CN111405142A - Image processing method, device and computer readable storage medium - Google Patents
Image processing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN111405142A CN111405142A CN202010239747.8A CN202010239747A CN111405142A CN 111405142 A CN111405142 A CN 111405142A CN 202010239747 A CN202010239747 A CN 202010239747A CN 111405142 A CN111405142 A CN 111405142A
- Authority
- CN
- China
- Prior art keywords
- image
- current background
- background image
- video
- terminal device
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/2224—Studio circuitry; Studio devices; Studio equipment related to virtual studio applications
- H04N5/2226—Determination of depth image, e.g. for foreground/background separation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Telephonic Communication Services (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides an image processing method, image processing equipment and a computer readable storage medium, which solve the problem that the conventional video compression amount is low, so that a larger bandwidth is required. The method of the invention comprises the following steps: acquiring a first video image of a first terminal device under the condition that the first terminal device and a second terminal device carry out video call; obtaining a current background image based on the first video image; performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background; and sending the current background image and the second video image to the second terminal equipment. Therefore, the first video image is processed into the second video image with the single-color background and the current background image, so that the compression rate can be increased, the compression amount is improved, the required bandwidth is reduced, and the requirement on the bandwidth in the video process is effectively reduced.
Description
Technical Field
The embodiment of the invention relates to the technical field of multimedia communication, in particular to an image processing method, image processing equipment and a computer readable storage medium.
Background
In recent years, video communication has become a hot spot for new application requirements because of a series of advantages such as intuitiveness and reliability. Video compression techniques have been introduced to reduce the bandwidth required for video transmission.
The existing video compression algorithm directly compresses video frames, and the compression amount is low, so that a larger bandwidth is required.
Disclosure of Invention
Embodiments of the present invention provide an image processing method, an image processing apparatus, and a computer-readable storage medium, so as to solve the problem that a large bandwidth is required due to a low amount of video compression in the prior art.
In order to solve the above problems, the present invention is realized by:
in a first aspect, an embodiment of the present invention provides an image processing method applied to a communication device, including:
acquiring a first video image of a first terminal device under the condition that the first terminal device and a second terminal device carry out video call;
obtaining a current background image based on the first video image;
performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background;
and sending the current background image and the second video image to the second terminal equipment.
Optionally, the obtaining a current background image based on the first video image includes:
identifying a photographic subject in the first video image, the photographic subject being located within a subject region;
extracting a background area except the shooting object in the first video image;
and obtaining a current background image according to the background area.
Optionally, after the current background image and the second video image are sent to the second terminal device, the method further includes:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
sending the updated current background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current scene image;
the preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Optionally, obtaining an updated current background image based on the current background image when a parameter representing a change of the current background image exceeds a preset threshold, where the obtaining includes:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold;
and updating the image of the target image unit to obtain an updated current background image.
Optionally, the method further comprises:
acquiring change data of the current background image;
sending the change data to the second terminal device;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
According to another aspect of the present invention, there is provided an image processing method applied to a second terminal device, including:
under the condition that a first terminal device and a second terminal device carry out video call, receiving a current background image and a second video image of a single-color background, which are sent by a communication device;
and synthesizing the current background image and the second video image to obtain a first video image corresponding to the first terminal device.
Optionally, the synthesizing the current background image and the second video image to obtain a first video image corresponding to the first terminal device includes:
superposing the second video image to the current background image to obtain an intermediate video image;
and carrying out cutout processing on the single-color background area in the intermediate video image to obtain a first video image corresponding to the first terminal device.
Optionally, after the current background image and the second video image are synthesized to obtain a first video image corresponding to the first terminal device, the method further includes:
receiving an updated current background image sent by the communication device;
replacing the current background image with the updated current background image.
Optionally, the method further comprises:
receiving the change data of the current background image sent by the communication equipment;
obtaining an updated current background image based on the change data and the current background image;
wherein the change data comprises one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
Optionally, the change data is difference data between the current background image and the previous background image;
obtaining an updated current background image based on the change data and the current background image, including:
and synthesizing the difference data and the current background image to obtain an updated current background image.
Optionally, the change data is shooting angle change data of a lens shooting the first video image;
obtaining an updated current background image based on the change data and the current background image, including:
and under the condition that the shooting angle change data comprises a first angle value deviated along a first direction, deviating the current background image by the first angle value along a second direction to obtain an updated current background image, wherein the second direction is opposite to the first direction.
Optionally, the change data is position change data of a reference coordinate point of the current background image;
obtaining an updated current background image based on the change data and the current background image, including:
under the condition that the position change data of the reference coordinate point comprises a first coordinate of the reference coordinate point before position change and a second coordinate of the reference coordinate point after position change, calculating a first distance value between the first coordinate and the second coordinate and a third direction of the second coordinate relative to the first coordinate according to the first coordinate and the second coordinate;
and moving the current background image by a first distance value along a fourth direction to obtain an updated current background image, wherein the fourth direction is opposite to the third direction.
In accordance with still another aspect of the present invention, there is provided a communication apparatus including: a processor, a memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the image processing method as described above.
According to still another aspect of the present invention, there is provided a terminal device including: a processor, a memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the image processing method as described above.
According to a further aspect of the present invention, a computer-readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the image processing method as set forth above.
According to the image processing method, a first video image of a first terminal device is obtained under the condition that the first terminal device and a second terminal device carry out video call; obtaining a current background image based on the first video image; performing image processing on a background area except for the main body area in the first video image to obtain a second video image with a single-color background; the current background image and the second video image are sent to the second terminal device, so that the first video image is processed into the second video image with the single-color background and the current background image, the compression rate can be increased, the compression amount is improved, the required bandwidth is reduced, and the requirement on the bandwidth in the video process is effectively reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flow chart of an image processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a process for obtaining a current background image according to an embodiment of the present invention;
FIG. 3 is a second flowchart illustrating an image processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart of an image processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an implementation of a communication device according to an embodiment of the present invention;
FIG. 6 is a second flowchart of an image processing apparatus according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an implementation structure of a terminal device according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help the full understanding of the embodiments of the present invention. Thus, it will be apparent to those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. In addition, the terms "system" and "network" are often used interchangeably herein.
In the process of communication, any one party can be a first terminal device, and the other party or other parties can be a second terminal device, so that the video of the first terminal device is sent to the second terminal device; or, each party is a first terminal device, and the other party is a second terminal device corresponding to the first terminal device, so that one terminal device watches the video of the other terminal device, and the other terminal device watches the video of the first terminal device at the same time.
As shown in fig. 1, an embodiment of the present invention provides an image processing method applied to a communication device. Here, the communication device may be the first terminal device, and may also be a network device such as a server. The method of the embodiment of the invention can specifically comprise the following steps:
in this step, if the execution subject of the image processing method according to the embodiment of the present invention is the first terminal device, acquiring the first video image of the first terminal device may include: and obtaining a first video image through the image collected by the lens of the first terminal device.
If the execution subject of the image processing method of the embodiment of the present invention is a network device, acquiring the first video image of the first terminal device may include: and receiving a first video image sent by the first terminal equipment.
102, obtaining a current background image based on the first video image;
in this step, the current background image specifically refers to a complete background image without the photographic subject, that is, a complete background image behind the photographic subject in the first video image. Here, based on the image segmentation technique and the image synthesis technique, a complete background image excluding the photographic subject in the first video image can be obtained.
Preferably, the current background image is a static background image.
103, performing image processing on a background area except for the main body area in the first video image to obtain a second video image with a single-color background;
in this step, optionally, the single color is black or green. Therefore, the matting processing of the second video image is convenient during the later image synthesis.
The background area is an image area outside the main area corresponding to the current background image.
And 104, sending the current background image and the second video image to the second terminal equipment.
It should be noted that the current background image may only need to be sent to the second terminal device once, and the main video stream composed of multiple frames of the second video image may be sent to the second terminal device in real time.
In this step, if the execution subject of the image processing method according to the embodiment of the present invention is the first terminal device, sending the current background image and the second video image to the second terminal device may include: and sending the current background image and the second video image to the second terminal equipment through network equipment.
According to the image processing method, a first video image of a first terminal device is obtained under the condition that the first terminal device and a second terminal device carry out video call; obtaining a current background image based on the first video image; performing image processing on a background area except for the main body area in the first video image to obtain a second video image with a single-color background; the current background image and the second video image are sent to the second terminal device, so that the first video image is processed into the second video image with the single-color background and the current background image, the compression rate can be increased, the compression amount is improved, the required bandwidth is reduced, and the requirement on the bandwidth in the video process is effectively reduced.
As an optional implementation manner, the method step 102 in the embodiment of the present invention may specifically include:
identifying a photographic subject in the first video image, the photographic subject being located within a subject region;
in this step, the photographic subject in the first video image may be identified by an image recognition technique.
Here, for the video conference, all the persons in the first video image are the photographic subjects; for ordinary video chat, when the shooting object is the operator of the first terminal equipment, the shooting object can be identified through face identification authentication. If the face recognition authentication is not performed, the recognition can be determined by the position, size, distance, and the like of the subject.
Extracting a background area except the shooting object in the first video image;
and obtaining a current background image according to the background area.
In the step, under the condition that the position of a shot object in a first video image is not changed, deleting the shot object to obtain a color block area; and repairing and completing the color block area based on the background image to obtain a current background image.
Under the condition that the position of a shooting object in the first video image changes, the color block area and the non-color block area in the image under the same coordinate are found by comparing the image difference of the current video image and the previous frame of video image, and then filling is carried out.
As shown in fig. 2, the person a moves from left to right, but the background of the person a does not change much, and the images except the region of the color block (i.e., the black region in the figure after the person a is removed) can be synthesized by referring to the coordinates of the background map by the similarity of the background, so that the rightmost complete background map in the figure is finally obtained.
As an optional implementation manner, after the method step 102 of the embodiment of the present invention, the method may further include:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
in this step, the preset condition includes one of the following:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Here, the parameter representing the change of the current background image exceeds a preset threshold, which indicates that the current background image has a large change, and in order to make a video image viewed by an opposite end of video communication (here, the second terminal device) more natural, the current background image needs to be updated.
Here, it is also possible to maintain the duration of the current background image unchanged for a preset duration, that is, update the background image every preset duration (for example, n seconds), which also makes the video image viewed by the opposite end of the video communication (here, the second terminal device) more natural.
Sending the second background image to the second terminal equipment, and enabling the second terminal equipment to replace the current background image with the updated current background image;
based on this, as an optional implementation manner, in a case that a parameter representing a change of the current background image exceeds a preset threshold, obtaining an updated current background image based on the current background image, including:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
in this step, when the current background image changes greatly, for example, the chair of the conference person changes, the current background image may be divided into a plurality of image units, that is, into a plurality of equal parts, for example, 256 × 256.
Determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold;
in this step, a target image unit is determined, where the parameter characterizing the change of the current background image exceeds a preset threshold, and continuing to explain by taking the above example as an example, when the change of a small part of the target image unit exceeds the preset threshold, the part is determined as a target image unit that needs to be replaced subsequently.
Here, the target image unit may include one or more image units.
And updating the image of the target image unit to obtain an updated current background image.
In this step, the corresponding parameters of the target image unit are modified to be changed.
As an optional implementation, the method may further include:
acquiring change data of the current background image;
in this step, the change data includes at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
Here, the difference data between the current background image and the previous frame background image may be obtained by comparing the image difference between the current first video image and the previous frame first video image.
Here, the shooting angle change data includes: direction of change and angle of change value.
The position change data of the reference coordinate point of the current background image includes: the first coordinates of the reference coordinate points before position change and the second coordinates of the reference coordinate points after position change.
And sending the change data to the second terminal equipment.
In an embodiment, if the main execution body of the image processing method is the first terminal device, the specific implementation steps of the method may be:
under the condition that a first terminal device and a second terminal device carry out video call, a first video image is obtained through an image collected by a lens of the first terminal device;
obtaining a current background image based on the first video image;
the step may specifically include: identifying a photographic subject in the first video image, the photographic subject being located within a subject region; extracting a background area except the shooting object in the first video image; and obtaining a current background image according to the background area.
Performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background;
and uploading the current background image and the second video image to network equipment, and sending the current background image and the second video image to the second terminal equipment by the network equipment.
Optionally, after obtaining the current background image based on the first video image, the method of this embodiment may further include:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
sending the updated current background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current background image;
here, specifically, the updated current background image is uploaded to the network device, and is sent to the second terminal device by the network device.
The preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Specifically, obtaining an updated current background image based on the current background image when a parameter representing a change of the current background image exceeds a preset threshold includes:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold value;
and updating the image of the target image unit to obtain an updated background image of the current background image.
Optionally, after the current background image and the second video image are sent to the second terminal device, the method of this embodiment may further include:
acquiring change data of the current background image;
sending the change data to the second terminal device;
here, specifically, the change data is uploaded to the network device, and the network device sends the change data to the second terminal device.
Wherein the change data comprises one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
In another embodiment, if the main execution body of the image processing method is a network device, the specific implementation steps of the method may be:
under the condition that a first terminal device and a second terminal device carry out video call, receiving a first video image sent by the first terminal device;
obtaining a current background image based on the first video image;
in this step, a photographic subject in the first video image may be recognized by the network device itself, the photographic subject being located in the subject area; extracting a background area except the shooting object in the first video image; and obtaining a current background image according to the background area.
The shooting object in the first video image identified by the first terminal device can be obtained through the notification of the first terminal device; then, the network equipment extracts a background area except the shooting object in the first video image; and obtaining a current background image according to the background area.
Performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background;
and sending the current background image and the second video image to the second terminal equipment.
Optionally, after obtaining the current background image based on the first video image, the method of this embodiment may further include:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
sending the updated current background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current background image;
the preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Specifically, obtaining an updated current background image based on the current background image when a parameter representing a change of the current background image exceeds a preset threshold includes:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold value;
and updating the image of the target image unit to obtain an updated current background image.
Optionally, after the current background image and the second video image are sent to the second terminal device, the method of this embodiment may further include:
acquiring change data of the current background image;
sending the change data to the second terminal device;
wherein the change data comprises one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
According to the image processing method, a first video image of a first terminal device is obtained under the condition that the first terminal device and a second terminal device carry out video call; obtaining a current background image based on the first video image; performing image processing on a background area except for the main body area in the first video image to obtain a second video image with a single-color background; the current background image and the second video image are sent to the second terminal device, so that the first video image is processed into the second video image with the single-color background and the current background image, the compression rate can be increased, the compression amount is improved, the required bandwidth is reduced, and the requirement on the bandwidth in the video process is effectively reduced.
As shown in fig. 3, an embodiment of the present invention provides an image processing method applied to a second terminal device. The method of the embodiment of the invention can specifically comprise the following steps:
in this step, the communication device may be the first terminal device or the network device.
Here, in a case where the communication device is the first terminal device, receiving the current background image and the second video image with a single-color background sent by the communication device may specifically include: and receiving a current background image and a second video image of a single-color background which are sent by the first terminal equipment through the network equipment.
In a case that the communication device is a network device, receiving the current background image and the second video image with a single-color background sent by the communication device may specifically include: and receiving a current background image and a second video image of a single-color background sent by the network equipment.
Here, the current background image is an image obtained by performing background region extraction processing on a first video image based on the first terminal device.
The second video image is a video image which is based on the first video image of the first terminal device and modifies the background color in the background area except the main body area in the first video image into a single-color background.
To illustrate, the second terminal may save the current background image locally.
Here, on the side of the second terminal device, the acquired current background image of the first terminal device and the second video image of the single-color background obtained based on the first video image are processed by the communication device respectively for the background image and the main video (i.e. the second video image), and after the second terminal device is synthesized, the video compression amount is greatly improved, i.e. the watching effect of the video is not affected, and the requirement for the bandwidth in the video process can be effectively reduced.
The image processing method of the embodiment of the invention receives the current background image and the second video image with the single color background sent by the communication equipment under the condition that the first terminal equipment and the second terminal equipment carry out video call; the current background image and the second video image are synthesized to obtain the first video image corresponding to the first terminal device, so that the video compression amount of the first video image corresponding to the first terminal device is greatly improved, the watching effect of the video can not be influenced, and the requirement on the bandwidth in the video process can be effectively reduced.
As an optional implementation manner, step 302 of the method according to the embodiment of the present invention may specifically include:
superposing the second video image to the current background image to obtain an intermediate video image;
in this step, the second video image is superimposed on the current background image, and since the second video image is an image in the main area of the first video image and has a background with a single color, after the second video image is superimposed on the current background image, the obtained intermediate video image is a video image in which the current background image is covered by the second video image. It is to be understood that the upper layer is the second video image and the lower layer is the current background image.
And carrying out cutout processing on the single-color background area in the intermediate video image to obtain a first video image corresponding to the first terminal device.
In this step, after the single-color background region in the intermediate video image is subjected to matting processing, the background image corresponding to the single-color background region in the lower-layer current background image is displayed, and finally, a first video image corresponding to the first terminal device is obtained.
As an optional implementation manner, after the method step 302 of the embodiment of the present invention, the method may further include:
receiving an updated current background image sent by the communication device;
replacing the current background image with the updated current background image.
Under the condition that the current background image on the first terminal equipment side is changed greatly, the updated current background image after the communication equipment updates the current background image is received, and the current background image stored on the second terminal equipment side is replaced by the updated current background image, so that the video image from the first terminal equipment side is more natural to be watched on the second terminal equipment side.
As an optional implementation, the method may further include:
receiving the change data of the current background image sent by the communication equipment;
obtaining an updated current background image based on the change data and the current background image;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
It should be noted that the present embodiment is also intended to make the video image from the first terminal device more natural when viewed from the second terminal device.
Different from the previous embodiment, in the case that the current background image of the first terminal device side is changed greatly, the first terminal device only needs to send the changed data of the current background image, and the second terminal device side updates the current background image according to the changed data to obtain the updated current background image, so that the requirement for bandwidth in the video process can be further reduced.
Optionally, the change data is difference data between the current background image and the previous background image; obtaining an updated current background image based on the change data and the current background image, including:
and synthesizing the difference data and the current background image to obtain an updated current background image.
Optionally, the change data is shooting angle change data of a lens shooting the first video image; obtaining an updated current background image based on the change data and the current background image, including:
and under the condition that the shooting angle change data comprises a first angle value deviated along a first direction, deviating the current background image by the first angle value along a second direction to obtain an updated current background image, wherein the second direction is opposite to the first direction.
Optionally, the change data is position change data of a reference coordinate point of the current background image; obtaining an updated current background image based on the change data and the current background image, including:
under the condition that the position change data of the reference coordinate point comprises a first coordinate of the reference coordinate point before position change and a second coordinate of the reference coordinate point after position change, calculating a first distance value between the first coordinate and the second coordinate and a third direction of the second coordinate relative to the first coordinate according to the first coordinate and the second coordinate;
and moving the current background image by a first distance value along a fourth direction to obtain an updated current background image, wherein the fourth direction is opposite to the third direction.
The image processing method of the embodiment of the invention receives the current background image and the second video image with the single color background sent by the communication equipment under the condition that the first terminal equipment and the second terminal equipment carry out video call; the current background image and the second video image are synthesized to obtain the first video image corresponding to the first terminal device, so that the video compression amount of the first video image corresponding to the first terminal device is greatly improved, the watching effect of the video can not be influenced, and the requirement on the bandwidth in the video process can be effectively reduced.
As shown in fig. 4, an embodiment of the present invention further provides an image processing apparatus, applied to a communication device, where the communication device is a first terminal device or a network device, and including:
a first obtaining module 401, configured to obtain a first video image of a first terminal device when the first terminal device and a second terminal device perform a video call;
a first processing module 402, configured to obtain a current background image based on the first video image;
a second processing module 403, configured to perform image processing on a background area, except for a main body area, in the first video image, to obtain a second video image with a background of a single color;
a first sending module 404, configured to send the current background image and the second video image to the second terminal device.
Optionally, the first processing module 402 includes:
an object identifying unit configured to identify a photographic subject in the first video image, the photographic subject being located within a subject region;
an image extraction unit configured to extract a background region in the first video image excluding the photographic subject;
and the first processing unit is used for obtaining a current background image according to the background area.
Optionally, the communication device further comprises:
the background image updating module is used for obtaining an updated current background image based on the current background image under the condition that a preset condition is met;
a second sending module, configured to send the second background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current background image;
the preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Optionally, the background image update module includes:
the image segmentation unit is used for segmenting the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
the second processing unit is used for determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold value;
and the background image updating unit is used for updating the image of the target image unit to obtain an updated current background image.
Optionally, the communication device further comprises:
the second acquisition module is used for acquiring the change data of the current background image;
a third sending module, configured to send the change data to the second terminal device;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
It should be noted that the apparatus is an apparatus corresponding to the above-mentioned method applied to image processing, and all the implementations in the above-mentioned method embodiment are applicable to the embodiment of the apparatus, and the same technical effects can be achieved.
The image processing device of the embodiment of the invention obtains the first video image of the first terminal device through the first obtaining module under the condition that the first terminal device and the second terminal device carry out video call; the first processing module obtains a current background image based on the first video image; the second processing module carries out image processing on a background area except the main body area in the first video image to obtain a second video image with a single-color background; the first sending module sends the current background image and the second video image to the second terminal device, so that the first video image is processed into the second video image with the single-color background and the current background image, the compression rate can be increased, the compression amount is improved, the required bandwidth is reduced, and the requirement on the bandwidth in the video process is effectively reduced.
As shown in fig. 5, an embodiment of the present invention further provides a communication device, where the communication device is a first terminal device or a network device, and the communication device includes: a transceiver 501, a processor 502, a memory 503 and a computer program stored on the memory 502 and executable on the processor 501, the processor 501 implementing the steps of the image processing method described above when executing the computer program. Specifically, the processor 502 obtains a first video image of a first terminal device when the first terminal device and a second terminal device perform a video call; obtaining a current background image based on the first video image; performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background; the transceiver 501 is configured to send the current background image and the second video image to the second terminal device.
Optionally, the processor 502 is further configured to:
identifying a photographic subject in the first video image, the photographic subject being located within a subject region;
extracting a background area except the shooting object in the first video image;
and obtaining a current background image according to the background area.
Optionally, the processor 502 is further configured to:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
the transceiver 501 is further configured to:
sending the updated current background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current background image;
the preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
Optionally, the processor 502 is further configured to:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold value;
and updating the image of the target image unit to obtain an updated current background image.
Optionally, the processor 502 is further configured to: acquiring change data of the current background image;
the transceiver 501 is further configured to: sending the change data to the second terminal device;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
The bus architecture may include any number of interconnected buses and bridges, among which are linked together by one or more processors 501, represented by processor 501, and various circuits of memory 502, represented by memory 502. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 503 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 501 is responsible for managing the bus architecture and general processing, and the memory 502 may store data used by the processor in performing operations.
As shown in fig. 6, an embodiment of the present invention further provides an image processing apparatus, which is applied to a terminal device, where the terminal device is a second terminal device, and includes:
a first receiving module 601, configured to receive a current background image and a second video image with a single-color background, which are sent by a communication device, when a first terminal device and a second terminal device perform a video call;
a first image processing module 602, configured to perform synthesis processing on the current background image and the second video image to obtain a first video image corresponding to the first terminal device.
Optionally, the first image processing module 602 includes:
the third processing unit is used for superposing the second video image to the current background image to obtain an intermediate video image;
and the first image processing unit is used for carrying out cutout processing on the single-color background area in the intermediate video image to obtain a first video image corresponding to the first terminal device.
Optionally, the terminal device further includes:
the second receiving module is used for receiving the updated current background image sent by the communication equipment;
and the second image processing module is used for replacing the current background image with the updated current background image.
Optionally, the terminal device further includes:
the third receiving module is used for receiving the change data of the current background image sent by the communication equipment;
the third image processing module is used for obtaining an updated current background image based on the change data and the current background image;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
Optionally, the change data is difference data between the current background image and the previous background image; the third image processing module includes:
and the second image processing unit is used for carrying out synthesis processing on the difference data and the current background image to obtain an updated current background image.
Optionally, the change data is shooting angle change data of a lens shooting the first video image; the third image processing module includes:
a third image processing unit, configured to, when the shooting angle change data includes a first angle value shifted in a first direction, shift the current background image by the first angle value in a second direction, where the second direction is opposite to the first direction, to obtain an updated current background image.
Optionally, the change data is position change data of a reference coordinate point of the current background image; the third image processing module includes:
the calculation unit is used for calculating a first distance value between the first coordinate and the second coordinate and a third direction of the second coordinate relative to the first coordinate under the condition that the position change data of the reference coordinate point comprises the first coordinate of the reference coordinate point before position change and the second coordinate of the reference coordinate point after position change according to the first coordinate and the second coordinate;
and the fourth image processing unit is used for moving the current background image by a first distance value along a fourth direction to obtain an updated current background image, wherein the fourth direction is opposite to the third direction.
It should be noted that the apparatus is an apparatus corresponding to the above-mentioned method applied to image processing, and all the implementations in the above-mentioned method embodiment are applicable to the embodiment of the apparatus, and the same technical effects can be achieved.
The image processing device of the embodiment of the invention receives the current background image and the second video image with the single color background sent by the communication equipment through the first receiving module under the condition that the first terminal equipment and the second terminal equipment carry out video call; the first image processing module carries out synthesis processing on the current background image and the second video image to obtain the first video image corresponding to the first terminal device, so that the video compression amount of the first video image corresponding to the first terminal device is greatly improved, the watching effect of the video can not be influenced, and the requirement on the bandwidth in the video process can be effectively reduced.
As shown in fig. 7, an embodiment of the present invention further provides a terminal device, where the terminal device is a second terminal device, and the terminal device includes: a transceiver 701, a processor 702, a memory 703 and a computer program stored on the memory 702 and executable on the processor 701, the processor 701 implementing the steps of the image processing method described above when executing the computer program. Specifically, the transceiver 701 is configured to receive a current background image and a second video image of a single-color background, which are sent by a communication device, when a first terminal device and a second terminal device perform a video call; the processor 702 is configured to perform synthesis processing on the current background image and the second video image to obtain a first video image corresponding to the first terminal device.
Optionally, the processor 702 is further configured to:
superposing the second video image to the current background image to obtain an intermediate video image;
and carrying out cutout processing on the single-color background area in the intermediate video image to obtain a first video image corresponding to the first terminal device.
Optionally, the transceiver 701 is further configured to: receiving an updated current background image sent by the communication device; the processor 702 is further configured to: replacing the current background image with the updated current background image.
Optionally, the transceiver 701 is further configured to: receiving the change data of the current background image sent by the communication equipment; the processor 702 is further configured to: obtaining an updated current background image based on the change data and the current background image;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
Optionally, the change data is difference data between the current background image and the previous background image; the processor 702 is further configured to:
and synthesizing the difference data and the current background image to obtain an updated current background image.
Optionally, the change data is shooting angle change data of a lens shooting the first video image; the processor 702 is further configured to:
and under the condition that the shooting angle change data comprises a first angle value deviated along a first direction, deviating the current background image by the first angle value along a second direction to obtain an updated current background image, wherein the second direction is opposite to the first direction.
Optionally, the change data is position change data of a reference coordinate point of the current background image; the processor 702 is further configured to:
under the condition that the position change data of the reference coordinate point comprises a first coordinate of the reference coordinate point before position change and a second coordinate of the reference coordinate point after position change, calculating a first distance value between the first coordinate and the second coordinate and a third direction of the second coordinate relative to the first coordinate according to the first coordinate and the second coordinate;
and moving the current background image by a first distance value along a fourth direction to obtain an updated current background image, wherein the fourth direction is opposite to the third direction.
Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be performed by hardware, or may be instructed to be performed by associated hardware by a computer program that includes instructions for performing some or all of the steps of the above methods; and the computer program may be stored in a readable storage medium, which may be any form of storage medium.
Preferably, the network device in the above embodiments is a mobile edge computing MEC component.
In addition, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the image processing method described above. And the same technical effect can be achieved, and in order to avoid repetition, the description is omitted.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the preferred embodiments of the present invention have been described, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the following claims.
Claims (15)
1. An image processing method applied to a communication device, comprising:
acquiring a first video image of a first terminal device under the condition that the first terminal device and a second terminal device carry out video call;
obtaining a current background image based on the first video image;
performing image processing on a background area except for a main body area in the first video image to obtain a second video image with a single-color background;
and sending the current background image and the second video image to the second terminal equipment.
2. The image processing method according to claim 1, wherein obtaining a current background image based on the first video image comprises:
identifying a photographic subject in the first video image, the photographic subject being located within a subject region;
extracting a background area except the shooting object in the first video image;
and obtaining a current background image according to the background area.
3. The image processing method according to claim 1, wherein after the current background image and the second video image are transmitted to the second terminal device, the method further comprises:
under the condition that a preset condition is met, obtaining an updated current background image based on the current background image;
sending the updated current background image to the second terminal device, so that the second terminal device replaces the current background image with the updated current background image;
the preset condition comprises one of:
the parameter representing the change of the current background image exceeds a preset threshold value;
and maintaining the unchanged duration of the current background image to reach a preset duration.
4. The image processing method according to claim 3, wherein obtaining an updated current background image based on the current background image if a parameter representing a change of the current background image exceeds a preset threshold includes:
dividing the current background image into M image units, wherein M is more than or equal to 2 and is a positive integer;
determining a target image unit, wherein the target image unit is an image unit of which the parameter representing the change of the current background image exceeds a preset threshold;
and updating the image of the target image unit to obtain an updated current background image.
5. The image processing method according to claim 1 or 3, characterized in that the method further comprises:
acquiring change data of the current background image;
sending the change data to the second terminal device;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
6. An image processing method applied to a second terminal device is characterized by comprising the following steps:
under the condition that a first terminal device and a second terminal device carry out video call, receiving a current background image and a second video image of a single-color background, which are sent by a communication device;
and synthesizing the current background image and the second video image to obtain a first video image corresponding to the first terminal device.
7. The image processing method according to claim 6, wherein synthesizing the current background image and the second video image to obtain a first video image corresponding to the first terminal device comprises:
superposing the second video image to the current background image to obtain an intermediate video image;
and carrying out cutout processing on the single-color background area in the intermediate video image to obtain a first video image corresponding to the first terminal device.
8. The image processing method according to claim 6, wherein after the current background image and the second video image are synthesized to obtain a first video image corresponding to the first terminal device, the method further comprises:
receiving an updated current background image sent by the communication device;
replacing the current background image with the updated current background image.
9. The image processing method according to claim 6 or 8, characterized in that the method further comprises:
receiving the change data of the current background image sent by the communication equipment;
obtaining an updated current background image based on the change data and the current background image;
wherein the change data comprises at least one of:
difference data of the current background image and the previous frame background image;
shooting angle change data of a lens for shooting the first video image;
position change data of a reference coordinate point of the current background image.
10. The image processing method according to claim 9, wherein the change data is difference data between a current background image and a previous background image;
obtaining an updated current background image based on the change data and the current background image, including:
and synthesizing the difference data and the current background image to obtain an updated current background image.
11. The image processing method according to claim 9, wherein the change data is shooting angle change data of a shot that shoots the first video image;
obtaining an updated current background image based on the change data and the current background image, including:
and under the condition that the shooting angle change data comprises a first angle value deviated along a first direction, deviating the current background image by the first angle value along a second direction to obtain an updated current background image, wherein the second direction is opposite to the first direction.
12. The image processing method according to claim 9, wherein the change data is position change data of a reference coordinate point of the current background image;
obtaining an updated current background image based on the change data and the current background image, including:
under the condition that the position change data of the reference coordinate point comprises a first coordinate of the reference coordinate point before position change and a second coordinate of the reference coordinate point after position change, calculating a first distance value between the first coordinate and the second coordinate and a third direction of the second coordinate relative to the first coordinate according to the first coordinate and the second coordinate;
and moving the current background image by a first distance value along a fourth direction to obtain an updated current background image, wherein the fourth direction is opposite to the third direction.
13. A communication device, comprising: processor, memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the image processing method according to any one of claims 1 to 5.
14. A terminal device, comprising: processor, memory and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the image processing method according to any one of claims 6 to 12.
15. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the image processing method of any one of claims 1 to 5 or the image processing method of any one of claims 6 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010239747.8A CN111405142A (en) | 2020-03-30 | 2020-03-30 | Image processing method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010239747.8A CN111405142A (en) | 2020-03-30 | 2020-03-30 | Image processing method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111405142A true CN111405142A (en) | 2020-07-10 |
Family
ID=71413687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010239747.8A Pending CN111405142A (en) | 2020-03-30 | 2020-03-30 | Image processing method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111405142A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07193796A (en) * | 1993-12-27 | 1995-07-28 | Hitachi Ltd | Video communication system |
| CN1946144A (en) * | 2006-11-01 | 2007-04-11 | 李博航 | Real time video image transmission technology |
| CN1980334A (en) * | 2005-12-09 | 2007-06-13 | 英业达股份有限公司 | Video-picture composition code transmission method |
| US20100048288A1 (en) * | 2008-08-21 | 2010-02-25 | Wms Gaming, Inc. | Multiple wagering game displays from single input |
| CN103037206A (en) * | 2012-12-14 | 2013-04-10 | 广东威创视讯科技股份有限公司 | Method and system of video transmission |
| CN103475877A (en) * | 2013-09-05 | 2013-12-25 | 广东威创视讯科技股份有限公司 | Video transmission method and system |
| US20140068624A1 (en) * | 2012-09-04 | 2014-03-06 | Microsoft Corporation | Quota-based resource management |
| WO2018207581A1 (en) * | 2017-05-09 | 2018-11-15 | Sony Corporation | Client apparatus, client apparatus processing method, server, and server processing method |
| CN110213485A (en) * | 2019-06-04 | 2019-09-06 | 维沃移动通信有限公司 | A kind of image processing method and terminal |
| CN110730362A (en) * | 2019-10-22 | 2020-01-24 | 中国农业科学院农业信息研究所 | Low-flow video communication transmission system and method |
| CN110769323A (en) * | 2018-07-27 | 2020-02-07 | Tcl集团股份有限公司 | Video communication method, system, device and terminal equipment |
-
2020
- 2020-03-30 CN CN202010239747.8A patent/CN111405142A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07193796A (en) * | 1993-12-27 | 1995-07-28 | Hitachi Ltd | Video communication system |
| CN1980334A (en) * | 2005-12-09 | 2007-06-13 | 英业达股份有限公司 | Video-picture composition code transmission method |
| CN1946144A (en) * | 2006-11-01 | 2007-04-11 | 李博航 | Real time video image transmission technology |
| US20100048288A1 (en) * | 2008-08-21 | 2010-02-25 | Wms Gaming, Inc. | Multiple wagering game displays from single input |
| US20140068624A1 (en) * | 2012-09-04 | 2014-03-06 | Microsoft Corporation | Quota-based resource management |
| CN103037206A (en) * | 2012-12-14 | 2013-04-10 | 广东威创视讯科技股份有限公司 | Method and system of video transmission |
| CN103475877A (en) * | 2013-09-05 | 2013-12-25 | 广东威创视讯科技股份有限公司 | Video transmission method and system |
| WO2018207581A1 (en) * | 2017-05-09 | 2018-11-15 | Sony Corporation | Client apparatus, client apparatus processing method, server, and server processing method |
| CN110769323A (en) * | 2018-07-27 | 2020-02-07 | Tcl集团股份有限公司 | Video communication method, system, device and terminal equipment |
| CN110213485A (en) * | 2019-06-04 | 2019-09-06 | 维沃移动通信有限公司 | A kind of image processing method and terminal |
| CN110730362A (en) * | 2019-10-22 | 2020-01-24 | 中国农业科学院农业信息研究所 | Low-flow video communication transmission system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921782B (en) | Image processing method, device and storage medium | |
| WO2016101883A1 (en) | Method for face beautification in real-time video and electronic equipment | |
| CN112954450B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN112330574A (en) | Portrait restoration method and device, electronic equipment and computer storage medium | |
| CN111754415A (en) | Face image processing method and device, image equipment and storage medium | |
| CN108694719B (en) | Image output method and device | |
| CN112802033B (en) | Image processing method and device, computer readable storage medium and electronic equipment | |
| CN111985281A (en) | Image generation model generation method and device and image generation method and device | |
| Stoffels et al. | Object‐oriented image analysis for very‐low‐bitrate video‐coding systems using the CNN universal machine | |
| CN113221767A (en) | Method for training living body face recognition model and method for recognizing living body face and related device | |
| CN114598919B (en) | Video processing method, device, computer equipment and storage medium | |
| WO2024104144A1 (en) | Image synthesis method and apparatus, storage medium, and electrical device | |
| CN111444822B (en) | Object recognition method and device, storage medium and electronic device | |
| CN112714263A (en) | Video generation method, device, equipment and storage medium | |
| CN111405142A (en) | Image processing method, device and computer readable storage medium | |
| CN112601029B (en) | Video segmentation method, terminal and storage medium with known background prior information | |
| CN114140320B (en) | Image migration method and training method and device of image migration model | |
| CN113362243B (en) | Model training method, image processing method and device, medium and electronic equipment | |
| US20230131418A1 (en) | Two-dimensional (2d) feature database generation | |
| CN112966575B (en) | Target face recognition method and device applied to smart community | |
| CN114944015A (en) | Image processing method and device, electronic equipment and storage medium | |
| WO2021164329A1 (en) | Image processing method and apparatus, and communication device and readable storage medium | |
| CN113810725A (en) | Video processing method, device, storage medium and video communication terminal | |
| CN111527518B (en) | Method for processing light field video based on use of hyper-ray representations | |
| CN113920023A (en) | Image processing method and device, computer readable 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200710 |
|
| RJ01 | Rejection of invention patent application after publication |