WO2023016150A1 - 图像处理方法、装置、设备及存储介质 - Google Patents

图像处理方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023016150A1
WO2023016150A1 PCT/CN2022/104273 CN2022104273W WO2023016150A1 WO 2023016150 A1 WO2023016150 A1 WO 2023016150A1 CN 2022104273 W CN2022104273 W CN 2022104273W WO 2023016150 A1 WO2023016150 A1 WO 2023016150A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
sky
attribute information
target image
brightness
Prior art date
Application number
PCT/CN2022/104273
Other languages
English (en)
French (fr)
Inventor
卢智雄
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 WO2023016150A1 publication Critical patent/WO2023016150A1/zh

Links

Images

Classifications

    • 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
    • G06F3/04842—Selection of displayed objects or displayed text elements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/60—Editing figures and text; Combining figures or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection

Definitions

  • Embodiments of the present disclosure relate to the technical field of image processing, and in particular, to an image processing method, device, device, and storage medium.
  • the video application provided by the related technology can add special effects to video images to increase the fun of the video.
  • related technologies often have the problem that the added special effect does not match the scene of the video, which reduces the added effect of the special effect and causes poor user experience.
  • embodiments of the present disclosure provide an image processing method, device, device, and storage medium.
  • an embodiment of the present disclosure provides an image processing method, including:
  • the acquiring the attribute information of the sky in the target image includes:
  • the target image is processed based on a preset recognition model to obtain attribute information of the sky in the target image, and the attribute information includes at least one of weather, time, and type of region.
  • the acquiring the attribute information of the sky in the target image includes:
  • At least one of the time, the region type, the orientation and the weather is used as attribute information of the sky.
  • performing corresponding special effect processing on the sky image in the target image including:
  • the insertion object is at least one of an image, an animation, or an AR object;
  • the determining an insertion object matching the attribute information based on the attribute information includes:
  • the selected candidate object is used as an insertion object.
  • the method further includes:
  • the brightness of the insertion object is adjusted, so that the brightness of the insertion object matches the brightness of the insertion position.
  • inserting the insertion object onto the sky image includes:
  • an image processing device including:
  • an acquisition unit configured to acquire a target image and acquire attribute information of the sky in the target image
  • An image segmentation unit configured to perform sky segmentation processing on the target image to obtain a sky image in the target image
  • a special effect processing unit configured to perform corresponding special effect processing on the sky image in the target image based on the attribute information.
  • the acquiring unit is specifically configured to process the target image based on a preset recognition model to obtain attribute information of the sky in the target image, and the attribute information includes weather, time, and location. at least one of the types.
  • the acquisition unit includes:
  • An attribute acquisition subunit configured to acquire at least one of the time, region type, orientation, and weather at the location when the shooting device captures the target image
  • the attribute assignment subunit is configured to use at least one of the time, the region type, the orientation and the weather as the attribute information of the sky.
  • the special effects processing unit includes:
  • An insertion object selection subunit configured to determine an insertion object matching the attribute information based on the attribute information; the insertion object is at least one of an image, an animation, or an AR object;
  • the special effect processing unit further includes:
  • a display subunit configured to display multiple candidate objects matching the attribute information
  • the selection detection subunit is configured to use the selected candidate object as an insertion object in response to a selection operation on a candidate object among the plurality of candidate objects.
  • the device also includes:
  • a brightness adjustment unit configured to adjust the brightness of the insertion object according to the brightness of the insertion position after the image adding subunit adds the insertion object to the sky image, so that the brightness of the insertion object is the same as The brightness at the insertion position is matched.
  • the special effect processing unit further includes an insertion position acquisition subunit, configured to acquire an insertion position designated by a user on the sky image;
  • the adding subunit inserts the insertion object at an insertion position designated by the user on the sky image.
  • an embodiment 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 method of the above-mentioned first aspect can be implemented .
  • an embodiment of the present disclosure provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method in the above-mentioned first aspect can be implemented.
  • the attribute information of the sky in the target image and the sky image in the target image are firstly acquired, and then the sky image in the target image is subjected to corresponding special effect processing according to the attribute information to ensure that the effect of the special effect processing is consistent with Matching the sky image in the target image improves the effect of adding special effects, which in turn improves the user experience.
  • FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a target image to be processed provided by an embodiment of the present disclosure
  • Fig. 3 is the target image obtained through special effects processing based on Fig. 2;
  • FIG. 4 is a target image to be processed provided by another embodiment of the present disclosure.
  • Fig. 5 is the target image obtained through special effects processing based on Fig. 4;
  • Fig. 6 is a flowchart of an image processing method provided by some other embodiments of the present disclosure.
  • Fig. 7 is a schematic diagram obtained by directly inserting the insertion object into the target image
  • Fig. 8 is a schematic diagram obtained by adjusting the brightness of an inserted object
  • FIG. 9 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure.
  • Fig. 10 is a schematic structural diagram of a terminal device in some embodiments of the present disclosure.
  • FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure.
  • the method can be executed by a terminal device.
  • the terminal device can be understood as an example of a smart phone, a tablet computer, a notebook computer, a desktop computer, and a smart TV, etc., which have image processing capabilities.
  • the image processing method provided by the embodiment of the present disclosure includes S101-S103.
  • S101 Acquire a target image, and acquire attribute information of the sky in the target image.
  • the target image is an image with sky pixel content.
  • the target image can be an image stored in a picture format, or a frame image in a video file stored in a video format.
  • the terminal device may load and obtain the target image from a local storage, or may acquire the target image through an image acquisition device on the terminal device. It should be noted that, the manner of acquiring the target image in the embodiments of the present disclosure is not limited to the foregoing manner of loading from a local memory and capturing by an image acquisition device, and may also be other manners known in the art.
  • the attribute information of the sky is information used to characterize the features of the sky in the target image.
  • the attribute information of the sky may include at least one of weather, time, type of region, and shooting orientation.
  • the weather can be sunny, cloudy, rainy or cloudy
  • the time can be early morning, morning, noon, evening or evening
  • the location can be urban, rural or wild
  • the shooting orientation can be against the sun or along the sun.
  • the attribute information of the sky is not limited to the aforementioned examples, and may be other attribute information.
  • acquiring the attribute information of the sky in the target image in S101 may include S1011: processing the target image based on a preset recognition model to obtain the attribute information of the sky in the target image.
  • the preset recognition model is a model trained by using sample images and corresponding attribute labels, wherein the sample image is an image including the sky, and the attribute label is a label made according to the attribute information of the sky in the sample image.
  • the terminal device after obtaining the target image, the terminal device first processes the target image to obtain a standard-sized target image. Then the terminal device inputs the target image of standard size into the preset recognition model to obtain the attribute information of the sky in the target image.
  • the attribute information of the sky obtained in S1011 may include at least one of weather, time, and type of region.
  • S101 acquiring the attribute information of the sky in the target image may include S1012-S1013.
  • S1012 Obtain at least one of the time, region type, orientation, and weather at the location when the shooting device shoots the target image.
  • S1013 Using at least one of time, region type, orientation and weather as attribute information of the sky.
  • the terminal device uses the image acquisition device to capture the target image, it obtains the aforementioned information such as time, region type, orientation or weather by acquiring detection signals generated by various sensors or by sending a query request to the server.
  • the terminal device may acquire the location coordinates generated by the positioning device, and determine the region type of the current region according to the location coordinates and map information. For another example, in some other embodiments, the terminal device may send the geographic location and time when the target image is captured to the weather server, so as to obtain the weather determined by the weather server according to the geographic location and time. For another example, the terminal device may obtain the detection signal generated by the magnetoresistive sensor, so as to obtain the orientation when the target image is captured.
  • S102 Perform sky segmentation processing on the target image to obtain a sky image in the target image.
  • Performing sky segmentation processing on the target image to obtain the sky image in the target image refers to identifying the sky-earth boundary in the target image, so as to use the pixel image above the sky-earth boundary as the sky image.
  • the terminal device may use a pre-trained sky segmentation model to perform sky segmentation processing on the target image to obtain the sky image in the target image.
  • the sky segmentation model is a model trained using sample images and corresponding marked sky regions.
  • the terminal device may also obtain the sky image in the target image by other methods known in the art.
  • the terminal device executes S103 to perform corresponding special effect processing on the sky image in the target image based on the attribute information, which may specifically include S1031-S1032.
  • the terminal device pre-stores insertion objects corresponding to various attribute information of the sky, and the insertion objects may be at least one of images, animations, or AR objects.
  • a sun image matching a sunny day, a rain cloud image matching a rainy day, and a dark cloud image matching a cloudy day may be stored in the database of the terminal device.
  • an image of an aircraft matching a sunny day in the daytime and an image of fireworks matching a sunny day at night may be stored in the database of the terminal device.
  • the terminal device queries the database based on the attribute information, and can determine an insertion object matching the attribute information.
  • the terminal device After determining the insertion object matching the attribute information, the terminal device adds the insertion object to the sky image area of the target image to obtain the target image with added special effects.
  • FIG. 2 is a target image to be processed provided by an embodiment of the present disclosure
  • FIG. 3 is a target image obtained based on FIG. 2 after special effect processing.
  • the target image 21 is an image of a sunny city
  • the corresponding attribute information of the sky includes the time being early morning, the weather being sunny, and the region type being city.
  • the terminal device may determine that the insertion object is the aircraft image 22 based on the foregoing attribute information.
  • the aircraft image 22 is added to the sky image of FIG. 2 to obtain FIG. 3 .
  • FIG. 4 is a target image to be processed provided by another embodiment of the present disclosure
  • FIG. 5 is a target image processed with special effects obtained based on FIG. 4
  • the target image 41 is an image of a sunny city
  • the corresponding attribute information of the sky includes the time being night, the weather being sunny, and the region type being city.
  • the object is determined to be the fireworks image 42 based on the aforementioned attribute information.
  • the fireworks image 42 is added to the sky image of FIG. 4 to obtain FIG. 5 .
  • special effect processing methods can also be used to process the sky image in the target image, such as performing animation processing on the sky image based on attribute information, or adjusting the brightness, clarity, color or saturation.
  • the special effect processing method is not limited to the foregoing method, and may also be other methods known in the art.
  • the image processing method provided by the embodiments of the present disclosure first acquires the attribute information of the sky in the target image and the sky image in the target image, and then performs corresponding special effect processing on the sky image in the target image according to the attribute information, so as to ensure that the effect of the special effect processing is consistent with Matching the sky image in the target image improves the effect of special effect addition, which in turn improves the user experience.
  • Fig. 6 is a flowchart of an image processing method provided by some other embodiments of the present disclosure. As shown in FIG. 6 , in some other embodiments of the present disclosure, the image processing method includes S601-S606.
  • S601 Acquire a target image, and acquire attribute information of the sky in the target image.
  • S602 Based on the attribute information, determine multiple candidate objects matching the attribute information.
  • S603 Display multiple candidate objects to the user.
  • S604 In response to detecting a selection operation on a candidate object, determine the selected candidate object as an insertion object.
  • S605 Perform sky segmentation processing on the target image to obtain a sky image in the target image.
  • a plurality of matching candidate objects are stored in the database of the terminal device, and the candidate objects can be images, animations, etc. or at least one of AR objects.
  • the terminal device After acquiring the attribute information of the sky in the target image, the terminal device determines a matching object as a candidate object based on the attribute information. Subsequently, the terminal device uses the display device to present multiple candidate objects to the user for selection by the user. After detecting the user's selection operation on a certain candidate object, the terminal device takes the selected candidate object as an insertion object and inserts it into the sky image.
  • the user can select an insertion object from multiple candidate objects, and then insert the insertion object into the target image to obtain a target image with special effects added. Since the insertion object is determined by the user's selection, the obtained target image with added special effects can better meet the needs of the user.
  • S606 adding the insertion object to the target image may include S6061-S6062.
  • S6061 Obtain the insertion position specified by the user on the sky image.
  • the user-specified inset position is used to indicate where the inset object is added to the sky image.
  • the terminal device may prompt the user to perform a click operation in the sky image, so as to obtain the insertion position specified by the user.
  • Adding the insertion object to the insertion position specified by the user can make the obtained target image with added special effects more in line with the needs of the user.
  • the image processing method may further include S607.
  • S607 Adjust the brightness of the insertion object according to the brightness of the insertion position, so that the brightness of the insertion object matches the brightness of the insertion position.
  • Fig. 7 is a schematic diagram obtained by directly inserting an insertion object into a target image.
  • Fig. 8 is a schematic diagram obtained by adjusting the inserted object.
  • the insertion object is an aircraft image 71 . If the aircraft image 71 is directly inserted into the target image without adjusting its brightness, as shown in FIG. 7 , the brightness difference between the aircraft image 71 and the target image is relatively large, so that the obtained special effect image has a large contrast.
  • FIG. 8 after the brightness of the airplane image 71 is adjusted based on the brightness of the insertion position, the brightness of the airplane image 71 matches the brightness of the target image, and the contrast of the special effect image is more reasonable.
  • the brightness of the inserted object does not match the brightness of the target image where it is inserted. Inserting an inset object into a sky image without adjustments can result in an unnaturally high contrast in the resulting image.
  • the embodiment of the present disclosure adjusts the brightness of the inserted object according to the brightness at the inserted position, so that the brightness of the inserted object matches the brightness of the inserted position, and finally obtains a more natural special effect image.
  • FIG. 9 is a schematic structural diagram of an image processing apparatus provided by an embodiment of the present disclosure, and the image processing apparatus may be understood as the above-mentioned terminal device or some functional modules in the above-mentioned terminal device.
  • an image processing device 900 includes an acquisition unit 901 , an image segmentation unit 902 and a special effect processing unit 903 .
  • the acquiring unit 901 is configured to acquire a target image and attribute information of the sky in the target image.
  • the image segmentation unit 902 is configured to perform sky segmentation processing on the target image to obtain a sky image in the target image.
  • the special effect processing unit 903 is configured to perform corresponding special effect processing on the sky image in the target image based on the attribute information.
  • the acquisition unit 901 processes the target image based on a preset recognition model to obtain attribute information of the sky in the target image, and the attribute information includes at least one of weather, time, and type of region .
  • the acquiring unit 901 includes an attribute acquiring subunit and an attribute assigning subunit.
  • the attribute acquisition subunit is used to acquire at least one of the time, region type, orientation and weather at the location when the shooting device shoots the target image.
  • the attribute assignment subunit is used to use at least one of time, region type, orientation and weather as attribute information of the sky.
  • the special effect processing unit 903 includes an insertion object selection subunit and an addition subunit.
  • the insertion object selection subunit is used to determine an insertion object matching the attribute information based on the attribute information; the insertion object is at least one of an image, an animation, or an AR object.
  • the image selection subunit determines a plurality of candidate objects matching the attribute information based on the attribute information.
  • the special effect processing unit 903 also includes a presentation subunit and a selection detection subunit.
  • the display subunit is used to display a plurality of candidate objects; the selection detection subunit is used to determine the selected candidate object as an insertion object when a selection operation on a candidate object is detected.
  • the image processing unit further includes a brightness adjustment unit configured to adjust the brightness of the inserted object according to the brightness of the insertion position after the adding subunit adds the inserted object to the sky image, Makes the brightness of the inserted object match the brightness at the insertion location.
  • a brightness adjustment unit configured to adjust the brightness of the inserted object according to the brightness of the insertion position after the adding subunit adds the inserted object to the sky image, Makes the brightness of the inserted object match the brightness at the insertion location.
  • the special effect processing unit 903 further includes an insertion position obtaining subunit, and the position obtaining subunit is configured to obtain the insertion position specified by the user on the sky image.
  • the corresponding image adding subunit adds the insertion object to the insertion position.
  • An embodiment of the present disclosure also 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 image processing method provided by any of the above method embodiments can be implemented .
  • FIG. 10 is a schematic structural diagram of a terminal device in some embodiments of the present disclosure.
  • FIG. 10 shows a schematic structural diagram of a terminal device 1000 suitable for implementing an embodiment of the present disclosure.
  • the terminal device 1000 in the embodiment of the present disclosure may include, but not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle-mounted terminals ( Mobile terminals such as car navigation terminals) and stationary terminals such as digital TVs, desktop computers and the like.
  • the terminal device shown in FIG. 10 is only an example, and should not limit the functions and application scope of this embodiment of the present disclosure.
  • a terminal device 1000 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 1001, which may be randomly accessed according to a program stored in a read-only memory (ROM) 1002 or loaded from a storage device 1008. Various appropriate actions and processes are executed by programs in the memory (RAM) 1003 . In the RAM 1003, various programs and data necessary for the operation of the terminal device 1000 are also stored.
  • the processing device 1001, ROM 1002, and 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), speaker, 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 perform wireless or wired communication with other devices to exchange data. While FIG. 10 shows a terminal device 1000 having various means, it is to be understood that implementing or possessing all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, where the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from a network via the communication means 1009, or from the storage means 1008, or from the ROM 1002.
  • the processing device 1001 the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • 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 carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and the server can communicate using any currently known or future network protocols such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol), and can communicate with digital data in any form or medium
  • HTTP HyperText Transfer Protocol
  • the communication eg, communication network
  • Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.
  • 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: acquires the target image, and acquires the attribute information of the sky in the target image; The sky segmentation process is used to obtain the sky image in the target image; based on the attribute information, corresponding special effect processing is performed on the sky image in the target image.
  • Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and Includes 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 can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they 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 by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. Wherein, the name of a unit does not constitute a limitation of the unit itself under certain circumstances.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs System on Chips
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, 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.
  • An embodiment of the present disclosure also 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 any one of the above-mentioned embodiments in FIGS. 1-8 can be implemented. Its execution method and beneficial effect are similar, and will not be repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开实施例提供一种图像处理方法、装置、设备及存储介质。其中图像处理方法包括：获取目标图像，以及获取所述目标图像中天空的属性信息；对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理。基于属性信息选择对应的特效处理步骤对天空图像进行特效处理，保证特效处理的效果与目标图像中的天空图像匹配，继而保证了特效添加效果，提高了用户体验。

Description

图像处理方法、装置、设备及存储介质
本申请要求于2021年08月09日提交国家知识产权局、申请号为202110909034.2、申请名称为“图像处理方法、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
本公开实施例涉及图像处理技术领域，尤其涉及一种图像处理方法、装置、设备及存储介质。
背景技术
相关技术提供的视频应用可以在视频图像中添加特技效果以增加视频的趣味性。但是相关技术往往存在添加的特技效果与视频的场景不匹配的问题，降低了特技效果的添加效果，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，本公开实施例提供了一种图像处理方法、装置、设备及存储介质。
第一方面，本公开实施例提供一种图像处理方法，包括：
获取目标图像，以及获取所述目标图像中天空的属性信息；
对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；
基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理。
可选地，所述获取目标图像中的天空的属性信息，包括：
基于预设的识别模型对所述目标图像进行处理，得到所述目标图像中的天空的属性信息，所述属性信息包括天气、时间、所处地域的类型中的至少一种。
可选地，所述获取目标图像中的天空的属性信息，包括：
获取拍摄设备拍摄所述目标图像时的时间、地域类型、朝向和所述位置处的天气中的至少一种；
将所述时间、所述地域类型、所述朝向和所述天气中的至少一种作为所述天空的属性信息。
可选地，基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理，包括：
基于所述属性信息，确定与所述属性信息相匹配的插入对象；所述插入对象为图像、动画或AR对象中的至少一种；
将所述插入对象插入到所述天空图像上。
可选地，所述基于所述属性信息，确定与所述属性信息相匹配的插入对象，包括：
基于所述属性信息，展示与所述属性信息相匹配的多个候选对象；
响应于针对所述多个候选对象中的候选对象的选择操作，将被选择的候选对象作为插入对象。
可选地，在将所述插入对象插入到所述天空图像上后，所述方法还包括：
根据插入位置的亮度，对所述插入对象的亮度进行调整，使得所述插入对象的亮度与所述插入位置处的亮度匹配。
可选地，所述将所述插入对象插入到所述天空图像上，包括：
获取用户在所述天空图像上指定的插入位置；
将所述插入对象插入到所述用户在天空图像上指定的插入位置。
第二方面，本公开提供一种图像处理装置，包括：
获取单元，用于获取目标图像以及获取所述目标图像中天空的属性信息；
图像分割单元，用于对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；
特效处理单元，用于基于所述属性信息对所述目标图像中的天空图像进行相应的特效处理。
可选地，所述获取单元，具体用于基于预设的识别模型对所述目标图像进行处理，得到所述目标图像中天空的属性信息，所述属性信息包括天气、时间和所处地域的类型中的至少一种。
可选地，所述获取单元包括：
属性获取子单元，用于获取拍摄设备拍摄所述目标图像时的时间、地域类型、朝向和所处位置处的天气中的至少一种；
属性赋值子单元，用于将所述时间、所述地域类型、所述朝向和所述天气中的至少一种作为所述天空的属性信息。
可选地，所述特效处理单元包括：
插入对象选择子单元，用于基于所述属性信息确定与所述属性信息相匹配的插入对象；所述插入对象为图像、动画或AR对象中的至少一种；
添加子单元，用于将所述插入对象添加至所述天空图像上。
可选地，所述特效处理单元还包括：
展示子单元，用于展示与所述属性信息相匹配的多个候选对象；
选择检测子单元，用于响应于针对所述多个候选对象中的候选对象的选择操作，将被选择的候选对象作为插入对象。
可选地，所述装置还包括：
亮度调整单元，用于在所述图像添加子单元将所述插入对象添加至所述天空图像之后，根据插入位置的亮度，对所述插入对象的亮度进行调整，使得所述插入对象的亮度与所述插入位置处的亮度匹配。
可选地，所述特效处理单元还包括插入位置获取子单元，用于获取用户在所述天空图像上指定的插入位置；
所述添加子单元将所述插入对象插入到所述用户在天空图像上指定的插入位置。
第三方面，本公开实施例提供一种终端设备，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。
第四方面，本公开实施例提供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中，首选获取目标图像中天空的属性信息和目标图像中的天空图像，随后根据属性信息对目标图像中的天空图像进行相应的特效处理，保证特效处理的效果与目标图像中的天空图像匹配，提高了添加特效的效果，继而提高用户体验。
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处理方法的流程图；
图2是本公开一个实施例提供的需处理的目标图像；
图3是基于图2得到的经过特效处理的目标图像；
图4是本公开另一实施例提供的需处理的目标图像；
图5是基于图4得到的经过特效处理的目标图像；
图6是本公开另外一些实施例提供的图像处理方法的流程图；
图7是直接将插入对象插入到目标图像得到的一个示意图；
图8是对插入对象进行亮度调整而得到的示意图；
图9是本公开实施例提供的一种图像处理装置的结构示意图；
图10是本公开一些实施例中的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处理方法的流程图。该方法可以由一种终端设备执行。该终端设备可以示例性的理解为智能手机、平板电脑、笔记本电脑、台式机和智能电视等具有图像处理能力的设备。如图1所示，本公开实施例提供的图像处理方法包括S101-S103。
S101：获取目标图像，以及获取目标图像中天空的属性信息。
目标图像是具有天空像素内容的图像。目标图像可以是以图片格式存储的图像，也可以是以视频方式存储的视频文件中的帧图像。本公开实施例中，终端设备可以从本地存储器中加载获得目标图像，也可以通过终端设备上的图像采集装置采集得到目标图像。应当 注意的是，本公开实施例获取目标图像的方式并不限于前述从本地存储器加载以及采用图像采集装置拍摄的方式，还可以是本领域已知的其他方式。
天空的属性信息是用于表征目标图像中天空特征的信息。天空的属性信息可以包括天气、时间、所处地域的类型、拍摄朝向中的至少一种。例如，天气可以为晴天、多云、雨天或者阴天，时间可以为清晨、上午、正午、傍晚或者晚上，所处地域可以为城市、农村或者野外，拍摄朝向可以是逆阳光方向还是顺阳光方向。当然，天空的属性信息并不限于前述的举例，还以是其他的属性信息。
本公开一些实施例中，S101中获取目标图像中天空的属性信息可以包括S1011：基于预设的识别模型对目标图像进行处理，得到目标图像中天空的属性信息。
预设的识别模型是采用样本图像和对应的属性标签训练得到的模型，其中样本图像为包括天空的图像，属性标签为根据样本图像中天空的属性信息制作的标签。
具体应用中，终端设备在获得目标图像后首先处理目标图像，得到标准尺寸的目标图像。随后终端设备将标准尺寸的目标图像输入到预设的识别模型中，得到目标图像中天空的属性信息。
本公开一些实施例中，采用S1011中获得的天空的属性信息可以包括天气、时间、所处地域的类型中的至少一种。
在本公开另外一些实施例中，S101获取目标图像中天空的属性信息可以包括S1012-S1013。
S1012：获取拍摄设备拍摄目标图像时的时间、地域类型、朝向和所处位置处的天气中的至少一种。
S1013：将时间、地域类型、朝向和天气中的至少一种作为天空的属性信息。
终端设备在使用图像采集装置拍摄目标图像时，通过获取各种传感器生成的检测信号或者通过向服务器发送查询请求，获得前述的时间、地域类型、朝向或者天气等信息。
例如，在一些实施例中，终端设备可以获取定位装置生成的位置坐标，并根据位置坐标和地图信息确定当前所述地域的地域类型。再例如，在另外一些实施例中，终端设备可以将拍摄目标图像时的地理位置和时间发送给天气服务器，以获取天气服务器根据地理位置和时间确定的天气。再例如，终端设备可以获取磁阻传感器生成的检测信号，以获得拍摄目标图像时的朝向。
S102：对目标图像进行天空分割处理，得到目标图像中的天空图像。
对目标图像进行天空分割处理，得到目标图像中的天空图像，是指识别目标图像中的天地分界线，以将天地分界线之上的像素图像作为天空图像。
本公开实施例中，终端设备可以采用预先训练的天空分割模型对目标图像进行天空分割处理，得到目标图像中的天空图像。天空分割模型采用样本图像和对应的标识天空区域训练得到的模型。在本公开的另外一些实施例中，终端设备还可以本领域已知的其他方法得到目标图像中的天空图像。
S103：基于属性信息，对目标图像中的天空图像进行相应的特效处理。
在本公开一些实施例中，终端设备执行S103基于属性信息，对目标图像中的天空图像 进行相应的特效处理具体可以包括S1031-S1032。
S1031：基于属性信息，确定与属性信息相匹配的插入对象。
在本公开的一些实施例中，终端设备预先存储有各种天空的属性信息对应的插入对象，插入对象可以为图像、动画或者AR对象中的至少一种。例如，终端设备的数据库中可以存储与晴天匹配的太阳图像、与雨天匹配的雨云图像和与阴天匹配的乌云图像。再例如，终端设备的数据库中可以存储与白天晴天匹配的飞行器图像、与夜晚晴天匹配的烟花图像。在获得天空的属性信息后，终端设备基于属性信息查询数据库，可以确定与属性信息匹配的插入对象。
S1032：将插入对象添加至天空图像上。
在确定与属性信息匹配的插入对象后，终端设备将插入对象添加至目标图像的天空图像区域，得到添加特效的目标图像。
图2是本公开一个实施例提供的需处理的目标图像，图3是基于图2得到的经过特效处理的目标图像。如图2所示，目标图像21是一晴天城市的图像，对应的天空的属性信息包括时间为清晨，天气为晴天，地域类型为城市。终端设备可以基于前述的属性信息确定插入对象为飞机图像22。对目标图像进行天空分割处理，得到的天空图像是目标图像中的上侧图像。最后，将飞机图像22添加至图2的天空图像中而得到图3。
图4是本公开另一实施例提供的需处理的目标图像，图5是基于图4得到的经过特效处理的目标图像。如图4所示，目标图像41是一晴天城市的图像，对应的天空的属性信息包括时间为夜晚，天气为晴天，地域类型为城市。基于前述的属性信息确定对象为烟花图像42。对目标图像进行天空分割处理，得到的天空图像是目标图像中的上侧图形。最后，将烟花图像42添加至图4的天空图像中而得到图5。
在本公开的其他实施例中，还可以采用其他的特效处理方式处理目标图像中的天空图像，例如基于属性信息对天空图像进行动画处理，或者基于属性信息对调整天空图像的亮度、清晰度、色彩或者饱和度。当然，特效处理方法并不限于前文的方法，还可以是本领域已知的其他方法。
本公开实施例提供的图像处理方法，首先获取目标图像中天空的属性信息和目标图像中的天空图像，随后根据属性信息对目标图像中的天空图像进行相应的特效处理，保证特效处理的效果与目标图像中的天空图像匹配，提高了特效添加的效果，继而提高用户体验。
图6是本公开另外一些实施例提供的图像处理方法的流程图。如图6所示，在本公开的另外一些实施例中，图像处理方法包括S601-S606。
S601：获取目标图像，以及获取目标图像中天空的属性信息。
S602：基于属性信息，确定与属性信息相匹配的多个候选对象。
S603：向用户展示多个候选对象。
S604：响应于检测到针对候选对象的选择操作，将被选中的候选对象确定为插入对象。
S605：对目标图像进行天空分割处理，得到目标图像中的天空图像。
S606：将插入对象添加至天空图像上。
在本公开一些实施例中，为了提高目标图像特效添加效果的多样性，针对天空的各种 属性信息，终端设备的数据库中均存储多个与之匹配的候选对象，候选对象可以为图像、动画或AR对象中的至少一种。
在获取目标图像中天空的属性信息后，终端设备基于属性信息确定匹配的对象作为候选对象。随后，终端设备采用显示装置向用户展示多个候选对象，以供用户选择。在检测到用户针对某一候选对象的选择操作后，终端设备将选中的候选对象作为插入对象，并将其插入到天空图像中。
采用本公开实施例提供的图像处理方法，可以由用户在多个候选对象中选择插入对象，再将插入对象插入到目标图像中而得到添加特效的目标图像。由于插入对象是由用户选择确定的，所以得到的添加特效的目标图像更能符合用户的需求。
在本公开的一些实施例中，S606将插入对象添加至目标图像可以包括S6061-S6062。
S6061：获取用户在天空图像上指定的插入位置。
用户指定的插入位置是用于指示插入对象添加至天空图像的位置。本公开实施例中，终端设备可以提示用户在天空图像中进行点选操作，以获取用户指定的插入位置。
S6062：将插入对象添加至插入位置。
将插入对象添加至用户指定的插入位置处，可以使得得到的添加特效的目标图像更符合用户的需求。
在本公开的一些实施例中，在执行前述的S606将插入对象添加至目标图像后，图像处理方法还可以包括S607。
S607：根据插入位置的亮度，对插入对象的亮度进行调整，使得插入对象的亮度与插入位置处的亮度匹配。
图7是直接将插入对象插入到目标图像得到的一个示意图。图8是对插入对象进行调整而得到的示意图。如图7和图8所示，插入对象为一飞机图像71。如果直接将飞机图像71插入到目标图像而不调整其亮度，如图7所示，飞机图像71的亮度与目标图像亮度差别较大而使得得到的特效图像反差较大。如图8所示，在基于插入位置的亮度调整飞机图像71的亮度后，飞机图像71的亮度与目标图像亮度匹配，特效图像的反差较为合理。
在一些具体应用中，插入对象的亮度与目标图像插入位置处的亮度并不匹配。如果将插入对象插入到天空图像而不做调整，则使得最终得到的图像对比度较大而不自然。为了使得最终得到的图像更为自然，本公开实施例根据插入位置处的亮度调整插入对象的亮度，使得插入对象的亮度与插入位置的亮度匹配，继而最终得到的特效图像更为自然。
图9是本公开实施例提供的图像处理装置的结构示意图，该图像处理装置可以被理解为上述终端设备或者上述终端设备中的部分功能模块。如图9所示，图像处理装置900包括获取单元901、图像分割单元902和特效处理单元903。
获取单元901用于获取目标图像以及获取目标图像中天空的属性信息。图像分割单元902，用于对目标图像进行天空分割处理，得到目标图像中的天空图像。特效处理单元903用于基于属性信息对目标图像中的天空图像进行相应的特效处理。
在本公开的一些实施例中，获取单元901基于预设的识别模型对目标图像进行处理，得到目标图像中天空的属性信息，属性信息包括天气、时间和所处地域的类型中的至少一 种。
在本公开的另外一些实施例中，获取单元901包括属性获取子单元和属性赋值子单元。属性获取子单元用于获取拍摄设备拍摄目标图像时的时间、地域类型、朝向和所处位置处的天气中的至少一种。属性赋值子单元用于将时间、地域类型、朝向和天气中的至少一种作为天空的属性信息。
在本公开的一些实施例中，特效处理单元903包括插入对象选择子单元和添加子单元。插入对象选择子单元用于基于属性信息确定与属性信息相匹配的插入对象；插入对象为图像、动画或AR对象中的至少一种。添加子单元用于将插入对象添加至天空图像上
在本公开的一些实施例中，图像选择子单元基于属性信息，确定与属性信息相匹配的多个候选对象。对应的，特效处理单元903还包括展示子单元和选择检测子单元。展示子单元用于展示多个候选对象；选择检测子单元用于检测到针对候选对象的选择操作的情况下，将被选择的候选对象确定为插入对象。
在本公开的一些实施例中，图像处理单元还包括亮度调整单元，亮度调整单元用于在添加子单元将插入对象添加至天空图像之后，根据插入位置的亮度，对插入对象的亮度进行调整，使得插入对象的亮度与插入位置处的亮度匹配。
在本公开的一些实施例中，特效处理单元903还包括插入位置获取子单元，位置获取子单元用于获取用户在天空图像上指定的插入位置。对应的图像添加子单元将插入对象添加至插入位置。
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，存储器中存储有计算机程序，当计算机程序被处理器执行时可以实现上述任一方法实施例提供的图像处理方法。
示例的，图10是本公开一些实施例中的终端设备的结构示意图。下面具体参考图10，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10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10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10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、或半导体的系统、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系统、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系统、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 Protocol，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：获取目标图像，以及获取目标图像中天空的属性信息；对目标图像进行天空分割处理，得到目标图像中的天空图像；基于属性信息，对目标图像中的天空图像进行相应的特效处理。
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、Smalltalk、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系统、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系统来实现，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)、片上系统(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系统、装置或设备使用或与指令执行系统、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、或半导体系统、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8中任一实施例的方法，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. 一种图像处理方法，其特征在于，包括：
    获取目标图像，以及获取所述目标图像中天空的属性信息；
    对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；
    基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理。
  2. 根据权利要求1所述的方法，其特征在于，所述获取目标图像中的天空的属性信息，包括：
    基于预设的识别模型对所述目标图像进行处理，得到所述目标图像中的天空的属性信息，所述属性信息包括天气、时间、所处地域的类型中的至少一种。
  3. 根据权利要求1所述的方法，其特征在于，所述获取目标图像中的天空的属性信息，包括：
    获取拍摄设备拍摄所述目标图像时的时间、地域类型、朝向和所处位置处的天气中的至少一种；
    将所述时间、所述地域类型、所述朝向和所述天气中的至少一种作为所述天空的属性信息。
  4. 根据权利要求1所述的方法，其特征在于，基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理，包括：
    基于所述属性信息，确定与所述属性信息相匹配的插入对象；所述插入对象为图像、动画或AR对象中的至少一种；
    将所述插入对象插入到所述天空图像上。
  5. 根据权利要求4所述的方法，其特征在于，所述基于所述属性信息，确定与所述属性信息相匹配的插入对象，包括：
    基于所述属性信息，展示与所述属性信息相匹配的多个候选对象；
    响应于针对所述多个候选对象中的候选对象的选择操作，将被选择的候选对象作为插入对象。
  6. 根据权利要求4或5所述的方法，其特征在于，在所述将所述插入对象插入到所述天空图像上后，所述方法还包括：
    根据插入位置的亮度，对所述插入对象的亮度进行调整，使得所述插入对象的亮度与所述插入位置处的亮度匹配。
  7. 根据权利要求4或5所述的方法，其特征在，所述将所述插入对象插入到所述天空图像上，包括：
    获取用户在所述天空图像上指定的插入位置；
    将所述插入对象插入到所述用户在天空图像上指定的插入位置。
  8. 一种图像处理装置，其特征在于，包括：
    获取单元，用于获取目标图像以及获取所述目标图像中天空的属性信息；
    图像分割单元，用于对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；
    特效处理单元，用于基于所述属性信息对所述目标图像中的天空图像进行相应的特效处理。
  9. 根据权利要求8所述的装置，其特征在于，
    所述获取单元，具体用于基于预设的识别模型对所述目标图像进行处理，得到所述目标图像中天空的属性信息，所述属性信息包括天气、时间和所处地域的类型中的至少一种。
  10. 根据权利要求8所述的装置，其特征在于，所述获取单元包括：
    属性获取子单元，用于获取拍摄设备拍摄所述目标图像时的时间、地域类型、朝向和所述位置处的天气中的至少一种；
    属性赋值子单元，用于将所述时间、所述地域类型、所述朝向和所述天气中的至少一种作为所述天空的属性信息。
  11. 根据权利要求8所述的装置，其特征在于，所述特效处理单元包括：
    插入对象选择子单元，用于基于所述属性信息确定与所述属性信息相匹配的插入对象；所述插入对象为图像、动画或AR对象中的至少一种；
    添加子单元，用于将所述插入对象添加至所述天空图像上。
  12. 根据权利要求11所述的装置，其特征在于，
    所述特效处理单元还包括：
    展示子单元，用于展示与所述属性信息相匹配的多个候选对象；
    选择检测子单元，用于响应于针对所述多个候选对象中的候选对象的选择操作，将被选择的候选对象作为插入对象。
  13. 根据权利要求11或12所述的装置，其特征在于，还包括：
    亮度调整单元，用于在所述图像添加子单元将所述插入对象添加至所述天空图像之后，根据插入位置的亮度，对所述插入对象的亮度进行调整，使得所述插入对象的亮度与所述插入位置处的亮度匹配。
  14. 根据权利要求11或12所述的装置，其特征在于，
    所述特效处理单元还包括插入位置获取子单元，用于获取用户在所述天空图像上指定的插入位置；
    所述添加子单元将所述插入对象插入到所述用户在天空图像上指定的插入位置。
  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，实现如权利要求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，实现如权利要求1-7中任一项所述的方法。
PCT/CN2022/104273 2021-08-09 2022-07-07 图像处理方法、装置、设备及存储介质 WO2023016150A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110909034.2A CN115705666A (zh) 2021-08-09 2021-08-09 图像处理方法、装置、设备及存储介质
CN202110909034.2 2021-08-09

Publications (1)

Publication Number Publication Date
WO2023016150A1 true WO2023016150A1 (zh) 2023-02-16

Family

ID=85179954

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/104273 WO2023016150A1 (zh) 2021-08-09 2022-07-07 图像处理方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115705666A (zh)
WO (1) WO2023016150A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090087123A1 (en) * 2007-09-28 2009-04-02 Fujifilm Corportation Image processing apparatus, imaging apparatus, and image processing method
CN107730461A (zh) * 2017-09-29 2018-02-23 北京金山安全软件有限公司 图像处理方法、装置、设备及介质
CN109859102A (zh) * 2019-02-01 2019-06-07 北京达佳互联信息技术有限公司 特效显示方法、装置、终端及存储介质
CN111127307A (zh) * 2019-12-09 2020-05-08 上海传英信息技术有限公司 图像处理方法、装置、电子设备及计算机可读存储介质
CN112200817A (zh) * 2020-10-15 2021-01-08 广州华多网络科技有限公司 基于图像的天空区域分割和特效处理方法、装置及设备
CN113034514A (zh) * 2021-03-19 2021-06-25 影石创新科技股份有限公司 天空区域分割方法、装置、计算机设备和存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090087123A1 (en) * 2007-09-28 2009-04-02 Fujifilm Corportation Image processing apparatus, imaging apparatus, and image processing method
CN107730461A (zh) * 2017-09-29 2018-02-23 北京金山安全软件有限公司 图像处理方法、装置、设备及介质
CN109859102A (zh) * 2019-02-01 2019-06-07 北京达佳互联信息技术有限公司 特效显示方法、装置、终端及存储介质
CN111127307A (zh) * 2019-12-09 2020-05-08 上海传英信息技术有限公司 图像处理方法、装置、电子设备及计算机可读存储介质
CN112200817A (zh) * 2020-10-15 2021-01-08 广州华多网络科技有限公司 基于图像的天空区域分割和特效处理方法、装置及设备
CN113034514A (zh) * 2021-03-19 2021-06-25 影石创新科技股份有限公司 天空区域分割方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN115705666A (zh) 2023-02-17

Similar Documents

Publication Publication Date Title
CN112380379B (zh) 歌词特效展示方法、装置、电子设备及计算机可读介质
CN106845470B (zh) 地图数据采集方法和装置
CN108717432B (zh) 资源查询方法及装置
CN109684589B (zh) 客户端的评论数据的处理方法、装置及计算机存储介质
WO2023011259A1 (zh) 一种信息显示方法、装置、电子设备和存储介质
WO2022042389A1 (zh) 搜索结果的展示方法、装置、可读介质和电子设备
CN110991373A (zh) 图像处理方法、装置、电子设备及介质
WO2023051294A1 (zh) 道具处理方法、装置、设备及介质
WO2023016349A1 (zh) 一种文本输入方法、装置、电子设备和存储介质
US20140347387A1 (en) Integrating Street View with Live Video Data
WO2023103653A1 (zh) 键值匹配方法、装置、可读介质及电子设备
WO2022171036A1 (zh) 视频目标追踪方法、视频目标追踪装置、存储介质及电子设备
US8218054B2 (en) Image display system, image display apparatus, image providing apparatus and method thereof
CN113315924A (zh) 图像特效处理方法及装置
WO2022071875A1 (zh) 图片转视频的方法、装置、设备及存储介质
CN110381356B (zh) 音视频生成方法、装置、电子设备及可读介质
CN111311358B (zh) 信息处理方法、装置和电子设备
CN112148962B (zh) 用于推送信息的方法和装置
CN112949430A (zh) 视频处理方法和装置、存储介质和电子设备
WO2023016150A1 (zh) 图像处理方法、装置、设备及存储介质
CN111797266A (zh) 图像处理方法和装置、存储介质和电子设备
CN111260445A (zh) 房源信息展示方法、装置、终端及存储介质
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
WO2022218028A1 (zh) 页面加载方法、装置、设备及存储介质
WO2021244614A1 (zh) 存储内容搜索方法、系统和电子设备

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: 22855134

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE