WO2022111201A1 - 一种图像处理方法、装置及计算机可读存储介质 - Google Patents

一种图像处理方法、装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2022111201A1
WO2022111201A1 PCT/CN2021/126879 CN2021126879W WO2022111201A1 WO 2022111201 A1 WO2022111201 A1 WO 2022111201A1 CN 2021126879 W CN2021126879 W CN 2021126879W WO 2022111201 A1 WO2022111201 A1 WO 2022111201A1
Authority
WO
WIPO (PCT)
Prior art keywords
preset
frame
image
pixel position
preset pixel
Prior art date
Application number
PCT/CN2021/126879
Other languages
English (en)
French (fr)
Inventor
陈考德
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2022111201A1 publication Critical patent/WO2022111201A1/zh
Priority to US17/969,618 priority Critical patent/US20230045166A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/30—Interconnection arrangements between game servers and game devices; Interconnection arrangements between game devices; Interconnection arrangements between game servers
    • A63F13/35—Details of game servers
    • A63F13/355—Performing operations on behalf of clients with restricted processing capabilities, e.g. servers transform changing game scene into an encoded video stream for transmitting to a mobile phone or a thin client
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/30—Interconnection arrangements between game servers and game devices; Interconnection arrangements between game devices; Interconnection arrangements between game servers
    • A63F13/35—Details of game servers
    • A63F13/358—Adapting the game course according to the network or server load, e.g. for reducing latency due to different connection speeds between clients
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/236—Assembling of a multiplex stream, e.g. transport stream, by combining a video stream with other content or additional data, e.g. inserting a URL [Uniform Resource Locator] into a video stream, multiplexing software data into a video stream; Remultiplexing of multiplex streams; Insertion of stuffing bits into the multiplex stream, e.g. to obtain a constant bit-rate; Assembling of a packetised elementary stream
    • H04N21/23608—Remultiplexing multiplex streams, e.g. involving modifying time stamps or remapping the packet identifiers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/434—Disassembling of a multiplex stream, e.g. demultiplexing audio and video streams, extraction of additional data from a video stream; Remultiplexing of multiplex streams; Extraction or processing of SI; Disassembling of packetised elementary stream
    • H04N21/4344—Remultiplexing of multiplex streams, e.g. by modifying time stamps or remapping the packet identifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Definitions

  • the present application relates to the field of communication technologies, and in particular, to an image processing method, an apparatus, and a computer-readable storage medium.
  • the local network is connected to the server.
  • the server transmits the game screen through the network in real time for vivid interactive entertainment.
  • the video stream of the cloud game needs to be repeatedly frame-reduced, and the fluency of the video stream after the frame-reduction processing is performed. Check until a suitable frame rate for the video stream is found.
  • Embodiments of the present application provide an image processing method, an apparatus, and a computer-readable storage medium, which can improve the accuracy of image detection, thereby improving the accuracy of cloud application fluency assessment.
  • An image processing method comprising:
  • the pixel digital frame mask includes a plurality of preset pixel position sets
  • For the video stream determine the frame sequence number corresponding to the image of each frame according to the positional relationship between the at least two target preset pixel position sets;
  • the video fluency of the video stream is determined according to the frame sequence number.
  • An image processing device comprising:
  • An acquisition unit for intercepting the pixel digital frame mask in the image of each frame in the video stream, and the pixel digital frame mask includes a plurality of preset pixel position sets
  • a first determining unit configured to determine, from the plurality of preset pixel position sets, at least two target preset pixel position sets including first preset pixels, the first preset pixels are set to a specified color to represent the frame number of the image;
  • a second determining unit configured to, for the video stream, determine the frame sequence number corresponding to the image of each frame according to the positional relationship between the at least two target preset pixel position sets;
  • a third determining unit configured to determine the video fluency of the video stream according to the frame sequence number.
  • An embodiment of the present application further provides an electronic device, including: a processor; a memory connected to the processor; the memory stores machine-readable instructions, and the machine-readable instructions can be executed by the processor to The above image processing method is completed.
  • Embodiments of the present application further provide a computer-readable storage medium, in which processor-executable instructions are stored, and the instructions are loaded by one or more processors to execute the above image processing method.
  • FIG. 1 is a schematic diagram of a scene of an image processing system provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present application.
  • 3a is a schematic diagram of a scene of an image processing method provided by an embodiment of the present application.
  • FIG. 3b is a schematic diagram of another scene of the image processing method provided by the embodiment of the present application.
  • FIG. 4 is another schematic flowchart of the image processing method provided by the embodiment of the present application.
  • FIG. 5 is a schematic diagram of another scene of the image processing method provided by the embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an image processing apparatus provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a server provided by an embodiment of the present application.
  • Embodiments of the present application provide an image processing method, an apparatus, and a computer-readable storage medium.
  • FIG. 1 is a schematic diagram of an image processing system provided by an embodiment of the application, including: a basic server A and a virtualized cloud host B (the basic server A and the virtualized cloud host B may also include: More, the specific number is not limited here), the basic server A is a physical machine, also called a physical server, which is the name of a physical computer relative to a virtual machine (Virtual Machine), and the physical machine is provided to the virtual machine.
  • hardware environment also known as "host” or "host”.
  • the basic server A can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, and cloud communications.
  • each basic server A can virtualize multiple cloud hosts B.
  • the cloud host B is a virtual machine, which can also be called a virtual private server (Virtual Private Server, VPS). It is a technology that partitions a server into multiple virtual independent dedicated servers. Each virtual independent server using VPS technology has its own independent Internet Protocol (Internet Protocol Address, IP) address, operating system, hard disk space, memory space, processor (Central Processing Unit, CPU) resources, etc. Installing programs, restarting the server, etc. is exactly the same as running a standalone server.
  • IP Internet Protocol Address
  • cloud host B is a VPS, but cloud host B further virtualizes all basic resources, such as memory bandwidth, etc., on all basic servers A or virtual machines.
  • the advantage of cloud host B is that it can store data in a distributed manner and dynamically expand basic resources. Strong security and scalability.
  • Each cloud host B has an independent operating system and hardware structure, which is exactly the same as running an independent host, except that the physical address in each cloud host B is the physical address of the virtual machine.
  • Multiple processors are installed.
  • multiple graphics processors Graphics Processing Unit, GPU
  • One cloud host B can be similar to a VMware virtual machine, and one physical machine can virtualize multiple Android operations.
  • a game board or container can be installed in the cloud host B to simulate the user's terminal environment, but there is no physical display screen, such as running cloud games (Cloud gaming), which can also be called game-on-demand (gaming). on demand), is an online game technology based on cloud computing technology.
  • Cloud gaming technology enables thin clients with relatively limited graphics processing and data computing capabilities to run high-quality games.
  • the game is not run on the player's game terminal, but in the cloud server, and the cloud server renders the game scene into a video and audio stream, and transmits it to the player's game terminal through the network.
  • the player's game terminal does not need to have powerful graphics computing and data processing capabilities, but only needs to have basic streaming media playback capabilities and the ability to obtain player input instructions and send them to the cloud server.
  • the cloud host B can intercept the pixel digital frame mask corresponding to the image of each frame in the video stream of the cloud game, and the pixel digital frame mask includes a plurality of preset pixel position sets; In the position set, at least two target preset pixel position sets are determined including the first preset pixel, and the first preset pixel is set to a specified color to represent the frame number of the image; for the video stream, according to the The positional relationship between the at least two target preset pixel position sets determines the frame sequence number corresponding to the image of each frame; the video fluency of the video stream is determined according to the frame sequence number, which greatly improves the accuracy of image detection, This in turn improves the accuracy of cloud game fluency assessment.
  • FIG. 1 the schematic diagram of the scene of the image processing system shown in FIG. 1 is only an example, and the image processing system and the scene described in the embodiments of the present application are for the purpose of illustrating the technical solutions of the embodiments of the present application more clearly, and do not constitute any
  • those of ordinary skill in the art know that with the evolution of image processing systems and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.
  • FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present application.
  • description will be made from the perspective of an image processing device, which may be specifically integrated in a cloud host having a storage unit and a microprocessor installed with computing capability.
  • the image processing method includes:
  • step 101 a pixel digital frame mask in the image of each frame in the video stream is intercepted, and the pixel digital frame mask includes a plurality of preset pixel position sets.
  • Pixels in the embodiments of the present application are composed of small squares of an image. These small squares have a definite position and assigned color value, and the color and position of the small squares determine the appearance of the image.
  • the video stream can be composed of multiple frames of continuous images, that is, the video stream can be a video playback screen.
  • the cloud host uses the network to stream the video at a set frame rate, such as 60 frames/second or 30 frames/second are transmitted to the user terminal in real time, and the user terminal plays the above-mentioned video stream.
  • the video stream may be a video stream generated by a cloud game screen of a cloud game in a cloud host, a video stream played by a video player, a video stream corresponding to a live screen played by a live broadcast platform, or a game when a common game is running.
  • the video stream formed by the screen is described in this embodiment of the present application as the video stream generated by the cloud game screen, which is not specifically limited, and the video stream in other scenarios can also be processed by the image processing method provided in this embodiment.
  • Different and different network environments can support different frame rates.
  • the cloud host corresponding to different user terminals needs to evaluate the smoothness of the pushed video stream, and find the frame rate that different user terminals feel is not stuck. Therefore, based on high When a video stream with a high frame rate starts, the video stream of the cloud game needs to be down-framed repeatedly, and the fluency detection is performed according to the video stream after the down-frame processing, until the appropriate frame rate of the video stream is found.
  • a corresponding mark may be written for the image of each frame in the video stream, and the mark recognition is performed by means of Optical Character Recognition (OCR) to determine the sequence of each image.
  • OCR Optical Character Recognition
  • the optical character recognition can determine the shape of the character by detecting the dark and bright patterns, and then translate the shape into computer text by character recognition.
  • noise will appear in some images, which is a random change in brightness or color information in the image (the object being photographed does not have it), usually electronic
  • the noise will affect the recognition of markers in the image, which will lead to a great decrease in the accuracy of image marker detection.
  • the embodiment of the present application may generate a pixel digital frame mask in advance, where the pixel digital frame mask includes the first preset pixels displayed on at least two preset pixel position sets, so as to form the frame serial number of the image, Add the corresponding pixel digital frame mask to the image of each frame in the video stream to realize the frame serial number labeling.
  • the server can obtain the pixel digital frame mask corresponding to the image of each frame in the video stream.
  • the image 11 in the video stream includes a pixel digital frame mask 111
  • the pixel digital frame mask 111 includes a plurality of preset pixel position sets
  • the preset pixel position sets can be understood as forming A rectangular stroke of numbers
  • the preset pixel position set is predefined
  • the size of the preset pixel position set can be 2n*n pixel size
  • the first preset pixel can be RGB (red (R), green ( G), blue (B)) pixels whose value is (255, 255, 255), that is, pure white pixels.
  • the pixels on the two preset pixel position sets can represent Number 1, the pixel number
  • the frame mask 111 contains numbers 0, 9, 9, and 1, and the numbers 0, 9, 9, and 1 are combined to determine the frame number of the image 11 as 0991.
  • the first preset pixels displayed on the at least two preset pixel position sets are set according to the numerical rules, and any number of frame serial numbers can be obtained. Accurate and fast identification.
  • step 102 from the plurality of preset pixel position sets, at least two target preset pixel position sets including a first preset pixel are determined, and the first preset pixel is set to a specified color to represent the The frame number of the image.
  • the rectangular stroke of each number is expressed by setting the first preset pixel on the preset pixel position set in the pixel digital frame mask. Therefore, it is necessary to first determine the pixel digital frame mask including The target preset pixel position set of the first preset pixel is determined to form a rectangular stroke of a number.
  • the pixel digital frame mask 111 includes 7 preset pixel position sets, which are respectively preset pixel position set 1, preset pixel position set 2, preset pixel position set 3, Preset pixel position set 4, preset pixel position set 5, preset pixel position set 6, preset pixel position set 7, through the preset pixel position set 1, preset pixel position set 2, preset pixel position set 3.
  • the pixels in the preset pixel position set 4, the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7 are analyzed to determine the preset pixel position set 1, the preset pixel position set 2,
  • the pixels in the preset pixel position set 3, the preset pixel position set 4, the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7 are all the first preset pixels.
  • Pixel position set 1, preset pixel position set 2, preset pixel position set 3, preset pixel position set 4, preset pixel position set 5, preset pixel position set 6, and preset pixel position set 7 are determined as targets A collection of preset pixel locations.
  • the step of determining a set of target preset pixel positions in the pixel digital frame mask that includes the first preset pixel may include:
  • a plurality of preset pixel position sets in the pixel digital frame mask can be determined first. Please refer to FIG. 3b together to determine the preset pixel position set 1 and the preset pixel position set in the pixel digital frame mask 111. 2. Preset pixel position set 3, preset pixel position set 4, preset pixel position set 5, preset pixel position set 6, preset pixel position set 7, extract preset pixel position set 1, preset pixel position set 2. The first preset number of pixels in the preset pixel position set 3, the preset pixel position set 4, the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7, the first preset The number may be 4, that is, 4 pixels in each preset pixel position set are randomly extracted.
  • the 4 pixels in the preset pixel position set are all the first preset pixels, it can be determined that all the pixels in the preset pixel position set are the first preset pixels, and the first preset number of pixels
  • the preset pixel position sets that are all the first preset pixels are determined as the target preset pixel position set, that is, the preset pixel position set 1, the preset pixel position set 2, the preset pixel position set 3, and the preset pixel position set 4 , the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7 are all determined as the target preset pixel position set.
  • step 103 for the video stream, a frame sequence number corresponding to the image of each frame is determined according to the positional relationship between the at least two target preset pixel position sets.
  • a digital information includes 7 preset pixel position sets, namely preset pixel position set 1, preset pixel position set 2, preset pixel position set 3, preset pixel position set 2 Pixel position set 4, preset pixel position set 5, preset pixel position set 6, preset pixel position set 7, when the pixel in the preset pixel position set is the first preset pixel, the digital stroke is lit, the When the pixel in the preset pixel position set is not the first preset pixel, that is, the digital stroke is not lit, through the preset pixel position set 1, the preset pixel position set 2, the preset pixel position set 3, the preset pixel
  • the position set 4, the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7 can represent any number from 0 to 9, for example:
  • any number of digital information can be set as required, which is not specifically limited here.
  • the present application can determine the frame sequence number corresponding to the image of each frame in the video stream according to the positional relationship between the target preset pixel position sets. Since the frame sequence number is formed by a specific first preset pixel, even if The appearance of noise in the image will not affect the pixel digital frame mask, so the frame serial number can be accurately identified, and since the pixel digital frame mask and the coordinate information of the preset pixel position set in the pixel digital frame mask are in the image The corresponding positions in the frame are determined, so the frame number can be quickly identified.
  • the step of determining the frame sequence number corresponding to the image of each frame in the video stream according to the positional relationship between the target preset pixel position sets may include:
  • the frame serial number can be single digits, ten digits or hundreds digits, so the digital information that constitutes the frame serial number can be 1, 2 or 3, etc. Therefore, you can pass The abscissa spacing distinguishes digital information, and the set of target preset pixel positions whose abscissa spacing is smaller than the preset threshold is marked as the same set. Collections are grouped into categories.
  • the positional relationship between the target preset pixel positions in the same type of set is compared with the aforementioned rules, the digital information corresponding to each similar set is obtained, the digital information corresponding to each similar set is combined, and the video is determined.
  • the frame number corresponding to the image of each frame in the stream is determined.
  • step 104 the video fluency of the video stream is determined according to the frame sequence number.
  • the frame sequence number corresponding to the image of each frame in the video stream it can be detected whether the frame sequence number is a linear sequence, and when it is detected that the frame sequence number is a linear sequence, it is determined that the video fluency of the video stream is Smooth, when it is detected that the frame sequence numbers are not in a linear sequence, it is determined that the video fluency of the video stream is non-smooth and needs to be adjusted.
  • the image that needs to be evaluated can be quickly located according to the frame serial number, and the image quality can be evaluated and scored through an image quality evaluation algorithm.
  • the pixel digital frame mask corresponding to the image of each frame in the video stream is obtained, and the pixel digital frame mask includes a plurality of preset pixel position sets; In the position set, at least two target preset pixel position sets are determined including the first preset pixel, and the first preset pixel is set to a specified color to represent the frame number of the image; for the video stream, according to the The positional relationship between the at least two target preset pixel position sets determines the frame sequence number corresponding to the image of each frame; and the video fluency of the video stream is determined according to the frame sequence number.
  • the pixel digital frame mask corresponding to the image of each frame in the video stream can be obtained, the target preset pixel position set containing the first preset pixel can be determined, and the video can be determined according to the arrangement and combination of the target preset pixel position set.
  • the frame sequence number corresponding to the image of each frame in the stream, and then the video fluency of the video stream is determined by the accurate frame sequence number.
  • the embodiment of the present application can be used without passing
  • the frame serial number of each frame of the image in the video stream of the cloud application is accurately determined, and the recognition is not inaccurate due to the change of the cloud application screen, which greatly improves the accuracy of image detection.
  • the accuracy of the fluency assessment of cloud applications is improved.
  • FIG. 4 is another schematic flowchart of an image processing method provided by an embodiment of the present application. According to the method described in the embodiment shown in FIG. 3 , the following examples will be used for further detailed description.
  • the image processing apparatus is specifically integrated in a server, and the server is a cloud host as an example for description, and specific reference is made to the following description.
  • the method flow may include:
  • the server In step 201, the server generates a video stream based on the video images running in the server, and obtains a preset number of second preset pixels to form a first mask, where the first mask includes a plurality of preset pixel position sets.
  • the second preset pixel may be a pixel with an RGB value of (0, 0, 0), that is, a pure black pixel, and the server may generate a video stream through a video image corresponding to a cloud application running in the cloud host.
  • Each frame of image in the generated video stream is the image of the cloud application, and a first mask composed of a preset number of second preset pixels is obtained.
  • the first mask includes multiple preset pixel position sets, for example, may include 28 preset pixel position sets.
  • each preset pixel position set may be 2n*n pixel size, where 2n is the length, n is the width, and n is manually set, for example, 3 or 7 preset pixel position sets may form A piece of digital information, that is, the embodiment of the present application can represent a maximum of 4 digits, the minimum is 1, and the maximum is 9999.
  • step 202 the server switches and displays the second preset pixel in the at least two preset pixel position sets in the first mask as the first preset pixel, and generates a pixel digital frame mask, the pixel digital frame
  • the mask is used to mark the frame number of each frame of image, obtain the frame sequence of each frame of image in the video stream, and insert the corresponding pixel digital frame mask in the preset position of each frame of image according to the frame sequence.
  • the first preset pixel may be a pixel with an RGB value of (255, 255, 255), that is, a pure white pixel.
  • the server may use this to assign the second pixel in the set of at least two preset pixel positions.
  • the preset pixel is switched and displayed as the first preset pixel, so that according to the digital display rule, a pixel digital frame mask whose number is any frame number from 1 to 9999 can be generated.
  • the frame sequence starts from 1, and determine the corresponding target image and target pixel digital frame mask according to the frame sequence. For example, if the frame sequence is 1, the corresponding The image of the first frame in the video stream and the target pixel digital frame mask, the frame number in the target digital frame mask is 1, so that the target pixel digital frame mask is inserted in the preset position of the target image, for example, Please continue to refer to FIG.
  • step 203 the server performs binarization processing on the image of each frame in the video stream to obtain a binarized image, and intercepts the pixel digital frame mask at a preset position of the binarized image. code.
  • the server may perform binarization processing on the image of each frame in the video stream in advance.
  • the processing can present the entire image with an obvious black and white effect, thereby highlighting the outline of the first preset pixel.
  • a preset position of the binarized image such as the pixel digital frame mask on the lower right corner of the image
  • the server pre-defined the position of the pixel digital frame mask, so that the defined position can be quickly passed.
  • the pixel digital frame mask is intercepted for subsequent identification. Please also refer to FIG. 5 , which is the pixel digital frame mask 112 at the preset position of the binarized image.
  • the server determines a plurality of preset pixel position sets in the pixel digital frame mask, extracts a first preset number of pixels in each preset pixel position set, and obtains the first preset number of pixels as the first The target number of preset pixels.
  • the first preset number is manually set, assuming that it is 4, and the server extracts 28 preset pixels Any 4 pixels in the location set.
  • the target number of pixels among the 4 pixels as the first preset pixels, assuming that there are 3 first preset pixels among the 4 pixels, and the target number is 3.
  • step 205 the server determines a preset pixel position set whose target number is greater than the second preset number as a target preset pixel position set.
  • a second preset number can be set, and the second preset number is smaller than the first preset number. Assuming that the second preset number can be 2, the server determines the preset pixel position set with the target number greater than 2 as the target preset pixel position set. Please refer to FIG. 5 together to determine that the set of target preset pixel positions is 25.
  • the server marks the set of target preset pixel positions whose abscissa spacing is smaller than the preset threshold as a homogeneous set, and generates corresponding digital information according to the positional relationship between the target preset pixel positions in the homogeneous set.
  • the server can mark the set of target preset pixel positions whose abscissa interval is smaller than the preset threshold as Similar sets, get set A, set B, set C and set D.
  • a digital information includes 7 preset pixel position sets, namely preset pixel position set 1, preset pixel position set 2, preset pixel position set 3, preset pixel position set 4.
  • the preset pixel position set 5, the preset pixel position set 6, and the preset pixel position set 7 can represent any number in the number 0 to 9, for example:
  • the server deduces the positional relationship between the target preset pixel positions in the same set according to the above rules, and generates digital information corresponding to set A, set B, set C and set D as 0, 9, 9, and 8, respectively.
  • step 207 the server combines the digital information corresponding to each homogeneous set to determine the frame sequence number corresponding to the image of each frame in the video stream.
  • the server combines set A, set B, set C and set D corresponding digital information 0, 9, 9, 8, and recognizes that the frame number of the current image is 0998, and so on, the server can quickly and accurately identify The frame number corresponding to the image of each frame in the video stream.
  • step 208 the server determines the video fluency of the video stream according to the frame sequence number.
  • the server determines the frame sequence number of each image in the video stream, it detects whether the frame sequence numbers are in a linear sequence, and when it is detected that the frame sequence numbers are in a linear sequence, it is determined that the video fluency of the video stream is smooth. , when it is detected that the frame sequence numbers are not in a linear sequence, it is determined that the video fluency of the video stream is non-smooth and needs to be adjusted.
  • the pixel digital frame mask in the image of each frame in the video stream is intercepted, and the pixel digital frame mask includes a plurality of preset pixel position sets;
  • the position set at least two target preset pixel position sets are determined including the first preset pixel, and the first preset pixel is set to a specified color to represent the frame number of the image; for the video stream, according to the The positional relationship between the at least two target preset pixel position sets determines the frame serial number corresponding to the image of each frame; and the video fluency of the video stream is determined according to the frame serial number.
  • the pixel digital frame mask corresponding to the image of each frame in the video stream can be obtained, the target preset pixel position set containing the first preset pixel can be determined, and the video can be determined according to the arrangement and combination of the target preset pixel position set.
  • the frame sequence number corresponding to the image of each frame in the stream, and then the video fluency of the video stream is determined by the accurate frame sequence number.
  • the embodiment of the present application can be used without passing the frame sequence number.
  • the embodiment of the present application further provides an apparatus based on the above-mentioned image processing method.
  • the meanings of the nouns are the same as those in the above image processing method, and the specific implementation details can refer to the description in the method embodiment.
  • FIG. 6 is a schematic structural diagram of an image processing apparatus provided by an embodiment of the present application, wherein the image processing apparatus may include an acquisition unit 301 , a first determination unit 302 , a second determination unit 303 , and a third determination unit 304 Wait.
  • the obtaining unit 301 is configured to intercept a pixel digital frame mask in an image of each frame in the video stream, where the pixel digital frame mask includes a plurality of preset pixel position sets.
  • a pixel digital frame mask may be generated in advance, and the pixel digital frame mask includes the first preset pixels displayed on at least two preset pixel position sets to form the frame serial number of the image, which is the frame number of each frame in the video stream.
  • the corresponding pixel digital frame mask is added to the image of the video stream to realize frame serial number labeling.
  • the acquiring unit 301 can acquire the pixel digital frame mask corresponding to the image of each frame in the video stream.
  • the obtaining unit 301 is configured to: perform binarization processing on the image of each frame in the video stream to obtain a binarized image; obtain the binarized image before pre-processing Set the position of the pixels on the digital frame mask.
  • the first determination unit 302 is configured to determine, from the plurality of preset pixel position sets, at least two target preset pixel position sets including a first preset pixel, the first preset pixel is set to a specified color to Represents the frame number of the image.
  • the first determining unit 302 expresses the rectangular stroke of each number by setting the first preset pixel on the preset pixel position set in the pixel digital frame mask.
  • the target preset pixel position set of the first preset pixel is determined to form a rectangular stroke of a number.
  • the first determining unit 302 includes:
  • a first determination subunit used for determining a plurality of preset pixel position sets in the pixel digital frame mask
  • an extraction subunit for extracting a first preset number of pixels in each preset pixel position set
  • the second determination subunit is configured to determine a preset pixel position set in which the first preset number of pixels are all the first preset pixels as the target preset pixel position set.
  • the second determination subunit is configured to: obtain the target number of pixels for which the first preset number of pixels is the first preset number of pixels;
  • the set is determined to be a set of target preset pixel positions, and the second preset number is smaller than the first preset number.
  • the second determining unit 303 is configured to, for the video stream, determine the frame sequence number corresponding to the image of each frame according to the positional relationship between the at least two target preset pixel position sets.
  • the second determining unit 303 can determine the frame sequence number corresponding to the image of each frame in the video stream according to the positional relationship between the target preset pixel position sets. , even if there is noise in the image, it will not affect the pixel digital frame mask, so the frame serial number can be accurately identified, and since the pixel digital frame mask and the coordinate information of the preset pixel position set in the pixel digital frame mask are in The corresponding position in the image is determined, so the frame number can be quickly identified.
  • the second determining unit 303 is configured to: mark a set of target preset pixel positions whose abscissa spacing is less than a preset threshold as a homogeneous set; according to the position between the target preset pixel positions in the homogeneous set The corresponding digital information is generated by the relationship; the digital information corresponding to each homogeneous set is combined to determine the frame sequence number corresponding to the image of each frame in the video stream.
  • the third determining unit 304 is configured to determine the video fluency of the video stream according to the frame sequence number.
  • the third determining unit 304 can detect whether the frame sequence numbers are a linear sequence according to the frame sequence number corresponding to the image of each frame in the video stream, and when the third determining unit 304 detects that the frame sequence numbers are a linear sequence , determine that the video fluency of the video stream is smooth, and when the third determining unit 304 detects that the frame numbers are not in a linear sequence, determine that the video fluency of the video stream is non-smooth and needs to be adjusted.
  • the apparatus further includes:
  • the video stream generating unit is used for generating a video stream based on the application picture running in the server.
  • the acquisition unit 301 obtains the pixel digital frame mask corresponding to the image of each frame in the video stream; the first determination unit 302 determines the target including the first preset pixel in the pixel digital frame mask. The preset pixel position set; the second determining unit 303 determines the frame sequence number corresponding to the image of each frame in the video stream according to the positional relationship between the target preset pixel position sets; the third determining unit 304 determines the video stream of the video stream according to the frame sequence number Fluency.
  • the pixel digital frame mask corresponding to the image of each frame in the video stream can be obtained, the target preset pixel position set containing the first preset pixel can be determined, and the video can be determined according to the arrangement and combination of the target preset pixel position set.
  • the frame sequence number corresponding to the image of each frame in the stream, and then the video fluency of the video stream is determined by the accurate frame sequence number.
  • the embodiment of the present application can be used without passing
  • the frame serial number of each frame of the image in the video stream of the cloud application is accurately determined, and the recognition is not inaccurate due to the change of the cloud application screen, which greatly improves the accuracy of image detection.
  • the accuracy of the fluency assessment of cloud applications is improved.
  • the embodiment of the present application further provides a server, as shown in FIG. 7 , which shows a schematic structural diagram of the server involved in the embodiment of the present application, specifically:
  • the server may be a cloud host, and may include a processor 401 of one or more processing cores, a memory 402 of one or more computer-readable storage media, a power supply 403 and an input unit 404 and other components.
  • a processor 401 of one or more processing cores may include a processor 401 of one or more processing cores, a memory 402 of one or more computer-readable storage media, a power supply 403 and an input unit 404 and other components.
  • FIG. 7 does not constitute a limitation on the server, and may include more or less components than the one shown, or combine some components, or arrange different components. in:
  • the processor 401 is the control center of the server, using various interfaces and lines to connect various parts of the entire server, by running or executing the software programs and/or modules stored in the memory 402, and calling the data stored in the memory 402, Execute various functions of the server and process data to monitor the server as a whole.
  • the processor 401 may include one or more processing cores; in some embodiments, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user Interfaces and applications, etc., the modem processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 401.
  • the memory 402 can be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402 .
  • the memory 402 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program (such as a sound playback function, an image playback function, etc.) required for at least one function, and the like; Data created by the use of the server, etc.
  • memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 402 may also include a memory controller to provide processor 401 access to memory 402 .
  • the server also includes a power supply 403 for supplying power to various components.
  • the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage charging, discharging, and power consumption management functions through the power management system.
  • Power source 403 may also include one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the server may also include an input unit 404, which may be used to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • an input unit 404 which may be used to receive input numerical or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • the server may also include a display processor and the like, which will not be described herein again.
  • the processor 401 in the server loads the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 executes the execution and stores them in the memory 402 in order to achieve various functions, as follows:
  • the pixel digital frame mask Intercept the pixel digital frame mask in the image of each frame in the video stream, the pixel digital frame mask includes a plurality of preset pixel position sets; from the plurality of preset pixel position sets, it is determined that the first preset is included At least two target preset pixel position sets of pixels, and the first preset pixel is set to a specified color to represent the frame number of the image; for the video stream, according to the at least two target preset pixel position sets.
  • the positional relationship between each frame determines the frame sequence number corresponding to the image of each frame; the video fluency of the video stream is determined according to the frame sequence number.
  • the server in the embodiment of the present application can obtain the pixel digital frame mask corresponding to the image of each frame in the video stream; determine the target preset pixel position set including the first preset pixel in the pixel digital frame mask. ; Determine the frame sequence number corresponding to the image of each frame in the video stream according to the positional relationship between the target preset pixel position sets; determine the video fluency of the video stream according to the frame sequence number.
  • the pixel digital frame mask corresponding to the image of each frame in the video stream can be obtained, the target preset pixel position set containing the first preset pixel can be determined, and the video can be determined according to the arrangement and combination of the target preset pixel position set.
  • the frame sequence number corresponding to the image of each frame in the stream, and then the video fluency of the video stream is determined by the accurate frame sequence number.
  • the embodiment of the present application can be used without passing
  • the frame serial number of each frame of the image in the video stream of the cloud application is accurately determined, and the recognition is not inaccurate due to the change of the cloud application screen, which greatly improves the accuracy of image detection.
  • the accuracy of the fluency assessment of cloud applications is improved.
  • the embodiments of the present application provide a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute steps in any image processing method provided by the embodiments of the present application .
  • the instruction can perform the following steps:
  • the pixel digital frame mask Intercept the pixel digital frame mask in the image of each frame in the video stream, the pixel digital frame mask includes a plurality of preset pixel position sets; from the plurality of preset pixel position sets, it is determined that the first preset is included At least two target preset pixel position sets of pixels, and the first preset pixel is set to a specified color to represent the frame number of the image; for the video stream, according to the at least two target preset pixel position sets.
  • the positional relationship between each frame determines the frame sequence number corresponding to the image of each frame; the video fluency of the video stream is determined according to the frame sequence number.
  • a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the various optional implementation manners provided by the foregoing embodiments.
  • the computer-readable storage medium may include: a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

本申请实施例公开了一种图像处理方法、装置、电子设备及计算机可读存储介质，所述方法包括：截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据帧序号确定视频流的视频流畅度。

Description

一种图像处理方法、装置及计算机可读存储介质
本申请要求于2020年11月25日提交中国专利局、申请号为2020113402003，发明名称为“一种图像检测方法、装置及计算机可读存储介质”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
本申请涉及通信技术领域，具体涉及一种图像处理方法、装置及计算机可读存储介质。
背景技术
随着互联网技术的飞速发展，计算机设备的处理能力也越来越强，从而衍生出很多基于人机交互的应用程序，例如云游戏(Cloud gaming)，该云游戏的游戏主机在服务器，玩家通过本地网络连接服务器，在玩游戏时，服务器将游戏画面通过网络进行实时传输，进行生动的互动娱乐。
需要对云游戏的流畅度进行评估，找到用户觉得不卡顿的帧率，为了实现评估过程，需要反复的对云游戏的视频流进行降帧处理，并根据降帧处理之后视频流进行流畅度检测，直至找到视频流合适的帧率。
技术内容
本申请实施例提供一种图像处理方法、装置及计算机可读存储介质，可以提升图像检测的准确率，进而提高云应用的流畅度评估的准确性。
一种图像处理方法，包括：
截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；
从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素位置设置为指定颜色以代表所述图像的帧序号；
针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定所述每一帧的图像对应的帧序号；
根据所述帧序号确定所述视频流的视频流畅度。
一种图像处理装置，包括：
获取单元，用于截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩 码包括多个预设像素位置集合；
第一确定单元，用于从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；
第二确定单元，用于针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定所述每一帧的图像对应的帧序号；
第三确定单元，用于根据所述帧序号确定所述视频流的视频流畅度。
本申请实施例还提供了一种电子设备，包括：处理器；与所述处理器相连接的存储器；所述存储器中存储有机器可读指令，所述机器可读指令可以由处理器执行以完成上述的图像处理方法。
本申请实施例还提供一种计算机可读存储介质，其内存储有处理器可执行指令，所述指令由一个或一个以上处理器加载，以执行上述图像处理方法。
附图简要说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的图像处理系统的场景示意图；
图2是本申请实施例提供的图像处理方法的流程示意图；
图3a为本申请实施例提供的图像处理方法的场景示意图；
图3b为本申请实施例提供的图像处理方法的另一场景示意图；
图4是本申请实施例提供的图像处理方法的另一流程示意图；
图5为本申请实施例提供的图像处理方法的另一场景示意图；
图6是本申请实施例提供的图像处理装置的结构示意图；
图7是本申请实施例提供的服务器的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例提供一种图像处理方法、装置、及计算机可读存储介质。
请参阅图1，图1为本申请实施例所提供的图像处理系统的场景示意图，包括：基础服务器A、和虚拟化的云主机B(该基础服务器A和虚拟化的云主机B还可以包括更多，具体个数在此不作限定)，该基础服务器A即为物理机，也称为实体服务器，是相对于虚拟机(Virtual Machine)而言的实体计算机的称呼，物理机提供给虚拟机的硬件环境，也称为“宿主”或者“寄主”。基础服务器A可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群或者分布式系统，还可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、CDN、以及大数据和人工智能平台等基础云计算服务的云服务器。通过对该基础服务器A进行虚拟化，每台基础服务器A都可以虚拟化出多个云主机B，该云主机B即为虚拟机，也可以称为虚拟专用服务器(Virtual Private Server，VPS)，是将一个服务器分区成多个虚拟独立专享服务器的技术。每个使用VPS技术的虚拟独立服务器拥有各自独立的公网互联网协议(Internet Protocol Address，IP)地址、操作系统、硬盘空间、内存空间、处理器(Central Processing Unit，CPU)资源等，还可以进行安装程序、重启服务器等操作，与运行一台独立服务器完全相同。也就是说通过软件层面，对一台服务器进行虚拟划分，虚拟出来多台服务器，这样就能让只需要一点点计算能力用户享用到大型服务器的计算资源。从广义上讲，云主机B就是VPS，只不过云主机B是在所有基础服务器A或者虚拟机上进一步虚拟化所有基础资源，例如内存带宽等等。云主机B的优势在于它可以分布式存储数据，动态扩展基础资源。安全性和扩展性较强。
该每台云主机B拥有独立的操作系统和硬件结构，与运行一台独立主机完全相同，只不过每台云主机B中的物理地址都为虚拟机的物理地址，每台云主机B中可以安装有多个处理器，如一台云主机B中安装有多个图形处理器(Graphics Processing Unit，GPU)，一台云主机B可以类似于VMware虚拟机，一个物理机可以虚拟化多个安卓操作系统实例，该一台云主机B中可以安装游戏的板卡或者容器，模拟用户的终端环境，但是无物理显示屏，例如运行云游戏(Cloud gaming)该云游戏又可称为游戏点播(gaming on demand)，是一种以云计算技术为基础的在线游戏技术。云游戏技术使图形处理与数据运算能力相对有限的轻端设备(thin client)能运行高品质游戏。在云游戏场景下，游戏并不在玩家游戏终端，而是在云端服务器中运行，并由云端服务器将游戏场景渲染为视频音频流，通过网络传输给玩家游戏终端。玩家游戏终端无需拥有强大的图形运算与数据处理能力，仅需拥有基本的流媒体播放能力与获取玩家输入指令并发送给云端服务器的能力即可。
以此，云主机B可以截取云游戏的视频流中每一帧的图像对应的像素数字帧掩码，该像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含 第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据该帧序号确定该视频流的视频流畅度，极大的提升了图像检测的准确率，进而提高云游戏的流畅度评估的准确性。
需要说明的是，图1所示的图像处理系统的场景示意图仅仅是一个示例，本申请实施例描述的图像处理系统以及场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着图像处理系统的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
基于上述应用场景的描述，以下分别进行详细说明。
请参阅图2，图2是本申请实施例提供的图像处理方法的流程示意图。在本实施例中，将从图像处理装置的角度进行描述，该图像处理装置具体可以集成在具备储存单元并安装有微处理器而具有运算能力的云主机中。
该图像处理方法包括：
在步骤101中，截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合。
本申请实施例中的像素是指由图像的小方格组成的，这些小方块都有一个明确的位置和被分配的色彩数值，小方块颜色和位置就决定该图像所呈现出来的样子。
需要说明的是，该视频流可以由多帧连续的图像组成，即该视频流可以为视频播放画面，在实际的场景中，该云主机通过网络将该视频流以设定的帧率，例如60帧/秒或者30帧/秒，实时的传输到用户终端中，用户终端播放上述视频流。
在一实施例中，该视频流可以为云主机中云游戏的云游戏画面生成的视频流、视频播放器播放画面的视频流、直播平台播放直播画面对应的视频流或者普通游戏运行时的游戏画面形成的视频流，本申请实施例以云游戏画面生成的视频流进行描述，不作为具体限定，其他场景下的视频流也可以通过本实施例提供的图像处理方法进行处理。
其中，该帧率越高，视频流播放的流畅性和稳定性越高，游戏效果越好，该帧率越低，视频流播放的流畅性和稳定性越低，但是由于不同终端的设备配置不同和网络环境不同，对应能支持的帧率也不同，云主机对应不同的用户终端需要对推送的视频流的流畅度进行评估，找到不同用户终端觉得不卡顿的帧率，因此，基于高频帧率的视频流开始，需要反复的对云游戏的视频流进行降帧处理，并根据降帧处理之后的视频流进行流畅度检测，直至找到视频流合适的帧率。
由于云游戏中的视频流中的每一帧的图像是没有特定序号的，所以为了判断降帧之后的图像的播放是否均匀正确，需要对视频流中的每一帧的图像打上标记，从而通过识别标记的方式对降帧均匀程度进行评估。
在一些实施例中，可以为视频流中的每一帧的图像写上对应的标记，通过光学字符识别(Optical Character Recognition，OCR)的方式进行标记识别确定每一图像的顺序，需要说明的是，该光学字符识别可以对字符通过检测暗、亮的模式确定其形状，然后用字符识别方式将形状翻译成计算机文字。但是，由于云游戏游戏画面的复杂性以及编码处理等技术，会导致部分图像中出现噪点，该噪点是图像中一种亮度或颜色信息的随机变化(被拍摄物体本身并没有)，通常是电子噪声的表现，是图像生成过程中不希望存在的副产品，给图像带来了错误和额外的信息。该噪点会影响图像中标记的识别，进而导致图像标记检测的准确率极大的降低。
本申请实施例为了解决上述问题，可以预先生成像素数字帧掩码，该像素数字帧掩码包括在至少两个预设像素位置集合上显示的第一预设像素，以形成图像的帧序号，为视频流中每一帧的图像增加对应的像素数字帧掩码，实现帧序号标注，基于此，服务器可以获取视频流中每一帧的图像对应的像素数字帧掩码，例如，请一并参阅图3a所示，该视频流中的图像11中包含像素数字帧掩码111，在该像素数字帧掩码111中包含多个预设像素位置集合，该预设像素位置集合可以理解为形成数字的矩形笔画，该预设像素位置集合为预先定义好的，该预设像素位置集合的大小可以为2n*n像素大小，该第一预设像素可以为RGB(红(R)、绿(G)、蓝(B))值为(255，255，255)的像素，即纯白色像素。通过将至少两个预设像素位置集合上的像素设置为第一预设像素，可以表示出任意的数字，例如，通过两个预设像素位置集合上的像素设置为第一预设像素可以表示数字1，像素数字帧掩码111中包含数字0、9、9、1，将该数字0、9、9、1进行组合，确定该图像11的帧序号为0991。以此类推，对至少两个预设像素位置集合上显示的第一预设像素按照数字规则进行设置，可以得到任意数量的帧序号，且由于该像素数字帧掩码111的表达简单，后续可以准确且快速进行识别。
在步骤102中，从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号。
在本申请实施例中，通过将像素数字帧掩码中的预设像素位置集合上设置第一预设像素来表达每一数字的矩形笔画，因此，需要首先确定像素数字帧掩码中的包含第一预设像素的目标预设像素位置集合，即确定形成数字的矩形笔画。
例如，请一并参阅图3a所示，像素数字帧掩码111中包含7个预设像素位置集合，分 别为预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7，通过对该预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7中的像素进行分析，确定预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7中的像素均为第一预设像素，因此，将预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7均确定为目标预设像素位置集合。
在一些实施方式中，该确定像素数字帧掩码中的包含第一预设像素的目标预设像素位置集合的步骤，可以包括：
(1)确定该像素数字帧掩码中的多个预设像素位置集合；
(2)提取每一预设像素位置集合中第一预设数量的像素；
(3)将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合。
其中，可以先确定像素数字帧掩码中的多个预设像素位置集合，请一并参阅图3b所示，确定像素数字帧掩码111中的预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7，提取预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7中第一预设数量的像素，该第一预设数量可以为4，即随机提取每一预设像素位置集合中的4个像素。
进一步的，假设预设像素位置集合中的4个像素均为第一预设像素，可以判定为该预设像素位置集合中的像素全部为第一预设像素，将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合，即将预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7均确定为目标预设像素位置集合。
在步骤103中，针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号。
其中，请一并参阅图3b所示，可以设定一个数字信息包含7个预设像素位置集合，即预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7，该预设像素位置集合中 的像素为第一预设像素时，即点亮数字笔画，该预设像素位置集合中的像素不为第一预设像素时，即不点亮数字笔画，通过该预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7可以表示数字0至9中的任一数字，例如：
0：预设像素位置集合1、2、3、5、6、7点亮。
1：预设像素位置集合3、6点亮。
2：预设像素位置集合1、3、4、5、7点亮。
3：预设像素位置集合1、3、4、6、7点亮。
4：预设像素位置集合2、3、4、6点亮。
5：预设像素位置集合1、2、4、6、7点亮。
6：预设像素位置集合1、2、4、5、6、7点亮。
7：预设像素位置集合1、3、6点亮。
8：预设像素位置集合1、2、3、4、5、6、7点亮。
9：预设像素位置集合1、2、3、4、6点亮。
本申请实施例可以根据需要设置任意数量的数字信息，在此不作具体限定。以此，本申请可以根据目标预设像素位置集合之间的位置关系确定视频流中每一帧的图像对应的帧序号，由于该帧序号为通过特定的第一预设像素组成，因此，即使图像中出现噪点也不会对像素数字帧掩码产生影响，所以可以准确的识别帧序号，且由于该像素数字帧掩码和像素数字帧掩码中的预设像素位置集合的坐标信息在图像中对应的位置都是确定的，所以可以快速进行识别帧序号。
在一些实施方式中，该根据目标预设像素位置集合之间的位置关系确定视频流中每一帧的图像对应的帧序号的步骤，可以包括：
(1)将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合；
(2)根据同类集合中的目标预设像素位置之间的位置关系生成对应的数字信息；
(3)将每一同类集合对应的数字信息进行组合，确定该视频流中每一帧的图像对应的帧序号。
其中，由于在实际的使用过程中，帧序号可以为个位数、十位数或者百位数，因此组成帧序号的数字信息可以为1个、2个或者3个等等，因此，可以通过横坐标间距将数字信息进行区分，将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合，该预设阈值可以为10个像素，即将组成同一数字信息的目标预设像素位置集合归为一类。
进一步的，将同一类集合中的目标预设像素位置之间的位置关系与前述规则进行对比， 得到每一同类集合对应的数字信息，将每一同类集合对应的数字信息进行组合，确定该视频流中每一帧的图像对应的帧序号。
在步骤104中，根据帧序号确定视频流的视频流畅度。
其中，可以根据视频流中每一帧的图像对应的帧序号，检测该帧序号之间是否为线性序列，当检测到该帧序号之间为线性序列时，判定该视频流的视频流畅度为流畅，当检测到该帧序号之间不为线性序列时，判定该视频流的视频流畅度为非流畅，需要进行调整。
在一实施方式中，在确定出每一帧的图像的帧序号之后，可以根据帧序号快速定位到需要进行画面测评的图像上，通过画质评估算法对图片的质量进行评估打分。
由上述可知，本申请实施例通过获取视频流中每一帧的图像对应的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据帧序号确定视频流的视频流畅度。以此，可以获取视频流中每一帧的图像对应的像素数字帧掩码，确定其中包含第一预设像素的目标预设像素位置集合，根据该目标预设像素位置集合的排列组合确定视频流中每一帧的图像对应的帧序号，进而通过准确的帧序号确定视频流的视频流畅度，相对于直接对视频画面进行识别确定帧序号的方案而言，本申请实施例可以在不通过画面识别的基础上，准确的确定出云应用的视频流中每一帧的图像的帧序号，不会因为云应用画面的变化而导致识别不准确，极大的提升了图像检测的准确率，进而提高了云应用的流畅度评估的准确性。
请参阅图4，图4为本申请实施例提供的图像处理方法的另一流程示意图。根据图3所示实施例所描述的方法，以下将举例作进一步详细说明。
在本实施例中，将以该图像处理装置具体集成在服务器中，该服务器为云主机为例进行说明，具体参照以下说明。
该方法流程可以包括：
在步骤201中，服务器基于运行在服务器中的视频画面生成视频流，获取预设数量的第二预设像素组成第一掩码，所述第一掩码包括多个预设像素位置集合。
其中，该第二预设像素可以为RGB值为(0，0，0)的像素，即纯黑色像素，服务器可以通过运行在云主机中的云应用对应的视频画面生成视频流，该方式下生成的视频流中的每一帧图像即为云应用的图像，获取预设数量的第二预设像素组成的第一掩码，该预设数量可以为人为设置，即生成预设尺度的纯黑色画布，该第一掩码中包含多个预设像素位置 集合，例如可以包含28个预设像素位置集合。
在一些实施例中，每个预设像素位置集合的大小可以为2n*n像素大小，该2n为长度，该n为宽度，n为人工设置，例如3，7个预设像素位置集合可以形成一个数字信息，即本申请实施例最多可以表示4位数字，最小为1，最大为9999。
在步骤202中，服务器将所述第一掩码中至少两个预设像素位置集合中的第二预设像素切换显示为第一预设像素，生成像素数字帧掩码，所述像素数字帧掩码用于标注每一帧图像的帧序号，获取视频流中每一帧的图像的帧顺序，根据帧顺序在每一帧图像的预设位置上插入对应的像素数字帧掩码。
其中，该第一预设像素可以为RGB值为(255，255，255)的像素，即纯白色像素，服务器为了表示帧序号，可以以此将至少两个预设像素位置集合中的第二预设像素切换显示为第一预设像素，以此根据数字显示规则，可以生成数字为1至9999中任一帧序号的像素数字帧掩码。
进一步的，获取视频流中每一帧的图像的帧顺序，该帧顺序从1开始，根据该帧顺序确定对应的目标图像和目标像素数字帧掩码，例如，获取帧顺序为1，对应为视频流中第一帧的图像和目标像素数字帧掩码，该目标数字帧掩码中的帧序号为1，以此，在目标图像的预设位置上插入目标像素数字帧掩码，例如，请继续参阅图3a所示，在目标图像11的右下角插入目标像素数字帧掩码111，以此，在图像的固定位置上插入目标像素数字帧掩码，使得后续可以根据预设位置快速定位到像素数字帧掩码的位置，进而截取该像素数字帧掩码进行帧序号识别。
在步骤203中，服务器对视频流中每一帧的图像进行二值化处理，得到二值化处理后的图像，在二值化处理后的图像的预设位置处截取所述像素数字帧掩码。
其中，为了增加像素数字帧掩码中的第一预设像素和第二预设像素之间的区分度，服务器可以预先对视频流中每一帧的图像进行二值化处理，该二值化处理可以将整个图像呈现出明显的黑白效果，从而凸显出第一预设像素的轮廓。
进一步的，获取二值化处理后的图像在预设位置，例如图像的右下角上的像素数字帧掩码，由于服务器预先定义了像素数字帧掩码的位置，以此，快速通过定义的位置截取到像素数字帧掩码以进行后续的识别，请一并参阅图5所示，该图5所示即为二值化处理后的图像在预设位置上的像素数字帧掩码112。
在步骤204中，服务器确定像素数字帧掩码中的多个预设像素位置集合，提取每一预设像素位置集合中第一预设数量的像素，获取第一预设数量的像素为第一预设像素的目标数量。
其中，请继续参阅图5所示，确定像素数字帧掩码112中包含的28个预设像素位置集合，该第一预设数量为人工设置，假设为4个，服务器提取28个预设像素位置集合中任意4个像素。
进一步的，确定4个像素中像素为第一预设像素的目标数量，假设为4个像素中3个第一预设像素，目标数量为3。
在步骤205中，服务器将目标数量大于第二预设数量的预设像素位置集合确定为目标预设像素位置集合。
其中，由于云应用画面在传输之前需要压缩码和编码等处理，会导致部分像素可能损失细节，为了避免出现误判，可以设定第二预设数量，该第二预设数量小于第一预设数量，假设该第二预设数量可以为2，以此，服务器将目标数量大于2的预设像素位置集合确定为目标预设像素位置集合。请一并参阅图5所示，确定目标预设像素位置集合为25个。
在步骤206中，服务器将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合，根据同类集合中的目标预设像素位置之间的位置关系生成对应的数字信息。
其中，请一并参阅图5所示，不同数字信息之间的横坐标间隔为固定的，纵坐标接近，以此，服务器可将横坐标间隔小于预设阈值的目标预设像素位置集合标记为同类集合，得到集合A、集合B、集合C和集合D。请继续参阅图3b所示，可以设定一个数字信息包含7个预设像素位置集合，即预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7，该预设像素位置集合中的像素为第一预设像素时，即点亮数字笔画，该预设像素位置集合中的像素不为第一预设像素时，即不点亮数字笔画，通过该预设像素位置集合1、预设像素位置集合2、预设像素位置集合3、预设像素位置集合4、预设像素位置集合5、预设像素位置集合6、预设像素位置集合7可以表示数字0至9中的任一数字，例如：
0：预设像素位置集合1、2、3、5、6、7点亮。
1：预设像素位置集合3、6点亮。
2：预设像素位置集合1、3、4、5、7点亮。
3：预设像素位置集合1、3、4、6、7点亮。
4：预设像素位置集合2、3、4、6点亮。
5：预设像素位置集合1、2、4、6、7点亮。
6：预设像素位置集合1、2、4、5、6、7点亮。
7：预设像素位置集合1、3、6点亮。
8：预设像素位置集合1、2、3、4、5、6、7点亮。
9：预设像素位置集合1、2、3、4、6点亮。
以此，服务器将同类集合中的目标预设像素位置之间的位置关系根据上述规则进行推导，生成集合A、集合B、集合C和集合D对应的数字信息分别为0、9、9、8。
在步骤207中，服务器将每一同类集合对应的数字信息进行组合，确定视频流中每一帧的图像对应的帧序号。
其中，服务器将集合A、集合B、集合C和集合D对应数字信息0、9、9、8进行组合，识别得到当前图像的帧序号为0998，以此类推，服务器可以快速且准确的识别出视频流中每一帧的图像对应的帧序号。
在步骤208中，服务器根据帧序号确定视频流的视频流畅度。
其中，在服务器确定视频流中每一图像的帧序号之后，检测该帧序号之间是否为线性序列，当检测到该帧序号之间为线性序列时，判定该视频流的视频流畅度为流畅，当检测到该帧序号之间不为线性序列时，判定该视频流的视频流畅度为非流畅，需要进行调整。
由上述可知，本申请实施例通过截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据帧序号确定视频流的视频流畅度。以此，可以获取视频流中每一帧的图像对应的像素数字帧掩码，确定其中包含第一预设像素的目标预设像素位置集合，根据该目标预设像素位置集合的排列组合确定视频流中每一帧的图像对应的帧序号，进而通过准确的帧序号确定视频流的视频流畅度，相对于直接对视频画面进行识别确定帧序号的方案而言，本申请实施例可以在不通过画面识别的基础上，准确的确定出云应用的视频流中每一帧的图像的帧序号，不会因为云应用画面的变化而导致识别不准确，极大的提升了图像检测的准确率，进而提高了云应用的流畅度评估的准确性。
为便于更好的实施本申请实施例提供的图像处理方法，本申请实施例还提供一种基于上述图像处理方法的装置。其中名词的含义与上述图像处理方法中相同，具体实现细节可以参考方法实施例中的说明。
请参阅图6，图6为本申请实施例提供的图像处理装置的结构示意图，其中该图像处理装置可以包括获取单元301、第一确定单元302、第二确定单元303、及第三确定单元304等。
获取单元301，用于截取视频流中每一帧的图像中的像素数字帧掩码，该像素数字帧掩码包括多个预设像素位置集合。
其中，可以预先生成像素数字帧掩码，该像素数字帧掩码包括在至少两个预设像素位置集合上显示的第一预设像素，以形成图像的帧序号，为视频流中每一帧的图像增加对应的像素数字帧掩码，实现帧序号标注，基于此，获取单元301可以获取视频流中每一帧的图像对应的像素数字帧掩码。
在一些实施方式中，该获取单元301，用于：对该视频流中每一帧的图像进行二值化处理，得到二值化处理后的图像；获取该二值化处理后的图像在预设位置上的像素数字帧掩码。
第一确定单元302，用于从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号。
其中，第一确定单元302通过将像素数字帧掩码中的预设像素位置集合上设置第一预设像素来表达每一数字的矩形笔画，因此，需要首先确定像素数字帧掩码中的包含第一预设像素的目标预设像素位置集合，即确定形成数字的矩形笔画。
在一些实施方式中，该第一确定单元302，包括：
第一确定子单元，用于确定该像素数字帧掩码中的多个预设像素位置集合；
提取子单元，用于提取每一预设像素位置集合中第一预设数量的像素；
第二确定子单元，用于将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合。
在一些实施方式中，该第二确定子单元，用于：获取该第一预设数量的像素为第一预设像素的目标数量；将该目标数量大于第二预设数量的预设像素位置集合确定为目标预设像素位置集合，该第二预设数量小于该第一预设数量。
第二确定单元303，用于针对所述视频流，根据该至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号。
其中，第二确定单元303可以根据目标预设像素位置集合之间的位置关系确定视频流中每一帧的图像对应的帧序号，由于该帧序号为通过特定的第一预设像素组成，因此，即使图像中出现噪点也不会像素数字帧掩码产生影响，所以可以准确的识别帧序号，且由于该像素数字帧掩码和像素数字帧掩码中的预设像素位置集合的坐标信息在图像中对应的位置都是确定的，所以可以快速进行识别帧序号。
在一些实施方式中，该第二确定单元303，用于：将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合；根据同类集合中的目标预设像素位置之间的位置关系生成对应的数字信息；将每一同类集合对应的数字信息进行组合，确定该视频流中每一帧 的图像对应的帧序号。
第三确定单元304，用于根据该帧序号确定该视频流的视频流畅度。
其中，第三确定单元304可以根据视频流中每一帧的图像对应的帧序号，检测该帧序号之间是否为线性序列，当第三确定单元304检测到该帧序号之间为线性序列时，判定该视频流的视频流畅度为流畅，当第三确定单元304检测到该帧序号之间不为线性序列时，判定该视频流的视频流畅度为非流畅，需要进行调整。
在一些实施方式中，该装置还包括：
视频流生成单元，用于基于运行在服务器中的应用画面生成视频流。
以上各个单元的具体实施可参见前面的实施例，在此不再赘述。
由上述可知，本申请实施例通过获取单元301获取视频流中每一帧的图像对应的像素数字帧掩码；第一确定单元302确定像素数字帧掩码中的包含第一预设像素的目标预设像素位置集合；第二确定单元303根据目标预设像素位置集合之间的位置关系确定视频流中每一帧的图像对应的帧序号；第三确定单元304根据帧序号确定视频流的视频流畅度。以此，可以获取视频流中每一帧的图像对应的像素数字帧掩码，确定其中包含第一预设像素的目标预设像素位置集合，根据该目标预设像素位置集合的排列组合确定视频流中每一帧的图像对应的帧序号，进而通过准确的帧序号确定视频流的视频流畅度，相对于直接对视频画面进行识别确定帧序号的方案而言，本申请实施例可以在不通过画面识别的基础上，准确的确定出云应用的视频流中每一帧的图像的帧序号，不会因为云应用画面的变化而导致识别不准确，极大的提升了图像检测的准确率，进而提高了云应用的流畅度评估的准确性。
本申请实施例还提供一种服务器，如图7所示，其示出了本申请实施例所涉及的服务器的结构示意图，具体来讲：
该服务器可以为云主机，可以包括一个或者一个以上处理核心的处理器401、一个或一个以上计算机可读存储介质的存储器402、电源403和输入单元404等部件。本领域技术人员可以理解，图7中示出的服务器结构并不构成对服务器的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器401是该服务器的控制中心，利用各种接口和线路连接整个服务器的各个部分，通过运行或执行存储在存储器402内的软件程序和/或模块，以及调用存储在存储器402内的数据，执行服务器的各种功能和处理数据，从而对服务器进行整体监控。在一些实施例中，处理器401可包括一个或多个处理核心；在一些实施例中，处理器401可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等， 调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器401中。
存储器402可用于存储软件程序以及模块，处理器401通过运行存储在存储器402的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器402可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据服务器的使用所创建的数据等。此外，存储器402可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器402还可以包括存储器控制器，以提供处理器401对存储器402的访问。
服务器还包括给各个部件供电的电源403，在一些实施例中，电源403可以通过电源管理系统与处理器401逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源403还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该服务器还可包括输入单元404，该输入单元404可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。
尽管未示出，服务器还可以包括显示处理器等，在此不再赘述。具体在本实施例中，服务器中的处理器401会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器402中，并由处理器401来运行存储在存储器402中的应用程序，从而实现各种功能，如下：
截取视频流中每一帧的图像中的像素数字帧掩码，该像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据该至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据该帧序号确定该视频流的视频流畅度。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见上文针对图像处理方法的详细描述，此处不再赘述。
由上述可知，本申请实施例的服务器可以通过获取视频流中每一帧的图像对应的像素数字帧掩码；确定像素数字帧掩码中的包含第一预设像素的目标预设像素位置集合；根据目标预设像素位置集合之间的位置关系确定视频流中每一帧的图像对应的帧序号；根据帧序号确定视频流的视频流畅度。以此，可以获取视频流中每一帧的图像对应的像素数字帧掩码，确定其中包含第一预设像素的目标预设像素位置集合，根据该目标预设像素位置集 合的排列组合确定视频流中每一帧的图像对应的帧序号，进而通过准确的帧序号确定视频流的视频流畅度，相对于直接对视频画面进行识别确定帧序号的方案而言，本申请实施例可以在不通过画面识别的基础上，准确的确定出云应用的视频流中每一帧的图像的帧序号，不会因为云应用画面的变化而导致识别不准确，极大的提升了图像检测的准确率，进而提高了云应用的流畅度评估的准确性。
本领域普通技术人员可以理解，上述实施例的各种方法中的全部或部分步骤可以通过指令来完成，或通过指令控制相关的硬件来完成，该指令可以存储于一计算机可读存储介质中，并由处理器进行加载和执行。
为此，本申请实施例提供一种计算机可读存储介质，其中存储有多条指令，该指令能够被处理器进行加载，以执行本申请实施例所提供的任一种图像处理方法中的步骤。例如，该指令可以执行如下步骤：
截取视频流中每一帧的图像中的像素数字帧掩码，该像素数字帧掩码包括多个预设像素位置集合；从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；针对所述视频流，根据该至少两个目标预设像素位置集合之间的位置关系确定每一帧的图像对应的帧序号；根据该帧序号确定该视频流的视频流畅度。
根据本申请的一个方面，提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备执行上述实施例提供的各种可选实现方式中提供的方法。
以上各个操作的具体实施可参见前面的实施例，在此不再赘述。
其中，该计算机可读存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
由于该计算机可读存储介质中所存储的指令，可以执行本申请实施例所提供的任一种图像处理方法中的步骤，因此，可以实现本申请实施例所提供的任一种图像处理方法所能实现的有益效果，详见前面的实施例，在此不再赘述。
以上对本申请实施例所提供的一种图像处理方法、装置、计算机可读存储介质进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种可由计算机设备执行的图像处理方法，包括：
    截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；
    从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；
    针对所述视频流，根据所述至少两个目标预设像素位置集合之间的位置关系确定所述视频流中每一帧的图像对应的帧序号；
    根据所述帧序号确定所述视频流的视频流畅度。
  2. 根据权利要求1所述的图像处理方法，其中，所述多个预设像素位置集合为形成数字的矩形笔画，所述第一预设像素为纯白色像素。
  3. 根据权利要求1所述的图像处理方法，其中，所述根据所述帧序号确定所述视频流的视频流畅度包括：
    当检测到该帧序号之间为线性序列时，判定该视频流的视频流畅度为流畅；
    当检测到该帧序号之间不为线性序列时，判定该视频流的视频流畅度为非流畅。
  4. 根据权利要求1所述的图像处理方法，其中，所述从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合的步骤，包括：
    确定所述像素数字帧掩码中的多个预设像素位置集合；
    提取每一预设像素位置集合中第一预设数量的像素；
    将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合。
  5. 根据权利要求4所述的图像处理方法，其中，所述将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合的步骤，包括：
    获取所述第一预设数量的像素为第一预设像素的目标数量；
    将所述目标数量大于第二预设数量的预设像素位置集合确定为目标预设像素位置集合，所述第二预设数量小于所述第一预设数量。
  6. 根据权利要求1所述的图像处理方法，其中，所述根据所述至少两个目标预设像素位置集合之间的位置关系确定所述每一帧的图像对应的帧序号的步骤，包括：
    将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合；
    根据同类集合中的目标预设像素位置之间的位置关系生成对应的数字信息；
    将每一同类集合对应的数字信息进行组合，确定所述视频流中每一帧的图像对应的帧 序号。
  7. 根据权利要求1至6任一项所述的图像处理方法，其中，所述截取视频流中每一帧的图像中的像素数字帧掩码的步骤之前，还包括：
    生成所述像素数字帧掩码；
    为视频流中每一帧的图像插入对应的像素数字帧掩码。
  8. 根据权利要求7所述的图像处理方法，其中，所述生成像素数字帧掩码的步骤，包括：
    获取预设数量的第二预设像素组成第一掩码，所述第一掩码中包含所述多个预设像素位置集合；
    将所述至少两个预设像素位置集合中的第二预设像素切换显示为第一预设像素，生成所述像素数字帧掩码。
  9. 根据权利要求7所述的图像处理方法，其中，所述为视频流中每一帧的图像插入对应的像素数字帧掩码的步骤，包括：
    获取所述视频流中每一帧的图像的帧顺序；
    根据所述帧顺序确定对应的像素数字帧掩码；
    在所述图像的预设位置上插入所述像素数字帧掩码。
  10. 根据权利要求9所述的图像处理方法，其中，所述截取视频流中每一帧的图像中的像素数字帧掩码的步骤，包括：
    对所述视频流中每一帧的图像进行二值化处理，得到二值化处理后的图像；
    在所述二值化处理后的图像的预设位置处截取所述像素数字帧掩码。
  11. 根据权利要求1所述的图像处理方法，其中，所述截取视频流中每一帧的图像中的像素数字帧掩码的步骤之前，还包括：
    基于运行在服务器中的视频画面生成视频流。
  12. 一种图像处理装置，包括：
    获取单元，用于截取视频流中每一帧的图像中的像素数字帧掩码，所述像素数字帧掩码包括多个预设像素位置集合；
    第一确定单元，用于从所述多个预设像素位置集合中，确定包含第一预设像素的至少两个目标预设像素位置集合，所述第一预设像素设置为指定颜色以代表所述图像的帧序号；
    第二确定单元，用于针对所述视频流，根据所述目标预设像素位置集合之间的位置关系确定所述每一帧的图像对应的帧序号；
    第三确定单元，用于根据所述帧序号确定所述视频流的视频流畅度。
  13. 根据权利要求12所述的图像处理装置，其中，所述多个预设像素位置集合为形成数字的矩形笔画，所述第一预设像素为纯白色像素。
  14. 根据权利要求12所述的图像处理装置，其中，所述第三确定单元进一步用于：
    当检测到该帧序号之间为线性序列时，判定该视频流的视频流畅度为流畅；
    当检测到该帧序号之间不为线性序列时，判定该视频流的视频流畅度为非流畅。
  15. 根据权利要求12所述的图像处理装置，其中，所述第一确定单元，包括：
    第一确定子单元，用于确定所述像素数字帧掩码中的多个预设像素位置集合；
    提取子单元，用于提取每一预设像素位置集合中第一预设数量的像素；
    第二确定子单元，用于将第一预设数量的像素均为第一预设像素的预设像素位置集合确定为目标预设像素位置集合。
  16. 根据权利要求15所述的图像处理装置，其中，所述第二确定子单元，用于：
    获取所述第一预设数量的像素为第一预设像素的目标数量；
    将所述目标数量大于第二预设数量的预设像素位置集合确定为目标预设像素位置集合，所述第二预设数量小于所述第一预设数量。
  17. 根据权利要求12所述的图像处理装置，其中，所述第二确定单元，用于：
    将横坐标间距小于预设阈值的目标预设像素位置集合标记为同类集合；
    根据同类集合中的目标预设像素位置之间的位置关系生成对应的数字信息；
    将每一同类集合对应的数字信息进行组合，确定所述视频流中每一帧的图像对应的帧序号。
  18. 根据权利要求12至17任一项所述的图像处理装置，其中，所述装置，还包括：
    生成单元，用于生成像素数字帧掩码；
    增加单元，用于为视频流中每一帧的图像增加对应的像素数字帧掩码。
  19. 一种电子设备，包括：处理器；与所述处理器相连接的存储器；所述存储器中存储有机器可读指令，所述机器可读指令可以由处理器执行以完成如权利要求1-11任一项所述的方法。
  20. 一种计算机可读存储介质，所述计算机可读存储介质存储有多条指令，所述指令适于处理器进行加载，以执行权利要求1至11任一项所述的图像处理方法中的步骤。
PCT/CN2021/126879 2020-11-25 2021-10-28 一种图像处理方法、装置及计算机可读存储介质 WO2022111201A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/969,618 US20230045166A1 (en) 2020-11-25 2022-10-19 Image processing method and apparatus, and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011340200.3 2020-11-25
CN202011340200.3A CN112184739B (zh) 2020-11-25 2020-11-25 一种图像检测方法、装置及计算机可读存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/969,618 Continuation US20230045166A1 (en) 2020-11-25 2022-10-19 Image processing method and apparatus, and computer-readable storage medium

Publications (1)

Publication Number Publication Date
WO2022111201A1 true WO2022111201A1 (zh) 2022-06-02

Family

ID=73918674

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/126879 WO2022111201A1 (zh) 2020-11-25 2021-10-28 一种图像处理方法、装置及计算机可读存储介质

Country Status (3)

Country Link
US (1) US20230045166A1 (zh)
CN (1) CN112184739B (zh)
WO (1) WO2022111201A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112184739B (zh) * 2020-11-25 2021-03-02 腾讯科技（深圳）有限公司 一种图像检测方法、装置及计算机可读存储介质
CN114173194B (zh) * 2021-12-08 2024-04-12 广州品唯软件有限公司 页面流畅度的检测方法、装置、服务器和存储介质
CN114155473B (zh) * 2021-12-09 2022-11-08 成都智元汇信息技术股份有限公司 基于帧补偿的切图方法、电子设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1622640A (zh) * 2004-12-13 2005-06-01 武汉大学 一种对视频序列中每一帧图像进行标记的方法
CN101527855A (zh) * 2009-04-21 2009-09-09 成都索贝数码科技股份有限公司 视频信号的自动侦测方法及其系统
US20130259139A1 (en) * 2012-03-29 2013-10-03 Dish Network L.L.C. Testing frame color counting technique
CN103942741A (zh) * 2014-04-29 2014-07-23 陕西科技大学 一种考试答题卡的填涂识别方法及其装置
CN112184739A (zh) * 2020-11-25 2021-01-05 腾讯科技（深圳）有限公司 一种图像检测方法、装置及计算机可读存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100507944C (zh) * 2006-11-27 2009-07-01 北京中星微电子有限公司 一种图像格式转换方法、图像处理方法与系统
FR2925206B1 (fr) * 2007-12-18 2015-05-29 Thales Sa Dispositif d'affichage et procede d'optimisation de la bande passante memoire
CN102256130B (zh) * 2011-07-27 2013-04-24 武汉大学 一种基于插入宏块亮度特殊值标记视频帧图像序号的方法
CN103024453B (zh) * 2012-12-26 2016-06-01 广东威创视讯科技股份有限公司 非直接获取视频应用场合拼接视频同步播放方法及装置
CN109561336A (zh) * 2018-12-27 2019-04-02 威创集团股份有限公司 分布式显示同步方法、装置及系统
CN110491502B (zh) * 2019-03-08 2021-03-16 腾讯科技（深圳）有限公司 显微镜视频流处理方法、系统、计算机设备和存储介质
CN110730345B (zh) * 2019-10-11 2022-09-02 京东方科技集团股份有限公司 图像显示方法、图像识别方法、装置、介质、设备及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1622640A (zh) * 2004-12-13 2005-06-01 武汉大学 一种对视频序列中每一帧图像进行标记的方法
CN101527855A (zh) * 2009-04-21 2009-09-09 成都索贝数码科技股份有限公司 视频信号的自动侦测方法及其系统
US20130259139A1 (en) * 2012-03-29 2013-10-03 Dish Network L.L.C. Testing frame color counting technique
CN103942741A (zh) * 2014-04-29 2014-07-23 陕西科技大学 一种考试答题卡的填涂识别方法及其装置
CN112184739A (zh) * 2020-11-25 2021-01-05 腾讯科技（深圳）有限公司 一种图像检测方法、装置及计算机可读存储介质

Also Published As

Publication number Publication date
US20230045166A1 (en) 2023-02-09
CN112184739B (zh) 2021-03-02
CN112184739A (zh) 2021-01-05

Similar Documents

Publication Publication Date Title
WO2022111201A1 (zh) 一种图像处理方法、装置及计算机可读存储介质
US11722727B2 (en) Special effect processing method and apparatus for live broadcasting, and server
US11057583B2 (en) Bullet comment processing method and apparatus, and storage medium
US11565178B2 (en) User interface rendering and post processing during video game streaming
US11928863B2 (en) Method, apparatus, device, and storage medium for determining implantation location of recommendation information
US10537799B1 (en) User interface rendering and post processing during video game streaming
WO2017129118A1 (zh) 图形指令数据的处理方法和装置及系统
WO2022062772A1 (zh) 图像检测方法、装置、计算机设备及计算机可读存储介质
US10171785B2 (en) Color balancing based on reference points
US10863230B1 (en) Content stream overlay positioning
BR112015011245A2 (pt) sistemas e métodos para o processamento em nuvem e sobreposição do conteúdo nos frames de streaming de vídeo de aplicações remotamente processadas.
WO2022089168A1 (zh) 具有三维效果的视频的生成方法、播放方法、装置及设备
US11206294B2 (en) Method for separating local and remote content in a camera-projector based collaborative system
CN104683787A (zh) 识别视频类型的方法、装置和显示设备及其投影视频方法
EP4282499A1 (en) Data processing method and apparatus, and device and readable storage medium
WO2014100936A1 (zh) 视频的关联信息库制作和视频播放的方法、平台及系统
CN111298434B (zh) 业务处理方法、装置、设备及存储介质
CN114845158A (zh) 视频封面的生成方法、视频发布方法及相关设备
JP7194864B2 (ja) ダイナミック性レベルの比較に基づく画像解析領域の選択
CN112257729B (zh) 图像识别方法、装置、设备及存储介质
US20180247431A1 (en) Process, system and apparatus for machine colour characterisation of digital media
CN114827718B (zh) 云会议中实时视频合屏文字自适应对齐显示的方法和装置
WO2023065961A1 (zh) 视频植入方法、装置、设备及计算机可读存储介质
CN113318441A (zh) 游戏场景的显示控制方法及装置、电子设备、存储介质
JP2021106378A5 (zh)

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: 21896703

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07.11.2023)