WO2023072173A1 - 一种视频处理方法、装置、电子设备和存储介质 - Google Patents

一种视频处理方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2023072173A1
WO2023072173A1 PCT/CN2022/127841 CN2022127841W WO2023072173A1 WO 2023072173 A1 WO2023072173 A1 WO 2023072173A1 CN 2022127841 W CN2022127841 W CN 2022127841W WO 2023072173 A1 WO2023072173 A1 WO 2023072173A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
video frame
blurred
edge image
frames
Prior art date
Application number
PCT/CN2022/127841
Other languages
English (en)
French (fr)
Inventor
许译天
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 WO2023072173A1 publication Critical patent/WO2023072173A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations

Definitions

  • the present disclosure relates to the field of information technology, and in particular, to a video processing method, device, electronic equipment and storage medium.
  • the embodiments of the present disclosure provide a video processing method, device, electronic equipment and storage medium, so as to achieve the purpose of removing blurred frames in the video and improving the video quality.
  • an embodiment of the present disclosure provides a video processing method, the method including:
  • an embodiment of the present disclosure further provides a video processing device, which includes:
  • the first determination module is used to determine the blurred video frame in the original video
  • a deletion module configured to delete the blurred video frame from the original video to obtain an intermediate video that does not include the blurred video frame
  • the second determination module is configured to determine a video frame to be inserted based on a video frame whose time stamp is adjacent to a target time stamp in the intermediate video, and the target time stamp is the time stamp of the blurred video frame;
  • a frame insertion module configured to insert the video frame to be inserted at a position corresponding to the target time stamp in the intermediate video to obtain the target video.
  • an embodiment of the present disclosure further provides an electronic device, and the electronic device includes:
  • processors one or more processors
  • the one or more processors implement the above video processing method.
  • an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned video processing method is implemented.
  • the video processing method provided by the embodiments of the present disclosure firstly determines the blurred video frame in the original video, then deletes the blurred video frame from the original video, and inserts a clear video frame at the position of the deleted video frame by frame interpolation, so as to achieve For the purpose of improving video quality.
  • FIG. 1 is a flowchart of a video processing method in an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a video processing method in an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of an edge position of an image in an embodiment of the present disclosure.
  • FIG. 4 is a schematic diagram of changes in the cumulative sum of pixel values of all pixels in an edge image corresponding to each video frame in an original video in an embodiment of the present disclosure
  • FIG. 5 is a flowchart of a video processing method in an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of a video processing device in an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure.
  • the term “comprise” and its variations are open-ended, ie “including but not limited to”.
  • the term “based on” is “based at least in part on”.
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one further embodiment”; the term “some embodiments” means “at least some embodiments.” Relevant definitions of other terms will be given in the description below.
  • FIG. 1 is a flowchart of a video processing method in an embodiment of the present disclosure.
  • the method can be executed by a video processing device, which can be implemented in the form of software and/or hardware.
  • the device can be configured in electronic equipment, such as a display terminal, specifically including but not limited to smart phones, palmtop computers, tablet computers, portable Electronic devices with display screens such as wearable devices and smart home devices (such as desk lamps).
  • the method may specifically include the following steps:
  • Step 110 Determine blurred video frames in the original video.
  • the edge image of each video frame in the original video can be determined by a preset algorithm, and then the video frame with blurred imaging and smear can be determined based on the edge image.
  • This type of video frame is a blurred video frame.
  • Step 120 Delete the blurred video frame from the original video to obtain an intermediate video that does not include the blurred video frame.
  • Step 130 Determine the video frame to be inserted based on the video frame whose time stamp is adjacent to the target time stamp in the intermediate video, where the target time stamp is the time stamp of the blurred video frame.
  • the position of the first video frame is the position where the original video is played to 2s
  • the intermediate video obtained after deleting the first video frame from the original video is at the 2sth on the playing time axis
  • a video frame will be missing at the position.
  • a video frame is inserted at the position of 2s (this video frame is called a video frame to be inserted) to ensure the continuity of the video picture.
  • the video frames to be inserted are determined based on the video frames at the 1s and 3s positions in the intermediate video.
  • the preset frame interpolation algorithm can be used to predict the two adjacent video frames based on the two adjacent video frames.
  • An intermediate video frame for example, a method based on motion estimation or a neural network is used to determine the video frame to be inserted.
  • the implementation of the present disclosure does not limit the manner of determining the video frame to be inserted based on the video frame whose time stamp is adjacent to the target time stamp in the intermediate video.
  • Step 140 Insert the video frame to be inserted into the intermediate video at a position corresponding to the target time stamp to obtain the target video.
  • the number of the first video frame is 1, and the corresponding timestamp is 2s, that is, the position of the first video frame is at the position where the original video is played to 2s, and after the first video frame is deleted from the original video, the original video A video frame will be missing at the 2s position on the playback time axis of .
  • a video frame is inserted at the 2s position to ensure the continuity of the video picture.
  • the inserted video frame is marked as the second video frame.
  • the number of inserted second video frames is the same as the number of deleted first video frames, for example, if two first video frames are deleted from the original video, then after deletion, two frames are inserted into the original video. second video frame.
  • the number of inserted second video frames is greater than the number of deleted first video frames, for example, two first video frames are deleted from the original video, and after deletion, three are inserted in the original video Second video frame.
  • the frame rate of the original video can be increased, thereby further improving the playback effect of the original video.
  • the video processing method provided by the embodiment of the present disclosure firstly determines the video frames with poor image quality in the original video, and then deletes the video frames with poor image quality from the original video, and inserts them at the position of the deleted video frame by frame interpolation
  • For video frames with better image quality blurred frames in the video can be removed, and clear video frames can be inserted to replace the removed blurred frames, so as to achieve the purpose of improving video quality.
  • FIG. 2 is a schematic flowchart of a video processing method.
  • this embodiment provides a specific implementation method for the above-mentioned step 110 of "determining blurred video frames in the original video".
  • the video processing method includes the following steps:
  • Step 210 Determine the first edge image at the preset position of the current video frame based on the Sobel operator, where the current video frame is any video frame in the original video.
  • Step 220 Determine the blurred video frame based on the edge image at the preset position of each video frame in the original video.
  • the preset position refers to the edge position of the image, as shown in Figure 3, a schematic diagram of the edge position of the image, wherein the part outlined by the white line is the edge position of the image, and the image that only includes the white line is the edge image, That is, the image composed of edge positions.
  • the Sobel operator sobel is mainly used for image edge detection, which performs edge detection based on the gray-scale weighted difference of the upper, lower, left, and right adjacent points of the pixel, and the feature that reaches the extreme value at the edge. Using this operator at any point in the image will generate the corresponding grayscale vector or its normal vector.
  • the edge image is calculated separately, and the video frame whose image quality does not meet the preset conditions is determined according to the edge image of each video frame, that is, the blurred video frame is determined according to the edge image, and the blurred video frame That is, the first video frame.
  • the number of blurred video frames in the original image may be multiple (multiple refers to more than two) or one.
  • the determination of the blurred video frame based on the edge image at the preset position of each video frame in the original video includes:
  • the blurred video frame is determined.
  • FIG. 4 a schematic diagram of changes in the cumulative sum of pixel values of all pixels in the edge image corresponding to each video frame in the original video, the position of the sudden change is the possible time point when the blur occurs.
  • determining the blurred video frame based on the absolute value of the first difference includes: based on the histogram of the first edge image and the second edge image determine the maximum value of the absolute value of the difference between the total number of pixels of the first edge image and the second edge image at each pixel value.
  • the first edge image determines the total number of first pixels whose pixel values in the first edge image are target values, and the target value is any of the pixel values in the first edge image One; based on the histogram of the second edge image, determine the second total number of pixels in the second edge image whose pixel value is the target value; determine the first total number of pixels and the second pixel The absolute value of the second difference between the total numbers; determine the maximum value of the absolute value of the second difference corresponding to each pixel value in the first edge image; based on the absolute value of the first difference and the maximum value determines the blurred video frame.
  • the value range of the pixel values of all pixels in the first edge image is 0-15, a total of 16 values, that is, the target value is any one of these 16 values; all pixels in the second edge image
  • the value range of the pixel value of the point is 0-15;
  • the maximum value in the absolute value of the second difference corresponding to each pixel value in the first edge image can be expressed as max ⁇ abs(hist(i)( k)-hist(i-1)(k)) ⁇ , where abs() represents the function of taking the absolute value, and hist(i)(k) represents the i-th edge image (which can be understood as the first edge image)
  • the total number of the first pixels with the middle pixel value k, hist(i-1)(k) indicates the total number of the second pixels with the pixel value k in the (i-1)th edge image (which can be understood as the second edge image) , that is, the target value is k, 0 ⁇ k ⁇ 16.
  • the total number of pixels with a pixel value of 0 is 5
  • the total number of pixels with a pixel value of 1 is 15
  • the total number of pixels with a pixel value of 2 is 2, and the pixel value
  • the total number of pixels with a value of 3 is 0
  • the total number of pixels with a pixel value of 0 is 4, the total number of pixels with a pixel value of 1 is 10, and the total number of pixels with a pixel value of 2
  • determining the blurred video frame based on the absolute value of the first difference and the maximum value includes: performing weighted summation on the absolute value of the first difference and the maximum value to obtain a blurred degree; if the degree of blur is greater than a second preset threshold, determine that the current video frame is the blurred video frame.
  • the degree of blur cond(i) c1*cond1(i)+c2*cond2(i)
  • c1 and c2 are preset constants.
  • cond(i)>thr1 it is determined that the i-th video frame is a blurred frame, that is, the first video frame whose image quality does not meet the preset condition, and thr1 is the second preset threshold.
  • the pre-calculation based on each video frame in the original video also includes: respectively performing normalization processing on the edge images at the preset positions of each video frame in the original video, so as to map the pixel values of the pixels in the edge image to to a preset interval; wherein, the edge image is a single-channel image. Initially, the value range of the pixel value of each pixel in the edge image is 0-255.
  • each edge image is normalized, and the pixel value of the pixel point in the edge image is mapped to To the preset interval, for example, the interval from 0-255 is mapped to 0-16.
  • the method further includes: Filter a plurality of first video frames, and only keep a limited number of first video frames, for example, the third preset threshold is 8, then at most 8 first video frames are kept, if determined according to the determination method in the above-mentioned embodiment If the number of first video frames is 10, then 2 need to be filtered out and 8 should be kept, that is, only 8 first video frames can be deleted from the original video at most.
  • the maximum of the absolute value of the first difference or the maximum of the blur degree is determined as an extreme point; based on the timestamp of the video frame corresponding to the extreme point, the blurred video frame is Screening is performed to obtain blurred video frames whose number of frames is the third preset threshold. Further, based on the timestamp of the video frame corresponding to the extreme point, the blurred video frame is screened to obtain a blurred video frame whose number of frames is the third preset threshold, including:
  • the degree of blur corresponding to the first video frame in the original video is 0, the degree of blur corresponding to the second video frame in the original video is 0, and the degree of blur corresponding to the third video frame in the original video is 6.
  • the blur degree corresponding to the fourth video frame in the original video is 7, the corresponding blur degree of the fifth video frame in the original video is 6, and the corresponding blur degree of the sixth video frame in the original video is 6, assuming the second preset
  • the threshold is 5
  • the threshold is 5
  • the threshold it is determined that the third video frame, the fourth video frame, the fifth video frame and the sixth video frame are the above-mentioned first video frame
  • the number of the first video frame is 4, that is, the number of blurred frames is 4, assuming that the third preset threshold is 3, it is necessary to filter out 1 of the above 4 first video frames and keep 3 of them.
  • the corresponding video frame corresponding to the extreme point is the fourth video frame
  • the timestamp of the video frame corresponding to the extreme point is the time stamp of the fourth video frame in the original video, centering on the time stamp
  • the video frames with the set number of frames are respectively taken forward and backward respectively as the blurred video frames retained after filtering, for example, taking forward
  • the video frame whose timestamp is closest to the timestamp of the fourth video frame is the third video frame
  • the video frame whose timestamp is closest to the timestamp of the fourth video frame is taken backward, that is, the fifth video frame
  • the third video frame, the fourth video frame and the fifth video frame are determined as the final first video frame, and the first video frame, the second video frame and the sixth video frame are filtered out.
  • Step 230 Delete the blurred video frame from the original video to obtain an intermediate video that does not include the blurred video frame.
  • Step 240 Determine the video frame to be inserted based on the video frame in the intermediate video whose time stamp is adjacent to the target time stamp, and the target time stamp is the time stamp of the blurred video frame.
  • Step 250 Insert the video frame to be inserted into the intermediate video at a position corresponding to the target time stamp to obtain the target video.
  • FIG. 6 is a schematic structural diagram of a video processing device in an embodiment of the present disclosure.
  • the video processing apparatus specifically includes: a first determination module 610 , a deletion module 620 , a second determination module 630 and a frame insertion module 640 .
  • the first determination module 610 is used to determine the blurred video frame in the original video
  • the deletion module 620 is used to delete the blurred video frame from the original video to obtain an intermediate video that does not include the blurred video frame
  • the second determination module 630 is used to determine the video frame to be inserted based on the video frame whose timestamp is adjacent to the target timestamp in the intermediate video, and the target timestamp is the timestamp of the fuzzy video frame
  • frame insertion module 640 is configured to insert the video frame to be inserted at a position corresponding to the target time stamp in the intermediate video to obtain a target video.
  • the first determining module 610 specifically includes: a first determining unit, configured to determine a first edge image at a preset position of a current video frame based on a Sobel operator sobel, the current video frame being an edge image in the original video Any video frame; a second determining unit, configured to determine the blurred video frame based on an edge image at a preset position of each video frame in the original video.
  • the second determination unit specifically includes: a first determination subunit, configured to determine a first cumulative sum of pixel values of each pixel in the first edge image; The second cumulative sum of the pixel values of each pixel point in the edge image, the neighbor video frame is a video frame adjacent to the current video frame in the original video; determine the first cumulative sum and the second an absolute value of a first difference between the accumulated sums; a second determining subunit, configured to determine the blurred video frame based on the absolute value of the first difference.
  • the second determining subunit is specifically configured to: determine that the current video frame is the blurred video frame if the absolute value of the first difference is greater than a first preset threshold.
  • the second determination subunit is specifically configured to: determine the total number of first pixels in the first edge image whose pixel values are target values based on the histogram of the first edge image, and the target value is any one of the pixel values in the first edge image; based on the histogram of the second edge image, determine the second total number of pixels whose pixel values in the second edge image are the target value; determine the The absolute value of the second difference between the first total number of pixels and the second total number of pixels; determine the maximum value of the absolute value of the second difference corresponding to each pixel value in the first edge image; based on The absolute value of the first difference and the maximum value determine the blurred video frame.
  • the second determination subunit is specifically configured to: perform a weighted summation of the absolute value of the first difference and the maximum value to obtain a degree of blur; if the degree of blur is greater than a second preset threshold, Then it is determined that the current video frame is the blurred video frame.
  • a normalization module which is used to preset positions for each video frame in the original video before determining the first cumulative sum of the pixel values of each pixel in the first edge image
  • the edge image of the edge image is normalized to map the pixel values of the pixel points in the edge image to a preset interval; wherein, the edge image is a single-channel image.
  • a screening module configured to select the maximum of the absolute value of the first difference or the maximum of the degree of blur when the number of the first video frames exceeds a third preset threshold The one is determined as an extreme point; the blurred video frame is screened based on the time stamp of the video frame corresponding to the extreme point, so as to obtain a blurred video frame whose number of frames is the third preset threshold.
  • the screening module is specifically configured to: take the time stamp of the video frame corresponding to the extreme point as the center, respectively take the video frames with the set number of frames forward and backward respectively as the reserved video frames after screening blurred video frames; the set number of frames is determined according to the third preset threshold.
  • the video processing device provided by the embodiment of the present disclosure firstly determines the video frames with poor image quality in the original video, and then deletes the video frames with poor image quality from the original video, and inserts them at the position of the deleted video frame by frame interpolation
  • For video frames with better image quality blurred frames in the video can be removed, and clear video frames can be inserted to replace the removed blurred frames, so as to achieve the purpose of improving video quality.
  • the video processing device provided by the embodiment of the present disclosure can execute the steps in the video processing method provided by the method embodiment of the present disclosure, and the execution steps and beneficial effects will not be repeated here.
  • FIG. 7 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Referring specifically to FIG. 7 , it shows a schematic structural diagram of an electronic device 700 suitable for implementing an embodiment of the present disclosure.
  • the electronic device 700 in the embodiment of the present disclosure may include, but is not limited to, such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal ( Mobile terminals such as car navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc.
  • the electronic device shown in FIG. 7 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.
  • an electronic device 700 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) Various appropriate actions and processes are executed by programs in the memory (RAM) 703 to implement the methods of the embodiments as described in the present disclosure. In the RAM 703, various programs and data necessary for the operation of the electronic device 700 are also stored.
  • the processing device 701, ROM 702, and RAM 703 are connected to each other through a bus 704.
  • An input/output (I/O) interface 705 is also connected to the bus 704 .
  • the following devices can be connected to the I/O interface 705: input devices 706 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 707 such as a computer; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709.
  • the communication means 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 7 shows electronic device 700 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided.
  • the processes described above with reference to the flowcharts can be implemented as computer software programs.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program includes program code for executing the method shown in the flow chart, thereby realizing the above the method described.
  • the computer program may be downloaded and installed from a network via communication means 709, or from storage means 708, or from ROM 702.
  • the processing device 701 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 Communications (eg, communication networks) are interconnected.
  • 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 electronic device, or may exist independently without being incorporated into the electronic 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 electronic device, the electronic device:
  • the video frame determines the video frame to be inserted, and the target time stamp is the time stamp of the blurred video frame; inserting the video frame to be inserted at a position corresponding to the target time stamp in the intermediate video to obtain the target video.
  • the electronic device may also perform other steps described in the above embodiments.
  • 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.
  • the present disclosure provides a video processing method, including: determining blurred video frames in the original video; deleting the blurred video frames from the original video, obtaining The intermediate video of the blurred video frame; determine the video frame to be inserted based on the video frame whose timestamp is adjacent to the target timestamp in the intermediate video, and the target timestamp is the timestamp of the blurred video frame; in the intermediate The position corresponding to the target time stamp in the video is inserted into the video frame to be inserted to obtain the target video.
  • the determining the blurred video frame in the original video includes: determining the current video frame preset based on the Sobel operator sobel The first edge image of the position, the current video frame is any video frame in the original video; the blurred video frame is determined based on the edge image at the preset position of each video frame in the original video.
  • the determining the blurred video frame based on the edge image at the preset position of each video frame in the original video includes : determine the first cumulative sum of the pixel values of each pixel point in the first edge image; determine the second cumulative sum of the pixel values of each pixel point in the second edge image of the neighbor video frame, the neighbor video frame be a video frame adjacent to the current video frame in the original video; determine an absolute value of a first difference between the first cumulative sum and the second cumulative sum; an absolute value based on the first difference value determines the blurred video frame.
  • determining the blurred video frame based on the absolute value of the first difference includes: if the first If the absolute value of the difference is greater than the first preset threshold, it is determined that the current video frame is the blurred video frame.
  • the determining the blurred video frame based on the absolute value of the first difference includes:
  • the target value is any one of the pixel values in the first edge image; based on The histogram of the second edge image, determining the second total number of pixels whose pixel values in the second edge image are the target value; determining the difference between the first total number of pixels and the second total number of pixels The absolute value of the second difference; determine the maximum value of the absolute value of the second difference corresponding to each pixel value in the first edge image; determine the absolute value based on the absolute value of the first difference and the maximum value Describe blurred video frames.
  • determining the blurred video frame based on the absolute value of the first difference and the maximum value includes: Perform weighted summation of the absolute value of the first difference and the maximum value to obtain a degree of blur; if the degree of blur is greater than a second preset threshold, determine that the current video frame is the blurred video frame.
  • the Determining the blurred video frame based on an edge image at a preset position of each video frame in the original video further comprising: respectively performing normalization processing on the edge image at a preset position of each video frame in the original video, so as to convert the blurred video frame into the original video.
  • the pixel values of the pixels in the edge image are mapped to a preset interval.
  • the method further includes: The maximum in the absolute value of a difference or the maximum in the degree of blur is determined as an extreme point; based on the timestamp of the video frame corresponding to the extreme point, the blurred video frame is filtered to obtain the number of frames is the blurred video frame of the third preset threshold.
  • the blurred video frame is screened based on the timestamp of the video frame corresponding to the extreme point, so as to Obtaining the blurred video frame whose number of frames is the third preset threshold includes: taking the time stamp of the video frame corresponding to the extreme point as the center, respectively taking the video frames with the set number of frames forward and backward respectively As fuzzy video frames retained after screening; the set number of frames is determined according to the third preset threshold.
  • the present disclosure provides a video processing device, including: a first determination module, configured to determine blurred video frames in the original video; a deletion module, configured to remove the blurred video frames Deleting from the original video to obtain an intermediate video that does not include the blurred video frame; a second determining module, configured to determine a video frame to be inserted based on a video frame whose timestamp is adjacent to the target timestamp in the intermediate video, The target time stamp is the time stamp of the fuzzy video frame; a frame insertion module is configured to insert the video frame to be inserted at a position corresponding to the target time stamp in the intermediate video to obtain the target video.
  • the first determination module specifically includes: a first determination unit, configured to determine the current video frame prediction based on the Sobel operator sobel Assuming the first edge image of the position, the current video frame is any video frame in the original video; the second determining unit is used to determine the edge image based on the preset position of each video frame in the original video Blurred video frames.
  • the second determining unit specifically includes: a first determining subunit, configured to determine The first cumulative sum of the pixel values of each pixel point; the second cumulative sum of the pixel values of each pixel point in the second edge image that determines the location of the neighbor video frame, and the neighbor video frame is the same as the original video frame A video frame adjacent to the current video frame; determine the absolute value of the first difference between the first cumulative sum and the second cumulative sum; a second determining subunit, configured to use the absolute value based on the first difference The blurred video frame is determined.
  • the second determining subunit is specifically configured to: if the absolute value of the first difference is greater than the first preset threshold, then it is determined that the current video frame is the blurred video frame.
  • the second determining subunit is specifically configured to: determine the The total number of first pixel points whose pixel values in the first edge image are target values, and the target value is any one of the pixel values in the first edge image; based on the histogram of the second edge image, determine the second edge image In the second edge image, the pixel value is the second total number of pixels of the target value; determine the absolute value of the second difference between the first total number of pixels and the second total number of pixels; determine the first edge A maximum value among the absolute values of the second difference corresponding to each pixel value in the image; determining the blurred video frame based on the absolute value of the first difference and the maximum value.
  • the second determining subunit is specifically configured to: calculate the absolute value of the first difference and the maximum value Perform weighted summation to obtain a blur degree; if the blur degree is greater than a second preset threshold, determine that the current video frame is the blur video frame.
  • a normalization module configured to determine the pixels of each pixel in the first edge image Before the first cumulative sum of values, the edge images at the preset positions of each video frame in the original video are respectively normalized to map the pixel values of the pixels in the edge images to a preset interval; wherein, The edge image is a single-channel image.
  • a screening module configured to, when the number of the first video frames exceeds a third preset threshold, determining the maximum of the absolute value of the first difference or the maximum of the degree of blur as an extreme point; filtering the blurred video frame based on the timestamp of the video frame corresponding to the extreme point, Obtain blurred video frames whose number of frames is the third preset threshold.
  • the screening module is specifically configured to: take the time stamp of the video frame corresponding to the extreme point as the center, respectively The video frames with a set number of frames are sequentially taken forward and backward respectively as the blurred video frames retained after screening; the set number of frames is determined according to the third preset threshold.
  • the present disclosure provides an electronic device, including:
  • processors one or more processors
  • memory for storing one or more programs
  • the one or more processors are made to implement any video processing method provided in the present disclosure.
  • the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the video processing as described in any one of the present disclosure is implemented. method.
  • An embodiment of the present disclosure further provides a computer program product, where the computer program product includes a computer program or an instruction, and when the computer program or instruction is executed by a processor, the above video processing method is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

本公开实施例公开了一种视频处理方法、装置、电子设备和存储介质，该方法包括：确定原始视频中的模糊视频帧；将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。本公开提供的视频处理方法，实现了去除视频中的模糊帧、改善视频质量的目的。

Description

一种视频处理方法、装置、电子设备和存储介质
相关申请的交叉引用
本申请要求于2021年10月27日提交的，申请号为202111257788.0、发明名称为“一种视频处理方法、装置、电子设备和存储介质”的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及信息技术领域，尤其涉及一种视频处理方法、装置、电子设备和存储介质。
背景技术
近年来，随着电子设备技术的快速发展，很多电子设备支持视频拍摄，视频的拍摄质量成为评价电子设备的重要指标之一。影响视频拍摄质量的因素很多，比如分辨率、饱和度、清晰度等，其中，清晰度是很重要的影响因素。
在基于电子设备拍摄视频时，若在曝光时间内，拍摄对象发生移动或者电子设备发生抖动，会导致所拍摄的视频中出现运动模糊的画面，具体表现为成像模糊、弥散或者有拖影。
因此，为了获得质量较好的视频，需要对视频中的模糊画面进行处理。
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视频处理方法、装置、电子设备和存储介质，实现了去除视频中的模糊帧、改善视频质量的目的。
第一方面，本公开实施例提供了一种视频处理方法，该方法包括：
确定原始视频中的模糊视频帧；
将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；
基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；
在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
第二方面，本公开实施例还提供了一种视频处理装置，该装置包括：
第一确定模块，用于确定原始视频中的模糊视频帧；
删除模块，用于将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；
第二确定模块，用于基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；
插帧模块，用于在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
第三方面，本公开实施例还提供了一种电子设备，所述电子设备包括：
一个或多个处理器；
存储装置，用于存储一个或多个程序；
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如上所述的视频处理方法。
第四方面，本公开实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上所述的视频处理方法。
本公开实施例提供的技术方案与现有技术相比至少具有如下优点：
本公开实施例提供的视频处理方法，优先确定原始视频中的模糊视频帧，然后将模糊视频帧从原始视频中删除，以插帧的方式在删除视频帧的位置插入清晰的视频帧，从而达到改善视频质量的目的。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本公开实施例中的一种视频处理方法的流程图；
图2为本公开实施例中的一种视频处理方法的流程图；
图3为本公开实施例中的一种图像的边缘位置的示意图；
图4为本公开实施例中的一种原始视频中各视频帧对应的边缘图像中所有像素点的像素值的累加和的变化示意图；
图5为本公开实施例中的一种视频处理方法的流程图；
图6为本公开实施例中的一种视频处理装置的结构示意图；
图7为本公开实施例中的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行以及并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
图1为本公开实施例中的一种视频处理方法的流程图。该方法可以由视频处理装置执行，该装置可以采用软件和/或硬件的方式实现，该装置可配置于电子设备中，例如显示终端，具体包括但不限于智能手机、掌上电脑、平板电脑、便携式可穿戴设备、智能家居设备(例如台灯)等具备显示屏的电子设备。
如图1所示，该方法具体可以包括如下步骤：
步骤110、确定原始视频中的模糊视频帧。
具体的，可以通过预设算法确定原始视频中每个视频帧的边缘图像，而后基于边缘图像确定成像模糊、有拖影的视频帧，该类视频帧即为模糊视频帧，在本公开实施例中，将模糊视频帧标记为第一视频帧。
步骤120、将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频。
步骤130、基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳。
假设模糊帧的时间戳为2s，即在原始视频播放到2s的位置为第一视频帧的位置，在将 第一视频帧从原始视频中删除之后获得的中间视频的播放时间轴上第2s的位置将缺失一个视频帧，为了获得较好的视频效果，保证视频的连续性，在第2s的位置插入一个视频帧(该视频帧称为待插入视频帧)，以保证视频画面的连续性。
可选的，待插入视频帧基于中间视频中在第1s和第3s位置的视频帧确定，具体的可以通过预设插帧算法，基于相邻两个视频帧预测位于该相邻两个视频帧中间的视频帧；例如基于运动估计的方法或者通过神经网络确定待插入视频帧。本公开实施不对基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧的方式进行限定。
步骤140、在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
例如，第一视频帧的数量为1，对应的时间戳为2s，即在原始视频播放到2s的位置为第一视频帧的位置，在将第一视频帧从原始视频中删除之后，原始视频的播放时间轴上第2s的位置将缺失一个视频帧，为了获得较好的视频效果，保证视频的连续性，在第2s的位置插入一个视频帧，以保证视频画面的连续性。在本公开实施例中，将插入的视频帧标记为第二视频帧。
在一些实施方式中，插入的第二视频帧的数量与删除的第一视频帧的数量相同，例如从原始视频中删除了两个第一视频帧，则在删除之后，在原始视频中插入两个第二视频帧。
在一些实施方式中，插入的第二视频帧的数量比删除的第一视频帧的数量多，例如从原始视频中删除了两个第一视频帧，在删除之后，在原始视频中插入三个第二视频帧。通过插入较多的第二视频帧可提高原始视频的帧率，进而进一步提升原始视频的播放效果。
本公开实施例提供的视频处理方法，优先确定原始视频中图像质量较差的视频帧，然后将图像质量较差的视频帧从原始视频中删除，以插帧的方式在删除视频帧的位置插入图像质量较好的视频帧，可去除视频中的模糊帧，并插入清晰的视频帧代替去除的模糊帧，从而达到改善视频质量的目的。
在上述实施例的基础上，图2为一种视频处理方法的流程示意图。在上述实施例的基础上，本实施例针对上述步骤110“确定原始视频中的模糊视频帧”给出了具体实施方式。
如图2所示，所述视频处理方法包括如下步骤：
步骤210、基于索贝尔算子sobel确定当前视频帧预设位置的第一边缘图像，所述当前视频帧为所述原始视频中的任意一个视频帧。
步骤220、基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧。
其中，预设位置指图像的边缘位置，如图3所示的一种图像的边缘位置的示意图，其中白色线条勾画的部分为图像的边缘位置，只包括白色线条的图像为所述边缘图像，即边缘位置组成的图像。索贝尔算子sobel主要用于图像的边缘检测，其根据像素点上、下、左、 右邻点的灰度加权差，在边缘处达到极值的特征进行边缘检测。在图像的任何一点使用此算子，将会产生对应的灰度矢量或是其法矢量。换言之，针对原始视频中的每个视频帧，分别计算其边缘图像，根据每个视频帧的边缘图像确定图像质量不符合预设条件的视频帧，即根据边缘图像确定模糊视频帧，模糊视频帧即为所述第一视频帧。原始图像中的模糊视频帧的数量可能是多个(多个指两个以上)，也可能是一个。
进一步的，在一些实施例中，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，包括：
确定所述第一边缘图像中各像素点的像素值的第一累加和；确定邻居视频帧设位置的第二边缘图像中各像素点的像素值的第二累加和，所述邻居视频帧为所述原始视频中与所述当前视频帧相邻的视频帧；确定所述第一累加和与所述第二累加和之间的第一差的绝对值；基于所述第一差的绝对值确定所述模糊视频帧。
可选的，在一些实施例中，若所述第一差的绝对值大于第一预设阈值，则确定所述当前视频帧为所述模糊视频帧。例如，假设原始视频中第i(i≥1)个视频帧的边缘图像中所有像素点的像素值的累加和为edge_sum(i)，第(i-1)个视频帧的边缘图像中所有像素点的像素值的累加和为edge_sum(i-1)，cond1＝abs(edge_sum(i)-edge_sum(i-1))，其中abs()表示取绝对值的函数；若cond1大于第一预设阈值，则认为原始视频中的第i个视频帧为所述第一视频帧。
更具体的，假设第i个视频帧的边缘图像包括4个像素点，该4个像素点分别对应的像素值分别为5、15、2和0，则该4个像素点对应的像素值的累加和即edge_sum(i)＝5+15+2+0＝22。第(i-1)个视频帧的边缘图像包括4个像素点，这四个像素点分别对应的像素值为4、10、1和3，则这4个像素点对应的像素值的累加和即edge_sum(i-1)＝4+10+1+3＝18。则cond1(i)＝abs(edge_sum(i)-edge_sum(i-1))＝abs(22-18)＝4。参考如图4所示的一种原始视频中各视频帧对应的边缘图像中所有像素点的像素值的累加和的变化示意图，突变的位置为模糊发生的可能时间点。
在一些实施例中，为了进一步提高模糊帧的确定精度，基于所述第一差的绝对值确定所述模糊视频帧，包括：基于所述第一边缘图像的直方图以及所述第二边缘图像的直方图，确定所述第一边缘图像与所述第二边缘图像在各像素值下像素点总数之差的绝对值的最大值。
具体的，基于所述第一边缘图像的直方图，确定所述第一边缘图像中像素值为目标值的第一像素点总数，所述目标值为所述第一边缘图像中像素值的任意一个；基于所述第二边缘图像的直方图，确定所述第二边缘图像中像素值为所述目标值的第二像素点总数；确定所述第一像素点总数与所述第二像素点总数之间的第二差的绝对值；确定所述第一边缘 图像中各像素值对应的所述第二差的绝对值中的最大值；基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧。例如，假设第一边缘图像中所有像素点的像素值的取值范围为0-15，共16个数值，即所述目标值为这16个数值中的任意一个；第二边缘图像中所有像素点的像素值的取值范围为0-15；则所述第一边缘图像中各像素值对应的所述第二差的绝对值中的最大值可以表示为max{abs(hist(i)(k)-hist(i-1)(k))}，其中，abs()表示取绝对值的函数，hist(i)(k)表示第i个边缘图像(可以理解为是第一边缘图像)中像素值为k的第一像素点总数，hist(i-1)(k)表示第(i-1)边缘图像(可以理解为第二边缘图像)中像素值为k的第二像素点总数，即所述目标值为k，0≤k＜16。更具体的，假设第i个视频帧的边缘图像中，像素值为0的像素点总数为5，像素值为1的像素点总数为15，像素值为2的像素点总数为2，像素值为3的像素点总数为0；第(i-1)个视频帧的边缘图像中，像素值为0的像素点总数为4，像素值为1的像素点总数为10，像素值为2的像素点总数为1，像素值为3的像素点总数为3；则cond2(i)＝max{abs(hist(i)(k)-hist(i-1)(k))}＝max{abs(5-4)，abs(15-10)，abs(2-1)，abs(0-3}＝5。
在一些实施例中，基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧，包括：对所述第一差的绝对值以及所述最大值进行加权求和，获得模糊程度；若所述模糊程度大于第二预设阈值，则确定所述当前视频帧为所述模糊视频帧。示例性的，模糊程度cond(i)＝c1*cond1(i)+c2*cond2(i)，c1和c2为预设常数。当cond(i)＞thr1时，则确定第i个视频帧为模糊帧，即图像质量不满足预设条件的第一视频帧，thr1为所述第二预设阈值。
在一些实施例中，为了降低计算量，提高计算速度，所述确定所述第一边缘图像中各像素点的像素值的第一累加和之前，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，还包括：分别对所述原始视频中各视频帧预设位置的边缘图像进行归一化处理，以将所述边缘图像中像素点的像素值映射至预设区间；其中，所述边缘图像为单通道图像。初始时，边缘图像中每个像素点的像素值的取值范围是0-255，在确定模糊帧时，需计算每个像素值对应的像素点总数以及各像素点的像素值的累加和，因此计算量较大，为了降低计算量，提高计算效率，在确定各像素点的像素值的第一累加和之前，对各边缘图像进行归一化处理，将边缘图像中像素点的像素值映射至预设区间，例如从0-255的区间映射到0-16。
在一些实施例中，为了保证视频的连续性，不允许对较多的第一视频帧进行删除操作，因此，若所述模糊视频帧的数量超过第三预设阈值，所述方法还包括：对多个第一视频帧进行过滤，仅保留有限个第一视频帧，例如第三预设阈值为8，则最多保留8个第一视频帧，若按照上述实施例中的确定方法确定出的第一视频帧的数量为10个，则需要过滤掉2 个，保留8个，即从原始视频中最多只能删除8个第一视频帧。具体的，将所述第一差的绝对值中的最大者或者所述模糊程度中的最大者确定为极值点；基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧。进一步的，基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧，包括：
以所述极值点对应的视频帧的时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧；所述设定帧数根据所述第三预设阈值确定。
例如，通过计算确定原始视频中第一个视频帧对应的模糊程度为0，原始视频中第二个视频帧对应的模糊程度为0，原始视频中第三个视频帧对应的模糊程度为6，原始视频中第四个视频帧对应的模糊程度为7，原始视频中第五个视频帧对应的模糊程度为6，原始视频中第六个视频帧对应的模糊程度为6，假设第二预设阈值为5，则确定第三个视频帧、第四个视频帧、第五个视频帧和第六个视频帧为上述第一视频帧，第一视频帧的数量为4，即模糊帧的数量为4，假设第三预设阈值为3，则需要从上述4个第一视频帧中过滤掉1个，保留其中的3个。具体的，由于模糊程度的最大值为7，因此，将7确定为极值点，该极值点对应的对应的视频帧为第四个视频帧，该极值点对应的视频帧的时间戳为原始视频中第四个视频帧的时间戳，以该时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧，例如向前取时间戳离第四个视频帧的时间戳最近的一个视频帧，即第三个视频帧，向后取时间戳离第四个视频帧的时间戳最近的一个视频帧，即第五个视频帧，故将第三个视频帧、第四个视频帧和第五个视频帧确定为最终的第一视频帧，将第一个视频帧、第二个视频帧和第六个视频帧过滤掉。
步骤230、将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频。
步骤240、基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳。
步骤250、在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
概括性的，参考如图5所示的一种视频处理方法的流程示意图，具体包括：针对原始视频进行模糊帧检测，获得模糊帧序列并将模糊帧序列从原始视频中删除，然后通过插帧的方式将删除掉的视频帧补回至原始视频，获得模糊修复后的目标视频，从而达到改善视频质量的目的。
图6为本公开实施例中的一种视频处理装置的结构示意图。如图6所示，该视频处理装置具体包括：第一确定模块610、删除模块620、第二确定模块630和插帧模块640。
其中，第一确定模块610，用于确定原始视频中的模糊视频帧；删除模块620，用于将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；第二确定模块630，用于基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；插帧模块640用于在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
可选的，第一确定模块610具体包括：第一确定单元，用于基于索贝尔算子sobel确定当前视频帧预设位置的第一边缘图像，所述当前视频帧为所述原始视频中的任意一个视频帧；第二确定单元，用于基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧。
可选的，所述第二确定单元具体包括：第一确定子单元，用于确定所述第一边缘图像中各像素点的像素值的第一累加和；确定邻居视频帧设位置的第二边缘图像中各像素点的像素值的第二累加和，所述邻居视频帧为所述原始视频中与所述当前视频帧相邻的视频帧；确定所述第一累加和与所述第二累加和之间的第一差的绝对值；第二确定子单元，用于基于所述第一差的绝对值确定所述模糊视频帧。
可选的，所述第二确定子单元具体用于：若所述第一差的绝对值大于第一预设阈值，则确定所述当前视频帧为所述模糊视频帧。
可选的，所述第二确定子单元具体用于：基于所述第一边缘图像的直方图，确定所述第一边缘图像中像素值为目标值的第一像素点总数，所述目标值为所述第一边缘图像中像素值的任意一个；基于所述第二边缘图像的直方图，确定所述第二边缘图像中像素值为所述目标值的第二像素点总数；确定所述第一像素点总数与所述第二像素点总数之间的第二差的绝对值；确定所述第一边缘图像中各像素值对应的所述第二差的绝对值中的最大值；基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧。
可选的，所述第二确定子单元具体用于：对所述第一差的绝对值以及所述最大值进行加权求和，获得模糊程度；若所述模糊程度大于第二预设阈值，则确定所述当前视频帧为所述模糊视频帧。
可选的，还包括：归一化模块，用于所述确定所述第一边缘图像中各像素点的像素值的第一累加和之前，分别对所述原始视频中各视频帧预设位置的边缘图像进行归一化处理，以将所述边缘图像中像素点的像素值映射至预设区间；其中，所述边缘图像为单通道图像。
可选的，还包括：筛选模块，用于在所述第一视频帧的数量超过第三预设阈值时，将所述第一差的绝对值中的最大者或者所述模糊程度中的最大者确定为极值点；基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧。
可选的，所述筛选模块具体用于：以所述极值点对应的视频帧的时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧；所述设定帧数根据所述第三预设阈值确定。
本公开实施例提供的视频处理装置，优先确定原始视频中图像质量较差的视频帧，然后将图像质量较差的视频帧从原始视频中删除，以插帧的方式在删除视频帧的位置插入图像质量较好的视频帧，可去除视频中的模糊帧，并插入清晰的视频帧代替去除的模糊帧，从而达到改善视频质量的目的。
本公开实施例提供的视频处理装置，可执行本公开方法实施例所提供的视频处理方法中的步骤，具备执行步骤和有益效果此处不再赘述。
图7为本公开实施例中的一种电子设备的结构示意图。下面具体参考图7，其示出了适于用来实现本公开实施例中的电子设备700的结构示意图。本公开实施例中的电子设备700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)、可穿戴电子设备等等的移动终端以及诸如数字TV、台式计算机、智能家居设备等等的固定终端。图7示出的电子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7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储装置708加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理以实现如本公开所述的实施例的方法。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：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706；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置707；包括例如磁带、硬盘等的存储装置708；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，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，从而实现如上所述的方法。在这样的实施例中，该计算机程序可以通过通信装置709从网络上 被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701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电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
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电子设备执行时，使得该电子设备：
确定原始视频中的模糊视频帧；将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
可选的，当上述一个或者多个程序被该电子设备执行时，该电子设备还可以执行上述实施例所述的其他步骤。
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。
根据本公开的一个或多个实施例，本公开提供了一种视频处理方法，包括：确定原始 视频中的模糊视频帧；将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述确定原始视频中的模糊视频帧，包括：基于索贝尔算子sobel确定当前视频帧预设位置的第一边缘图像，所述当前视频帧为所述原始视频中的任意一个视频帧；基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，包括：确定所述第一边缘图像中各像素点的像素值的第一累加和；确定邻居视频帧设位置的第二边缘图像中各像素点的像素值的第二累加和，所述邻居视频帧为所述原始视频中与所述当前视频帧相邻的视频帧；确定所述第一累加和与所述第二累加和之间的第一差的绝对值；基于所述第一差的绝对值确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述基于所述第一差的绝对值确定所述模糊视频帧，包括：若所述第一差的绝对值大于第一预设阈值，则确定所述当前视频帧为所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述基于所述第一差的绝对值确定所述模糊视频帧，包括：
基于所述第一边缘图像的直方图，确定所述第一边缘图像中像素值为目标值的第一像素点总数，所述目标值为所述第一边缘图像中像素值的任意一个；基于所述第二边缘图像的直方图，确定所述第二边缘图像中像素值为所述目标值的第二像素点总数；确定所述第一像素点总数与所述第二像素点总数之间的第二差的绝对值；确定所述第一边缘图像中各像素值对应的所述第二差的绝对值中的最大值；基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧，包括：对所述第一差的绝对值以及所述最大值进行加权求和，获得模糊程度；若所述模糊程度大于第二预设阈值，则确定所述当前视频帧为所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述确定所述第一边缘图像中各像素点的像素值的第一累加和之前，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，还包括：分别对所述原始视频中各视频 帧预设位置的边缘图像进行归一化处理，以将所述边缘图像中像素点的像素值映射至预设区间。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，若所述模糊视频帧的数量超过第三预设阈值，所述方法还包括：将所述第一差的绝对值中的最大者或者所述模糊程度中的最大者确定为极值点；基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理方法中，可选的，所述基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧，包括：以所述极值点对应的视频帧的时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧；所述设定帧数根据所述第三预设阈值确定。
根据本公开的一个或多个实施例，本公开提供了一种视频处理装置，包括：第一确定模块，用于确定原始视频中的模糊视频帧；删除模块，用于将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；第二确定模块，用于基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；插帧模块，用于在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，第一确定模块具体包括：第一确定单元，用于基于索贝尔算子sobel确定当前视频帧预设位置的第一边缘图像，所述当前视频帧为所述原始视频中的任意一个视频帧；第二确定单元，用于基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，所述第二确定单元具体包括：第一确定子单元，用于确定所述第一边缘图像中各像素点的像素值的第一累加和；确定邻居视频帧设位置的第二边缘图像中各像素点的像素值的第二累加和，所述邻居视频帧为所述原始视频中与所述当前视频帧相邻的视频帧；确定所述第一累加和与所述第二累加和之间的第一差的绝对值；第二确定子单元，用于基于所述第一差的绝对值确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，所述第二确定子单元具体用于：若所述第一差的绝对值大于第一预设阈值，则确定所述当前视频帧为所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，所述第二确定子单元具体用于：基于所述第一边缘图像的直方图，确定所述第一边缘图像中像素 值为目标值的第一像素点总数，所述目标值为所述第一边缘图像中像素值的任意一个；基于所述第二边缘图像的直方图，确定所述第二边缘图像中像素值为所述目标值的第二像素点总数；确定所述第一像素点总数与所述第二像素点总数之间的第二差的绝对值；确定所述第一边缘图像中各像素值对应的所述第二差的绝对值中的最大值；基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，所述第二确定子单元具体用于：对所述第一差的绝对值以及所述最大值进行加权求和，获得模糊程度；若所述模糊程度大于第二预设阈值，则确定所述当前视频帧为所述模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，还包括：归一化模块，用于所述确定所述第一边缘图像中各像素点的像素值的第一累加和之前，分别对所述原始视频中各视频帧预设位置的边缘图像进行归一化处理，以将所述边缘图像中像素点的像素值映射至预设区间；其中，所述边缘图像为单通道图像。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，还包括：筛选模块，用于在所述第一视频帧的数量超过第三预设阈值时，将所述第一差的绝对值中的最大者或者所述模糊程度中的最大者确定为极值点；基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧。
根据本公开的一个或多个实施例，在本公开提供的视频处理装置中，可选的，所述筛选模块具体用于：以所述极值点对应的视频帧的时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧；所述设定帧数根据所述第三预设阈值确定。
根据本公开的一个或多个实施例，本公开提供了一种电子设备，包括：
一个或多个处理器；
存储器，用于存储一个或多个程序；
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如本公开提供的任一所述的视频处理方法。
根据本公开的一个或多个实施例，本公开提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本公开提供的任一所述的视频处理方法。
本公开实施例还提供了一种计算机程序产品，该计算机程序产品包括计算机程序或指令，该计算机程序或指令被处理器执行时实现如上所述的视频处理方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组 合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (12)

  1. 一种视频处理方法，其特征在于，所述方法包括：
    确定原始视频中的模糊视频帧；
    将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；
    基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；
    在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
  2. 根据权利要求1所述的方法，其特征在于，所述确定原始视频中的模糊视频帧，包括：
    基于索贝尔算子sobel确定当前视频帧预设位置的第一边缘图像，所述当前视频帧为所述原始视频中的任意一个视频帧；
    基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧。
  3. 根据权利要求2所述的方法，其特征在于，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，包括：
    确定所述第一边缘图像中各像素点的像素值的第一累加和；
    确定邻居视频帧设位置的第二边缘图像中各像素点的像素值的第二累加和，所述邻居视频帧为所述原始视频中与所述当前视频帧相邻的视频帧；
    确定所述第一累加和与所述第二累加和之间的第一差的绝对值；
    基于所述第一差的绝对值确定所述模糊视频帧。
  4. 根据权利要求3所述的方法，其特征在于，所述基于所述第一差的绝对值确定所述模糊视频帧，包括：
    若所述第一差的绝对值大于第一预设阈值，则确定所述当前视频帧为所述模糊视频帧。
  5. 根据权利要求3所述的方法，其特征在于，所述基于所述第一差的绝对值确定所述模糊视频帧，包括：
    基于所述第一边缘图像的直方图，确定所述第一边缘图像中像素值为目标值的第一像素点总数；
    基于所述第二边缘图像的直方图，确定所述第二边缘图像中像素值为所述目标值的第二像素点总数；
    确定所述第一像素点总数与所述第二像素点总数之间的第二差的绝对值；
    确定所述第一边缘图像中各像素值对应的所述第二差的绝对值中的最大值；
    基于所述第一差的绝对值以及所述最大值确定所述模糊视频帧。
  6. 根据权利要求5所述的方法，其特征在于，所述基于所述第一差的绝对值以及所述 最大值确定所述模糊视频帧，包括：
    对所述第一差的绝对值以及所述最大值进行加权求和，获得模糊程度；
    若所述模糊程度大于第二预设阈值，则确定所述当前视频帧为所述模糊视频帧。
  7. 根据权利要求6所述的方法，其特征在于，若所述模糊视频帧的数量超过第三预设阈值，所述方法还包括：
    将所述第一差的绝对值中的最大者或者所述模糊程度中的最大者确定为极值点；
    基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧。
  8. 根据权利要求7所述的方法，其特征在于，所述基于所述极值点对应的视频帧的时间戳对所述模糊视频帧进行筛选，以获得帧数为所述第三预设阈值的模糊视频帧，包括：
    以所述极值点对应的视频帧的时间戳为中心，分别向前和向后依次各取设定帧数的视频帧作为经过筛选后保留的模糊视频帧；
    所述设定帧数根据所述第三预设阈值确定。
  9. 根据权利要求3-8任一项所述的方法，其特征在于，所述确定所述第一边缘图像中各像素点的像素值的第一累加和之前，所述基于所述原始视频中各视频帧预设位置的边缘图像确定所述模糊视频帧，还包括：
    分别对所述原始视频中各视频帧预设位置的边缘图像进行归一化处理，以将所述边缘图像中像素点的像素值映射至预设区间。
  10. 一种视频处理装置，其特征在于，包括：
    第一确定模块，用于确定原始视频中的模糊视频帧；
    删除模块，用于将所述模糊视频帧从所述原始视频中删除，获得不包括所述模糊视频帧的中间视频；
    第二确定模块，用于基于所述中间视频中时间戳与目标时间戳相邻的视频帧确定待插入视频帧，所述目标时间戳为所述模糊视频帧的时间戳；
    插帧模块，用于在所述中间视频中与所述目标时间戳对应的位置插入所述待插入视频帧，获得目标视频。
  11. 一种电子设备，其特征在于，所述电子设备包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序；
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-9中任一项所述的方法。
  12. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理 器执行时实现如权利要求1-9中任一项所述的方法。
PCT/CN2022/127841 2021-10-27 2022-10-27 一种视频处理方法、装置、电子设备和存储介质 WO2023072173A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111257788.0 2021-10-27
CN202111257788.0A CN116055876A (zh) 2021-10-27 2021-10-27 一种视频处理方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2023072173A1 true WO2023072173A1 (zh) 2023-05-04

Family

ID=86118670

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/127841 WO2023072173A1 (zh) 2021-10-27 2022-10-27 一种视频处理方法、装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN116055876A (zh)
WO (1) WO2023072173A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110274412A1 (en) * 2009-03-06 2011-11-10 Canon Kabushiki Kaisha Image processing apparatus and image processing method
CN103763515A (zh) * 2013-12-24 2014-04-30 浙江工业大学 一种基于机器学习的视频异常检测方法
CN111131688A (zh) * 2018-10-31 2020-05-08 Tcl集团股份有限公司 一种图像处理方法、装置及移动终端
CN111641835A (zh) * 2020-05-19 2020-09-08 Oppo广东移动通信有限公司 视频处理方法、视频处理装置和电子设备
CN113297420A (zh) * 2021-04-30 2021-08-24 百果园技术(新加坡)有限公司 视频图像处理方法、装置、存储介质及电子设备
WO2021182759A1 (ko) * 2020-03-12 2021-09-16 삼성전자 주식회사 이미지 처리 방법 및 장치

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110274412A1 (en) * 2009-03-06 2011-11-10 Canon Kabushiki Kaisha Image processing apparatus and image processing method
CN103763515A (zh) * 2013-12-24 2014-04-30 浙江工业大学 一种基于机器学习的视频异常检测方法
CN111131688A (zh) * 2018-10-31 2020-05-08 Tcl集团股份有限公司 一种图像处理方法、装置及移动终端
WO2021182759A1 (ko) * 2020-03-12 2021-09-16 삼성전자 주식회사 이미지 처리 방법 및 장치
CN111641835A (zh) * 2020-05-19 2020-09-08 Oppo广东移动通信有限公司 视频处理方法、视频处理装置和电子设备
CN113297420A (zh) * 2021-04-30 2021-08-24 百果园技术(新加坡)有限公司 视频图像处理方法、装置、存储介质及电子设备

Also Published As

Publication number Publication date
CN116055876A (zh) 2023-05-02

Similar Documents

Publication Publication Date Title
WO2022116772A1 (zh) 视频裁剪方法、装置、存储介质及电子设备
WO2022105622A1 (zh) 图像分割方法、装置、可读介质及电子设备
CN111080595A (zh) 图像处理方法、装置、电子设备及计算机可读介质
CN111935425B (zh) 视频降噪方法、装置、电子设备及计算机可读介质
CN112381717A (zh) 图像处理方法、模型训练方法、装置、介质及设备
CN111833269B (zh) 视频降噪方法、装置、电子设备及计算机可读介质
CN112561840A (zh) 视频裁剪方法、装置、存储介质及电子设备
WO2023274005A1 (zh) 图像处理方法、装置、电子设备和存储介质
WO2022127853A1 (zh) 拍摄模式确定方法、装置、电子设备和存储介质
US20240112299A1 (en) Video cropping method and apparatus, storage medium and electronic device
CN113038176B (zh) 视频抽帧方法、装置和电子设备
CN111783632B (zh) 针对视频流的人脸检测方法、装置、电子设备及存储介质
CN110349108B (zh) 处理图像的方法、装置、电子设备、及存储介质
CN115409696A (zh) 图像处理方法、装置、电子设备及存储介质
CN110852250B (zh) 一种基于最大面积法的车辆排重方法、装置及存储介质
CN110399802B (zh) 处理面部图像眼睛亮度的方法、装置、介质和电子设备
WO2023072173A1 (zh) 一种视频处理方法、装置、电子设备和存储介质
CN114972021A (zh) 一种图像处理方法、装置、电子设备及存储介质
CN111737575B (zh) 内容分发方法、装置、可读介质及电子设备
CN112418233A (zh) 图像处理方法、装置、可读介质及电子设备
WO2023093838A1 (zh) 超分图像处理方法、装置、设备及介质
WO2023024986A1 (zh) 一种视频流畅度确定方法、装置、设备及介质
WO2023020493A1 (zh) 一种画质调节方法、装置、设备及介质
CN112651909B (zh) 图像合成方法、装置、电子设备及计算机可读存储介质
WO2023143233A1 (zh) 视频噪声检测方法、装置、设备及介质

Legal Events

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

Ref document number: 22886048

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023578982

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2022886048

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022886048

Country of ref document: EP

Effective date: 20240325