WO2015168893A1 - 一种视频质量检测的方法及装置 - Google Patents
一种视频质量检测的方法及装置 Download PDFInfo
- Publication number
- WO2015168893A1 WO2015168893A1 PCT/CN2014/077008 CN2014077008W WO2015168893A1 WO 2015168893 A1 WO2015168893 A1 WO 2015168893A1 CN 2014077008 W CN2014077008 W CN 2014077008W WO 2015168893 A1 WO2015168893 A1 WO 2015168893A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- frame data
- quality detection
- video frame
- video quality
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 511
- 238000012545 processing Methods 0.000 claims abstract description 219
- 230000002159 abnormal effect Effects 0.000 claims abstract description 119
- 238000000034 method Methods 0.000 claims description 45
- 230000015572 biosynthetic process Effects 0.000 claims description 10
- 238000003786 synthesis reaction Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 208000003028 Stuttering Diseases 0.000 claims 1
- 230000008014 freezing Effects 0.000 claims 1
- 238000007710 freezing Methods 0.000 claims 1
- 230000005856 abnormality Effects 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 4
- 230000002194 synthesizing effect Effects 0.000 description 4
- 230000002547 anomalous effect Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/87—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving scene cut or scene change detection in combination with video compression
Definitions
- the present invention relates to the field of communications technologies, and in particular, to a method and apparatus for video quality detection.
- Video quality is an important detection item for related media products. Video quality detection is a hot research topic in the industry. It is mainly divided into active video quality detection (hereinafter referred to as active detection) and passive video quality detection (hereinafter referred to as passive detection).
- active detection refers to a video quality detection mode that includes a reference source of video comparison
- passive detection refers to a video quality detection manner that does not include a reference source of video comparison.
- the mainstream active detection in the prior art is to measure the video quality through relevant indicators, so it is necessary to set the reference threshold for the relevant indicators.
- different media products and different sources are selected. There are certain differences in values.
- the detected indicators are not completely consistent with the video quality perceived by the human eye. Therefore, the active detection detection of the video quality through the related indicators is low in accuracy and low in practicability.
- the active detection mainly detects the video through the video quality detecting instrument, wherein the video quality detecting instrument detects the video by comparing the two pairs, so that a video quality detecting instrument can The number of media products that support simultaneous detection is limited. If you need to scale the media products, it will increase the cost of video quality detection.
- the passive detection algorithm mainly matches the abnormality by analyzing the characteristics of the video image.
- the prior art has no passive detection instrument and no mainstream passive detection algorithm, so that the detection scene of the passive detection is limited.
- Video quality detection either uses active detection or passive detection, video quality. The detection method is single, the accuracy of video quality detection is not guaranteed, and the user experience is low. Summary of the invention
- the embodiment of the invention provides a method and a device for detecting video quality, which can simultaneously detect video frames of multi-channel media products, and can select active video quality detection or passive video quality detection for video frame data, which can improve
- the diversity of video quality detection methods ensures the accuracy of video quality detection and improves the user experience of video quality detection.
- a first aspect of the embodiments of the present invention provides a video quality detection method, which may include: collecting video frame data, where the video frame data is derived from at least two media products;
- the video detection conditions include: at least one of a type of video frame data and a video quality detection accuracy;
- the type of the video frame data includes: video frame data of a customized video, or video frame data of a streaming video.
- the performing active video quality detection or passive video quality detection on the video frame data according to preset video detection conditions including:
- the video frame data is video frame data of the customized video, selecting to perform active video quality detection on the video frame data; or
- the video frame data is video frame data of the streaming media video
- passive video quality detection is performed on the video frame data.
- the performing active video quality detection or passive video quality detection on the video frame data according to preset video detection conditions including:
- the video frame data is video frame data of the streaming media video
- the predetermined video quality detection accuracy is the second detection accuracy
- passive video quality detection is performed on the video frame data.
- the video processing algorithm for the active video quality detection includes: At least one of a fuzzy processing algorithm, a gray processing algorithm, and a synthetic processing algorithm.
- the video processing algorithm according to active video quality detection performs active video quality detection on the video frame data, or
- the video processing algorithm of the source video quality detection performs passive video quality detection on the video frame data, including:
- the video processing algorithm for the passive video quality detection includes a binarization processing algorithm At least one of a marginalization algorithm and a macroblock coding.
- the video processing algorithm according to active video quality detection performs active video quality detection on the video frame data, or
- the video processing algorithm of the source video quality detection performs passive video quality detection on the video frame data, including:
- the main features of the abnormal region of the video image include: at least one of a mosaic, a flower screen, a black screen, and a card.
- a second aspect of the embodiments of the present invention provides an apparatus for video quality detection, which may include: a collection module, configured to collect video frame data, where the video frame data is derived from at least two media outlets
- a selection module configured to perform active video quality detection or passive video quality detection on the video frame data according to preset video detection conditions, where the video detection conditions include: a type of video frame data, and a video quality detection accuracy At least one
- a detecting module configured to perform active video quality detection on the video frame data according to a video processing algorithm of active video quality detection, or perform passive video quality on the video frame data according to a video processing algorithm of passive video quality detection Detection
- the sending module is configured to obtain abnormal video frame data, and send the quality detection report of the abnormal video frame data to the video frame exception processing module.
- the type of the video frame data collected by the collection module includes: video frame data of a customized video, or video frame data of a streaming video.
- the selecting module is specifically configured to:
- the video frame data is video frame data of the customized video, selecting to perform active video quality detection on the video frame data; or
- the video frame data is video frame data of the streaming media video
- passive video quality detection is performed on the video frame data.
- the selecting module is specifically configured to:
- the video frame data is video frame data of the streaming media video
- the predetermined video quality detection accuracy is the second detection accuracy
- passive video quality detection is performed on the video frame data.
- the video processing algorithm for the active video quality detection includes: a Gaussian fuzzy processing algorithm At least one of a grayscale processing algorithm and a synthesis processing algorithm.
- the detecting module includes:
- a first processing unit configured to acquire a target image of the video frame data, and perform Gaussian blur processing on the target image and the preset reference image
- a second processing unit configured to perform grayscale processing on the target image and the reference image processed by the first processing unit, and synthesize the processed target image and the reference image to obtain a difference image of the target image and the reference image;
- a third processing unit configured to acquire the pixel point whose pixel value is the first pixel value, to obtain abnormal video frame data.
- the video processing algorithm for the passive video quality detection includes a binarization processing algorithm At least one of a marginalization algorithm and a macroblock coding.
- the detecting module includes:
- a fourth processing unit configured to perform binarization processing on the video image of the video frame data according to the binarization processing algorithm, and perform edgeization on the video image of the video frame data according to the edged processing algorithm Processing, acquiring main features of the abnormal region of the video image;
- a fifth processing unit configured to extract an effective edge of the abnormal region of the video image according to the macroblock encoding feature, and use the preset abnormal feature template to match an edge of the abnormal region of the video image to obtain abnormal video frame data;
- the main features of the abnormal region of the video image include: at least one of a mosaic, a flower screen, a black screen, and a card.
- 1 is a schematic flowchart diagram of a first embodiment of a method for detecting video quality according to an embodiment of the present invention
- 2 is a schematic flowchart diagram of a second embodiment of a method for detecting video quality according to an embodiment of the present invention
- FIG. 3 is a schematic flow chart of a third embodiment of a method for detecting video quality according to an embodiment of the present invention.
- FIG. 4 is a schematic structural diagram of a first embodiment of an apparatus for detecting video quality according to an embodiment of the present invention
- FIG. 5 is a schematic structural diagram of a second embodiment of an apparatus for detecting video quality according to an embodiment of the present invention.
- FIG. 6 is a schematic structural diagram of a third embodiment of an apparatus for detecting video quality according to an embodiment of the present invention. detailed description
- FIG. 1 is a schematic flowchart diagram of a first embodiment of a method for detecting video quality according to an embodiment of the present invention.
- the method for video quality detection described in this embodiment includes the following steps:
- the platform for the video quality detection described in the embodiment of the present invention may be a workstation server, that is, the execution body of the video quality detection method described in the embodiment of the present invention may be a workstation server, which is used in the embodiment of the present invention.
- the device for the described video quality detection can be a workstation server.
- the video frame data to be detected needs to be collected, and the video quality detection method described in this embodiment of the present invention can simultaneously detect multiple (ie, at least two) video frame data, that is, Video frame data can be collected from multiple media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame number of the streaming media video, where the customized video may be a video with a video source. It may include recorded video, or produced video, etc.
- the video of the video source may be used for quality detection.
- the above streaming video is a video without a video source, and there is no video source. Passive video quality detection can be used for quality inspection.
- the types that can be included in the above custom video The embodiments of the present invention do not limit the detection manner of the customized video or the streaming video, for example, but not limited to the above.
- S102 Perform active video quality detection or passive video quality detection on the video frame data according to preset video detection conditions.
- S103 Perform active video quality detection on the video frame data according to a video processing algorithm of active video quality detection, or perform passive video quality detection on the video frame data according to a video processing algorithm of passive video quality detection.
- the active video quality detection or the passive video quality detection of the video frame data may be directly selected according to the type of the video frame data.
- the collected video frame data is the video frame data of the customized video
- the active video quality detection may be performed on the video frame data
- the collected video frame data is the video frame of the streaming video.
- passive video quality detection can be performed on the video frame data.
- the user has the accuracy requirement for the video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data. Quality detection of video frame data.
- the user may preset the detection precision of the video quality detection, which may include the first detection precision, the second detection precision, and the like. After setting the video quality detection accuracy, the type of the video frame data collected may be combined. Active video quality detection or passive video quality detection on video frame data. For example, when the video frame data collected by the video frame is video frame data of a customized video having a video source, and the preset video quality detection accuracy is the first detection precision, the active video quality of the customized video may be selected.
- the passive video quality detection may be selected for the streaming video, and the video processing algorithm according to the passive video quality detection may be selected. Passive video quality detection is performed on the video frame data collected above, and abnormal video frame data is acquired.
- the method for selecting the method for performing active video quality detection or passive video quality detection on the video frame data collected according to the preset video detection condition may be any of the foregoing two description manners. One type, that is, directly selects according to the type of video frame data, or selects according to the type of video frame data and the video quality detection accuracy, and is not limited herein.
- S104 Acquire abnormal video frame data, and report quality detection of the abnormal video frame data. Send to the video frame exception handling module.
- abnormal video frame data may be acquired, and information such as time when the video abnormality occurs and log information may be recorded as abnormal video frame data.
- the quality detection report further sends a quality detection report of the abnormal video frame data to the video frame exception processing module, so that the video exception processing module processes the abnormal video frame data.
- the embodiment of the invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, and may also be based on the type of the video frame data or the preset Video quality detection accuracy selects active video quality detection or passive video quality detection for video frame data, and then performs video quality detection on video frame data according to active video quality detection algorithm or passive video quality detection algorithm to obtain abnormality Video frame data.
- the embodiment of the invention can simultaneously support passive video quality detection and active video quality detection, enrich the video quality detection mode, improve the flexibility of video quality detection, ensure the accuracy of video quality detection, and improve video quality detection. user experience.
- FIG. 2 is a schematic flowchart diagram of a second embodiment of a method for detecting video quality according to an embodiment of the present invention.
- the method for video quality detection described in this embodiment includes the following steps:
- the platform for the video quality detection described in the embodiment of the present invention may be a workstation server, that is, the execution body of the video quality detection method described in the embodiment of the present invention may be a workstation server, which is used in the embodiment of the present invention.
- the device for the described video quality detection can be a workstation server.
- the video frame data to be detected needs to be collected, and the video quality detection method described in this embodiment of the present invention can simultaneously detect multiple (ie, at least two) video frame data, that is, Video frame data can be collected from multiple media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame data of a streaming video, and the like, where the customized video may be a video with a video source. It may include recorded video, or produced video, etc.
- the video of the video source may be used for quality detection.
- the above streaming video is a video without a video source, and there is no video source. Passive video quality detection can be used for quality inspection.
- the types that can be included in the customized video are only examples, and are not exhaustive, including but not limited to the above types.
- the embodiments of the present invention do not limit the detection manner of the customized video or the streaming video.
- S202. Perform active video quality detection on the video frame data according to preset video detection conditions.
- the difference image is subjected to black and white binarization processing, and if the pixel value of the difference image is greater than a preset threshold, the pixel value is set to a first pixel value, otherwise the pixel value is Set to the second pixel value.
- the active video quality detection of the video frame data may be directly selected according to the type of the video frame data when detecting the video quality. Specifically, when the collected video frame data is the video frame data of the customized video, the active video quality detection of the video frame data may be selected.
- the user has the accuracy requirement for video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data. Quality detection of video frame data.
- the user may preset the detection precision of the video quality detection, and may include the first detection precision, the second detection precision, and the like. After setting the video quality detection accuracy, the type of the video frame data collected may be combined. Active video quality detection or passive video quality detection on video frame data. In a specific implementation, when the video frame data collected by the video is the video frame data of the customized video with the video source, and the preset video quality detection accuracy is the first detection precision, the customized video may be selected.
- the source video quality detection may further perform active video quality detection on the video frame data collected by the video processing algorithm according to the active video quality detection to obtain abnormal video frame data.
- the selection manner of performing active video quality detection on the collected video frame data according to the preset video detection condition may be any one of the foregoing two description manners, that is, directly according to the video frame.
- the type of data is selected, or it is selected according to the type of video frame data and the accuracy of video quality detection, and no limitation is imposed here.
- the video processing algorithm for the active video quality detection includes: a Gaussian blur processing algorithm, a gray processing algorithm, a synthesis processing algorithm, etc., wherein the processing algorithm is based on a specific
- the processing action is named, not the name of the specific algorithm, but a kind of processing algorithm, which can realize the Gaussian blur processing algorithm for the target image and the reference image, which can be called Gaussian blur processing algorithm, and can perform the target image and the reference image.
- the gray processing algorithm can be called a gray processing algorithm, and the algorithm for synthesizing the target image and the reference image can be called a synthesis processing algorithm.
- the target image of the video frame data when performing active video quality detection on the collected video frame data, may be first acquired, and the target image and the preset reference image are subjected to Gaussian blur processing.
- the target image may be specifically the image to be detected in the video frame data.
- the reference image before performing quality detection on the target image, may be first generated, that is, after the video frame data is collected, a standard reference source is generated according to the collected video frame data, and obtained.
- the reference image may further perform active video quality detection on the collected video frame data according to the reference image.
- the difference of the image may not be seen by the human eye observation, but by comparing the pixels, it may be found that the data of the two images is different, and the Gaussian blurring processing may be Smooths the edges of the image, removing the effects of aliasing and highlighting the main features of the image.
- the Gaussian blurring processing may be Smooths the edges of the image, removing the effects of aliasing and highlighting the main features of the image.
- the processed target image and the reference image may be subjected to grayscale processing, and since the human visual system is more sensitive to brightness than to the chroma, For general video, the chrominance details do not cause appreciable loss.
- the gradation processing of the target image and the reference image can remove the influence of the chrominance signal to better obtain the difference characteristics of the target image and the reference image, and further Get abnormal video frame data.
- the processed target image and the reference image may be combined to obtain a difference image of the target image and the reference image, and then the difference image may be black and white binarized. deal with.
- the human eye when the pixel value of the image is greater than a certain threshold (ie, a preset threshold), the human eye can feel the difference between the target image and the reference image, so the target image and the reference image are synthesized.
- the difference between the two images can be obtained during processing.
- the absolute value of the pixel value can be obtained when the difference between the two images is obtained, so that the value range of the pixel value is between 0 and 255 (due to the pixel of the image)
- the component values are between 0 and 255, so the above pixel values can range from 0 to 255).
- the difference image may be subjected to black and white binarization processing.
- the pixel value of the difference image when the pixel value of the difference image is greater than the preset When the value is wide, the pixel value can be set to the first pixel value (that is, the pixel value can be set to the maximum value, for example, 255), otherwise the pixel value is set to the second pixel value (ie, the pixel can be used)
- the point value is set to a minimum value, such as 0), to better separate the abnormal pixel points from the normal pixel points.
- the pixel point of the pixel value is obtained as the first pixel value, and the abnormal video is obtained. Frame data.
- abnormal video frame data may be acquired, and information such as time when the video abnormality occurs and log information may be recorded as abnormal video frame data.
- the quality detection report further sends a quality detection report of the abnormal video frame data to the video frame exception processing module, so that the video exception processing module processes the abnormal video frame data.
- the embodiment of the invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, and may also be based on the type of the video frame data or the preset Video quality detection accuracy selects active video quality detection for video frame data, and then can perform video quality detection on video frame data according to active video quality detection algorithm, and obtain abnormal video frame data, thereby improving the flexibility of video quality detection. The accuracy of video quality detection is guaranteed, and the user experience of video quality detection is improved.
- FIG. 3 is a schematic flowchart diagram of a third embodiment of a method for detecting video quality according to an embodiment of the present invention.
- the method for video quality detection described in this embodiment includes the following steps:
- the platform for the video quality detection described in the embodiment of the present invention may be a workstation server, that is, the execution body of the video quality detection method described in the embodiment of the present invention may be a workstation server, which is used in the embodiment of the present invention.
- the device for the described video quality detection can be a workstation server.
- the video frame data to be detected needs to be collected, and the video quality detection method described in this embodiment of the present invention can simultaneously detect multiple (ie, at least two) video frame data, that is, Video frame data can be collected from multiple media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame number of the streaming media video, where the customized video may be a video with a video source.
- the above streaming media video is a video without a video source, and the video without the video source can use the passive video quality detection method for quality detection.
- the types that can be included in the customized video are only examples, and are not exhaustive, including but not limited to the above types.
- the embodiments of the present invention do not limit the detection manner of the customized video or the streaming video.
- S302. Perform passive video quality detection on the video frame data according to preset video detection conditions.
- passive video quality detection of video frame data may be directly selected according to the type of video frame data when detecting video quality.
- the video frame data collected by the video is the video frame data of the streaming video
- the passive video quality detection of the video frame data may be selected.
- the user has the accuracy requirement for video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data.
- Quality detection of video frame data Specifically, the user may preset the detection precision of the video quality detection, and may include the first detection precision, the second detection precision, and the like.
- the type of the video frame data collected may be combined. Active video quality detection or passive video quality detection on video frame data. For example, when the video frame data collected by the video is a streaming video without a video source, and the preset video quality detection accuracy is the second detection precision, the passive video quality detection may be selected for the streaming video. Further, according to the video processing algorithm of the passive video quality detection, passive video quality detection is performed on the video frame data collected by the foregoing, and abnormal video frame data is acquired.
- the method for selecting a method for performing passive video quality detection on the collected video frame data according to the preset video detection condition may be any one of the foregoing two description manners, that is, directly The type of the video frame data is selected, or the selection is based on the type of the video frame data and the video quality detection accuracy, and no limitation is imposed here.
- the video processing algorithm for the passive video quality detection includes: The processing algorithm, the edge processing algorithm, the macroblock coding, etc., the above processing algorithm is named according to the specific processing action, not the name of the specific algorithm, but a type of processing algorithm, which can realize the binarization processing of the video image.
- the algorithms can be called binarization algorithms, and the algorithms that can marginalize video images can be called edge processing algorithms.
- the video image of the collected video frame data when performing passive video quality detection on the collected video frame data, may be first binarized according to a binarization processing algorithm, and The video image of the video frame data is edge-processed according to the edge processing algorithm to obtain the main features of the abnormal region of the video image.
- the main features of the anomaly area of the video image include: a mosaic, a flower screen, a black screen, a card, and the like.
- a video quality detection method described in the embodiment of the present invention is specifically described by using a mosaic as an example.
- the mosaic when there is a mosaic anomaly in the video image of the video frame data collected, the mosaic may be represented as a regular square or rectangle, and the video image may be binarized and edged to remove the influence of the mosaic region, highlighting the mosaic.
- the main features of the area After the video image of the video frame data collected by the video is binarized and edged, and the main features of the mosaic are highlighted, the edge of the mosaic can be further extracted.
- the macroblock coding feature is analyzed, and the edge of the mosaic may be a square or a long strip with a fixed side length, and the edge may only appear on a specific line, instead of an irregular shape such as a diagonal line or an arc, and thus, according to The macroblock coding feature can extract the effective edge of the abnormal region of the video image, and the mosaic edge can be extracted.
- the preset abnormal feature template may be used to match the edge of the abnormal region of the video image to obtain abnormal video frame data, for example, due to mosaic
- the edge has a regular shape.
- a fixed template can be used for matching. If the number of template matching success regions is larger than the specified number, the mosaic may be considered to exist in the video image, and then the mosaiced video may be The image is set to an abnormal video image, and abnormal video frame data can be obtained based on the above video image.
- abnormal video frame data after performing video quality detection on the collected video frame data, abnormal video frame data may be acquired, and information such as time when the video abnormality occurs and log information may be recorded as abnormal video frame data.
- the quality detection report and then sends the quality detection report of the abnormal video frame data to the video frame exception processing module, so that the video exception processing module has an abnormal video frame.
- the data is processed.
- the embodiment of the invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, and may also be based on the type of the video frame data or the preset
- the video quality detection precision selects the passive video quality detection of the video frame data, and then the video quality detection of the video frame data according to the passive video quality detection algorithm, and the abnormal video frame data is obtained.
- the embodiment of the invention can support passive video quality detection, improve the practicability of the video quality detection scenario, ensure the accuracy of the video quality detection, and improve the user experience of the video quality detection.
- FIG. 4 it is a schematic structural diagram of a first embodiment of a device for detecting video quality according to an embodiment of the present invention.
- the device for detecting video quality in the embodiment of the present invention includes:
- the collection module 10 is configured to collect video frame data, where the video frame data is derived from at least two media products.
- the selecting module 20 is configured to perform active video quality detection or passive video quality detection on the video frame data according to preset video detection conditions.
- the detecting module 30 is configured to perform active video quality detection on the video frame data according to a video processing algorithm of active video quality detection, or perform passive video on the video frame data according to a video processing algorithm of passive video quality detection. Quality Inspection.
- the sending module 40 is configured to acquire abnormal video frame data, and send the quality detection report of the abnormal video frame data to the video frame exception processing module.
- the apparatus for detecting video quality described in the embodiment of the present invention may specifically be a workstation server.
- the video frame data to be detected may be collected by the collection module 10, and the video quality detection device described in the embodiment of the present invention may simultaneously multiplex (ie, at least two) video frames.
- the data is detected, that is, the collection module 10 can collect video frame data from a plurality of media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame number of the streaming media video, where the customized video may be a video with a video source. It can include recorded video, or produced video, etc.
- the video of the video source can be used for quality detection.
- the above streaming video is video without video source, video without video source. Passive video quality detection can be used for quality inspection.
- the types that can be included in the customized video are only examples, and are not exhaustive, including but not limited to the above types.
- the embodiments of the present invention do not limit the detection manner of the customized video or the streaming video. Implementation For the specific implementation process of the video frame data collection, the step S101 in the first embodiment of the video quality detection method is not described here.
- the selection module 20 when the selection module 20 selects a detection mode for performing video quality detection on the video frame data, the active video quality detection or the passive video quality detection of the video frame data may be directly selected according to the type of the video frame data. Specifically, when the video frame data collected by the collection module 10 is the video frame data of the customized video, the selection module 20 may select to perform active video quality detection on the video frame data, when the collection module 10 collects When the video frame data is the video frame data of the streaming video, the selection module 20 may select to perform passive video quality detection on the video frame data.
- the user has the accuracy requirement for video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data.
- Quality detection of video frame data the user may preset the detection precision of the video quality detection, which may include the first detection precision, the second detection accuracy, and the like.
- the selection module 20 may combine the collected video frame data. The type selection performs active video quality detection or passive video quality detection on the video frame data.
- the selection module 20 may select to perform the customized video.
- the source video quality detection can further perform active video quality detection on the video frame data collected by the collection module 10 by the detection module 30.
- the detecting module 30 may perform active video quality detection on the video frame data collected by the video processing algorithm according to the active video quality detection to obtain abnormal video frame data; and collect video from the video module 10
- the selection module 20 may select the passive video quality detection for the streaming video, and then pass the detection module 30.
- Passive video quality detection is performed on the video frame data collected by the collection module 10.
- the detecting module 30 may perform the passive video quality detection on the video frame data collected by the video processing algorithm according to the passive video quality detection to obtain abnormal video frame data.
- the selection manner of the method for selecting the active video quality detection or the passive video quality detection for the video frame data collected by the selection module 20 according to the preset video detection condition may be the foregoing two descriptions. Any one of the modes, that is, directly selects according to the type of the video frame data, or selects according to the type of the video frame data and the video quality detection accuracy, and is not limited herein.
- the sending module 40 can acquire abnormal video frame data, and can record the time when the video abnormality occurs and the log information and other information are sorted into the quality detection report of the abnormal video frame data, and then the abnormal video frame is recorded.
- the quality detection report of the data is sent to the video frame exception processing module, so that the video exception processing module processes the abnormal video frame data.
- the device for detecting video quality described in the embodiment of the present invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, or
- the type of video frame data or the preset video quality detection accuracy selects whether the video frame data is subjected to active video quality detection or passive video quality detection, and then the video frame can be based on the active video quality detection algorithm or the passive video quality detection algorithm.
- the data is subjected to video quality detection to obtain abnormal video frame data.
- the device for detecting video quality described in the embodiments of the present invention can simultaneously support passive video quality detection and active video quality detection, enrich the video quality detection mode, improve the flexibility of video quality detection, and ensure video quality detection. Accuracy to improve the user experience of video quality detection.
- FIG. 5 is a schematic structural diagram of a second embodiment of a device for detecting video quality according to an embodiment of the present invention.
- the device for detecting video quality in the embodiment described in the embodiment includes:
- the collection module 10 is configured to collect video frame data, where the video frame data is derived from at least two media products.
- the selecting module 50 selects to perform active video quality detection on the video frame data when the video frame data is video frame data of the customized video, or the predetermined video quality detection accuracy is the first detection precision.
- the detecting module 60 is configured to perform active video quality detection on the video frame data according to a video processing algorithm of active video quality detection.
- the sending module 40 is configured to acquire abnormal video frame data, and send the quality detection report of the abnormal video frame data to the video frame exception processing module.
- the foregoing detecting module 60 includes:
- the first processing unit 61 is configured to acquire a target image of the video frame data, and perform Gaussian blur processing on the target image and the preset reference image.
- a second processing unit 62 configured to perform grayscale processing on the target image and the reference image processed by the first processing unit, and perform synthesis processing on the processed target image and the reference image, Obtaining a difference image of the target image and the reference image.
- the third processing unit 63 is configured to acquire the pixel point whose pixel value is the first pixel value, and obtain abnormal video frame data.
- the apparatus for detecting video quality described in the embodiment of the present invention may specifically be a workstation server.
- the collection module 10 can collect video frame data to be detected, and the apparatus for detecting video quality described in the embodiment of the present invention can simultaneously simultaneously multiplex (ie, at least two) video frame data.
- the detection is performed, that is, the collection module 10 can collect video frame data from a plurality of media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame number of the streaming media video, where the customized video may be a video with a video source. It can include recorded video, or produced video, etc.
- the video of the video source can be used for quality detection.
- the above streaming video is video without video source, video without video source. Passive video quality detection can be used for quality inspection.
- the types that can be included in the customized video are only examples, and are not exhaustive, including but not limited to the above types.
- the embodiments of the present invention do not limit the detection manner of the customized video or the streaming video.
- the step S201 in the first embodiment of the method for detecting video quality according to the embodiment of the present invention is not described herein.
- the active video quality detection of the video frame data may be directly selected according to the type of the video frame data.
- the video frame data collected by the collection module 10 is the video frame data of the customized video
- the selection module 50 may select to perform active video quality detection on the video frame data.
- the user has the accuracy requirement for video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data. Quality detection of video frame data.
- the user may preset the detection accuracy of the video quality detection, and may include the first detection precision, the second detection accuracy, and the like.
- the selection module 50 may be combined with the collection module 10
- the type of video frame data is selected for active video quality detection of video frame data.
- the selecting module 50 may select the above customization. After the video is subjected to active video quality detection, the selection module 50 selects the active video quality detection for the customized video, and the detection module 60 can perform the above-mentioned collection according to the video processing algorithm of the active video quality detection.
- the obtained video frame data is subjected to active video quality detection to obtain abnormal video frame data.
- the selection mode of the selection module 50 for performing active video quality detection on the video frame data collected by the video detection condition according to the type of the video frame data or the video quality detection accuracy may be the above two descriptions. Any one of the modes, that is, directly selects according to the type of the video frame data, or selects according to the type of the video frame data and the video quality detection accuracy, and is not limited herein.
- the video processing algorithm for the active video quality detection includes: a Gaussian blur processing algorithm, a gray processing algorithm, a synthesis processing algorithm, etc.
- the processing algorithm is named according to a specific processing action, not a specific algorithm.
- the name, but a class of processing algorithms, the algorithm that can achieve Gaussian blur processing on the target image and the reference image can be called Gaussian blur processing algorithm, and the algorithm for grayscale processing of the target image and the reference image can be called
- a synthesis processing algorithm or the like an algorithm that can perform synthesis processing on the target image and the reference image can be referred to as a synthesis processing algorithm or the like.
- the target image of the video frame data may be first acquired by the first processing unit 61, and the target image and the target image are The set reference image is subjected to Gaussian blurring processing, wherein the target image may be an image to be detected in the video frame data.
- the reference image before the quality detection of the target image, the reference image may be first generated, that is, after the video frame data is collected, a standard reference source is generated according to the collected video frame data, and the reference source is obtained.
- the reference image may further perform active video quality detection on the collected video frame data according to the reference image.
- Unit 61 performs Gaussian blurring on the target image and the reference image to smooth the edges of the image, removing the effects of aliasing and highlighting the main features of the image.
- Gaussian blurring By performing Gaussian blurring on the target image and the reference image, the sawtooth effect of the edge of the image can be removed, and the edge data which has little influence on the human eye observation can be removed, and the target image and the reference image can be further detected to find the abnormality.
- Video frame data is performed.
- the second processing unit 62 may perform gray processing on the target image and the reference image processed by the first processing unit 61, due to human vision.
- the sensitivity of the system to brightness is higher than the sensitivity to chromaticity.
- chromaticity details do not cause appreciable loss, and the target image and the reference image are grayed out by the second processing unit 62, which can be removed.
- the influence of the chrominance signal to better acquire the difference characteristics of the target image and the reference image, thereby acquiring abnormal video frame data.
- Second processing unit 62 on the target map After the gradation processing is performed on the image and the reference image, the processed target image and the reference image may be combined to obtain a difference image between the target image and the reference image, and then the difference image may be subjected to black and white binarization processing.
- a certain threshold ie, a preset threshold
- the human eye can feel the difference between the target image and the reference image, so the target image and the reference image are synthesized. The difference between the two images can be obtained during processing.
- the absolute value of the pixel value can be obtained when the difference between the two images is obtained, so that the value range of the pixel value is between 0 and 255 (due to the pixel of the image)
- the component values are between 0 and 255, so the above pixel values can range from 0 to 255).
- the difference image may be subjected to black and white binarization processing. Specifically, when the pixel value of the difference image is greater than a preset threshold, the pixel value may be set.
- the pixel value can be set to a maximum value, such as 255
- the pixel value is set to the second pixel value (ie, the pixel value can be set to a minimum value, such as 0)
- the pixel with the pixel value as the first pixel value may be acquired by the third processing unit 63. Point, get the abnormal video frame data.
- the third implementation of the video quality detection method provided by the embodiment of the present invention may be referred to as a specific implementation process for selecting the active video quality detection of the video frame data and the quality detection of the video frame data. Steps S202-S206 in the example are not described herein again.
- the sending module 40 may acquire abnormal video frame data, and may record the time when the video abnormality occurs.
- the information such as the log information is sorted into a quality detection report of the abnormal video frame data, and the quality detection report of the abnormal video frame data is sent to the video frame exception processing module, so that the video abnormality processing module processes the abnormal video frame data.
- the specific implementation process of the quality detection report that the sending module obtains and sends the abnormal video frame data may be referred to step S207 in the third embodiment of the video quality detection method provided by the embodiment of the present invention, and details are not described herein again. .
- the device for detecting video quality described in the embodiment of the present invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, or
- the type of video frame data or the preset video quality detection accuracy is selected to perform active video quality detection on the video frame data, and then the number of video frames can be determined according to the active video quality detection algorithm.
- the video quality detection abnormal video frame data is obtained.
- the embodiment of the invention can simultaneously support passive video quality detection and active video quality detection, enrich the video quality detection mode, improve the flexibility of video quality detection, ensure the accuracy of video quality detection, and improve video quality detection. user experience.
- FIG. 6 is a schematic structural diagram of a third embodiment of an apparatus for detecting video quality according to an embodiment of the present invention.
- the device for detecting video quality in this embodiment includes:
- the collection module 10 is configured to collect video frame data, where the video frame data is derived from at least two media products.
- the selecting module 70 is configured to perform passive video quality detection on the video frame data when the video frame data is video frame data of the streaming video, or the predetermined video quality detection accuracy is the second detection precision.
- the detecting module 80 is configured to perform passive video quality detection on the video frame data according to a video processing algorithm for passive video quality detection.
- the sending module 40 is configured to acquire abnormal video frame data, and send the quality detection report of the abnormal video frame data to the video frame exception processing module.
- the foregoing detecting module 80 includes:
- a fourth processing unit 81 configured to perform binarization processing on the video image of the video frame data according to the binarization processing algorithm, and perform edge on the video image of the video frame data according to the edged processing algorithm Processing, acquiring main features of the abnormal region of the video image.
- the fifth processing unit 82 is configured to extract an effective edge of the video image abnormal region according to the macroblock encoding feature, and use the preset abnormal feature template to match an edge of the video image abnormal region to obtain abnormal video frame data. .
- the apparatus for detecting video quality described in the embodiment of the present invention may specifically be a workstation server.
- the video frame data to be detected may be collected by the collection module 10, and the video quality detection device described in the embodiment of the present invention may simultaneously multiplex (ie, at least two) video frames.
- the data is detected, that is, the collection module 10 can collect video frame data from a plurality of media files.
- the video frame data in the embodiment of the present invention may include a video frame data of a customized video, or a video frame number of the streaming media video, where the customized video may be a video with a video source.
- the active video quality detection method can be used for quality detection; the above streaming video is a video without a video source, and the video without a video source can use a passive video quality detection method for quality detection.
- the types that can be included in the customized video are only examples, and are not exhaustive, including but not limited to the above types.
- the embodiments of the present invention do not limit the detection manner of the customized video or the streaming video.
- the specific implementation process of the video frame data to be detected by the foregoing collection module may be referred to step S301 in the first embodiment of the video quality detection method provided by the embodiment of the present invention, and details are not described herein again.
- the selection module 70 selects a detection mode for performing video quality detection on the video frame data
- the active video quality detection or the passive video quality detection may be directly selected according to the type of the video frame data.
- the selection module 70 may select to perform passive video quality detection on the video frame data.
- the user has the accuracy requirement for video quality detection, that is, the user can determine the video quality detection accuracy according to actual needs, and after determining the video quality detection accuracy, the corresponding video quality detection mode can be selected according to the type of the video frame data. Quality detection of video frame data.
- the user may preset the detection precision of the video quality detection, and may include the first detection precision, the second detection precision, and the like.
- the selection module 70 may be combined with the collection module 10
- the type of video frame data is selected to perform active video quality detection or passive video quality detection on the video frame data (in this embodiment, mainly for passive quality detection of video frame data).
- the selection module 70 may select the streaming video. Passive video quality detection is performed, and then video quality detection of the video frame data collected by the collection module 10 can be performed by the detection module 80.
- the detecting module 80 may perform passive video quality detection on the video frame data collected by the video processing algorithm according to the passive video quality detection to obtain abnormal video frame data.
- the selecting module 70 selects a passive video quality detection method for the collected video frame data according to the type of the video frame data or the video quality detection accuracy, and may be any one of the foregoing two description manners.
- the type is directly selected according to the type of the video frame data, or is selected according to the type of the video frame data and the video quality detection accuracy, and is not limited herein.
- the video processing algorithm for the passive video quality detection includes: a binarization processing algorithm, an edge processing algorithm, a macroblock encoding, etc., where the processing algorithm is named according to a specific processing action, not specific The name of the algorithm, but a type of processing algorithm, the algorithm that can realize the binarization processing of the video image can be called the binarization processing algorithm.
- Algorithms for marginalizing video images can be referred to as edge processing algorithms and the like.
- the detection module 80 when the detection module 80 performs passive video quality detection on the video frame data collected by the collection module 10, the detection module 80 may first collect the collected data according to the binarization processing algorithm by the fourth processing unit 81.
- the video image of the video frame data is binarized, and the video image of the video frame data is edge-processed according to the edge processing algorithm to obtain the main features of the abnormal region of the video image.
- the main features of the anomalous area of the video image include: a mosaic, a flower screen, a black screen, a card, and the like.
- a video quality detection method described in the embodiment of the present invention is specifically described by using a mosaic as an example.
- the video image when there is a mosaic abnormality in the video image of the video frame data collected by the collection module 10, the video image may be binarized and edged by the fourth processing unit 81 because the mosaic may be expressed as a regular square or rectangle.
- the treatment removes the influence of the mosaic area and highlights the main features of the mosaic area.
- the video image of the video frame data collected by the collection module 10 is subjected to binarization processing and edge processing by the fourth processing unit 81. After highlighting the main features of the mosaic, the mosaic may be further extracted by the fifth processing unit 82. the edge of.
- the edge of the mosaic may be a square or a long strip with a fixed side length, and the edge will only appear on a specific line, instead of an irregular shape such as a slash or an arc, and thus,
- the five processing unit 82 can extract the effective edge of the abnormal region of the video image according to the macroblock coding feature, and the mosaic edge can be extracted.
- the preset abnormal feature template may be used to match the edge of the video image abnormal region to obtain abnormal video frame data.
- the edge of the mosaic has a regular shape
- the fifth processing unit 83 extracts the mosaic edge
- the fixed template can be used for matching. If the number of successful template matching regions is greater than the specified number, the mosaic may be considered to exist in the video image. Further, the video image in which the mosaic is present may be set as an abnormal video image, and abnormal video frame data may be obtained based on the video image.
- the third implementation of the video quality detection method provided by the embodiment of the present invention may be referred to as the specific implementation process of the above-mentioned selection module and the detection module for performing passive video quality detection on the video frame data and performing quality detection on the video frame data. Steps S302-S304 in the example are not described herein again.
- the sending module 40 may acquire abnormal video frame data, and may record the time and log of the video abnormality occurrence. Information such as information is organized into a quality detection report of abnormal video frame data, and then a quality detection report of abnormal video frame data is sent to the video frame exception processing module. So that the video exception processing module processes the abnormal video frame data.
- the specific implementation process of the quality detection report that the sending module obtains and sends the abnormal video frame data may be referred to step S305 in the third embodiment of the video quality detecting method provided by the embodiment of the present invention, and details are not described herein again. .
- the device for detecting video quality described in the embodiment of the present invention can simultaneously collect the video frame data decoded by the multi-channel media file, and simultaneously perform video quality detection on the video frame data decoded by the multi-channel media file, or
- the type of the video frame data or the preset video quality detection accuracy is selected to perform passive video quality detection on the video frame data, and then the video quality detection of the video frame data may be performed according to the passive video quality detection algorithm to obtain abnormal video frame data.
- the embodiment of the invention can support passive video quality detection, improve the practicability of the video quality detection scenario, ensure the accuracy of the video quality detection, and improve the user experience of the video quality detection.
- the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2014/077008 WO2015168893A1 (zh) | 2014-05-08 | 2014-05-08 | 一种视频质量检测的方法及装置 |
EP14891479.9A EP3076674B1 (en) | 2014-05-08 | 2014-05-08 | Video quality detection method and device |
US15/107,320 US20170006281A1 (en) | 2014-05-08 | 2014-05-08 | Video Quality Detection Method and Apparatus |
CN201480028464.1A CN105264896A (zh) | 2014-05-08 | 2014-05-08 | 一种视频质量检测的方法及装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2014/077008 WO2015168893A1 (zh) | 2014-05-08 | 2014-05-08 | 一种视频质量检测的方法及装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015168893A1 true WO2015168893A1 (zh) | 2015-11-12 |
Family
ID=54391981
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2014/077008 WO2015168893A1 (zh) | 2014-05-08 | 2014-05-08 | 一种视频质量检测的方法及装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20170006281A1 (zh) |
EP (1) | EP3076674B1 (zh) |
CN (1) | CN105264896A (zh) |
WO (1) | WO2015168893A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108540792A (zh) * | 2017-03-02 | 2018-09-14 | 中国移动通信有限公司研究院 | 一种视频质量测量方法及装置 |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110324665A (zh) * | 2019-07-25 | 2019-10-11 | 深圳创维-Rgb电子有限公司 | 一种自动审片的方法、终端及存储介质 |
CN112383676B (zh) * | 2020-11-03 | 2024-02-09 | 北京百度网讯科技有限公司 | 一种视频文件处理方法、装置、电子设备以及存储介质 |
CN113286197A (zh) * | 2021-05-14 | 2021-08-20 | 北京字跳网络技术有限公司 | 信息展示方法、装置、电子设备和存储介质 |
CN114928740A (zh) * | 2021-11-25 | 2022-08-19 | 广东利通科技投资有限公司 | 视频质量检测方法、装置、设备、存储介质和程序产品 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542282A (zh) * | 2010-12-16 | 2012-07-04 | 北京大学 | 一种无源图像马赛克检测方法及装置 |
CN102685545A (zh) * | 2011-03-18 | 2012-09-19 | 特克特朗尼克国际销售有限责任公司 | 视频数据流评价系统和方法 |
CN102740121A (zh) * | 2012-07-11 | 2012-10-17 | 赛特斯网络科技(南京)有限责任公司 | 应用于视频监控网络的视频质量诊断控制系统及方法 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9113147B2 (en) * | 2005-09-27 | 2015-08-18 | Qualcomm Incorporated | Scalability techniques based on content information |
WO2009007133A2 (en) * | 2007-07-11 | 2009-01-15 | Technische Universität München | Method and apparatus for determining the visual quality of processed visual information |
CN101477620B (zh) * | 2008-12-31 | 2010-11-03 | 清华大学 | 用于汽车防盗的两级图像异动检测方法 |
US8520734B1 (en) * | 2009-07-31 | 2013-08-27 | Teradici Corporation | Method and system for remotely communicating a computer rendered image sequence |
US20110271307A1 (en) * | 2009-12-18 | 2011-11-03 | Tektronix International Sales Gmbh | Video data stream evaluation systems and methods |
US20110221895A1 (en) * | 2010-03-10 | 2011-09-15 | Vinay Sharma | Detection of Movement of a Stationary Video Camera |
CN102118629B (zh) * | 2011-03-30 | 2014-04-09 | 上海美琦浦悦通讯科技有限公司 | 基于监控平台的网络视频监控服务质量保障系统及方法 |
CN104246823A (zh) * | 2011-11-24 | 2014-12-24 | 汤姆逊许可公司 | 基于图像内容的伪像检测方案的方法和装置 |
US10389780B2 (en) * | 2012-02-08 | 2019-08-20 | Arris Enterprises Llc | Managed adaptive streaming |
CN102685547B (zh) * | 2012-04-26 | 2014-02-05 | 华北电力大学 | 一种基于块效应和噪声的低码率视频质量检测方法 |
-
2014
- 2014-05-08 US US15/107,320 patent/US20170006281A1/en not_active Abandoned
- 2014-05-08 CN CN201480028464.1A patent/CN105264896A/zh active Pending
- 2014-05-08 EP EP14891479.9A patent/EP3076674B1/en active Active
- 2014-05-08 WO PCT/CN2014/077008 patent/WO2015168893A1/zh active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542282A (zh) * | 2010-12-16 | 2012-07-04 | 北京大学 | 一种无源图像马赛克检测方法及装置 |
CN102685545A (zh) * | 2011-03-18 | 2012-09-19 | 特克特朗尼克国际销售有限责任公司 | 视频数据流评价系统和方法 |
CN102740121A (zh) * | 2012-07-11 | 2012-10-17 | 赛特斯网络科技(南京)有限责任公司 | 应用于视频监控网络的视频质量诊断控制系统及方法 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108540792A (zh) * | 2017-03-02 | 2018-09-14 | 中国移动通信有限公司研究院 | 一种视频质量测量方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
EP3076674A1 (en) | 2016-10-05 |
EP3076674B1 (en) | 2018-09-05 |
CN105264896A (zh) | 2016-01-20 |
EP3076674A4 (en) | 2017-01-25 |
US20170006281A1 (en) | 2017-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8406462B2 (en) | Signature derivation for images | |
US9888171B2 (en) | Mobile camera device capable of improving facial patterns of a captured image | |
WO2015168893A1 (zh) | 一种视频质量检测的方法及装置 | |
CN111695540B (zh) | 视频边框识别方法及裁剪方法、装置、电子设备及介质 | |
CN110366001B (zh) | 视频清晰度的确定方法和装置、存储介质、电子装置 | |
US9594958B2 (en) | Detection of spoofing attacks for video-based authentication | |
WO2014044158A1 (zh) | 一种图像中的目标物体识别方法及装置 | |
US9310908B2 (en) | Color sampling method and touch control device thereof | |
TW201541364A (zh) | 影像處理裝置及處理方法 | |
US11107206B2 (en) | Techniques for detecting spatial anomalies in video content | |
CN107886518B (zh) | 图片检测方法、装置、电子设备及可读取存储介质 | |
KR101336240B1 (ko) | 저장된 영상을 이용한 영상 처리 방법 및 장치 | |
JP6819445B2 (ja) | 情報処理装置、制御方法、及びプログラム | |
CN112073713B (zh) | 视频漏录测试方法、装置、设备及存储介质 | |
CN112672102B (zh) | 一种视频生成方法及装置 | |
WO2017113735A1 (zh) | 一种视频格式区分方法及系统 | |
US8538142B2 (en) | Face-detection processing methods, image processing devices, and articles of manufacture | |
JPWO2021112205A5 (zh) | ||
CN112801932A (zh) | 图像显示方法、装置、电子设备和存储介质 | |
Chen et al. | No-reference video quality assessment on mobile devices | |
JP6504708B2 (ja) | 前景領域における被写体の重なりを識別する識別装置、識別方法及びコンピュータ可読記憶媒体 | |
CN108122214B (zh) | 一种去除伪色的方法及装置 | |
JP2017117066A (ja) | 画像処理方法、画像処理装置および画像処理プログラム | |
US9031348B2 (en) | Edge-preserving filtering method and apparatus | |
US20130223729A1 (en) | Identifying points of interest in an image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201480028464.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14891479 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15107320 Country of ref document: US |
|
REEP | Request for entry into the european phase |
Ref document number: 2014891479 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014891479 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |