CN111970518B - Image frame loss processing method, system, equipment and computer storage medium - Google Patents
Image frame loss processing method, system, equipment and computer storage medium Download PDFInfo
- Publication number
- CN111970518B CN111970518B CN202010820073.0A CN202010820073A CN111970518B CN 111970518 B CN111970518 B CN 111970518B CN 202010820073 A CN202010820073 A CN 202010820073A CN 111970518 B CN111970518 B CN 111970518B
- Authority
- CN
- China
- Prior art keywords
- image
- captured
- captured image
- sampling
- similarity value
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The application discloses an image frame loss processing method, system, device and computer medium, which is used for obtaining an image data set to be frame lost; selecting two adjacent frames of images in the image data set; taking a former frame image in two adjacent frame images as a reference image, and taking a latter frame image in the two adjacent frame images as a captured image; judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is reserved, and the step of selecting two adjacent frames of images in the image data set is returned. In the method, whether the next frame of image is discarded or not is determined based on the similarity degree between two adjacent frames of images, so that the content of the next frame of image can be reflected by the previous frame of image, and the influence of the discarded image on the quality of the original image can be reduced.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, a system, a device, and a computer storage medium for processing an image frame loss.
Background
In the current information society, with the rapid development of communication, network and microelectronic technologies, digital image products are more and more abundant, which brings convenience and richness to life. Meanwhile, the data of the video image is larger and larger, the image has spatial redundancy between adjacent pixels, human vision has visual redundancy for some insensitive images, and the storage space required by the image can be greatly reduced by removing the redundancy. Video image compression is of great importance for both storage and transmission of data. When video image data is transmitted, due to the limitation of network bandwidth, almost all video data transmission under the protocol has frame loss processing. In the fixed frame dropping algorithm per second adopted in the prior art, the phenomenon that redundant data information still exists can occur, especially for a continuous video image source, and the image quality after frame dropping is poor.
In view of the above, how to reduce the influence of frame loss on image quality is a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The application aims to provide an image frame loss processing method which can solve the technical problem of reducing the influence of frame loss on image quality to a certain extent. The application also provides an image frame loss processing system, equipment and a computer readable storage medium.
In order to achieve the above purpose, the present application provides the following technical solutions:
an image loss frame processing method comprises the following steps:
acquiring an image data set to be subjected to frame loss;
selecting two adjacent frames of images in the image data set;
taking a former frame image in two adjacent frame images as a reference image, and taking a latter frame image in the two adjacent frame images as a captured image;
determining whether the reference image is similar to the captured image;
if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image dataset;
if the reference image is not similar to the captured image, the captured image is reserved, and the step of selecting two adjacent frames of images in the image data set is executed in a returning mode.
Preferably, the determining whether the reference image is similar to the captured image includes:
and calculating a target similarity value of the reference image and the captured image, and judging whether the reference image and the captured image are similar or not based on the target similarity value.
Preferably, the calculating a target similarity value between the reference image and the captured image, and determining whether the reference image and the captured image are similar based on the target similarity value, includes:
sampling the reference image for one time to obtain a reference sampling image;
sampling the captured image for one time to obtain a captured sampled image;
calculating a current similarity value of the reference sample image and the captured sample image;
acquiring historical similarity values of the reference sampling image and the capture sampling image obtained by historical calculation;
determining the target similarity value based on the current similarity value and the historical similarity value;
judging whether the target similarity value is smaller than a preset value or not;
if the target similarity value is smaller than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are smaller than a preset sampling value, if so, returning to the step of performing primary sampling on the reference image to obtain a reference sampling image, and if not, judging that the reference image is not similar to the captured image;
and if the target similarity value is larger than or equal to the preset value, judging that the reference image is similar to the captured image.
Preferably, the determining the target similarity value based on the current similarity value and the historical similarity value includes:
and determining the target similarity value based on the current similarity value, the weight of the current similarity value, the historical similarity values and the weights of the historical similarity values.
Preferably, the sampling method for sampling the reference image and the captured image includes random sampling or equidistant sampling.
Preferably, the step of discarding the captured image and returning to the step of selecting two adjacent frames of images in the image data set includes:
discarding the captured image;
keeping the reference image unchanged, and taking the next frame image of the captured image as the captured image;
returning to the step of judging whether the reference image is similar to the captured image;
the step of retaining the captured image and returning to the step of selecting two adjacent frames of images in the image data set comprises:
taking the captured image as the reference image;
taking a next frame image of the reference image as the captured image;
and returning to execute the step of judging whether the reference image is similar to the captured image.
Preferably, the step of setting an image of a frame next to the captured image as the captured image while keeping the reference image unchanged includes:
accumulating the real-time number of the captured images discarded without changing the reference image;
judging whether the real-time quantity is smaller than a preset quantity or not;
and if the real-time number is smaller than the preset number, taking the next frame image of the captured image as the captured image.
An image drop frame processing system, comprising:
the first acquisition module is used for acquiring an image data set to be subjected to frame loss;
the first selection module is used for selecting two adjacent frames of images in the image data set;
the first setting module is used for taking the previous frame image in the two adjacent frame images as a reference image and taking the next frame image in the two adjacent frame images as a captured image;
a first judgment module for judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and prompting the first selection module to execute the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is retained, and the first selection module is prompted to execute the step of selecting two adjacent frames of images in the image data set.
An image drop frame processing apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the image frame loss processing method as described above when executing the computer program.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the image drop frame processing method as set forth in any one of the above.
The image frame loss processing method provided by the application obtains an image data set to be frame lost; selecting two adjacent frames of images in the image data set; taking a previous frame image in two adjacent frame images as a reference image, and taking a next frame image in the two adjacent frame images as a captured image; judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is retained, and the step of selecting two adjacent frames of images in the image data set is returned to be executed. In the method, whether the next frame of image is discarded or not is determined based on the similarity degree between two adjacent frames of images, so that even if the next frame of image is discarded, because the next frame of image is similar to the previous frame of image, the content of the next frame of image can also be reflected by the previous frame of image, namely the frame discarding method can reduce the influence of the discarded image on the quality of the original image. The image frame loss processing system, the image frame loss processing equipment and the computer readable storage medium solve the corresponding technical problems.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an image frame loss processing method according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of similarity determination between a reference image and a captured image;
fig. 3 is a schematic structural diagram of an image frame loss processing system according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an image frame loss processing device according to an embodiment of the present application;
fig. 5 is another schematic structural diagram of an image frame loss processing device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of an image frame loss processing method according to an embodiment of the present disclosure.
An image frame loss processing method provided by the embodiment of the application can include the following steps:
step S101: and acquiring an image data set to be subjected to frame loss.
In practical application, an image data set with frame loss may be obtained first, that is, the image data set is a data set that needs to be processed by frame loss. The content of the image data set may be determined according to actual needs, for example, the image data set may be a data set obtained by splitting an image of a target video.
Step S102: two adjacent frames of images are selected in the image dataset.
Step S103: and taking the former frame image of the two adjacent frame images as a reference image, and taking the latter frame image of the two adjacent frame images as a captured image.
In practical application, after an image data set to be subjected to frame loss is acquired, two adjacent frames of images can be selected from the image data set, a former frame of image in the two adjacent frames of images is taken as a reference image, a latter frame of image in the two adjacent frames of images is taken as a captured image, and a frame loss processing mode of the image data set is determined according to the reference image and the captured image.
Step S104: judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, performing step S105; if the reference image is not similar to the captured image, step S106 is performed.
Step S105: the captured image is discarded and the process returns to step S102.
Step S106: the captured image is retained and the process returns to step S102.
In practical application, after the previous image in the two adjacent frames of images is taken as a reference image and the next image in the two adjacent frames of images is taken as a captured image, whether the reference image is similar to the captured image or not can be judged; if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is reserved, and the step of selecting two adjacent frames of images in the image data set is returned.
It should be noted that after discarding the captured image, the frame image does not exist in the image data set, and at this time, after returning to the step of selecting two adjacent frame images in the image data set, two adjacent frame images including the frame image are not obtained; after the captured image is retained, the frame image still exists in the image data set, and at this time, after the step of selecting two adjacent frame images in the image data set is returned, two adjacent frame images including the frame image still exist, but the frame image at this time may become the reference image. At this time, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set, which may specifically be: discarding the captured image, keeping the reference image unchanged, taking the next frame image of the captured image as the captured image, and returning to execute the step of judging whether the reference image is similar to the captured image; the step of retaining the captured image and returning to the step of selecting two adjacent frames of images in the image data set may specifically be: and taking the captured image as a reference image, taking the next frame image of the reference image as the captured image, and returning to execute the step of judging whether the reference image is similar to the captured image.
In the method for processing frame loss of an image provided by the embodiment of the application, if the number of discarded images is not limited, the quality of the image after frame loss processing may be poor, and in order to avoid this situation, the number of discarded images can be limited, that is, the reference image is kept unchanged, and in the process of taking the next frame image of the captured image as the captured image, the real-time number of the discarded captured images can be accumulated under the condition that the reference image is unchanged; judging whether the real-time quantity is smaller than a preset quantity or not; and if the real-time number is less than the preset number, taking the next frame of image of the captured image as the captured image, and if the real-time number is greater than or equal to the preset number, directly taking one frame of image of the captured image as a reference image, taking the next frame of image of the reference image as the captured image, and returning to execute the step of judging whether the reference image is similar to the captured image.
The application provides an image frame loss processing method, which comprises the steps of obtaining an image data set to be frame lost; selecting two adjacent frames of images in the image data set; taking a former frame image in two adjacent frame images as a reference image, and taking a latter frame image in the two adjacent frame images as a captured image; judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is retained, and the step of selecting two adjacent frames of images in the image data set is returned to be executed. In the method, whether the next frame of image is discarded or not is determined based on the similarity degree between two adjacent frames of images, so that even if the next frame of image is discarded, because the next frame of image is similar to the previous frame of image, the content of the next frame of image can also be reflected by the previous frame of image, namely the frame discarding method can reduce the influence of the discarded image on the quality of the original image.
In the image frame loss processing method provided by the embodiment of the application, in order to rapidly judge whether the reference image is similar to the captured image, the similarity between the reference image and the captured image can be calculated, and whether the reference image is similar to the captured image is judged according to the similarity, that is, in the process of judging whether the reference image is similar to the captured image, the target similarity value between the reference image and the captured image can be calculated, and whether the reference image is similar to the captured image is judged based on the target similarity value.
Referring to fig. 2, fig. 2 is a flowchart illustrating a similarity determination between a reference image and a captured image.
In practical applications, the process of calculating a target similarity value between a reference image and a captured image, and determining whether the reference image and the captured image are similar based on the target similarity value may include the following steps:
step S201: and carrying out primary sampling on the reference image to obtain a reference sampling image.
Step S202: and carrying out primary sampling on the captured image to obtain a captured sampled image.
Step S203: a current similarity value of the reference sample image and the captured sample image is calculated.
In practical application, if the similarity between the reference image and the captured image is very high, the reference sampled image and the captured sampled image with very high similarity can be obtained only by sampling the reference image and the captured image once, and correspondingly, whether the reference image is similar to the captured image can be judged only according to the similarity between the reference sampled image and the captured sampled image, so that the reference image and the captured image are prevented from being sampled for many times, the similarity calculation of the whole image is avoided, the calculation amount is reduced, and the calculation efficiency is improved.
In practical applications, in the process of sampling the reference image and the captured image, the image sampling may be performed by a random sampling method or an equidistant sampling method for the convenience of sampling. In the process, the image can be subjected to multi-dimensional sampling according to the sampling setting of the reference image, and multi-dimensional captured image sampling data with the same position as the reference image sampling data is obtained.
Step S204: and acquiring historical similarity values of the reference sampling image and the captured sampling image obtained by historical calculation.
Step S205: and determining a target similarity value based on the current similarity value and the historical similarity value.
In practical application, the calculated current similarity value can only reflect the similarity between the currently sampled reference sampling image and the captured sampling image, at this time, the situation that the reference sampling image is not similar to the captured sampling image may exist, but the previously sampled reference sampling image is similar to the captured sampling image, and after the similarities are accumulated, the similarity between the reference image and the captured image can be judged, so that in order to avoid the influence of a single sampling image on the target similarity, after the current similarity values of the reference sampling image and the captured sampling image are calculated, the historical similarity values of the historically calculated reference sampling image and the captured sampling image can be obtained; and determining a target similarity value based on the current similarity value and the historical similarity value.
It should be noted that, since the positions of the respective sampling images in the images may be different and the carried image information may be different, the respective sampling images have different influence on the image similarity, and in order to enable the target similarity value to reflect the similarity between the reference image and the captured image more accurately, in the process of determining the target similarity value based on the current similarity value and the historical similarity value, the target similarity value may be determined based on the current similarity value, the weight of the current similarity value, the historical similarity value, and the weight of the respective historical similarity value.
Step S206: judging whether the target similarity value is smaller than a preset value or not; if the target similarity value is smaller than the preset value, step S207 is executed; if the target similarity value is greater than or equal to the predetermined value, step S210 is performed.
Step S207: the number of sampling times for the reference image is accumulated.
Step S208: judging whether the sampling times are less than a preset sampling value or not, and if the sampling times are less than the preset sampling value, executing the step S201; if the sampling number is greater than or equal to the preset sampling value, step S209 is executed.
Step S209: it is determined that the reference image is not similar to the captured image.
Step S210: the reference image is determined to be similar to the captured image.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an image frame loss processing system according to an embodiment of the present disclosure.
An image frame loss processing system provided in an embodiment of the present application may include:
a first obtaining module 101, configured to obtain an image data set to be frame lost;
a first selecting module 102, configured to select two adjacent frames of images in an image data set;
a first setting module 103, configured to use a previous frame image of two adjacent frame images as a reference image, and use a next frame image of the two adjacent frame images as a captured image;
a first judging module 104, configured to judge whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and prompting the first selection module to execute a step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, the captured image is retained, and the first selection module is prompted to perform a step of selecting two adjacent frames of images in the image data set.
In an image frame loss processing system provided in an embodiment of the present application, the first determining module may include:
and the first judgment submodule is used for calculating a target similarity value of the reference image and the captured image and judging whether the reference image and the captured image are similar or not based on the target similarity value.
In an image frame loss processing system provided in an embodiment of the present application, the first determining sub-module may include:
the first sampling unit is used for sampling the reference image for one time to obtain a reference sampling image;
the second sampling unit is used for sampling the captured image for one time to obtain a captured sampling image;
a first calculation unit for calculating a current similarity value between the reference sample image and the captured sample image;
a first acquisition unit, configured to acquire historical similarity values of a reference sample image and a captured sample image obtained by historical calculation;
the first determining unit is used for determining a target similarity value based on the current similarity value and the historical similarity value;
the first judgment unit is used for judging whether the target similarity value is smaller than a preset value or not; if the target similarity value is smaller than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are smaller than a preset sampling value, if the sampling times are smaller than the preset sampling value, returning to the step of performing one-time sampling on the reference image to obtain a reference sampling image, and if the sampling times are larger than or equal to the preset sampling value, judging that the reference image is not similar to the captured image; and if the target similarity value is larger than or equal to a preset value, judging that the reference image is similar to the captured image.
In an image frame loss processing system provided in an embodiment of the present application, the first determining unit may include:
and the second determining unit is used for determining the target similarity value based on the current similarity value, the weight of the current similarity value, the historical similarity values and the weights of the historical similarity values.
In the image frame loss processing system provided by the embodiment of the application, the sampling method for sampling the reference image and the captured image comprises random sampling or equidistant sampling.
In an image frame loss processing system provided in an embodiment of the present application, the first determining module may include:
a first discarding unit configured to discard the captured image;
a first processing unit configured to take an image of a next frame of the captured image as a captured image while keeping the reference image unchanged; returning to execute the step of judging whether the reference image is similar to the captured image;
a second processing unit configured to take the captured image as a reference image; taking the next frame image of the reference image as a captured image; and returning to execute the step of judging whether the reference image is similar to the captured image.
In an image frame loss processing system provided in an embodiment of the present application, a first processing unit may include:
a first accumulation unit configured to accumulate a real-time number of captured images discarded in a case where the reference image is not changed;
the second judging unit is used for judging whether the real-time quantity is smaller than the preset quantity or not; and if the real-time number is smaller than the preset number, taking the next frame image of the captured image as the captured image.
The application also provides an image frame loss processing device and a computer readable storage medium, which have the corresponding effects of the image frame loss processing method provided by the embodiment of the application. Referring to fig. 4, fig. 4 is a schematic structural diagram of an image frame loss processing apparatus according to an embodiment of the present disclosure.
An image frame loss processing device provided in an embodiment of the present application includes a memory 201 and a processor 202, where the memory 201 stores a computer program, and the processor 202 implements the following steps when executing the computer program:
acquiring an image data set to be subjected to frame loss;
selecting two adjacent frames of images in the image data set;
taking a previous frame image in two adjacent frame images as a reference image, and taking a next frame image in the two adjacent frame images as a captured image;
judging whether the reference image is similar to the captured image;
if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set;
if the reference image is not similar to the captured image, the captured image is reserved, and the step of selecting two adjacent frames of images in the image data set is returned.
The image frame loss processing device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 executes the computer program to realize the following steps: and calculating a target similarity value of the reference image and the captured image, and judging whether the reference image and the captured image are similar based on the target similarity value.
An image frame loss processing device provided in an embodiment of the present application includes a memory 201 and a processor 202, where the memory 201 stores a computer program, and the processor 202 implements the following steps when executing the computer program: sampling the reference image for one time to obtain a reference sampling image; carrying out primary sampling on the captured image to obtain a captured sampled image; calculating the current similarity value of the reference sampling image and the captured sampling image; acquiring historical similarity values of a reference sampling image and a captured sampling image obtained by historical calculation; determining a target similarity value based on the current similarity value and the historical similarity value; judging whether the target similarity value is smaller than a preset value or not; if the target similarity value is less than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are less than the preset sampling value, if the sampling times are less than the preset sampling value, returning to the step of performing one-time sampling on the reference image to obtain a reference sampling image, and if the sampling times are more than or equal to the preset sampling value, judging that the reference image is not similar to the captured image; and if the target similarity value is larger than or equal to a preset value, judging that the reference image is similar to the captured image.
An image frame loss processing device provided in an embodiment of the present application includes a memory 201 and a processor 202, where the memory 201 stores a computer program, and the processor 202 implements the following steps when executing the computer program: and determining the target similarity value based on the current similarity value, the weight of the current similarity value, the historical similarity values and the weights of the historical similarity values.
The image frame loss processing device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 executes the computer program to realize the following steps: sampling methods for sampling the reference image and the captured image include random sampling or equidistant sampling.
The image frame loss processing device provided by the embodiment of the application comprises a memory 201 and a processor 202, wherein a computer program is stored in the memory 201, and the processor 202 executes the computer program to realize the following steps: discarding the captured image; keeping the reference image unchanged, and taking the next frame image of the captured image as a captured image; returning to execute the step of judging whether the reference image is similar to the captured image; correspondingly, the captured image is taken as a reference image; taking the next frame image of the reference image as a captured image; and returning to execute the step of judging whether the reference image is similar to the captured image.
An image frame loss processing device provided in an embodiment of the present application includes a memory 201 and a processor 202, where the memory 201 stores a computer program, and the processor 202 implements the following steps when executing the computer program: accumulating the real-time number of captured images discarded without changing the reference image; judging whether the real-time quantity is smaller than a preset quantity or not; and if the real-time number is smaller than the preset number, taking the next frame image of the captured image as the captured image.
Referring to fig. 5, another image frame loss processing apparatus according to the embodiment of the present application may further include: an input port 203 connected to the processor 202, for transmitting an externally input command to the processor 202; a display unit 204 connected to the processor 202, for displaying the processing result of the processor 202 to the outside; and the communication module 205 is connected with the processor 202 and is used for realizing the communication between the image missing frame processing device and the outside world. The display unit 204 may be a display panel, a laser scanning display, or the like; the communication method adopted by the communication module 205 includes, but is not limited to, mobile high definition link technology (HML), Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), and wireless connection: wireless fidelity technology (WiFi), bluetooth communication technology, bluetooth low energy communication technology, ieee802.11s based communication technology.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps:
acquiring an image data set to be frame lost;
selecting two adjacent frames of images in the image data set;
taking a previous frame image in two adjacent frame images as a reference image, and taking a next frame image in the two adjacent frame images as a captured image;
judging whether the reference image is similar to the captured image;
if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image data set;
if the reference image is not similar to the captured image, the captured image is retained, and the step of selecting two adjacent frames of images in the image data set is returned to be executed.
A computer-readable storage medium is provided in an embodiment of the present application, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps: and calculating a target similarity value of the reference image and the captured image, and judging whether the reference image and the captured image are similar based on the target similarity value.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps: sampling the reference image for one time to obtain a reference sampling image; carrying out primary sampling on the captured image to obtain a captured sampling image; calculating the current similarity value of the reference sampling image and the captured sampling image; acquiring historical similarity values of a reference sampling image and a captured sampling image obtained by historical calculation; determining a target similarity value based on the current similarity value and the historical similarity value; judging whether the target similarity value is smaller than a preset value or not; if the target similarity value is smaller than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are smaller than a preset sampling value, if the sampling times are smaller than the preset sampling value, returning to the step of performing one-time sampling on the reference image to obtain a reference sampling image, and if the sampling times are larger than or equal to the preset sampling value, judging that the reference image is not similar to the captured image; and if the target similarity value is larger than or equal to a preset value, judging that the reference image is similar to the captured image.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps: and determining the target similarity value based on the current similarity value, the weight of the current similarity value, the historical similarity values and the weights of the historical similarity values.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps: sampling methods for sampling the reference image and the captured image include random sampling or equidistant sampling.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps: discarding the captured image; keeping the reference image unchanged, and taking the next frame image of the captured image as a captured image; returning to execute the step of judging whether the reference image is similar to the captured image; correspondingly, the captured image is taken as a reference image; taking the next frame image of the reference image as a captured image; and returning to execute the step of judging whether the reference image is similar to the captured image.
A computer-readable storage medium provided in an embodiment of the present application stores a computer program, and when executed by a processor, the computer program implements the following steps: accumulating the real-time number of captured images discarded without changing the reference image; judging whether the real-time quantity is smaller than a preset quantity or not; and if the real-time number is smaller than the preset number, taking the next frame of image of the captured image as the captured image.
The computer-readable storage media to which the present application relates include Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage media known in the art.
For a description of a relevant part in the image frame loss processing system, the device, and the computer readable storage medium provided in the embodiment of the present application, reference is made to detailed descriptions of a corresponding part in the image frame loss processing method provided in the embodiment of the present application, and details are not repeated here. In addition, parts of the technical solutions provided in the embodiments of the present application that are consistent with implementation principles of corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An image frame loss processing method is characterized by comprising the following steps:
acquiring an image data set to be frame lost;
selecting two adjacent frames of images in the image data set;
taking a former frame image in two adjacent frame images as a reference image, and taking a latter frame image in the two adjacent frame images as a captured image;
determining whether the reference image is similar to the captured image;
if the reference image is similar to the captured image, discarding the captured image, and returning to the step of selecting two adjacent frames of images in the image dataset;
if the reference image is not similar to the captured image, retaining the captured image, and returning to the step of selecting two adjacent frames of images in the image data set;
wherein the determining whether the reference image is similar to the captured image comprises:
calculating a target similarity value of the reference image and the captured image, and judging whether the reference image and the captured image are similar based on the target similarity value;
wherein the calculating a target similarity value of the reference image and the captured image, and the determining whether the reference image and the captured image are similar based on the target similarity value, comprises:
sampling the reference image for one time to obtain a reference sampling image;
sampling the captured image for one time to obtain a captured sampled image;
calculating a current similarity value of the reference sample image and the captured sample image;
acquiring historical similarity values of the reference sampling image and the capture sampling image obtained by historical calculation;
determining the target similarity value based on the current similarity value and the historical similarity value;
judging whether the target similarity value is smaller than a preset value or not;
if the target similarity value is less than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are less than a preset sampling value, if so, returning to the step of performing primary sampling on the reference image to obtain a reference sampling image, and if not, judging that the reference image is not similar to the captured image;
and if the target similarity value is larger than or equal to the preset numerical value, judging that the reference image is similar to the captured image.
2. The method of claim 1, wherein determining the target similarity value based on the current similarity value and the historical similarity value comprises:
and determining the target similarity value based on the current similarity value, the weight of the current similarity value, the historical similarity values and the weights of the historical similarity values.
3. The method of claim 2, wherein the sampling method of sampling the reference image and the captured image comprises random sampling or equidistant sampling.
4. A method according to any one of claims 1 to 3, wherein said discarding said captured image and returning to said step of selecting two adjacent frames of said image data set comprises:
discarding the captured image;
keeping the reference image unchanged, and taking the next frame image of the captured image as the captured image;
returning to the step of judging whether the reference image is similar to the captured image;
the step of retaining the captured image and returning to the step of selecting two adjacent frames of images in the image data set comprises:
taking the captured image as the reference image;
taking a next frame image of the reference image as the captured image;
and returning to execute the step of judging whether the reference image is similar to the captured image.
5. The method according to claim 4, wherein the keeping the reference image unchanged, regarding a next frame image of the captured image as the captured image, comprises:
accumulating the real-time number of the captured images discarded without changing the reference image;
judging whether the real-time quantity is smaller than a preset quantity or not;
and if the real-time number is smaller than the preset number, taking the next frame of image of the captured image as the captured image.
6. An image drop frame processing system, comprising:
the first acquisition module is used for acquiring an image data set to be subjected to frame loss;
the first selection module is used for selecting two adjacent frames of images in the image data set;
the first setting module is used for taking the previous frame image in the two adjacent frame images as a reference image and taking the next frame image in the two adjacent frame images as a captured image;
a first judgment module for judging whether the reference image is similar to the captured image; if the reference image is similar to the captured image, discarding the captured image, and prompting the first selection module to execute the step of selecting two adjacent frames of images in the image data set; if the reference image is not similar to the captured image, retaining the captured image, and prompting the first selection module to execute the step of selecting two adjacent frames of images in the image data set;
wherein, the first judging module comprises:
a first judgment sub-module, configured to calculate a target similarity value between the reference image and the captured image, and judge whether the reference image and the captured image are similar based on the target similarity value;
wherein the first judgment sub-module includes:
the first sampling unit is used for sampling the reference image for one time to obtain a reference sampling image;
the second sampling unit is used for sampling the captured image for one time to obtain a captured sampling image;
a first calculation unit configured to calculate a current similarity value between the reference sample image and the captured sample image;
a first acquisition unit configured to acquire a history similarity value between the reference sample image and the captured sample image obtained by history calculation;
a first determining unit, configured to determine the target similarity value based on a current similarity value and the historical similarity value;
the first judgment unit is used for judging whether the target similarity value is smaller than a preset value or not; if the target similarity value is smaller than the preset value, accumulating the sampling times of the reference image, judging whether the sampling times are smaller than a preset sampling value, if so, returning to the step of performing primary sampling on the reference image to obtain a reference sampling image, and if not, judging that the reference image is not similar to the captured image; and if the target similarity value is larger than or equal to the preset value, judging that the reference image is similar to the captured image.
7. An image drop frame processing apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the image drop frame processing method according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the image loss frame processing method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010820073.0A CN111970518B (en) | 2020-08-14 | 2020-08-14 | Image frame loss processing method, system, equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010820073.0A CN111970518B (en) | 2020-08-14 | 2020-08-14 | Image frame loss processing method, system, equipment and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111970518A CN111970518A (en) | 2020-11-20 |
CN111970518B true CN111970518B (en) | 2022-07-22 |
Family
ID=73387681
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010820073.0A Active CN111970518B (en) | 2020-08-14 | 2020-08-14 | Image frame loss processing method, system, equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111970518B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112714273A (en) * | 2020-12-25 | 2021-04-27 | 北京字节跳动网络技术有限公司 | Screen sharing display method, device, equipment and storage medium |
CN112804527B (en) * | 2021-01-07 | 2023-01-24 | 苏州浪潮智能科技有限公司 | Image output method, image output device and computer-readable storage medium |
CN114302140B (en) * | 2021-11-30 | 2023-11-03 | 山东云海国创云计算装备产业创新中心有限公司 | Pre-frame-loss method, system, equipment and computer readable storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102420941A (en) * | 2011-11-18 | 2012-04-18 | 深圳市万兴软件有限公司 | Automatic shooting method and device |
CN109740499A (en) * | 2018-12-28 | 2019-05-10 | 北京旷视科技有限公司 | Methods of video segmentation, video actions recognition methods, device, equipment and medium |
CN110147465A (en) * | 2019-05-23 | 2019-08-20 | 上海闻泰电子科技有限公司 | Image processing method, device, equipment and medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542298A (en) * | 2010-12-30 | 2012-07-04 | 富泰华工业(深圳)有限公司 | Electronic device and image similarity degree comparison method thereof |
CN108304755B (en) * | 2017-03-08 | 2021-05-18 | 腾讯科技(深圳)有限公司 | Training method and device of neural network model for image processing |
CN107613357B (en) * | 2017-09-13 | 2020-05-19 | 广州酷狗计算机科技有限公司 | Sound and picture synchronous optimization method and device and readable storage medium |
-
2020
- 2020-08-14 CN CN202010820073.0A patent/CN111970518B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102420941A (en) * | 2011-11-18 | 2012-04-18 | 深圳市万兴软件有限公司 | Automatic shooting method and device |
CN109740499A (en) * | 2018-12-28 | 2019-05-10 | 北京旷视科技有限公司 | Methods of video segmentation, video actions recognition methods, device, equipment and medium |
CN110147465A (en) * | 2019-05-23 | 2019-08-20 | 上海闻泰电子科技有限公司 | Image processing method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN111970518A (en) | 2020-11-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111970518B (en) | Image frame loss processing method, system, equipment and computer storage medium | |
CN105979092B (en) | Abnormity monitoring method and device | |
CN105469381B (en) | Information processing method and terminal | |
CN105338323A (en) | Video monitoring method and device | |
CN109194866B (en) | Image acquisition method, device, system, terminal equipment and storage medium | |
EP2563019B1 (en) | Method and device for compressing and encoding image data | |
CN104580907A (en) | Anti-shake photographing method and device | |
CN108777765B (en) | Method and device for acquiring full-definition image and electronic equipment | |
CN113068042A (en) | Video compression method, system and device | |
CN108462825A (en) | Method for processing video frequency and device | |
CN115396705A (en) | Screen projection operation verification method, platform and system | |
JP4936083B2 (en) | Thumbnail image generation method and apparatus | |
CN111314395A (en) | Image transmission method, terminal and storage medium | |
CN112714321A (en) | Compressed video processing method, device, equipment and computer readable storage medium | |
US20150043833A1 (en) | Image processing method and electronic device | |
CN113067984B (en) | Binocular shooting correction method, binocular shooting correction device and electronic equipment | |
CN115761600A (en) | Video fusion circuit, video fusion method, video fusion device, electronic apparatus, and computer-readable medium | |
CN113055601A (en) | Binocular shooting correction method, binocular shooting correction device and electronic equipment | |
CN112633198A (en) | Picture processing method and device, storage medium and electronic device | |
CN112073718A (en) | Television screen splash detection method and device, computer equipment and storage medium | |
CN111754387B (en) | Image processing method and device | |
CN112639868A (en) | Image processing method and device and movable platform | |
US8004569B2 (en) | Method and apparatus for obtaining still image frame with anti-vibration clearness for image processing device | |
CN110689565A (en) | Depth map determination method and device and electronic equipment | |
CN112887726B (en) | Image processing method and apparatus, storage medium, and electronic device |
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 |