CN114363659A - Method, device, equipment and storage medium for reducing video flicker - Google Patents
Method, device, equipment and storage medium for reducing video flickerDownload PDFInfo
- Publication number
- CN114363659A CN114363659ACN202111531311.7ACN202111531311ACN114363659ACN 114363659 ACN114363659 ACN 114363659ACN 202111531311 ACN202111531311 ACN 202111531311ACN 114363659 ACN114363659 ACN 114363659A
- Authority
- CN
- China
- Prior art keywords
- reference value
- file
- frame
- comparison
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription62
- 238000012545processingMethods0.000claimsabstractdescription46
- 230000000052comparative effectEffects0.000claimsabstractdescription8
- 230000002194synthesizing effectEffects0.000claimsabstractdescription4
- 230000011218segmentationEffects0.000claimsdescription18
- 238000004364calculation methodMethods0.000claimsdescription16
- 238000012935AveragingMethods0.000claimsdescription12
- 238000009432framingMethods0.000claimsdescription10
- 230000000694effectsEffects0.000description7
- 230000009286beneficial effectEffects0.000description4
- 230000015572biosynthetic processEffects0.000description3
- 238000003786synthesis reactionMethods0.000description3
- 238000004891communicationMethods0.000description2
- 238000001514detection methodMethods0.000description2
- 238000010586diagramMethods0.000description1
- 230000006870functionEffects0.000description1
- 238000009434installationMethods0.000description1
- 238000003062neural network modelMethods0.000description1
- 238000003672processing methodMethods0.000description1
- 238000011002quantificationMethods0.000description1
Images
Classifications
- 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
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- 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
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Picture Signal Circuits (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及视频处理领域，尤其涉及一种降低视频闪烁的方法、装置、设备及存储介质。The present invention relates to the field of video processing, and in particular, to a method, device, device and storage medium for reducing video flicker.
背景技术Background technique
目前，往往采取相关的神经网络模型对视频进行处理，但这种方法成本高且无法保证效率。因此如何提供一种简单高效的降低视频闪烁的方法，成为了一个亟待解决的问题。At present, related neural network models are often used to process videos, but this method is costly and cannot guarantee efficiency. Therefore, how to provide a simple and efficient method for reducing video flicker has become an urgent problem to be solved.
发明内容SUMMARY OF THE INVENTION
本发明旨在至少解决现有技术中存在的技术问题之一。为此，本发明提出一种降低视频闪烁的，能够简单高效的降低视频闪烁。The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the present invention provides a method for reducing video flicker, which can reduce video flicker simply and efficiently.
本发明还提出一种具有上述降低视频闪烁的方法的降低视频闪烁的装置。The present invention also provides an apparatus for reducing video flicker having the above method for reducing video flicker.
本发明还提出一种具有上述降低视频闪烁的装置的降低视频闪烁的设备。The present invention also provides a device for reducing video flicker having the above-mentioned device for reducing video flicker.
本发明还提出一种计算机可读存储介质。The present invention also provides a computer-readable storage medium.
根据本发明的第一方面实施例的降低视频闪烁的方法，包括：The method for reducing video flicker according to the embodiment of the first aspect of the present invention includes:
获取所述原始视频数据的图像文件；其中所述图像文件包括全部的图像帧；Obtain an image file of the original video data; wherein the image file includes all image frames;
将所述图像文件纳入待处理集合；incorporating the image file into the pending collection;
比较参考值生成步骤：计算所述图像文件中每两个相连的所述图像帧之间的比较参考值；A comparison reference value generation step: calculating a comparison reference value between every two connected image frames in the image file;
比较预设的比较阈值和所述比较参考值，并更新所述待处理集合或返回所述比较参考值生成步骤；comparing a preset comparison threshold with the comparison reference value, and updating the set to be processed or returning to the comparison reference value generating step;
对更新后的所述待处理集合中的所述图像文件进行合成处理，得到目标视频。The image files in the updated set to be processed are synthesized to obtain a target video.
根据本发明实施例的降低视频闪烁的方法，至少具有如下有益效果：本发明所提供的降低视频闪烁的方法可以拆解获取到的原始视频数据得到包括全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值，本方法可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；本方法还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。这一方法通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The method for reducing video flicker according to the embodiment of the present invention has at least the following beneficial effects: the method for reducing video flicker provided by the present invention can disassemble the acquired original video data to obtain an image file including all image frames, and convert the image The file is included in the set to be processed; by performing the step of generating the comparative reference value, the present invention can quantify the image difference between the two connected image frames in the image file, and obtain an image that can represent every two connected image frames in the image file. The comparison reference value of the difference degree between the image frames, and the comparison reference value is used as the reference standard to measure the difference degree between the two image frames; Whether there is a big difference between the connected image frames, update the to-be-processed set according to the comparison result or re-execute the comparison reference value generation step; this method can also detect that when the to-be-processed set is updated, the updated to-be-processed set is updated. The image files in the file are synthesized to obtain the target video with reduced flicker. This method splits the original video data and compares the difference between each two connected image frames one by one, so as to update the image frames with large differences to generate the target video with reduced flicker, which effectively improves the Reduces the efficiency of video flickering.
根据本发明的一些实施例，所述获取所述原始视频数据的图像文件，包括：According to some embodiments of the present invention, the acquiring the image file of the original video data includes:
获取所述原始视频数据；obtain the original video data;
对所述原始视频数据进行分帧处理，得到原始帧文件；Framing processing is performed on the original video data to obtain the original frame file;
根据本发明的一些实施例，所述比较参考值生成步骤：计算所述图像文件中每两个相连的所述图像帧之间的比较参考值，包括：According to some embodiments of the present invention, the step of generating the comparison reference value: calculating the comparison reference value between every two connected image frames in the image file, including:
获取所述第一帧文件的第一平均值、第一标准差和第一协方差；obtaining the first average value, the first standard deviation and the first covariance of the first frame file;
获取所述第二帧文件的第二平均值、第二标准差和第二协方差；obtaining the second mean, the second standard deviation and the second covariance of the second frame file;
根据预设的第一常数和第二常数，对所述第一平均值、所述第一标准差、所述第一协方差、所述第二平均值、所述第二标准差和所述第二协方差进行SSIM值计算，得到所述比较参考值。According to a preset first constant and a second constant, the first average value, the first standard deviation, the first covariance, the second average value, the second standard deviation and the The SSIM value is calculated for the second covariance to obtain the comparison reference value.
根据本发明的一些实施例，所述比较预设的比较阈值和所述比较参考值，并更新所述待处理集合或返回所述比较参考值生成步骤，包括：According to some embodiments of the present invention, the step of comparing a preset comparison threshold with the comparison reference value, and updating the set to be processed or returning to the generation step of the comparison reference value includes:
比较预设的比较阈值和所述比较参考值；comparing a preset comparison threshold with the comparison reference value;
若所述比较参考值大于或者等于所述比较阈值，则根据所述比较参考值对应的连续两个所述图像帧的时间先后顺序，得到第一帧文件和第二帧文件；If the comparison reference value is greater than or equal to the comparison threshold, obtain the first frame file and the second frame file according to the time sequence of two consecutive image frames corresponding to the comparison reference value;
根据所述第一帧文件、所述第二帧文件和预设的平均算法，得到第二更新帧；Obtain a second update frame according to the first frame file, the second frame file and a preset averaging algorithm;
将所述待处理集合中的第二帧文件替换为所述第二更新帧，以更新所述待处理集合。The second frame file in the to-be-processed set is replaced with the second update frame to update the to-be-processed set.
或者，or,
若所述比较参考值小于所述比较阈值，则不更新所述待处理集合，并返回所述比较参考值生成步骤。If the comparison reference value is smaller than the comparison threshold value, the to-be-processed set is not updated, and the step of generating the comparison reference value is returned.
根据本发明的一些实施例，所述根据所述第一帧文件、所述第二帧文件和预设的平均算法，得到第二更新帧，包括：According to some embodiments of the present invention, obtaining the second update frame according to the first frame file, the second frame file and a preset averaging algorithm includes:
对所述第一帧文件和所述第二帧文件做均值化处理，得到更新平均值；Perform averaging processing on the first frame file and the second frame file to obtain an updated average value;
根据所述更新平均值更新所述第二帧文件的平均值，得到所述第二更新帧。The average value of the second frame file is updated according to the updated average value to obtain the second updated frame.
根据本发明的第二方面实施例的降低视频闪烁的装置，包括：The apparatus for reducing video flicker according to the embodiment of the second aspect of the present invention includes:
拆分模块，用于获取所述视频数据的图像文件；其中所述图像文件包括全部的图像帧；A splitting module, used to obtain an image file of the video data; wherein the image file includes all image frames;
收集模块，用于将所述图像文件纳入待处理集合；a collection module, used to incorporate the image files into a collection to be processed;
计算模块，用于执行比较参考值生成步骤：计算所述图像文件中每两个相连的所述图像帧之间的比较参考值；a calculation module for performing a comparison reference value generation step: calculating a comparison reference value between every two connected image frames in the image file;
比较模块，用于比较预设的比较阈值和所述比较参考值，并更新所述待处理集合或返回所述比较参考值生成步骤；a comparison module, configured to compare a preset comparison threshold with the comparison reference value, and update the to-be-processed set or return to the comparison reference value generating step;
输出模块，用于对更新后的所述待处理集合中的所述图像文件进行合成处理，得到目标视频。An output module, configured to perform synthesis processing on the image files in the updated set to be processed to obtain a target video.
根据本发明实施例的降低视频闪烁的装置，至少具有如下有益效果：本发明所提供的降低视频闪烁的装置中包括拆分模块、收集模块、计算模块、比较模块和输出模块。其中，拆分模块用于将获取到的数据视频拆分为包括全部图像帧的图像文件；收集模块可以生成用于执行降低闪烁处理的待处理集合，并将当前的图像文件纳入待处理集合；计算模块可以执行根据本发明第一方面实施例中提供的比较参考值生成步骤，以实现计算生成图像文件中两两相连的图像帧之间的比较参考值；比较模块可以获取预设的比较阈值，并将比较参考值与比较阈值进行比对，从而提供图像帧之间差异程度的量化指标，并根据比对的结果更新待处理集合中的图像文件或者重新执行比较参考值生成步骤；输出模块可以获取经过比较模块更新后的待处理集合，并对待处理集合中的图像文件进行合成，从而得到降低闪烁处理后的输出视频。本装置通过检测原始视频数据中各帧之间的图像差异判断视频中具体出现闪烁的视频图像位置，并对发生闪烁前后的图像帧进行处理，从而降低图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The device for reducing video flicker according to the embodiment of the present invention has at least the following beneficial effects: the device for reducing video flicker provided by the present invention includes a splitting module, a collection module, a calculation module, a comparison module and an output module. Wherein, the splitting module is used for splitting the acquired data video into image files including all image frames; the collecting module can generate a set to be processed for performing flicker reduction processing, and include the current image file into the set to be processed; The calculation module can perform the comparison reference value generation step provided in the embodiment according to the first aspect of the present invention, so as to realize the calculation and generation of the comparison reference value between the two connected image frames in the image file; the comparison module can obtain a preset comparison threshold value , and compare the comparison reference value with the comparison threshold to provide a quantitative index of the degree of difference between image frames, and update the image files in the set to be processed according to the comparison result or re-execute the comparison reference value generation step; output module The to-be-processed set updated by the comparison module can be acquired, and the image files in the to-be-processed set can be synthesized, thereby obtaining the output video after flicker reduction processing. The device determines the position of the video image where the flicker occurs in the video by detecting the image difference between the frames in the original video data, and processes the image frames before and after the flicker, so as to reduce the difference between the image frames, so as to compare the difference between the image frames. The large image frame is updated to generate the target video with reduced flicker, which effectively improves the efficiency of reducing video flicker.
根据本发明的一些实施例，所述拆分模块包括：According to some embodiments of the present invention, the splitting module includes:
获取单元，用于获取所述视频数据；an acquisition unit for acquiring the video data;
分帧单元，用于对所述视频数据进行分帧处理，得到原始帧文件；a framing unit, for performing framing processing on the video data to obtain an original frame file;
生成单元，用于通过预设的分割模型对所述原始帧文件进行分割处理，得到所述图像文件。The generating unit is configured to perform segmentation processing on the original frame file by using a preset segmentation model to obtain the image file.
根据本发明的一些实施例，所述比较模块包括：According to some embodiments of the present invention, the comparison module includes:
比较单元，用于比较预设的比较阈值和所述比较参考值；a comparison unit for comparing a preset comparison threshold with the comparison reference value;
第一处理单元，用于实现若所述比较参考值大于或者等于所述比较阈值，则根据所述比较参考值对应的连续两个图像帧的时间先后顺序，得到第一帧文件和第二帧文件；A first processing unit, configured to obtain a first frame file and a second frame according to the time sequence of two consecutive image frames corresponding to the comparison reference value if the comparison reference value is greater than or equal to the comparison threshold value document;
第一更新单元，用于根据所述第一帧文件、所述第二帧文件和预设的平均算法，得到第二更新帧；a first update unit, configured to obtain a second update frame according to the first frame file, the second frame file and a preset averaging algorithm;
第二处理单元，用于将所述待处理集合中的第二帧文件替换为所述第二更新帧，以更新所述待处理集合；a second processing unit, configured to replace the second frame file in the to-be-processed set with the second update frame to update the to-be-processed set;
或者，or,
第二比较单元，用于实现若所述比较参考值小于所述比较阈值，则不更新所述待处理集合，并返回所述比较参考值生成步骤。A second comparison unit, configured to implement that if the comparison reference value is smaller than the comparison threshold value, do not update the to-be-processed set, and return to the comparison reference value generating step.
根据本发明第三方面所提供的降低视频闪烁的设备，包括：The device for reducing video flicker provided according to the third aspect of the present invention includes:
至少一个存储器，以及at least one memory, and
与所述至少一个存储器通信连接的处理器，其中a processor in communication with the at least one memory, wherein
所述存储器中存储有指令，所述至少一个处理器可以执行所述指令，以使所述至少一个处理器执行所述指令时可以实现如本发明第一方面实施例所述的降低视频闪烁的方法。Instructions are stored in the memory, and the at least one processor can execute the instructions, so that when the at least one processor executes the instructions, the video flicker reduction method according to the embodiment of the first aspect of the present invention can be implemented. method.
根据本发明实施例的降低视频闪烁的设备，至少具有如下有益效果：本发明所提供的降低视频闪烁的设备包括处理器和至少一个存储器。其中，存储器与处理器之间通信连接，处理器可以执行存储器中存储的指令，从而实现拆解获取到的原始视频数据得到包括全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The device for reducing video flicker according to the embodiment of the present invention has at least the following beneficial effects: the device for reducing video flicker provided by the present invention includes a processor and at least one memory. Wherein, the memory and the processor are communicatively connected, and the processor can execute the instructions stored in the memory, so as to disassemble the acquired original video data to obtain image files including all image frames, and include the image files in the set to be processed; By performing the step of generating the comparative reference value, the present invention can quantify the image difference between two connected image frames in the image file, and obtain a degree of difference that can represent the difference between every two connected image frames in all the image frames in the image file. and the comparison reference value is used as the reference standard to measure the degree of difference between two image frames; by comparing the preset comparison AND value and the comparison reference value, it can be judged whether there is a comparison between each two connected image frames. If there is a large difference, update the set to be processed according to the comparison result or re-execute the comparison reference value generation step; it is also possible to synthesize the image files in the updated set to be processed when it is detected that there is an update in the set to be processed, so as to reduce the The target video after flashing. By splitting the original video data and comparing the difference between each two connected image frames, the image frames with large differences are updated to generate the target video after flicker reduction, which effectively improves the reduction of video frequency. flickering efficiency.
根据本发明第四方面所提供的计算机可读存储介质，所述计算机可读存储介质中存储有计算机可执行指令，计算机通过执行所述计算机可执行指令可以实现如本发明第一方面实施例所述的降低视频闪烁的方法。According to the computer-readable storage medium provided in the fourth aspect of the present invention, the computer-readable storage medium stores computer-executable instructions, and by executing the computer-executable instructions, a computer can implement the embodiment of the first aspect of the present invention. The method described above to reduce video flicker.
根据本发明实施例的计算机可读存储介质，至少具有如下有益效果：本发明所提供的计算机可读存储介质中存储的计算机及可执行指令可以被计算机执行，从而通过计算机实现拆解获取到的原始视频数据得到摆阔全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值，可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The computer-readable storage medium according to the embodiment of the present invention has at least the following beneficial effects: the computer and the executable instructions stored in the computer-readable storage medium provided by the present invention can be executed by the computer, so that the disassembled and obtained The image files of all the image frames are obtained from the original video data, and the image files are included in the to-be-processed set; by performing the step of comparing the reference value generation, the present invention can quantify the image differences between the image frames connected to each other in the image files, And obtain a comparison reference value that can represent the degree of difference between every two connected image frames in all image frames in the image file, and use the comparison reference value as a reference standard to measure the degree of difference between two image frames; by comparing the preset It can judge whether there is a big difference between each two connected image frames, update the set to be processed or re-execute the comparison reference value generation step according to the comparison result; When the set is updated, the image files in the updated set to be processed are synthesized to obtain the target video with reduced flicker. By splitting the original video data and comparing the difference between each two connected image frames, the image frames with large differences are updated to generate the target video after flicker reduction, which effectively improves the reduction of video frequency. flickering efficiency.
本发明的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。Additional aspects and advantages of the present invention will be set forth, in part, from the following description, and in part will be apparent from the following description, or may be learned by practice of the invention.
附图说明Description of drawings
下面结合附图和实施例对本发明做进一步的说明，其中：The present invention will be further described below in conjunction with the accompanying drawings and embodiments, wherein:
图1为本发明降低视频闪烁的方法的流程图；Fig. 1 is the flow chart of the method for reducing video flicker of the present invention;
图2为图1中步骤S100的具体流程图。FIG. 2 is a specific flowchart of step S100 in FIG. 1 .
图3为图1中步骤S300的具体流程图。FIG. 3 is a specific flowchart of step S300 in FIG. 1 .
图4为图1中步骤S400的具体流程图。FIG. 4 is a specific flowchart of step S400 in FIG. 1 .
图5为图4中步骤S430的具体流程图。FIG. 5 is a specific flowchart of step S430 in FIG. 4 .
图6为本发明降低视频闪烁的装置的结构示意图。FIG. 6 is a schematic structural diagram of an apparatus for reducing video flicker according to the present invention.
附图标记：100、拆分模块；200、收集模块；300、计算模块；400、比较模块；500、输出模块。Reference numerals: 100, splitting module; 200, collecting module; 300, calculating module; 400, comparing module; 500, outputting module.
具体实施方式Detailed ways
下面详细描述本发明的实施例，实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能理解为对本发明的限制。Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention.
在本发明的描述中，需要理解的是，涉及到方位描述，例如上、下、前、后、左、右等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。In the description of the present invention, it should be understood that the azimuth description, such as the azimuth or position relationship indicated by up, down, front, rear, left, right, etc., is based on the azimuth or position relationship shown in the drawings, only In order to facilitate the description of the present invention and simplify the description, it is not indicated or implied that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the present invention.
在本发明的描述中，若干的含义是一个以上，多个的含义是两个以上，大于、小于、超过等理解为不包括本数，以上、以下、以内等理解为包括本数。如果有描述到第一、第二只是用于区分技术特征为目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量或者隐含指明所指示的技术特征的先后关系。In the description of the present invention, the meaning of several means one or more, the meaning of multiple means two or more, greater than, less than, exceeding, etc. are understood as not including this number, above, below, within, etc. are understood as including this number. If it is described that the first and the second are only for the purpose of distinguishing technical features, it cannot be understood as indicating or implying relative importance, or indicating the number of the indicated technical features or the order of the indicated technical features. relation.
本发明的描述中，除非另有明确的限定，设置、安装、连接等词语应做广义理解，所属技术领域技术人员可以结合技术方案的具体内容合理确定上述词语在本发明中的具体含义。In the description of the present invention, unless otherwise clearly defined, words such as setting, installation, connection should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in the present invention in combination with the specific content of the technical solution.
本发明的描述中，参考术语“一个实施例”、“一些实施例”、“示意性实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。In the description of the present invention, reference to the terms "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" or the like is meant to be used in conjunction with the embodiment. A particular feature, structure, material or characteristic described or exemplified is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
第一方面，参照图1，本发明提供了一种降低视频闪烁的方法，包括：In a first aspect, referring to FIG. 1 , the present invention provides a method for reducing video flicker, including:
S100，获取原始视频数据的图像文件；其中图像文件包括全部的图像帧；S100, obtain an image file of the original video data; wherein the image file includes all image frames;
S200，将图像文件纳入待处理集合；S200, incorporating the image file into the set to be processed;
S300，比较参考值生成步骤：计算图像文件中每两个相连的图像帧之间的比较参考值；S300, a comparison reference value generating step: calculating a comparison reference value between every two connected image frames in the image file;
S400，比较预设的比较阈值和比较参考值，并更新待处理集合或返回比较参考值生成步骤；S400, compare the preset comparison threshold value and the comparison reference value, and update the set to be processed or return to the comparison reference value generation step;
S500，对更新后的待处理集合中的图像文件进行合成处理，得到目标视频。S500: Perform synthesis processing on the image files in the updated set to be processed to obtain a target video.
本发明所提供的降低视频闪烁的方法可以拆解获取到的原始视频数据得到包括全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值，本方法可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；本方法还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。这一方法通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The method for reducing video flicker provided by the present invention can disassemble the obtained original video data to obtain image files including all image frames, and include the image files in the set to be processed; by performing the step of generating comparative reference values, the present invention can Quantify the image difference between two connected image frames in the image file, and obtain a comparison reference value that can represent the degree of difference between every two connected image frames in all image frames in the image file, and use the comparison reference value as a measure The reference standard of the difference degree between two image frames; by comparing the preset comparison sum value and the comparison reference value, this method can judge whether there is a large difference between each two connected image frames, and update the pending processing according to the comparison result Collect or re-execute the step of generating the comparative reference value; when detecting that the to-be-processed set is updated, the method can further synthesize the image files in the updated to-be-processed set to obtain a target video with reduced flicker. This method splits the original video data and compares the difference between each two connected image frames one by one, so as to update the image frames with large differences to generate the target video with reduced flicker, which effectively improves the Reduces the efficiency of video flickering.
参照图2，在一些实施例中，步骤S100包括：2, in some embodiments, step S100 includes:
S110，获取原始视频数据；S110, obtain original video data;
S120，对原始视频数据进行分帧处理，得到原始帧文件。S120: Perform frame-by-frame processing on the original video data to obtain an original frame file.
S130，通过预设的分割模型对原始帧文件进行分割处理，得到图像文件。S130: Perform segmentation processing on the original frame file by using a preset segmentation model to obtain an image file.
本发明所提供的降低视频闪烁的方法可以获取用户需要处理的原始视频数据，并对视频数据进行分帧处理，到原始帧文件，并通过预设的分割模型对原始帧文件进行逐一分割处理，以得到本方法降低视频闪烁过程中需要处理的最小单元，即通过分帧模型处理得到全部的图像帧，并根据全部图像帧得到图像文件。通过这一方法可以实现对原始视频数据中的每一最小单元进行分割，从而提供通过对每一最小单元，即图像帧的处理，实现降低视频的闪烁的处理方法。由于处理过程中仅需对每一图像帧进行平均化计算，本方法可以避免由于采用传统的需要大量数据集进行计算的分割类算法等产生的额外时间、金钱等方面的支出，从而简单高效的实现降低视频的闪烁的效果。The method for reducing video flicker provided by the present invention can obtain the original video data that needs to be processed by the user, perform frame-by-frame processing on the video data to obtain the original frame file, and perform the segmentation processing on the original frame file one by one through the preset segmentation model, In order to obtain the minimum unit that needs to be processed in the process of reducing video flicker by the method, all image frames are obtained through frame division model processing, and image files are obtained according to all image frames. Through this method, each minimum unit in the original video data can be segmented, thereby providing a processing method for reducing video flicker by processing each minimum unit, that is, an image frame. Since only the average calculation of each image frame is required in the processing process, this method can avoid the extra time, money and other expenditures caused by using traditional segmentation algorithms that require a large number of data sets for calculation. Achieve the effect of reducing the flicker of the video.
在一些具体的实施例中，本发明通过分帧处理可以将原始视频数据分割为若干张图片，并将这若干张图片作为原始帧文件。其中，分帧处理后的图片数量根据用户需求具体定制，不做限制。本发明还可以通过分割模型将原始帧文件中每一图片内的实例分割出来，其中实例的选取同样由用户指定，不做限制。如在一些其他的实施例中，用户对于原始视频数据中存在的人像进行选取，本发明即可以通过分帧处理将原始视频数据分割成若干张图片，得到原始帧文件，并通过分割模型对原始帧文件进行处理，得到包含每一张图片中人像信息的全部图像帧，从而得到对应用户需求中全部人像信息的图像文件。In some specific embodiments, the present invention can divide the original video data into several pictures through frame division processing, and use the several pictures as the original frame file. Among them, the number of pictures after frame-by-frame processing is specifically customized according to user requirements, and there is no limit. In the present invention, instances in each picture in the original frame file can also be segmented by a segmentation model, wherein the selection of instances is also specified by the user without limitation. As in some other embodiments, the user selects a portrait existing in the original video data, the present invention can divide the original video data into several pictures through frame division processing, obtain the original frame file, and use the segmentation model to divide the original video data into several pictures. The frame file is processed to obtain all image frames containing the portrait information in each picture, so as to obtain an image file corresponding to all the portrait information in the user's needs.
参照图3，在一些实施例中，步骤S300包括：3, in some embodiments, step S300 includes:
S310，获取第一帧文件的第一平均值、第一标准差和第一协方差；S310, obtaining the first average value, the first standard deviation and the first covariance of the first frame file;
S320，获取第二帧文件的第二平均值、第二标准差和第二协方差；S320, obtaining the second average value, the second standard deviation and the second covariance of the second frame file;
S330，根据预设的第一常数和第二常数，对第一平均值、第一标准差、第一协方差、第二平均值、第二标准差和第二协方差进行SSIM值计算，得到比较参考值。S330, according to the preset first constant and the second constant, perform SSIM value calculation on the first average value, the first standard deviation, the first covariance, the second average value, the second standard deviation and the second covariance, to obtain Compare reference values.
本方法可以将图像文件中每两个相连的图像帧分组，并将每组内的两个图像帧按照时间顺序分为第一帧文件和第二帧文件，并获取第一帧文件的获取第一帧文件的第一平均值、第一标准差和第一协方差，以及获取第二帧文件的第二平均值、第二标准差和第二协方差，进而根据预设的第一常数和第二常数，对第一平均值、第一标准差、第一协方差、第二平均值、第二标准差和第二协方差进行SSIM值计算，得到比较参考值。通过这一方法，本发明可以将图像帧之间的差异程度以SSIM值对应的比较参考值作为量化指标，区分第一帧文件和第二帧文件之间的差异程度，从而根据这一差异程度对图像帧进行优化，以实现对原始视频数据降低闪烁的处理。其中，SSIM值的计算采用与图像处理领域一致的算法，在此不做赘述。The method can group every two connected image frames in an image file, divide the two image frames in each group into a first frame file and a second frame file according to time sequence, and obtain the first frame file. The first average value, first standard deviation and first covariance of one frame file, and the second average value, second standard deviation and second covariance of the second frame file are obtained, and then according to the preset first constant and For the second constant, the SSIM value is calculated for the first average value, the first standard deviation, the first covariance, the second average value, the second standard deviation and the second covariance to obtain a comparison reference value. Through this method, the present invention can use the comparison reference value corresponding to the SSIM value as a quantification index to distinguish the difference degree between the first frame file and the second frame file, so that according to the difference degree Image frames are optimized for flicker reduction on raw video data. Among them, the calculation of the SSIM value adopts an algorithm consistent with the field of image processing, which is not repeated here.
在一些具体的实施例中，本方法在将每两个相连的图像帧分组时，为了保证降低视频闪烁的效率，每组内的第一图像帧与上一组的第二图像帧并不一致，即，相邻的分组内图像帧并不重叠。通过这一方法，本发明可以有效的减少图像帧分组的组数，从而提高降低视频闪烁的效率。In some specific embodiments, when the method groups every two connected image frames, in order to ensure the efficiency of reducing video flickering, the first image frame in each group is not consistent with the second image frame in the previous group, That is, adjacent intra-group image frames do not overlap. Through this method, the present invention can effectively reduce the number of groups of image frame groups, thereby improving the efficiency of reducing video flicker.
参照图4，在一些实施例中，步骤S400包括：4, in some embodiments, step S400 includes:
S410，比较预设的比较阈值和比较参考值；S410, compare a preset comparison threshold with a comparison reference value;
S420，若比较参考值大于或者等于比较阈值，则根据比较参考值对应的连续两个图像帧的时间先后顺序，得到第一帧文件和第二帧文件；S420, if the comparison reference value is greater than or equal to the comparison threshold value, obtain the first frame file and the second frame file according to the time sequence of two consecutive image frames corresponding to the comparison reference value;
S430，根据第一帧文件、第二帧文件和预设的平均算法，得到第二更新帧；S430, obtain a second update frame according to the first frame file, the second frame file and the preset averaging algorithm;
S440，将待处理集合中的第二帧文件替换为第二更新帧，以更新待处理集合。S440: Replace the second frame file in the to-be-processed set with a second update frame to update the to-be-processed set.
或者，or,
S450，若比较参考值小于比较阈值，则不更新待处理集合，并返回比较参考值生成步骤。S450, if the comparison reference value is less than the comparison threshold, the set to be processed is not updated, and the step of generating the comparison reference value is returned.
本方法可以通过比较预设的比较阈值和比较参考值以对待处理集合进行处理。具体地，本方法首先比对比较阈值和比较参考值，并在比较参考值大于或者等于比较阈值时，按照时间顺序划分得到比较参考值对应的第一帧文件和第二帧文件，并根据平均算法、第一帧文件和第二帧文件对第二帧文件进行更新，得到第二更新帧，并将第二更新帧作为新的第二帧文件代替原有的第二帧文件，从而将更新后的第一帧文件和新的第二帧文件更新至待处理集合；或者在本方法比对比较阈值和比较参考值之后，检测到比较参考值小于比较阈值时，跳过这一比较参考值对应分组内的图像帧，并保持待处理集合内的图像文件不变，并重新执行比较参考值生成步骤，以生成下一分组内的两个连续图像帧之间的比较参考值，从而实现对下一分组内的图像帧是否需要进行如步骤S410至步骤S450的更新操作，直至对全部分组内的图像帧进行检测是结束检测，得到最终的待处理集合。通过这一方法可以将第二图像帧与第一图像帧之间的差异通过比较阈值进行判断，并对第二图像帧进行更新，有效的实现了降低视频闪烁的效果。The method can process the set to be processed by comparing a preset comparison threshold with a comparison reference value. Specifically, the method first compares the comparison threshold with the comparison reference value, and when the comparison reference value is greater than or equal to the comparison threshold, divides the first frame file and the second frame file corresponding to the comparison reference value according to the time sequence, and obtains the first frame file and the second frame file corresponding to the comparison reference value according to the average The algorithm, the first frame file and the second frame file update the second frame file to obtain the second update frame, and use the second update frame as the new second frame file to replace the original second frame file, so that the updated The new first frame file and the new second frame file are updated to the set to be processed; or after the comparison threshold value and the comparison reference value are compared in this method, when it is detected that the comparison reference value is smaller than the comparison threshold value, the comparison reference value is skipped Corresponding to the image frames in the group, keep the image files in the set to be processed unchanged, and re-execute the comparison reference value generation step to generate the comparison reference value between two consecutive image frames in the next group, so as to realize the Whether the image frames in the next group need to be updated as in steps S410 to S450 until the image frames in all the groups are detected is the end of the detection, and the final set to be processed is obtained. Through this method, the difference between the second image frame and the first image frame can be judged by comparing the threshold value, and the second image frame can be updated, which effectively achieves the effect of reducing video flicker.
在一些具体的实施例中，比较阈值可以是0.7，在一些实施例中也可以是其它，不做限制。In some specific embodiments, the comparison threshold may be 0.7, and in some embodiments, it may be other, which is not limited.
参照图5，在一些实施例中，步骤S430包括：5, in some embodiments, step S430 includes:
S431，对第一帧文件和第二帧文件做均值化处理，得到更新平均值；S431, perform averaging processing on the first frame file and the second frame file to obtain an updated average value;
S432，根据更新平均值更新第二帧文件的平均值，得到第二更新帧。S432, update the average value of the second frame file according to the updated average value to obtain a second updated frame.
本方法可以根据第一帧文件和第二帧文件得到第一帧文件和第二帧文件各自对应的平均值，并将第一帧文件的平均值与第二帧文件的平均值进行均值化处理，得到更新平均值；在一些具体的实施例中，均值化处理可以采用计算第一帧文件的平均值与第二帧文件的平均值的算术平均值。本方法通过将更新平均值赋值至原第二帧文件的平均值，可以实现对第二帧文件的更新，从而得到第二更新帧。这一方法简单快速的实现了对两者之间差异过大的图像帧之间的相似化处理，从而简单高效的实现降低视频闪烁方法的过程。The method can obtain the respective average values of the first frame file and the second frame file according to the first frame file and the second frame file, and average the average value of the first frame file and the second frame file. , to obtain the updated average value; in some specific embodiments, the averaging process may adopt the arithmetic average value of the average value of the first frame file and the average value of the second frame file. In this method, by assigning the updated average value to the average value of the original second frame file, the update of the second frame file can be realized, thereby obtaining the second update frame. This method simply and quickly realizes the similarity processing between the image frames with too large difference between the two, so as to realize the process of reducing the video flickering method simply and efficiently.
值得说明的是，本发明所提供的降低视频的闪烁方法中，为了提高降低视频闪烁的处理效率，在步骤S300中采用计算图像文件中每两个相连的图像帧之间的比较参考值，实现比对每两个相连的图像帧之间的差异，并以两个图像帧为一组实现降低视频中闪烁的效果，在另一些实施例中，为了提高降低视频的闪烁的处理效果，本发明还可以计算图像文件中每三个或者三个以上的相连的图像帧之间的比较参考值，并且在步骤S431、S432中采用计算这三个或者三个以上的相连的图像帧的加权平均值以进行均值化处理。It should be noted that, in the method for reducing video flicker provided by the present invention, in order to improve the processing efficiency of reducing video flicker, in step S300, a comparison reference value between every two connected image frames in the image file is calculated to achieve Compare the difference between every two connected image frames, and use the two image frames as a group to achieve the effect of reducing the flicker in the video. In other embodiments, in order to improve the processing effect of reducing the flicker of the video, the present invention It is also possible to calculate the comparison reference value between every three or more connected image frames in the image file, and in steps S431, S432, calculate the weighted average of these three or more connected image frames. for averaging.
第二方面，参照图6，本方面提供了一种降低视频闪烁的装置，包括：In a second aspect, referring to FIG. 6 , this aspect provides a device for reducing video flicker, including:
拆分模块100，用于获取视频数据的图像文件；其中图像文件包括全部的图像帧；The
收集模块200，用于将图像文件纳入待处理集合；a
计算模块300，用于执行比较参考值生成步骤：计算图像文件中每两个相连的图像帧之间的比较参考值；The
比较模块400，用于比较预设的比较阈值和比较参考值，并更新待处理集合或返回比较参考值生成步骤；A
输出模块500，用于对更新后的待处理集合中的图像文件进行合成处理，得到目标视频。The
本发明所提供的降低视频闪烁的装置中包括拆分模块100、收集模块200、计算模块300、比较模块400和输出模块500。其中，拆分模块100用于将获取到的数据视频拆分为包括全部图像帧的图像文件；收集模块200可以生成用于执行降低闪烁处理的待处理集合，并将当前的图像文件纳入待处理集合；计算模块300可以执行根据本发明第一方面实施例中提供的比较参考值生成步骤，以实现计算生成图像文件中两两相连的图像帧之间的比较参考值；比较模块400可以获取预设的比较阈值，并将比较参考值与比较阈值进行比对，从而提供图像帧之间差异程度的量化指标，并根据比对的结果更新待处理集合中的图像文件或者重新执行比较参考值生成步骤；输出模块500可以获取经过比较模块400更新后的待处理集合，并对待处理集合中的图像文件进行合成，从而得到降低闪烁处理后的输出视频。本装置通过检测原始视频数据中各帧之间的图像差异判断视频中具体出现闪烁的视频图像位置，并对发生闪烁前后的图像帧进行处理，从而降低图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The device for reducing video flicker provided by the present invention includes a
在一些实施例中，拆分模块100包括：In some embodiments, the
获取单元，用于获取视频数据；an acquisition unit for acquiring video data;
分帧单元，用于对视频数据进行分帧处理，得到原始帧文件；A framing unit, which is used to perform framing processing on the video data to obtain the original frame file;
生成单元，用于通过预设的分割模型对原始帧文件进行分割处理，得到图像文件。The generating unit is configured to perform segmentation processing on the original frame file through a preset segmentation model to obtain an image file.
本发明所提供的拆分模块100包括获取单元、分帧单元和生成单元。其中，获取单元可以获取用户需要处理的原始视频数据，并通过分帧单元对视频数据进行分帧处理，到原始帧文件，生成单元中预设有分割模型，通过这一分割模型，生成单元可以对原始帧文件进行逐一分割处理，以得到本装置降低视频闪烁过程中需要处理的最小单元，即通过分帧模型处理得到全部的图像帧，并根据全部图像帧得到图像文件。通过这一装置，本发明可以实现对原始视频数据中的每一最小单元进行分割，从而提供通过对每一最小单元的处理，即对图像帧的处理，实现降低视频的闪烁的技术效果。由于处理过程中仅需对每一图像帧进行平均化计算，本装置可以避免由于采用传统的需要大量数据集进行计算的分割类算法等产生的额外时间、金钱等方面的支出，从而简单高效的实现降低视频的闪烁的效果。The
在一些实施例中，标记模块包括：In some embodiments, the marking module includes:
比较单元，用于比较预设的比较阈值和比较参考值；a comparison unit for comparing a preset comparison threshold with a comparison reference value;
第一处理单元，用于实现若比较参考值大于或者等于比较阈值，则根据比较参考值对应的连续两个图像帧的时间先后顺序，得到第一帧文件和第二帧文件；a first processing unit, configured to obtain a first frame file and a second frame file according to the time sequence of two consecutive image frames corresponding to the comparison reference value if the comparison reference value is greater than or equal to the comparison threshold value;
第一更新单元，用于根据第一帧文件、第二帧文件和预设的平均算法，得到第二更新帧；a first update unit, configured to obtain a second update frame according to the first frame file, the second frame file and a preset averaging algorithm;
第二更新单元，用于将待处理集合中的第二帧文件替换为第二更新帧，以更新待处理集合；a second update unit, configured to replace the second frame file in the set to be processed with a second update frame to update the set to be processed;
或者，or,
第二处理单元，用于实现若比较参考值小于比较阈值，则不更新待处理集合，并返回比较参考值生成步骤。The second processing unit is configured to implement that if the comparison reference value is smaller than the comparison threshold value, the set to be processed is not updated, and the step of generating the comparison reference value is returned.
本装置可以通过比较单元比对比较阈值和比较参考值，并在比较参考值大于或者等于比较阈值时，控制第一处理单元按照时间顺序划分得到比较参考值对应的第一帧文件和第二帧文件，并控制第一更新单元根据预设的平均算法、第一帧文件和第二帧文件对第二帧文件进行更新，得到第二更新帧，并控制第二更新单元440将第二更新帧作为新的第二帧文件代替原有的第二帧文件，从而将更新后的第一帧文件和新的第二帧文件更新至待处理集合；或者在本装置中的比对模块比对比较阈值和比较参考值之后，控制第二处理单元450在比较参考值小于比较阈值时，跳过这一比较参考值对应分组内的图像帧，并保持待处理集合内的图像文件不变，并重新执行比较参考值生成步骤，以生成下一分组内的两个连续图像帧之间的比较参考值，从而实现对下一分组内的图像帧是否需要更新下一分组内的比较参考值对应的第二帧文件，直至对全部分组内的图像帧进行检测是结束检测，得到最终的待处理集合。通过这一装置，本发明可以将第二图像帧与第一图像帧之间的差异通过比较阈值进行判断，并对第二图像帧进行更新，有效的实现了降低视频闪烁的效果。The device can compare the comparison threshold value and the comparison reference value through the comparison unit, and when the comparison reference value is greater than or equal to the comparison threshold value, control the first processing unit to divide the first frame file and the second frame corresponding to the comparison reference value according to the time sequence file, and control the first update unit to update the second frame file according to the preset averaging algorithm, the first frame file and the second frame file to obtain the second update frame, and control the second update unit 440 to update the second update frame As the new second frame file to replace the original second frame file, the updated first frame file and the new second frame file are updated to the set to be processed; or the comparison module in the device compares and compares After the threshold value and the comparison reference value, the second processing unit 450 is controlled to skip the image frame in the group corresponding to the comparison reference value when the comparison reference value is smaller than the comparison threshold value, and keep the image files in the to-be-processed set unchanged, and re-create the image frame. The step of generating a comparison reference value is performed to generate a comparison reference value between two consecutive image frames in the next group, so as to realize whether the image frame in the next group needs to update the first corresponding to the comparison reference value in the next group. Two-frame files, until the image frames in all the groups are detected, the detection is ended, and the final set to be processed is obtained. Through this device, the present invention can judge the difference between the second image frame and the first image frame by comparing the threshold value, and update the second image frame, effectively realizing the effect of reducing video flicker.
第三方面，本发明提供了一种降低视频闪烁的设备，包括：In a third aspect, the present invention provides a device for reducing video flicker, including:
至少一个存储器，以及at least one memory, and
与至少一个存储器通信连接的处理器，其中a processor in communication with at least one memory, wherein
存储器中存储有指令，至少一个处理器可以执行指令，以使至少一个处理器执行指令时可以实现如本发明第一方面实施例的降低视频闪烁的方法。Instructions are stored in the memory, and at least one processor can execute the instructions, so that when the at least one processor executes the instructions, the method for reducing video flicker according to the embodiment of the first aspect of the present invention can be implemented.
本发明所提供的降低视频闪烁的设备包括处理器和至少一个存储器。其中，存储器与处理器之间通信连接，处理器可以执行存储器中存储的指令，从而实现拆解获取到的原始视频数据得到包括全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The device for reducing video flicker provided by the present invention includes a processor and at least one memory. Wherein, the memory and the processor are communicatively connected, and the processor can execute the instructions stored in the memory, so as to disassemble the acquired original video data to obtain image files including all image frames, and include the image files in the set to be processed; By performing the step of generating the comparison reference value, the present invention can quantify the image difference between the two connected image frames in the image file, and obtain a degree of difference that can represent the difference between every two connected image frames in all the image frames in the image file. and the comparison reference value is used as the reference standard to measure the degree of difference between two image frames; by comparing the preset comparison AND value and the comparison reference value, it can be judged whether there is a comparison between each two connected image frames. If there is a large difference, update the set to be processed according to the comparison result or re-execute the comparison reference value generation step; when it is detected that there is an update in the set to be processed, the image files in the updated set to be processed can be synthesized, so as to reduce the The target video after flashing. By splitting the original video data and comparing the difference between each two connected image frames, the image frames with large differences are updated to generate the target video after flicker reduction, which effectively improves the reduction of video frequency. flickering efficiency.
第四方面，本发明提供了一种计算机可读存储介质，计算机可读存储介质中存储有计算机可执行指令，计算机通过执行计算机可执行指令可以实现如本发明第一方面实施例的降低视频闪烁的方法。In a fourth aspect, the present invention provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and by executing the computer-executable instructions, the computer can achieve the reduction of video flicker as in the embodiment of the first aspect of the present invention Methods.
本发明所提供的计算机可读存储介质中存储的计算机及可执行指令可以被计算机执行，从而通过计算机实现拆解获取到的原始视频数据得到摆阔全部的图像帧的图像文件，并将图像文件纳入待处理集合；通过执行比较参考值生成步骤，本发明可以将图像文件中两两相连的图像帧之间的图像差异量化，并得到可以代表图像文件中全部图像帧中每两个相连的图像帧之间差异程度的比较参考值，并以比较参考值作为衡量两个图像帧之间差异程度的参考标准；通过比较预设的比较与值和比较参考值可以判断每两个相连的图像帧之间是否存在较大差异，根据比较结果更新待处理集合或者重新执行比较参考值生成步骤；还可以在检测到当待处理集合存在更新时，对更新后的待处理集合中的图像文件进行合成处理，从而得到降低闪烁后的目标视频。这一方法通过对原始视频数据的拆分，并逐对比对每两个相连的图像帧之间的差异，从而对差异较大的图像帧进行更新以生成降低闪烁后的目标视频，有效的提高了降低视频闪烁的效率。The computer and the executable instructions stored in the computer-readable storage medium provided by the present invention can be executed by the computer, so that the obtained original video data can be disassembled by the computer to obtain an image file that expands all the image frames, and the image file is included in the image file. The set to be processed; by performing the step of generating the comparative reference value, the present invention can quantify the image difference between the two connected image frames in the image file, and obtain the image frames that can represent every two connected image frames in all the image frames in the image file. The comparison reference value of the difference degree between the two image frames, and the comparison reference value is used as the reference standard to measure the difference degree between the two image frames; by comparing the preset comparison AND value and the comparison reference value, it can be judged that the difference between each two connected image frames is If there is a big difference between the two, update the set to be processed or re-execute the comparison reference value generation step according to the comparison result; it is also possible to perform synthesis processing on the image files in the updated set to be processed when it is detected that there is an update in the set to be processed , so as to obtain the target video with reduced flicker. This method splits the original video data and compares the difference between each two connected image frames one by one, so as to update the image frames with large differences to generate the target video with reduced flicker, which effectively improves the Reduced the efficiency of video flickering.
上面结合附图对本发明实施例作了详细说明，但是本发明不限于上述实施例，在所属技术领域普通技术人员所具备的知识范围内，还可以在不脱离本发明宗旨的前提下作出各种变化。此外，在不冲突的情况下，本发明的实施例及实施例中的特征可以相互组合。The embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned embodiments, and within the scope of knowledge possessed by those of ordinary skill in the art, various Variety. Furthermore, the embodiments of the present invention and features in the embodiments may be combined with each other without conflict.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531311.7ACN114363659A (en) | 2021-12-15 | 2021-12-15 | Method, device, equipment and storage medium for reducing video flicker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111531311.7ACN114363659A (en) | 2021-12-15 | 2021-12-15 | Method, device, equipment and storage medium for reducing video flicker |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114363659Atrue CN114363659A (en) | 2022-04-15 |
Family
ID=81099077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111531311.7APendingCN114363659A (en) | 2021-12-15 | 2021-12-15 | Method, device, equipment and storage medium for reducing video flicker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114363659A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050018920A1 (en)* | 2003-07-22 | 2005-01-27 | Warner Bros. Entertainment Inc. | Method and apparatus for flicker removal from an image sequence |
| CN102006423A (en)* | 2010-11-15 | 2011-04-06 | 无锡中星微电子有限公司 | Camera and method and device for eliminating flicker phenomenon of same |
| CN109063694A (en)* | 2018-09-12 | 2018-12-21 | 北京科技大学 | A kind of video object detection recognition method |
| CN109274984A (en)* | 2018-10-16 | 2019-01-25 | 深圳开阳电子股份有限公司 | Detect the method, apparatus and image processing equipment of light source scintillation in video sequence |
| CN109862389A (en)* | 2018-11-20 | 2019-06-07 | 北京奇艺世纪科技有限公司 | A kind of method for processing video frequency, device, server and storage medium |
| CN110381276A (en)* | 2019-05-06 | 2019-10-25 | 华为技术有限公司 | A kind of video capture method and electronic equipment |
| CN110675342A (en)* | 2019-09-18 | 2020-01-10 | 努比亚技术有限公司 | Video frame optimization method, mobile terminal and computer readable storage medium |
| CN113129312A (en)* | 2018-10-15 | 2021-07-16 | 华为技术有限公司 | Image processing method, device and equipment |
| CN113596573A (en)* | 2021-07-28 | 2021-11-02 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN113705665A (en)* | 2021-08-26 | 2021-11-26 | 荣耀终端有限公司 | Training method of image transformation network model and electronic equipment |
- 2021
- 2021-12-15CNCN202111531311.7Apatent/CN114363659A/enactivePending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050018920A1 (en)* | 2003-07-22 | 2005-01-27 | Warner Bros. Entertainment Inc. | Method and apparatus for flicker removal from an image sequence |
| CN102006423A (en)* | 2010-11-15 | 2011-04-06 | 无锡中星微电子有限公司 | Camera and method and device for eliminating flicker phenomenon of same |
| CN109063694A (en)* | 2018-09-12 | 2018-12-21 | 北京科技大学 | A kind of video object detection recognition method |
| CN113129312A (en)* | 2018-10-15 | 2021-07-16 | 华为技术有限公司 | Image processing method, device and equipment |
| CN109274984A (en)* | 2018-10-16 | 2019-01-25 | 深圳开阳电子股份有限公司 | Detect the method, apparatus and image processing equipment of light source scintillation in video sequence |
| CN109862389A (en)* | 2018-11-20 | 2019-06-07 | 北京奇艺世纪科技有限公司 | A kind of method for processing video frequency, device, server and storage medium |
| CN110381276A (en)* | 2019-05-06 | 2019-10-25 | 华为技术有限公司 | A kind of video capture method and electronic equipment |
| CN110675342A (en)* | 2019-09-18 | 2020-01-10 | 努比亚技术有限公司 | Video frame optimization method, mobile terminal and computer readable storage medium |
| CN113596573A (en)* | 2021-07-28 | 2021-11-02 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN113705665A (en)* | 2021-08-26 | 2021-11-26 | 荣耀终端有限公司 | Training method of image transformation network model and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 周磊;倪强;周源华;: "一种基于块的图像序列闪烁修复方法", 上海交通大学学报* |
| 管萌萌;曹纭;张怡暄;赵险峰;: "基于自适应奇异值调制的抗转码视频隐写算法", 信息安全学报* |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961303B (en) | Image processing method and device, electronic equipment and computer readable medium | |
| CN1093669C (en) | Histogram equalization device and method for moving image contrast enhancement | |
| JP5478047B2 (en) | Video data compression pre-processing method, video data compression method and video data compression system using the same | |
| WO2012122682A1 (en) | Method for calculating image visual saliency based on color histogram and overall contrast | |
| CN108475425A (en) | Image processing apparatus, image processing method and image processing program | |
| CN118138801B (en) | Video data processing method and device, electronic equipment and storage medium | |
| KR101437626B1 (en) | System and method for region-of-interest-based artifact reduction in image sequences | |
| US20220318563A1 (en) | Information processing method, information processing apparatus, and program | |
| JP5820284B2 (en) | Image processing apparatus, method, and program | |
| CN110047077B (en) | Image processing method for Ether house consensus mechanism | |
| CN115731513A (en) | Intelligent park management system based on digital twin | |
| CN117974811A (en) | Color correction matrix determining method, device, electronic equipment and storage medium | |
| CN110336943A (en) | A scene recognition method and device | |
| US20210272250A1 (en) | Tone-mapping of colors of a video content | |
| KR102099030B1 (en) | Mutual noise estimation for video | |
| CN114363659A (en) | Method, device, equipment and storage medium for reducing video flicker | |
| JP7610521B2 (en) | High Dynamic Range Video Format Detection | |
| CN116977372A (en) | Video frame anomaly detection method and device, computer equipment and storage medium | |
| CN1436426A (en) | Adaptive early exit techniques for image correlation minimum distortion calculation | |
| CN111832433B (en) | Device for extracting object characteristics from image and working method thereof | |
| KR101631023B1 (en) | Neighbor-based intensity correction device, background acquisition device and method thereof | |
| JP2018200506A (en) | Image processing apparatus and image processing method | |
| CN113780226B (en) | Thermal imaging video data processing method, device and storage medium | |
| CN110647933B (en) | Video classification method and device | |
| CN108133210A (en) | A kind of picture format recognition methods and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20220415 | |
| RJ01 | Rejection of invention patent application after publication |