number of pixels in at least one of the two adjacent original images. For example, in any frame of original image, the number of rows is x, the number of columns is y, and the second predetermined ratio is β. When the second number is the number corresponding to the first type of pixel point in any one of the two adjacent original images, the value of the fourth threshold value m may be β x y; when the second number is the number corresponding to all the first type pixel points in the two adjacent frames of original images, the value of the fourth threshold m may be 2 × β × x × y.
In an example, the value of the fifth threshold n' may be a third preset proportion of the total number of pixels in the interpolated frame image. For example, if the number of rows of pixels in the interpolated frame image is x, the number of columns is y, and the third predetermined ratio is δ, the value of the fifth threshold n' may be δ x y. The first preset ratio α and the third preset ratio δ may be the same or different, and the disclosure is not particularly limited.
In an example, the value of the fifth threshold n' may be a fourth preset proportion of the second number corresponding to the first type of pixel point. For example, if the second number of the first-type pixel points included in at least one of the two adjacent frames of original images is M, and the fourth preset proportion is γ, the value of the fifth threshold n' may be γ × M.
And the third is that:
in a possible implementation manner, the determining whether the interpolation frame quality of the interpolation frame image meets the standard at least according to the pixel quality of the interpolation pixel point in the interpolation frame image includes: and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original frames of images and the pixel quality of the interpolation pixel points in the interpolation frame image.
In the optical flow frame interpolation process, if the optical flow quality is poor, it is difficult to obtain an interpolated frame image with the standard interpolated frame quality. And judging the consistency of the optical flow between two adjacent original images, and determining whether the optical flow quality in the optical flow frame interpolation process meets the requirement. By comprehensively considering the consistency of optical flows between the original images of the adjacent frames and the pixel quality of the interpolation pixel points in the interpolation frame image, whether the interpolation frame image obtained based on the optical flow interpolation method reaches the standard or not can be more accurately judged.
In a possible implementation manner, determining whether the interpolation frame quality of the interpolation frame image meets the standard according to the optical flow consistency between two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image includes: determining a fourth number corresponding to a second type of pixel point included in at least one frame of original image in the two adjacent frames of original images, wherein the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent frames of original images do not have optical flow consistency; determining a fifth number corresponding to a first type of interpolation pixel points included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel points in two adjacent original frames of images are all smaller than a first threshold value; when the fourth number is larger than a sixth threshold and the fifth number is larger than a seventh threshold, it is determined that the interpolation frame quality of the interpolation frame image does not meet.
In the process of judging whether the interpolation frame quality of an interpolation frame image between two adjacent original images reaches the standard, at least judging the optical flow consistency between the two adjacent original images, namely judging whether the optical flow consistency exists between any pixel point in at least one original image in the two adjacent original images and a mapping pixel point of the pixel point in the adjacent original image, and if the optical flow consistency does not exist, determining the pixel point as a second type of pixel point.
In a possible implementation manner, two adjacent frames of original images are a t-th frame of original image and a t + 1-th frame of original image; the second-class pixel points and the second-class pixel points do not have optical flow consistency between the mapping pixel points in the adjacent frame original image, and the method comprises at least one of the following steps: the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold; the second type pixel points are located in the t +1 th frame original image, and the difference of the optical flow absolute values between the backward optical flows of the second type pixel points and the forward optical flows of the mapping pixel points of the second type pixel points in the t th frame original image is larger than an eighth threshold.
For example, the two adjacent frames of original images are the 2 nd frame of original image and the 3 rd frame of original image:
aiming at pixel points (u, v) in the 2 nd frame original image, determining forward optical flows (vx-a, vy-a) of the pixel points (u, v); determining a mapping pixel point (i + vx-a, j + vy-b) of the pixel point (u, v) in a 3 rd frame original image according to the forward optical flows (vx-a, vy-a) of the pixel point (u, v); determining a backward optical flow (vx-b, vy-b) of the mapping pixel point (i + vx-a, j + vy-b); determining the difference s between the absolute values of the forward optical flow (vx-a, vy-a) and the backward optical flow (vx-b, vy-b) whensWhen the pixel point (u, v) in the 2 nd frame original image is larger than the eighth threshold, the pixel point (u, v) in the 2 nd frame original image can be determined as a second type pixel point; and/or the presence of a gas in the gas,
determining backward optical flows (vx-c, vy-c) of the pixel points (p, q) aiming at the pixel points (p, q) in the 3 rd frame original image; determining a mapping pixel point (x + vx-c, y + vy-c) of the pixel point (p, q) in the 2 nd frame original image according to the backward optical flows (vx-c, vy-c) of the pixel point (p, q); determining a forward optical flow (vx-d, vy-d) of the mapping pixel point (x + vx-c, y + vy-c); and determining the difference k between the absolute values of the backward optical flow (vx-c, vy-c) and the forward optical flow (vx-d, vy-d), and when k is larger than an eighth threshold, determining the pixel points (p, q) in the 3 rd frame original image as the second type pixel points. The specific value of the eighth threshold is not limited in this disclosure.
In a possible implementation manner, the step of the second-type pixel point and the second-type pixel point having no optical flow consistency between the mapped pixel points in the original image of the adjacent frame may further include: the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the backward optical flow of the second type pixel points and the forward optical flow of the mapping pixel points of the second type pixel points in the t-1 frame original image is larger than an eighth threshold; the second type pixel points are located in the t +1 th frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +2 th frame original image is larger than an eighth threshold value.
And determining the fourth number corresponding to the pixel points of the second type in at least one of the two adjacent frames of original images, namely determining the fourth number corresponding to the pixel points without optical flow consistency. And determining a fifth number corresponding to the first type of pixel points in the interpolated frame image between the two adjacent frames of original images determined based on the optical flow method, namely determining the fifth number corresponding to the interpolated pixel points with unqualified pixel quality.
When the fourth number is greater than the sixth threshold and the fifth number is greater than the seventh threshold, that is, when the number of pixel points having no optical flow consistency is greater than the sixth threshold and the number of interpolation pixel points having pixel quality that does not meet the standard is greater than the seventh threshold, it may be determined that the interpolation frame quality of the interpolation frame image does not meet the standard. The specific values of the seventh threshold and the eighth threshold are not limited in this disclosure.
For example, the fourth number corresponding to the second type of pixel points included in at least one of the two adjacent original images is R, the first number corresponding to the first type of interpolation pixel points included in the interpolation frame image between the two adjacent original images is N, the sixth threshold is R, the seventh threshold is N '", and when R > R and N > N'", it may be determined that the interpolation frame quality of the interpolation frame image does not meet the standard.
In an example, the value of the sixth threshold r may be a fifth preset proportion of the total number of pixels in at least one of the two adjacent original images. For example, in any frame of original image, the number of rows is x, the number of columns is y, and the fifth predetermined ratio is σ. When the fourth number R is the number corresponding to the second type of pixel points in any one of the two adjacent original images, the value of the sixth threshold R may be σ x y; when the fourth number is the number corresponding to all the second-type pixel points in the two adjacent original images, the value of the sixth threshold r may be 2 × σ × x × y.
In an example, the value of the seventh threshold n' "may be a sixth preset proportion of the total number of pixels in the interpolated frame image. For example, if the number of rows of pixels in the interpolated frame image is x, the number of columns is y, and the sixth predetermined ratio is η, the value of the seventh threshold n' ″ may be η × x × y. The first preset ratio α and the sixth preset ratio η may be the same or different, and the disclosure is not limited specifically.
In an example, the value of the seventh threshold n' "may be a seventh preset proportion of the second number corresponding to the first type of pixel point. For example, the second number of the first type of pixel points included in at least one of the two adjacent frames of original images is M, and the seventh preset proportion is μ, then the value of the seventh threshold n' "may be μ × M. The fourth preset proportion γ and the seventh preset proportion μmay be the same or different, and the disclosure is not particularly limited.
The three methods for determining whether the interpolation frame quality of the interpolation frame image meets the standard may be used alone or in combination, and this disclosure is not limited in this respect.
Still taking the above-mentioned fig. 3 as an example, after determining whether the interpolation frame quality of the interpolation frame image reaches the standard, the interpolation frame image is updated according to the determination result, so as to improve the interpolation effect of the interpolation frame image.
When it is determined that the interpolation frame quality of the interpolation frame image does not meet the standard, the interpolation frame image needs to be updated in order to ensure the user's viewing effect on the high frame rate video after the interpolation frame.
In one possible implementation, updating the interpolated frame image when the interpolated frame image does not meet the criterion, includes: and re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other frame interpolation methods except the optical flow frame interpolation method.
That is, when the interpolation frame quality of the interpolation frame image does not meet the criterion, the pixel values corresponding to all the interpolation pixel points in the interpolation frame image are updated.
In one possible implementation manner, the method further includes: and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
That is, when the interpolation frame quality of the interpolation frame image meets the standard, the pixel values corresponding to part of the interpolation pixel points (first-class interpolation pixel points) in the interpolation frame image are updated.
In an example, for an interpolation pixel point that needs to be updated in an interpolation frame image, a pixel value corresponding to the interpolation pixel point may be obtained in a fusion manner according to a pixel value corresponding to a pixel point in an original image of an adjacent frame that has the same coordinate position as the interpolation pixel point.
For example, the pixel value corresponding to the interpolation pixel point (i, j) in the frame image of the t +0.5 th frame is updated by the following formula
Figure BDA0001891470660000151
Figure BDA0001891470660000152
Wherein the content of the first and second substances,
Figure BDA0001891470660000153
is the pixel value corresponding to the pixel point (i, j) in the original image of the t-th frame,
Figure BDA0001891470660000154
and the pixel value is the pixel value corresponding to the pixel point (i, j) in the original image of the t +1 th frame.
In an example, for an interpolation pixel point that needs to be updated in an interpolation frame image, a pixel value corresponding to the interpolation pixel point may be obtained in a repeated manner according to a pixel value corresponding to a pixel point in an original image of an adjacent frame that has the same coordinate position as the interpolation pixel point.
For example, the pixel value corresponding to the interpolation pixel point (i, j) in the frame image of the t +0.5 th frame is updated by the following formula
Figure BDA0001891470660000161
Figure BDA0001891470660000162
Or the like, or, alternatively,
Figure BDA0001891470660000163
after the interpolation frame image between two adjacent original images is determined based on the optical flow interpolation frame method, whether the interpolation frame quality of the interpolation frame image reaches the standard or not is judged, and when the interpolation frame quality of the interpolation frame image does not reach the standard, the interpolation frame image is updated, so that the interpolation frame quality of the interpolation frame image obtained based on the optical flow interpolation frame method can be improved, and the watching experience of a user on a high-frame-rate video obtained after frame interpolation is effectively improved.
Fig. 4 is a schematic structural diagram illustrating an apparatus for improving an effect of frame interpolation according to an embodiment of the disclosure. The apparatus 40 shown in fig. 4 may be used to perform the steps of the above-described method embodiment shown in fig. 1, the apparatus 40 comprising:
a determining module 41, configured to determine an interpolated frame image between two adjacent original frames based on an optical flow frame interpolation method;
a judging module 42, configured to judge whether an interpolation frame quality of the interpolation frame image meets a standard;
an updating block 43 for updating the interpolated frame image when the interpolated frame quality of the interpolated frame image does not meet a criterion.
In one possible implementation, the determining module 42 is specifically configured to:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of the interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights corresponding to a plurality of mapping pixel points of the interpolation pixel points in two adjacent original frames of images.
In one possible implementation, the determining module 42 includes:
the first determining submodule is used for determining a first number corresponding to a first type of interpolation pixel points included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel points in two adjacent frame original images are all smaller than a first threshold value;
a second determination sub-module for determining that the interpolation frame quality of the interpolated frame image does not meet when the first number is larger than a second threshold.
In one possible implementation, the determining module 42 is specifically configured to:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one frame of original image in the two adjacent frames of original images and the pixel quality of the interpolation pixel point in the interpolation frame image.
In one possible implementation, the determining module 42 includes:
the third determining submodule is used for determining a second number corresponding to the first type of pixel points in at least one frame of original image in two adjacent frames of original images, wherein the optical flow value corresponding to the first type of pixel points is larger than a third threshold value;
the fourth determining submodule is used for determining a third number corresponding to the first type of interpolation pixel points in the interpolation frame image, wherein the weights corresponding to the first type of interpolation pixel points in a plurality of mapping pixel points in two adjacent frame original images are all smaller than a first threshold value;
a fifth determination sub-module for determining that the interpolation frame quality of the interpolated frame image does not meet when the second number is greater than the fourth threshold and the third number is greater than the fifth threshold.
In one possible implementation, the determining module 42 is specifically configured to:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original frames of images and the pixel quality of the interpolation pixel points in the interpolation frame image.
In one possible implementation, the determining module 42 includes:
a sixth determining submodule, configured to determine, for at least one of the two adjacent original images, a fourth number corresponding to a second type of pixel point included in the at least one original image, where the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent original image do not have optical flow consistency;
a seventh determining submodule, configured to determine a fifth number corresponding to first-class interpolation pixel points included in the interpolated frame image, where weights corresponding to a plurality of mapping pixel points of the first-class interpolation pixel points in two adjacent original frames of images are all smaller than a first threshold;
an eighth determining sub-module for determining that the interpolation frame quality of the interpolated frame image does not meet when the fourth number is larger than the sixth threshold and the fifth number is larger than the seventh threshold.
In a possible implementation manner, two adjacent frames of original images are a t-th frame of original image and a t + 1-th frame of original image;
the second-class pixel points and the second-class pixel points do not have optical flow consistency between the mapping pixel points in the adjacent frame original image, and the method comprises at least one of the following steps:
the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold;
the second type pixel points are located in the t +1 th frame original image, and the difference of the optical flow absolute values between the backward optical flows of the second type pixel points and the forward optical flows of the mapping pixel points of the second type pixel points in the t th frame original image is larger than an eighth threshold.
In a possible implementation manner, the updating module 43 is specifically configured to:
and re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other frame interpolation methods except the optical flow frame interpolation method.
In one possible implementation, the updating module 43 is further configured to:
and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
In one possible implementation, the determining module 41 includes:
a ninth determining submodule, configured to determine, based on an optical flow frame interpolation method, for any interpolation pixel in the interpolation frame image, a plurality of mapping pixels of the interpolation pixel in two adjacent original images;
a tenth determining submodule, configured to determine a weight corresponding to any one of the plurality of mapping pixel points;
and the eleventh determining submodule is used for determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
The apparatus 40 provided in the present disclosure can implement each step in the method embodiment shown in fig. 1, and implement the same technical effect, and is not described herein again to avoid repetition.
Fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, at the hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
And a memory for storing the program. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program, and the device for improving the frame insertion effect is formed on the logic level. And a processor executing the program stored in the memory and specifically executing the steps of the embodiment of the method shown in fig. 1.
The method described above with reference to fig. 1 may be applied in or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may execute the method executed in the method embodiment shown in fig. 1, and implement the functions of the method embodiment shown in fig. 1, which are not described herein again in this specification.
The present specification also proposes a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to execute the method for improving the frame insertion effect in the embodiment shown in fig. 1, and specifically execute the steps in the embodiment of the method shown in fig. 1.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (22)

1. A method for improving frame interpolation, comprising:
determining an interpolation frame image between two adjacent original frames of images based on an optical flow frame interpolation method;
judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not;
and when the interpolation frame quality of the interpolation frame image does not meet the standard, re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other interpolation frame methods except the optical flow interpolation frame method.
2. The method of claim 1, wherein determining whether the interpolation frame quality of the interpolated frame image meets a criterion comprises:
judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights of the interpolation pixel points corresponding to a plurality of mapping pixel points in the two adjacent original frames of images.
3. The method of claim 2, wherein determining whether the interpolation frame image meets the interpolation quality at least according to the pixel quality of the interpolation pixel points in the interpolation frame image comprises:
determining a first number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent frame original images are all smaller than a first threshold value;
when the first number is larger than a second threshold, it is determined that the interpolation frame quality of the interpolation frame image does not meet.
4. The method of claim 2, wherein determining whether the interpolation frame image meets the interpolation quality at least according to the pixel quality of the interpolation pixel points in the interpolation frame image comprises:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one of the two adjacent original frames of images and the pixel quality of the interpolation pixel point in the interpolation frame image.
5. The method of claim 4, wherein determining whether the interpolation frame quality of the interpolation frame image meets the criterion according to the optical flow value of the pixel point in at least one of the two adjacent original images and the pixel quality of the interpolation pixel point in the interpolation frame image comprises:
determining a second number corresponding to a first type of pixel points included in at least one frame of original image in the two adjacent frames of original images, wherein optical flow values corresponding to the first type of pixel points are greater than a third threshold value;
determining a third number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent frame original images are all smaller than a first threshold value;
when the second number is greater than a fourth threshold and the third number is greater than a fifth threshold, determining that the interpolation frame quality of the interpolation frame image does not meet.
6. The method of claim 2, wherein determining whether the interpolation frame image meets the interpolation quality at least according to the pixel quality of the interpolation pixel points in the interpolation frame image comprises:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image.
7. The method of claim 6, wherein determining whether the interpolation frame quality of the interpolation frame image meets the standard according to the optical flow consistency between the two adjacent original images and the pixel quality of the interpolation pixel point in the interpolation frame image comprises:
determining a fourth number corresponding to a second type of pixel point included in at least one frame of original image in the two adjacent frames of original images, wherein the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent frames of original images do not have optical flow consistency;
determining a fifth number corresponding to a first type of interpolation pixel point included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent original frames of images are all smaller than a first threshold value;
when the fourth number is greater than a sixth threshold and the fifth number is greater than a seventh threshold, determining that the interpolation frame quality of the interpolated frame image does not meet.
8. The method according to claim 7, wherein the two adjacent frames of original images are a t frame of original image and a t +1 frame of original image;
the second-class pixel points and the second-class pixel points have no optical flow consistency between the mapping pixel points in the original image of the adjacent frame, and the method comprises at least one of the following steps:
the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold;
the second type pixel points are located in a t +1 th frame original image, and the difference of optical flow absolute values between backward optical flows of the second type pixel points and forward optical flows of mapping pixel points of the second type pixel points in the t th frame original image is larger than the eighth threshold.
9. The method of claim 3, 5 or 7, further comprising:
and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
10. The method of claim 1, wherein determining an interpolated frame image between two adjacent original frames based on optical flow interpolation comprises:
based on an optical flow frame interpolation method, aiming at any interpolation pixel point in the interpolation frame image, determining a plurality of mapping pixel points of the interpolation pixel point in the two adjacent original frames of images;
determining the weight corresponding to any mapping pixel point in the plurality of mapping pixel points;
and determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
11. An apparatus for improving the effect of frame interpolation, comprising:
the determination module is used for determining an interpolation frame image between two adjacent original frames of images based on an optical flow frame interpolation method;
the judging module is used for judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not;
and the updating module is used for re-determining the pixel value corresponding to any interpolation pixel point in the interpolation frame image based on other interpolation methods except the optical flow interpolation method when the interpolation frame quality of the interpolation frame image does not meet the standard.
12. The apparatus according to claim 11, wherein the determining module is specifically configured to:
judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not at least according to the pixel quality of interpolation pixel points in the interpolation frame image, wherein the pixel quality is related to the weights of the interpolation pixel points corresponding to a plurality of mapping pixel points in the two adjacent original frames of images.
13. The apparatus of claim 12, wherein the determining module comprises:
the first determining submodule is used for determining a first number corresponding to a first type of interpolation pixel points included in the interpolation frame image, wherein the weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel points in the two adjacent original frames of images are all smaller than a first threshold value;
a second determination sub-module for determining that the interpolation frame quality of the interpolation frame image does not meet when the first number is larger than a second threshold.
14. The apparatus of claim 12, wherein the determining module is specifically configured to:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the optical flow value of a pixel point in at least one of the two adjacent original frames of images and the pixel quality of the interpolation pixel point in the interpolation frame image.
15. The apparatus of claim 14, wherein the determining module comprises:
a third determining sub-module, configured to determine, for at least one original image of the two adjacent original images, a second number corresponding to a first type of pixel point included in the at least one original image, where an optical flow value corresponding to the first type of pixel point is greater than a third threshold;
a fourth determining submodule, configured to determine a third number corresponding to a first type of interpolation pixel point included in the interpolated frame image, where weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel point in the two adjacent original frames of images are all smaller than a first threshold;
a fifth determination sub-module configured to determine that the interpolation frame quality of the interpolated frame image does not meet when the second number is greater than a fourth threshold and the third number is greater than a fifth threshold.
16. The apparatus of claim 12, wherein the determining module is specifically configured to:
and judging whether the interpolation frame quality of the interpolation frame image reaches the standard or not according to the consistency of the optical flows between the two adjacent original images and the pixel quality of an interpolation pixel point in the interpolation frame image.
17. The apparatus of claim 16, wherein the determining module comprises:
a sixth determining submodule, configured to determine, for at least one original image of the two adjacent original images, a fourth number corresponding to a second type of pixel point included in the at least one original image, where the second type of pixel point and a mapping pixel point of the second type of pixel point in the adjacent original image do not have optical flow consistency;
a seventh determining submodule, configured to determine a fifth number corresponding to a first type of interpolation pixel included in the interpolation frame image, where weights corresponding to a plurality of mapping pixel points of the first type of interpolation pixel in the two adjacent original frames of images are all smaller than a first threshold;
an eighth determination submodule configured to determine that the interpolation frame quality of the interpolation frame image does not meet when the fourth number is larger than a sixth threshold and the fifth number is larger than a seventh threshold.
18. The apparatus according to claim 17, wherein the two adjacent frames of original images are a t frame of original image and a t +1 frame of original image;
the second-class pixel points and the second-class pixel points have no optical flow consistency between the mapping pixel points in the original image of the adjacent frame, and the method comprises at least one of the following steps:
the second type pixel points are positioned in the t frame original image, and the difference of the optical flow absolute values between the forward optical flows of the second type pixel points and the backward optical flows of the mapping pixel points of the second type pixel points in the t +1 frame original image is larger than an eighth threshold;
the second type pixel points are located in a t +1 th frame original image, and the difference of optical flow absolute values between backward optical flows of the second type pixel points and forward optical flows of mapping pixel points of the second type pixel points in the t th frame original image is larger than the eighth threshold.
19. The apparatus of any one of claims 13, 15 or 17, wherein the update module is further configured to:
and when the interpolation frame quality of the interpolation frame image reaches the standard and the interpolation frame image comprises the first-class interpolation pixel points, re-determining the pixel values corresponding to the first-class interpolation pixel points based on other interpolation frame methods except the optical flow interpolation frame method.
20. The apparatus of claim 11, wherein the determining module comprises:
a ninth determining submodule, configured to determine, based on an optical flow frame interpolation method, for any interpolation pixel in the interpolation frame image, multiple mapping pixels of the interpolation pixel in the two adjacent original images;
a tenth determining submodule, configured to determine a weight corresponding to any one of the plurality of mapping pixel points;
and the eleventh determining submodule is used for determining the pixel value corresponding to the interpolation pixel point according to the weight and the pixel value corresponding to any mapping pixel point.
21. An apparatus for improving the effect of frame interpolation, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method of improving the effect of frame interpolation of any one of claims 1-10.
22. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method for improving the effect of frame insertion according to any one of claims 1 to 10.
CN201811473025.8A 2018-12-04 2018-12-04 Method and device for improving frame interpolation effect Active CN111277780B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811473025.8A CN111277780B (en) 2018-12-04 2018-12-04 Method and device for improving frame interpolation effect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811473025.8A CN111277780B (en) 2018-12-04 2018-12-04 Method and device for improving frame interpolation effect

Publications (2)

Publication Number Publication Date
CN111277780A CN111277780A (en) 2020-06-12
CN111277780B true CN111277780B (en) 2021-07-20

Family

ID=71001296

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811473025.8A Active CN111277780B (en) 2018-12-04 2018-12-04 Method and device for improving frame interpolation effect

Country Status (1)

Country Link
CN (1) CN111277780B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114071223A (en) * 2020-07-30 2022-02-18 武汉Tcl集团工业研究院有限公司 Optical flow-based video interpolation frame generation method, storage medium and terminal equipment
CN114286126A (en) * 2020-09-28 2022-04-05 阿里巴巴集团控股有限公司 Video processing method and device
CN113837136B (en) * 2021-09-29 2022-12-23 深圳市慧鲤科技有限公司 Video frame insertion method and device, electronic equipment and storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102779268A (en) * 2012-02-06 2012-11-14 西南科技大学 Hand swing motion direction judging method based on direction motion historigram and competition mechanism

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7119837B2 (en) * 2002-06-28 2006-10-10 Microsoft Corporation Video processing system and method for automatic enhancement of digital video
JP2008244846A (en) * 2007-03-27 2008-10-09 Toshiba Corp Device and method for interpolating frame
US20090052532A1 (en) * 2007-08-24 2009-02-26 Simon Robinson Automatically identifying edges of moving objects
US8730268B2 (en) * 2010-02-05 2014-05-20 Arizona Board Of Regents, A Body Corporate Of The State Of Arizona, Acting For And On Behalf Of Arizona State University Image processing systems and methods
CN105517671B (en) * 2015-05-25 2020-08-14 北京大学深圳研究生院 Video frame interpolation method and system based on optical flow method
CN106878704A (en) * 2017-02-14 2017-06-20 福建师范大学 Turn altering detecting method on video frame rate based on light stream cyclophysis
CN108347549B (en) * 2018-02-26 2020-11-10 华东理工大学 Method for improving video jitter based on time consistency of video frames

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102779268A (en) * 2012-02-06 2012-11-14 西南科技大学 Hand swing motion direction judging method based on direction motion historigram and competition mechanism

Also Published As

Publication number Publication date
CN111277780A (en) 2020-06-12

Similar Documents

Publication Publication Date Title
CN111277895B (en) Video frame interpolation method and device
CN111277780B (en) Method and device for improving frame interpolation effect
US8810692B2 (en) Rolling shutter distortion correction
CN109035158B (en) Image blurring processing method, image blurring processing device, storage medium and electronic equipment
WO2021179826A1 (en) Image processing method and related product
CN109377508B (en) Image processing method and device
US20200372614A1 (en) Image/video deblurring using convolutional neural networks with applications to sfm/slam with blurred images/videos
CN108989804B (en) Image coding method and device
EP2938064B1 (en) Method and apparatus for determining exposure setting
CN111415371B (en) Sparse optical flow determination method and device
US11336826B2 (en) Method and apparatus having a function of constant automatic focusing when exposure changes
CN110213479B (en) Anti-shake method and device for video shooting
CN103702032A (en) Image processing method, device and terminal equipment
CN112272832A (en) Method and system for DNN-based imaging
CN110874809A (en) Image processing method and device, electronic equipment and storage medium
WO2023019870A1 (en) Video processing method and apparatus, electronic device, storage medium, computer program, and computer program product
US11902571B2 (en) Region of interest (ROI)-based upscaling for video conferences
CN111277863B (en) Optical flow frame interpolation method and device
CN112464301A (en) Image display method and device
CN111277815A (en) Method and device for evaluating quality of inserted frame
CN110689565B (en) Depth map determination method and device and electronic equipment
CN111126372A (en) Method and device for marking logo area in video and electronic equipment
CN113810755B (en) Panoramic video preview method and device, electronic equipment and storage medium
CN107818584B (en) Method and device for determining finger position information of user, projector and projection system
CN109308690B (en) Image brightness balancing method and terminal

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant