WO2022088970A1 - 一种图像的处理方法、装置、设备及存储介质 - Google Patents

一种图像的处理方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2022088970A1
WO2022088970A1 PCT/CN2021/116137 CN2021116137W WO2022088970A1 WO 2022088970 A1 WO2022088970 A1 WO 2022088970A1 CN 2021116137 W CN2021116137 W CN 2021116137W WO 2022088970 A1 WO2022088970 A1 WO 2022088970A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
display
area
displayed
super
Prior art date
Application number
PCT/CN2021/116137
Other languages
English (en)
French (fr)
Inventor
熊一能
符乐安
唐志新
Original Assignee
北京字跳网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2022088970A1 publication Critical patent/WO2022088970A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/04817—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/0486—Drag-and-drop
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks

Definitions

  • the present disclosure relates to the technical field of image processing, and in particular, to an image processing method, apparatus, device, and storage medium.
  • Video applications can provide users with video browsing services and display videos to users. Users can obtain relevant information based on the displayed video.
  • the present disclosure provides an image processing method, apparatus, device and storage medium.
  • a first aspect of the embodiments of the present disclosure provides an image processing method, the method comprising:
  • the enlargement instruction acquire the image area designated to be enlarged on the display image, and use the image area designated to enlarge on the display image as the target image;
  • the super-clear enlarged image is displayed superimposed on the display image.
  • a second aspect of the embodiments of the present disclosure provides an image processing apparatus, the apparatus comprising:
  • a receiving module configured to receive an enlargement instruction for the displayed image
  • a first acquisition module configured to acquire, according to the enlargement instruction, an image area designated to be enlarged on the display image, and use the designated enlarged image area on the display image as a target image;
  • a super-resolution magnification module used for performing super-resolution magnification processing on the target image to obtain an ultra-clear magnified image of the target image
  • a display module configured to superimpose and display the ultra-clear enlarged image on the display image.
  • a third aspect of the embodiments of the present disclosure provides a terminal device, the terminal device includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned first aspect can be implemented method.
  • a fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by a processor, the method of the first aspect can be implemented.
  • the technical solutions provided by the embodiments of the present disclosure allow a user to select a local area of an image displayed by a terminal, and perform super-resolution enlargement processing and display based on the local area selected by the user. It can meet the user's demand for super-resolution magnification of a local area of an image, and can improve user experience.
  • the technical solution of the present disclosure can reduce the area that needs to be enlarged and reduce the calculation difficulty by allowing the user to independently select the target image, and does not need to consider the power consumption of the terminal too much. . Moreover, it can bring a stronger sense of clarity improvement without affecting business performance.
  • the technical solutions provided by the embodiments of the present disclosure may be applicable to the case of processing pictures or videos. If the technical solution is applied to a video (such as a short video, a long video or a live broadcast) playing scene, it can make up for the blank that the partial region of the video is not currently enlarged.
  • a video such as a short video, a long video or a live broadcast
  • a mobile terminal such as a mobile phone
  • NPU embedded neural network processor
  • the technical solution provided by the embodiments of the present disclosure is to set if the ultra-clear magnified image includes a pre-calibrated object; then, the calibration information of the object is displayed on the terminal display device together with the ultra-clear magnified image of the object. Because the calibration information can include information not included in the ultra-clear enlarged image. In essence, the calibration information is a supplement to the information related to the calibration object, and supplements the information that cannot be obtained only through the ultra-clear magnified image of the calibration object. In this way, the user does not need to conduct a network search for the calibrated object, and can quickly and conveniently understand its related content, which can simplify the user's operation steps and improve the user's favorability. This approach is conducive to the derivation of new business models.
  • FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of performing step 120 according to an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of displaying an image before executing the image processing method provided by the present disclosure according to an embodiment of the present disclosure
  • FIGS. 4-6 are schematic diagrams of displaying an image after executing the image processing method provided by the present disclosure, according to an embodiment of the present disclosure
  • FIG. 7 is a flowchart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 8 is a structural block diagram of an image processing apparatus provided by an embodiment of the present disclosure.
  • FIG. 9 is a schematic structural diagram of a terminal device in an embodiment of the present disclosure.
  • FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure, and the method may be executed by a terminal device.
  • the terminal device can be exemplarily understood as a device with image processing capabilities, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a smart TV.
  • the terminal device referred to in this embodiment may be equipped with an image display device (such as a display screen, but not limited to a display screen), and the terminal device may display images through the display screen, and use the method of this embodiment to display images. Perform ultra-clear magnification display on a local area of the image (ie, the target image).
  • the terminal device referred to in this embodiment may also be equipped with a photographing device at the same time. After the photographing device captures an image, the terminal device may use the method of this embodiment to perform ultra-clear magnification display on a local area of the image.
  • the method provided in this application is called an image processing method, wherein the image includes a picture or a video. Further, if the image is a video, it may specifically be a short video, a long video, or a live video.
  • the method provided by this embodiment includes the following steps:
  • Step 110 Receive an enlargement instruction for the displayed image.
  • the zoom-in instruction refers to an instruction used to instruct the terminal to zoom in on a certain local area (ie, the target image) in the displayed image. Therefore, the zoom-in command has two functions, one is to activate the zoom-in function, and the other is to determine the target image.
  • the zoom-in instruction is triggered by a user's operation of selecting an image area on the displayed image.
  • a virtual key with a zoom-in function can be displayed in advance on the display screen of the terminal. After recognizing that the user clicks the virtual key, the terminal enters the image area selection interface. Alternatively, it is preset to trigger the terminal to enter the image area selection interface through a certain touch action (eg, a finger draws a specific figure on the screen, such as "L", "W” or "O”, etc.). After recognizing that the user inputs the preset touch action, the terminal enters the image area selection interface.
  • a certain touch action eg, a finger draws a specific figure on the screen, such as "L”, "W” or “O”, etc.
  • the user selects the target magnified image area through a finger or a first icon (such as a brush tool, a magnifying glass tool, etc.) provided on the display interface.
  • a finger or a first icon such as a brush tool, a magnifying glass tool, etc.
  • you can use your finger to click on the displayed image then the image area within the preset range centered on the clicked position can specify the enlarged target image for the user, or drag the first icon to a certain part of the displayed image. position, then take the position as the center of the image area within the preset range, specify the enlarged target image for the user, or use the finger or the first icon to draw an enclosed area (such as a circle, quadrilateral, etc.) on the displayed image, so The image on the drawn closed area is the target image.
  • an enclosed area such as a circle, quadrilateral, etc.
  • the virtual key that enables the terminal to enter the image area selection interface and the first icon used to select the icon area may be the same icon, for example, a magnifying glass icon is used.
  • it can also be set to enable the zoom-in function and perform image area selection in one operation.
  • it is preset that after receiving a certain touch action (such as drawing “L”, “W” or “O” on the screen, etc.), the terminal automatically enables the zoom function, and based on the touch action in the touch action
  • the control trajectory determines the area of the image that the target zooms in.
  • Step 120 Acquire the image area designated to be enlarged on the display image according to the enlargement instruction, and use the image area designated to be enlarged on the display image as the target image.
  • selecting the image area through the first icon provided on the display interface includes: specifying the position of the first icon on the display image; the execution method of this step may include: acquiring the position of the first icon on the display image; The position is the center, the image displayed in the image area within the preset range around the position is acquired, and the image displayed in the image area within the preset range is used as the target image.
  • FIG. 2 is a schematic diagram of performing step 120 according to an embodiment of the present disclosure.
  • the method for determining the preset range is to take the designated position of the first icon on the displayed image as the center of the circle and 1cm as the radius, and the obtained area is the preset range. .
  • the position of the magnifying glass tool on the displayed image is designated as the position of point B.
  • first obtain the position data of point B then take the position of point B as the center of the circle and take 1 cm as the radius to determine the preset range, and then use the image displayed in the image area within the preset range as the target image.
  • the preset range is a circle, and the specified radius is 1 cm, which is only a specific example of the present disclosure.
  • the present disclosure does not limit the shape of the preset range, and optionally, the preset range may be a polygon, an ellipse, or the like.
  • the present application does not limit the size of the preset range.
  • the target image includes: delineating the area position of the target image on the display image through the first icon; the execution method of this step may include: acquiring the first icon on the display image The delineated area position; according to the area position, the image at the area position is acquired, and the image at the area position is used as the target image.
  • the user drags the magnifying glass tool, so that the drag track forms a closed area, that is, the position of the area of the target image on the display image is delineated by the magnifying glass tool.
  • the position of the area enclosed by the closed area is acquired, and then the image in the area is used as the target image.
  • the delineated area may be completed according to the shape of the drag track. For example, when the drag track is an arc with a central angle of 300 degrees, the arc can be completed as a complete closed circle based on the current shape of the drag track. Then obtain the position of the area enclosed by the closed circle, and use the image in the area as the target image.
  • Step 130 Perform super-resolution enlargement processing on the target image to obtain an ultra-clear enlarged image of the target image.
  • the target image may be subjected to super-resolution amplification processing based on a preset model to obtain a super-clear amplification image of the target resolution.
  • the preset model is a model used to perform super-resolution enlargement processing on the input image and output the processed image.
  • the preset model may include, for example, an adversarial network model.
  • the super-resolution upscaled image is sensory more like a real image.
  • GAN Generative Adversarial Network
  • the general adversarial network model consists of two parts: an image generator and an image judge, where the image generator generates a higher resolution image based on the original resolution of the input image, and the image judge is used to identify the newly generated image. Whether the resolution reaches the preset resolution standard, if not, continue to train the image generator until the image generator can generate images higher than the preset resolution standard, and obtain the adversarial network in this embodiment. Model.
  • Step 140 superimpose and display the enlarged ultra-clear image on the displayed image.
  • the present disclosure does not limit the superimposed position of the ultra-clear magnified image relative to the original displayed image.
  • FIG. 3 is a schematic diagram of displaying an image before executing the image processing method provided by the present disclosure according to an embodiment of the present disclosure.
  • 4-6 are schematic diagrams of displaying an image after the image processing method provided by the present disclosure is executed according to an embodiment of the present disclosure.
  • the terminal displays the image A, and performs super-resolution enlarging processing on the target image B1 through the image processing method provided in the present application to obtain an ultra-clear enlarged image B2 of the target image B1 .
  • step 140 is executed, optionally, as shown in FIG.
  • the super-clear enlarged image B2 is placed at the original target image B1, and the layer of the super-clear enlarged image B2 is positioned above the layer of the target image B1, Make the ultra-clear enlarged image B2 block the target image B1.
  • the ultra-clear enlarged image B2 is placed in an area outside the original target image B1 , so that the ultra-clear enlarged image B2 does not block the target image B1 .
  • the super-clear enlarged image B2 is made to completely cover the original image A, so that the display device of the terminal only displays the super-clear enlarged image B2 and does not display the image A.
  • the essence of the above technical solution is to allow the user to select a local area of the image displayed by the terminal, and to perform super-resolution enlargement processing and display based on the local area selected by the user. It can meet the user's demand for super-resolution magnification of a local area of an image, and can improve user experience.
  • the technical solution of the present disclosure can reduce the area that needs to be enlarged by allowing the user to independently select the target image, reduce the calculation difficulty, and do not need to think too much about the terminal. power consumption. Moreover, it can bring a stronger sense of clarity improvement without affecting business performance.
  • the above technical solutions can be applied to the case of processing pictures or videos. If the technical solution is applied to a video (such as a short video, a long video or a live broadcast) playing scene, it can make up for the blank that the partial region of the video is not currently enlarged.
  • a video such as a short video, a long video or a live broadcast
  • a mobile terminal such as a mobile phone
  • NPU embedded neural network processor
  • FIG. 7 is a flowchart of another image processing method provided by an embodiment of the present disclosure.
  • FIG. 7 is a specific example of FIG. 1 .
  • the image processing method includes:
  • Step 210 Receive an enlargement instruction for the displayed image.
  • Step 220 Acquire the image area designated to be enlarged on the display image according to the enlargement instruction, and use the image area designated to be enlarged on the display image as the target image.
  • Step 230 performing super-resolution magnification processing on the target image to obtain a super-clear magnified image of the target image.
  • Step 240 superimposing and displaying the enlarged ultra-clear image on the displayed image.
  • Steps 210 to 240 are respectively similar to the above S110 to S140. For specific descriptions, please refer to the above, which will not be repeated here.
  • Step 250 Determine whether the pre-calibrated object is included in the ultra-clear enlarged image. If yes, go to step 260; if no, end.
  • the image often includes at least one object, and some or all of the objects in the image can be calibrated in advance.
  • Calibration means establishing an association relationship between the selected object (ie, the calibration object) and calibration information.
  • the calibration information refers to information related to the calibration object.
  • the image includes a girl carrying a pink bag and wearing black shoes. Only the pink bag can be calibrated in advance, or only the black shoe can be calibrated, or the pink bag and the black shoe can be calibrated at the same time.
  • the calibration information can reflect attribute information related to the pink bag.
  • the calibration information may be set as the purchase link of the package, the selling price of the package, a multi-angle picture of the package, the item number of the package, and the like.
  • the calibration information of the object and the content displayed by the calibrated object in the ultra-clear magnified image may be partially the same, or may be completely different.
  • the identification information of the bag may or may not include its brand logo.
  • step of calibrating the object in the image needs to be performed before this step.
  • the execution subject for calibrating the object in the image and the execution subject of this step may be the same execution subject, or may be different execution subjects.
  • image recognition is performed on the ultra-clear magnified image, and based on the recognition result, it is determined whether the pre-calibrated object is included in the ultra-clear magnified image.
  • Step 260 Acquire the calibration information of the object, and superimpose the calibration information of the displayed object on the display image.
  • the present disclosure does not limit the display position of the calibration information.
  • the calibration information is occluded complementary to the ultra-clear magnified image.
  • the technical solution of this embodiment is set by setting that if the ultra-clear magnified image includes a pre-calibrated object, the calibration information of the object is displayed on the terminal display device together with the ultra-clear magnified image of the object. Because the calibration information can include information not included in the ultra-clear enlarged image. In essence, the calibration information is a supplement to the information related to the calibration object, and supplements the information that cannot be obtained only through the ultra-clear magnified image of the calibration object. In this way, the user does not need to conduct a network search for the calibrated object, and can quickly and conveniently understand its related content, which can simplify the user's operation steps and improve the user's favorability. This approach is conducive to the derivation of new business models.
  • FIG. 8 is a structural block diagram of an image processing apparatus provided by an embodiment of the present disclosure.
  • the image processing device includes:
  • a receiving module 310 configured to receive an enlargement instruction for the displayed image
  • the first obtaining module 320 is configured to obtain, according to the enlargement instruction, an image area designated to be enlarged on the display image, and use the designated image area to be enlarged on the display image as a target image;
  • a super-resolution magnification module 330 configured to perform super-resolution magnification processing on the target image to obtain a super-clear magnified image of the target image;
  • the display module 340 is configured to superimpose and display the ultra-clear enlarged image on the display image.
  • the zoom-in instruction is triggered by the user's operation of selecting the image area on the displayed image.
  • the operation of the user selecting the image area includes:
  • the image area is selected through the first icon provided on the display interface.
  • the selecting an image area through the first icon provided on the display interface includes:
  • the first acquisition module includes:
  • a first obtaining sub-module for obtaining the position of the first icon on the displayed image; and taking the position as the center, obtaining an image area within a preset range around the position, and using the position as the center
  • the image displayed inside is used as the target image.
  • selecting the image area through the first icon provided on the display interface includes:
  • An area is delineated on the display image by the first icon as the image area of the target image
  • the first acquisition module includes:
  • the second obtaining sub-module is configured to obtain the position of the area delineated by the first icon on the display image; and obtain the image displayed at the position, and use the image displayed at the position as the target image.
  • the super-resolution amplification module is used for:
  • the device also includes:
  • the determining module is configured to determine whether the super-resolution zoomed image includes a pre-calibrated zoomed image after the super-resolution zoomed-in process is performed on the target image by the super-resolution zoomed-in module to obtain an ultra-clear zoomed image of the target image. object;
  • a second acquisition module configured to acquire calibration information of the object when the pre-calibrated object is included in the ultra-clear magnified image
  • the display module is further configured to superimpose and display the calibration information of the object on the display image.
  • the image processing apparatus provided by the embodiment of the present disclosure can be used to execute any image processing method provided by the embodiment of the present disclosure, it has the same or corresponding beneficial effects as the executable image processing method, which is not repeated here.
  • An embodiment of the present disclosure further provides a terminal device, the terminal device includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned FIG. 1-FIG. The method of any one of 7.
  • FIG. 9 is a schematic structural diagram of a terminal device in an embodiment of the present disclosure.
  • the terminal device 1000 in the embodiment of the present disclosure may include, but is not limited to, such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal ( For example, mobile terminals such as car navigation terminals) and the like, and stationary terminals such as digital TVs, desktop computers, and the like.
  • the terminal device shown in FIG. 9 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.
  • a terminal device 1000 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 1001, which may be loaded into random access according to a program stored in a read only memory (ROM) 1002 or from a storage device 1008 Various appropriate operations and processes are executed by the programs in the memory (RAM) 1003 . In the RAM 1003, various programs and data required for the operation of the terminal device 1000 are also stored.
  • the processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004.
  • An input/output (I/O) interface 1005 is also connected to the bus 1004 .
  • the following devices can be connected to the I/O interface 1005: input devices 1006 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 1007 such as a computer; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009 .
  • the communication means 1009 may allow the terminal device 1000 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 9 shows the terminal device 1000 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 1009, or from the storage device 1008, or from the ROM 1002.
  • the processing apparatus 1001 the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium.
  • Data communications eg, communication networks
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • LAN local area networks
  • WAN wide area networks
  • the Internet eg, the Internet
  • peer-to-peer networks eg, ad hoc peer-to-peer networks
  • the above-mentioned computer-readable medium may be included in the above-mentioned terminal device; or may exist independently without being assembled into the terminal device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the terminal device, the terminal device:
  • the enlargement instruction acquire the image area designated to be enlarged on the display image, and use the image area designated to enlarge on the display image as the target image;
  • the super-clear enlarged image is displayed superimposed on the display image.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, or a combination thereof, or a combination thereof. , C++, and also conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider Internet service provider
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. Among them, the name of the unit does not constitute a limitation of the unit itself under certain circumstances.
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program is stored in the storage medium.
  • a computer program is stored in the storage medium.
  • the computer program is executed by a processor, the method of any of the foregoing embodiments in FIG. 1 to FIG. The implementation manner and beneficial effects are similar, and are not repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Controls And Circuits For Display Device (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开涉及一种图像的处理方法、装置、设备及存储介质，方法包括：接收到针对显示图像的放大指令；根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；对目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；在所述显示图像上叠加显示所述超清放大图像。本公开实施例提供的技术方案适用于对图片或视频进行处理的情况。其允许用户对终端显示图像的局部区域进行选择，并基于用户所选择的局部区域进行超分辨率放大处理并显示。其可以满足用户对图像局部区域进行超分辨率放大的需求，可以提高用户体验。

Description

一种图像的处理方法、装置、设备及存储介质
本申请要求于2020年10月30日提交中国专利局、申请号为202011189933.1、申请名称为“图像的处理方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及图像处理技术领域，尤其涉及一种图像的处理方法、装置、设备及存储介质。
背景技术
视频应用能够为用户提供视频浏览服务，向用户展示视频。用户可以基于展示的视频获取相关信息。
但是，受限于网络环境、视频数据大小以及视频的帧级编码方式，无法保证视频图像上的任意区域都能够清晰地向用户展示，从而导致视频的展示效果不佳，用户体验较差。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种图像的处理方法、装置、设备及存储介质。
本公开实施例的第一方面提供了一种图像的处理方法，方法包括：
接收到针对显示图像的放大指令；
根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
在所述显示图像上叠加显示所述超清放大图像。
本公开实施例的第二方面提供了一种图像处理装置，装置包括：
接收模块，用于接收到针对显示图像的放大指令；
第一获取模块，用于根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
超分辨率放大模块，用于对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
显示模块，用于在所述显示图像上叠加显示所述超清放大图像。
本公开实施例的第三方面提供了一种终端设备，该终端设备包括存储器和处理器，其中，存储器中存储有计算机程序，当该计算机程序被处理器执行时，可以实现上述第一方面的方法。
本公开实施例的第四方面提供了一种计算机可读存储介质，该存储介质中存储有计算机程序，当该计算机程序被处理器执行时，可以实现上述第一方面的方法。
本公开实施例提供的技术方案与现有技术相比具有如下优点：
本公开实施例提供的技术方案允许用户对终端显示图像的局部区域进行选择，并基于用户所选择的局部区域进行超分辨率放大处理并显示。其可以满足用户对图像局部区域进行超分辨率放大的需求，可以提高用户体验。
相比于全场景、全时段的视频超分辨率技术，本公开技术方案采用通过让用户来自主选择目标图像的方式，可缩小需要放大的区域，降低计算难度，不需要过多考虑终端功耗。并且，其可以带来更加强烈的清晰度感官提升，且不会对业务性能带来影响。
本公开实施例提供的技术方案可以适用于对图片或视频进行处理的情况。若将该技术方案应用于视频(如短视频、长视频或直播)播放场景时，其可以弥补目前完全没有对视频的局部区域进行放大处理的空白。
如果将本公开实施例提供的技术方案应用于移动终端(如手机)时，其可以充分发挥手机的嵌入式神经网络处理器(NPU)算力，有利于实现将性能优异的大型高清增强算法落地移动端的目的。
本公开实施例提供的技术方案通过设置若超清放大图像中包括预先标定的物体；则将该物体的标定信息，与该物体的超清放大图像一并显示于终端显示设备上。由于标定信息可以包括超清放大图像中不包括的信息。从本质上来说，标定信息是对标定物体相关信息的补充，补充仅通过标定物体的超清放大图像无法获得的信息。这样用户不需要对标定的物体进行网络搜索，就可以快速、便捷地了解其相关的内容，可以简化用户操作步骤，提升用户好感度。这种方式有利于衍生出新的商业模式。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本公开实施例提供的一种图像的处理方法的流程图；
图2为本公开实施例提供的一种执行步骤120的示意图；
图3为本公开实施例提供的一种在执行本公开提供的图像处理方法之前显示图像的示意图；
图4-图6为本公开实施例提供的一种在执行本公开提供的图像处理方法之后显示图像的示意图；
图7是本公开实施例提供的另一种图像的处理方法的流程图；
图8是本公开实施例提供的一种图像的处理装置的结构框图；
图9是本公开实施例中的一种终端设备的结构示意图。
具体实施方式
为了能够更清楚地理解本公开的上述目的、特征和优点，下面将对本公开的方案进行进一步描述。需要说明的是，在不冲突的情况下，本公开的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本公开，但本公开还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本公开的一部分实施例，而不是全部的实施例。
图1是本公开实施例提供的一种图像的处理方法的流程图，该方法可以由一种终端设备来执行。该终端设备可以示例性的理解为诸如手机、平板电脑、笔记本电脑、台式机、智能电视等具有图像处理能力的设备。在一些实施例中，本实施例所称的终端设备上可以搭载图像显示设备(比如显示屏，但不局限于显示屏)，终端设备可以通过显示屏进行图像显示，并通过本实施例的方法对图像的局部区域(即目标图像)进行超清放大显示。在另一些实施例中，本实施例所称的终端设备上还可以同时搭载拍摄设备，拍摄设备采集图像后，终端设备可以采用本实施例的方法对图像的局部区域进行超清放大显示。
需要说明的是，本申请提供的方法称之为图像的处理方法，其中图像包括图片或视频。进一步地，若图像为视频，其具体可以为短视频、长视频或直播视频等。
如图1所示，本实施例提供的方法包括如下步骤：
步骤110、接收到针对显示图像的放大指令。
放大指令是指用于指示终端针对其所显示的图像中某一局部区域(即目标图像)进行放大的指令。因此，放大指令的作用有两个，一是启动放大功能，二是确定目标图像。
可选地，放大指令由用户在显示图像上选择图像区域的操作触发。
用户在显示图像上选择图像区域的操作方法有多种，本申请对此不作限制。示例性地，可以预先在终端的显示屏中显示具有开启放大功能的虚拟按键。当识别到用户点击虚拟按键后，终端进入图像区域选择界面。或者，预先设置通过某种触控动作(如手指在屏幕中画出特定图形，如“L”、“W”或“O”等)来触发终端进入图像区域选择界面。当识别到用户输入该预设的触控动作后，终端进入图像区域选择界面。
在进入目标图像选择界面后，用户通过手指或显示界面上提供的第一图标(如画笔工具、放大镜工具等)进行目标放大的图像区域的选择。具体选择时，可以利用手指在显示图像上进行点击，那么以点击位置为中心的预设范围内的图像区域，为用户指定放大的目标图像，或将第一图标拖动到显示图像的某一位置处，那么以该位置为中心的预设范围内的图像区域，为用户指定放大的目标图像，或用手指或第一图标在显示图像上绘制封闭区域(如圆形、四边形等)，所绘制的封闭区域上的图像为目标图像。
可选地，使终端进入图像区域选择界面的虚拟按键和用于对图标区域进行选择的第一图标可以为同一图标，如均使用放大镜图标。
可选地，还可以设置开启放大功能和进行图像区域选择在一次操作中完成。例如，预先设置当接收到某个确定的触控动作(如在屏幕中画出“L”、“W”或“O”等)后，终端自 动开启放大功能，并基于触控动作中的触控轨迹确定目标放大的图像区域。
步骤120、根据放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像。
本步骤的实现方法有多种，本公开对此不作限制。在实际设置时，放大指令的输入方式不同，可以设置不同的用于执行本步骤的方法。
示例性地，若通过显示界面上提供的第一图标选择图像区域包括：指定第一图标在显示图像上的位置；本步骤的执行方法可以包括：获取第一图标在显示图像上的位置；以该位置为中心，获取该位置周围预设范围内的图像区域中显示的图像，将在预设范围内的图像区域中显示的图像作为目标图像。
图2为本公开实施例提供的一种执行步骤120的示意图。示例性地，参见图2，假设A为当前终端显示的图像，预设范围的确定方法为以第一图标在显示图像上的指定位置为圆心，以1cm为半径，得到的区域为预设范围。继续参见图2，若用户将放大镜工具拖动到B点，即指定放大镜工具在显示图像上的位置为B点的位置。在执行本步骤时，首先获取B点的位置数据，然后以B点所在位置为圆心，以1cm为半径，确定预设范围，进而将预设范围内的图像区域中显示的图像作为目标图像。
需要说明的是，在上述示例中，预设范围为圆形，并规定了半径为1cm，这仅是本公开的一个具体示例。本公开对预设范围的形状不作限制，可选地，预设范围可以为多边形、椭圆形等。此外，本申请对预设范围的尺寸也不作限制。
可选地，若通过显示界面上的第一图标选择目标图像，包括：通过第一图标圈定目标图像在显示图像上的区域位置；本步骤的执行方法可以包括：获取第一图标在显示图像上圈定的区域位置；根据区域位置，获取区域位置上的图像，并将区域位置上的图像作为目标图像。
示例性地，假设用户拖动放大镜工具，使拖动轨迹形成一个封闭区域，即通过放大镜工具圈定目标图像在显示图像上的区域的位置。在执行本步骤时，获取封闭区域所包围的区域的位置，然后，将该区域内的图像作为目标图像。
在另一种可能的实现方式中，当拖动轨迹未形成一个封闭区域时，可以根据拖动轨迹的形状进行圈定区域的补全。例如，当拖动轨迹为一个圆心角为300度的圆弧时，可以基于拖动轨迹当前的形状将圆弧补全为完整的封闭的圆形。再获取封闭的圆形所包围的区域的位置，将该区域内的图像作为目标图像。
步骤130、对目标图像进行超分辨率放大处理，得到目标图像的超清放大图像。
本步骤的实现方法有多种，示例性地，可以基于预设模型对目标图像进行超分辨率放大处理，得到目标分辨率的超清放大图像。
预设模型是用于对输入的图像进行超分辨率放大处理，输出处理后的图像的模型。具体的，预设模型，例如可以包括对抗网络模型。
示例性地，使用基于深度学习卷积神经网络图像超分辨率技术，结合生成对抗网络(GAN)，使得超分辨率放大处理后的图像在感官上更像真实图像。如使得用户可以看清原本模糊的车牌、文字，商品的品牌、商品的细节、人脸或者月球表面的沟壑等，以获得令 人惊艳的放大效果。
一般的对抗网络模型包括两部分分别为图像生成器和图像判断器，其中图像生成器以输入图像的原始分辨率为基础，生成更高分辨率的图像，图像判断器用于识别新生成的图像的分辨率是否达到预设分辨率标准，若未达到，则继续对图像生成器进行训练，直到图像生成器能够生成高于预设分辨率标准的图像为止，得到本实施例中所称的对抗网络模型。
步骤140、在显示图像上叠加显示超清放大图像。
在执行本步骤时，本公开对超清放大图像相对于原显示图像的叠加位置不作限制。
示例性地，图3为本公开实施例提供的一种在执行本公开提供的图像处理方法之前显示图像的示意图。图4-图6为本公开实施例提供的一种在执行本公开提供的图像处理方法之后显示图像的示意图。参见图3，在执行本公开提供的图像处理方法之前终端显示图像A，通过本申请提供的图像处理方法对目标图像B1进行超分辨率放大处理，得到目标图像B1的超清放大图像B2。在执行步骤140时，可选地，如图4所示，将超清放大图像B2放置于原目标图像B1处，并使得超清放大图像B2的图层位于目标图像B1的图层之上，使得超清放大图像B2遮挡目标图像B1。可选地，如图5所示，将超清放大图像B2放置于原目标图像B1之外的区域，使得超清放大图像B2不遮挡目标图像B1。或者，如图6所示，使得超清放大图像B2完全覆盖原图像A，使得终端的显示设备仅显示超清放大图像B2，不显示图像A。
上述技术方案的实质是，允许用户对终端显示图像的局部区域进行选择，并基于用户所选择的局部区域进行超分辨率放大处理并显示。其可以满足用户对图像局部区域进行超分辨率放大的需求，可以提高用户体验。
并且，相比于全场景、全时段的视频超分辨率技术，本公开技术方案采用通过让用户来自主选择目标图像的方式，可缩小需要放大的区域，降低计算难度，不需要过多考虑终端功耗。并且，其可以带来更加强烈的清晰度感官提升，且不会对业务性能带来影响。
此外，上述技术方案可以适用于对图片或视频进行处理的情况。若将该技术方案应用于视频(如短视频、长视频或直播)播放场景时，其可以弥补目前完全没有对视频的局部区域进行放大处理的空白。
如果将上述技术方案应用于移动终端(如手机)时，其可以充分发挥手机的嵌入式神经网络处理器(NPU)算力，有利于实现将性能优异的大型高清增强算法落地移动端的目的。
图7是本公开实施例提供的另一种图像的处理方法的流程图。图7为图1中的一个具体示例。参见图7，该图像的处理方法包括：
步骤210、接收到针对显示图像的放大指令。
步骤220、根据放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像。
步骤230、对目标图像进行超分辨率放大处理，得到目标图像的超清放大图像。
步骤240、在显示图像上叠加显示超清放大图像。
步骤210-步骤240分别与上述S110-S140类似，具体描述请参见上文，在此不再赘述。
步骤250、判断超清放大图像中是否包括预先标定的物体。若是，执行步骤260；若否， 结束。
在实际中，图像中往往包括至少一个物体，可以预先针对图像中的部分或全部物体进行标定。标定的意思是建立所选中的物体(即标定物体)和标定信息的关联关系。标定信息是指与该标定物体相关的信息。
示例性地，假设图像中包括一个女孩，女孩手提粉色的包，脚穿黑色的鞋。可以预先仅对该粉色的包进行标定，也可以仅对该黑色的鞋进行标定，或者同时对该粉色的包和黑色的鞋进行标定。
进一步地，假设仅对该粉色的包进行标定，标定信息为能够反映与该粉色的包相关的属性信息。示例性地，标定信息可以设置为该包的购买链接、该包的售价、该包多角度图片以及该包的货号等。
需要说明的是，在实际中，物体的标定信息与超清放大图像中标定的物体所展示的内容可以部分相同，也可以完全不同。示例性地，若超清放大图像中清楚的展示出包的品牌标识(logo)，与该包的标定信息可以包括其品牌标识，也可以不包括其品牌标识。
需要说明的是，对图像中的物体进行标定的步骤需要在本步骤之前执行。并且对图像中的物体进行标定的执行主体与本步骤的执行主体可以是同一个执行主体，也可以是不同的执行主体。
需要对图像中的物体进行标定的实际场景有多种，本申请对此不作限制。示例性地，商家在制作新产品的推广视频时，对其推广视频中展示的商品进行标定。
本步骤的实现方法有多种，例如，对超清放大图像进行图像识别，基于识别结果，判断超清放大图像中是否包括预先标定的物体。
步骤260、获取物体的标定信息，并在显示图像上叠加显示物体的标定信息。
在执行本步骤时，本公开对标定信息的显示位置不作限制。可选地，该标定信息与超清放大图像互补遮挡。
本实施例技术方案通过设置若超清放大图像中包括预先标定的物体；则将该物体的标定信息，与该物体的超清放大图像一并显示于终端显示设备上。由于标定信息可以包括超清放大图像中不包括的信息。从本质上来说，标定信息是对标定物体相关信息的补充，补充仅通过标定物体的超清放大图像无法获得的信息。这样用户不需要对标定的物体进行网络搜索，就可以快速、便捷地了解其相关的内容，可以简化用户操作步骤，提升用户好感度。这种方式有利于衍生出新的商业模式。
图8是本公开实施例提供的一种图像的处理装置的结构框图。参见图8，该图像的处理装置包括：
接收模块310，用于接收到针对显示图像的放大指令；
第一获取模块320，用于根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
超分辨率放大模块330，用于对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
显示模块340，用于在所述显示图像上叠加显示所述超清放大图像。
进一步地，所述放大指令由所述用户在所述显示图像上选择所述图像区域的操作触发。
进一步地，所述用户选择所述图像区域的操作包括：
通过显示界面上提供的第一图标选择图像区域。
进一步地，
所述通过显示界面上提供的第一图标选择图像区域，包括：
指定所述第一图标在所述显示图像上的位置；
所述第一获取模块，包括：
第一获取子模块，用于获取所述第一图标在所述显示图像上的位置；以及以所述位置为中心，获取所述位置周围预设范围内的图像区域，将在所述图像区域内显示的图像作为目标图像。
进一步地，所述通过显示界面上提供的第一图标选择图像区域，包括：
通过所述第一图标在所述显示图像上圈定一个区域作为目标图像的图像区域；
所述第一获取模块，包括：
第二获取子模块，用于获取所述第一图标在所述显示图像上圈定的区域的位置；以及获取所述位置上显示的图像，将所述位置上显示的图像作为目标图像。
进一步地，所述超分辨率放大模块，用于：
基于预设模型对所述目标图像进行超分辨率放大处理，得到目标分辨率的超清放大图像。
进一步地，所述装置还包括：
确定模块，用于在所述超分辨率放大模块对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像之后，确定所述超清放大图像中是否包括预先标定的物体；
第二获取模块，用于在所述超清放大图像中包括所述预先标定的物体时，获取所述物体的标定信息；
所述显示模块，还用于在所述显示图像上叠加显示所述物体的标定信息。
由于本公开实施例提供的图像处理装置，可以用于执行本公开实施例提供的任意一种图像处理方法，其具有其可执行的图像处理方法相同或相应的有益效果，此处不再赘述。
本公开实施例还提供一种终端设备，该终端设备包括处理器和存储器，其中，所述存储器中存储有计算机程序，当所述计算机程序被所述处理器执行时可以实现上述图1-图7中任一实施例的方法。
示例的，图9是本公开实施例中的一种终端设备的结构示意图。下面具体参考图9，其示出了适于用来实现本公开实施例中的终端设备1000的结构示意图。本公开实施例中的终端设备1000可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图9示出的终端设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图9所示，终端设备1000可以包括处理装置(例如中央处理器、图形处理器等)1001，其可以根据存储在只读存储器(ROM)1002中的程序或者从存储装置1008加载到随机访问 存储器(RAM)1003中的程序而执行各种适当的动作和处理。在RAM 1003中，还存储有终端设备1000操作所需的各种程序和数据。处理装置1001、ROM 1002以及RAM 1003通过总线1004彼此相连。输入/输出(I/O)接口1005也连接至总线1004。
通常，以下装置可以连接至I/O接口1005：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置1006；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置1007；包括例如磁带、硬盘等的存储装置1008；以及通信装置1009。通信装置1009可以允许终端设备1000与其他设备进行无线或有线通信以交换数据。虽然图9示出了具有各种装置的终端设备1000，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置1009从网络上被下载和安装，或者从存储装置1008被安装，或者从ROM 1002被安装。在该计算机程序被处理装置1001执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protoco l，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述终端设备中所包含的；也可以是单独存在，而未装配入该终端设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该终端设备执行时，使得该终端设备：
接收到针对显示图像的放大指令；
根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
在所述显示图像上叠加显示所述超清放大图像。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Sma l lta l k、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上***(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行***、装置或设备使用或与指令执行***、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体***、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、 磁储存设备、或上述内容的任何合适组合。
本公开实施例还提供一种计算机可读存储介质，所述存储介质中存储有计算机程序，当所述计算机程序被处理器执行时可以实现上述图1-图7任一实施例的方法，其执行方式和有益效果类似，在这里不再赘述。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所述的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (16)

  1. 一种图像的处理方法，其特征在于，包括：
    接收到针对显示图像的放大指令；
    根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
    对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
    在所述显示图像上叠加显示所述超清放大图像。
  2. 根据权利要求1所述的方法，其特征在于，所述放大指令由所述用户在所述显示图像上选择所述图像区域的操作触发。
  3. 根据权利要求2所述的方法，其特征在于，所述用户选择所述图像区域的操作包括：
    通过显示界面上提供的第一图标选择图像区域。
  4. 根据权利要求3所述的方法，其特征在于，所述通过显示界面上提供的第一图标选择图像区域，包括：
    指定所述第一图标在所述显示图像上的位置；
    所述获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像，包括：
    获取所述第一图标在所述显示图像上的位置；
    以所述位置为中心，获取所述位置周围预设范围内的图像区域，将在所述图像区域内显示的图像作为目标图像。
  5. 根据权利要求3所述的方法，其特征在于，所述通过显示界面上提供的第一图标选择图像区域，包括：
    通过所述第一图标在所述显示图像上圈定一个区域作为目标图像的图像区域；
    所述获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像，包括：
    获取所述第一图标在所述显示图像上圈定的区域的位置；
    获取所述位置上显示的图像，将所述位置上显示的图像作为目标图像。
  6. 根据权利要求1-5中任一项所述的方法，其特征在于，所述对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像，包括：
    基于预设模型对所述目标图像进行超分辨率放大处理，得到目标分辨率的超清放大图像。
  7. 根据权利要求1所述的方法，其特征在于，所述对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像之后，所述方法还包括：
    当所述超清放大图像中包括预先标定的物体时，获取所述物体的标定信息，并在所述显示图像上叠加显示所述物体的标定信息。
  8. 一种图像处理装置，其特征在于，包括：
    接收模块，用于接收到针对显示图像的放大指令；
    第一获取模块，用于根据所述放大指令，获取在显示图像上被指定放大的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像；
    超分辨率放大模块，用于对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像；
    显示模块，用于在所述显示图像上叠加显示所述超清放大图像。
  9. 根据权利要求8所述的装置，其特征在于，所述放大指令由所述用户在所述显示图像上选择所述图像区域的操作触发。
  10. 根据权利要求9所述的装置，其特征在于，所述用户选择所述图像区域的操作包括：
    通过显示界面上提供的第一图标选择图像区域。
  11. 根据权利要求10所述的装置，其特征在于，所述通过显示界面上提供的第一图标选择图像区域，包括：
    指定所述第一图标在所述显示图像上的位置；
    所述第一获取模块，包括：
    第一获取子模块，用于获取所述第一图标在所述显示图像上的位置；以及以所述位置为中心，获取所述位置周围预设范围内的图像区域，将所述在显示图像上被指定放大的图像区域作为目标图像。
  12. 根据权利要求10所述的装置，其特征在于，所述通过显示界面上提供的第一图标选择图像区域，包括：
    通过所述第一图标在所述显示图像上圈定一个区域作为目标图像的图像区域；
    所述第一获取模块，包括：
    第二获取子模块，用于获取所述第一图标在所述显示图像上圈定的区域的位置；以及获取所述位置上显示的图像，将所述位置上显示的图像作为目标图像。
  13. 根据权利要求8-12中任一项所述的装置，其特征在于，所述超分辨率放大模块，用于：
    基于预设的对抗网络模型对所述目标图像进行超分辨率放大处理，得到目标分辨率的超清放大图像。
  14. 根据权利要求8所述的装置，其特征在于，所述装置还包括：
    确定模块，用于在所述超分辨率放大模块对所述目标图像进行超分辨率放大处理，得到所述目标图像的超清放大图像之后，确定所述超清放大图像中是否包括预先标定的物体；
    第二获取模块，用于在所述超清放大图像中包括所述预先标定的物体时，获取所述物体的标定信息；
    所述显示模块，还用于在所述显示图像上叠加显示所述物体的标定信息。
  15. 一种终端设备，其特征在于，包括：
    存储器和处理器；
    其中，所述存储器中存储有计算机程序，当所述计算机程序被所述处理器执行时，所述处理器执行如权利要求1-7中任一项所述的方法。
  16. 一种计算机可读存储介质，其特征在于，所述存储介质中存储有计算机程序，当所述计算机程序被处理器执行时，所述处理器执行如权利要求1-7中任一项所述的方法。
PCT/CN2021/116137 2020-10-30 2021-09-02 一种图像的处理方法、装置、设备及存储介质 WO2022088970A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011189933.1 2020-10-30
CN202011189933.1A CN112308780A (zh) 2020-10-30 2020-10-30 图像的处理方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022088970A1 true WO2022088970A1 (zh) 2022-05-05

Family

ID=74334148

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/116137 WO2022088970A1 (zh) 2020-10-30 2021-09-02 一种图像的处理方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN112308780A (zh)
WO (1) WO2022088970A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024066661A1 (zh) * 2022-09-27 2024-04-04 万有引力（宁波）电子科技有限公司 图像处理器、处理方法、存储介质及扩展现实显示装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112308780A (zh) * 2020-10-30 2021-02-02 北京字跳网络技术有限公司 图像的处理方法、装置、设备及存储介质
CN114598823B (zh) * 2022-03-11 2024-06-14 北京字跳网络技术有限公司 特效视频生成方法、装置、电子设备及存储介质
TWI825951B (zh) * 2022-08-26 2023-12-11 瑞昱半導體股份有限公司 顯示裝置及影像顯示方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6816626B1 (en) * 2001-04-27 2004-11-09 Cisco Technology, Inc. Bandwidth conserving near-end picture-in-picture videotelephony
CN102106145A (zh) * 2008-07-30 2011-06-22 三星电子株式会社 用于显示再现图像的放大的目标区域的装置和方法
CN104268827A (zh) * 2014-09-24 2015-01-07 三星电子（中国）研发中心 视频图像局部区域放大的方法和装置
CN110362250A (zh) * 2018-04-09 2019-10-22 杭州海康威视数字技术股份有限公司 一种图像局部放大的方法、装置和显示设备
CN111741274A (zh) * 2020-08-25 2020-10-02 北京中联合超高清协同技术中心有限公司 一种支持画面局部放大和漫游的超高清视频监看方法
CN112308780A (zh) * 2020-10-30 2021-02-02 北京字跳网络技术有限公司 图像的处理方法、装置、设备及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9635246B2 (en) * 2013-06-21 2017-04-25 Qualcomm Incorporated Systems and methods to super resolve a user-selected region of interest
CN111710017A (zh) * 2020-06-05 2020-09-25 北京有竹居网络技术有限公司 展示方法、装置和电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6816626B1 (en) * 2001-04-27 2004-11-09 Cisco Technology, Inc. Bandwidth conserving near-end picture-in-picture videotelephony
CN102106145A (zh) * 2008-07-30 2011-06-22 三星电子株式会社 用于显示再现图像的放大的目标区域的装置和方法
CN104268827A (zh) * 2014-09-24 2015-01-07 三星电子（中国）研发中心 视频图像局部区域放大的方法和装置
CN110362250A (zh) * 2018-04-09 2019-10-22 杭州海康威视数字技术股份有限公司 一种图像局部放大的方法、装置和显示设备
CN111741274A (zh) * 2020-08-25 2020-10-02 北京中联合超高清协同技术中心有限公司 一种支持画面局部放大和漫游的超高清视频监看方法
CN112308780A (zh) * 2020-10-30 2021-02-02 北京字跳网络技术有限公司 图像的处理方法、装置、设备及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024066661A1 (zh) * 2022-09-27 2024-04-04 万有引力（宁波）电子科技有限公司 图像处理器、处理方法、存储介质及扩展现实显示装置

Also Published As

Publication number Publication date
CN112308780A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
WO2022088970A1 (zh) 一种图像的处理方法、装置、设备及存储介质
WO2021218519A1 (zh) 应用程序的页面切换方法、装置、电子设备及非暂时性可读存储介质
WO2023051185A1 (zh) 图像处理方法、装置、电子设备及存储介质
CN110070496B (zh) 图像特效的生成方法、装置和硬件装置
WO2023125374A1 (zh) 图像处理方法、装置、电子设备及存储介质
WO2021139382A1 (zh) 人脸图像的处理方法、装置、可读介质和电子设备
WO2022100735A1 (zh) 视频处理方法、装置、电子设备及存储介质
CN111935544B (zh) 交互方法、装置和电子设备
WO2022171024A1 (zh) 图像显示方法、装置、设备及介质
WO2022142875A1 (zh) 图像处理方法、装置、电子设备及存储介质
US20240119082A1 (en) Method, apparatus, device, readable storage medium and product for media content processing
JP2023515607A (ja) 画像特殊効果の処理方法及び装置
WO2024037556A1 (zh) 图像处理方法、装置、设备及存储介质
CN113535105B (zh) 媒体文件处理方法、装置、设备、可读存储介质及产品
WO2024051639A1 (zh) 图像处理方法、装置、设备及存储介质和产品
WO2023098576A1 (zh) 图像处理方法、装置、设备及介质
WO2023109564A1 (zh) 视频图像处理方法、装置、电子设备及存储介质
WO2023098649A1 (zh) 视频生成方法、装置、设备及存储介质
US9723206B1 (en) Enabling a true surround view of a 360 panorama via a dynamic cylindrical projection of the panorama
WO2022257677A1 (zh) 图像处理方法、装置、设备及存储介质
WO2022262473A1 (zh) 图像处理方法、装置、设备及存储介质
WO2022237435A1 (zh) 更换画面中的背景的方法、设备、存储介质及程序产品
EP4170588A2 (en) Video photographing method and apparatus, and device and storage medium
WO2021073204A1 (zh) 对象的显示方法、装置、电子设备及计算机可读存储介质
WO2021031909A1 (zh) 数据内容的输出方法、装置、电子设备及计算机可读介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21884701

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21884701

Country of ref document: EP

Kind code of ref document: A1