WO2021169632A1 - 视频质量检测方法、装置和计算机设备 - Google Patents

视频质量检测方法、装置和计算机设备 Download PDF

Info

Publication number
WO2021169632A1
WO2021169632A1 PCT/CN2021/071066 CN2021071066W WO2021169632A1 WO 2021169632 A1 WO2021169632 A1 WO 2021169632A1 CN 2021071066 W CN2021071066 W CN 2021071066W WO 2021169632 A1 WO2021169632 A1 WO 2021169632A1
Authority
WO
WIPO (PCT)
Prior art keywords
duration
detection result
audio quality
recording
audio
Prior art date
Application number
PCT/CN2021/071066
Other languages
English (en)
French (fr)
Inventor
朱敏
Original Assignee
深圳壹账通智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2021169632A1 publication Critical patent/WO2021169632A1/zh

Links

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
    • 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
    • H04N17/00—Diagnosis, testing or measuring for television systems or their details
    • 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
    • H04N21/233—Processing of audio elementary streams
    • 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
    • H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
    • H04N21/4334—Recording operations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording

Definitions

  • This application relates to the field of computer technology, in particular to a video quality detection method, device, computer equipment and storage medium.
  • the inventor realizes that when users currently record videos, due to software versions or terminal system problems, the video images and audio data in the video are prone to be incompatible with the audio data, and there may even be a problem that audio data is not recorded. If the user does not manually click to check whether the recorded video is normal before uploading, it is difficult to find that there is a problem with the quality of the video.
  • a video quality detection method comprising: when the start of video recording is detected, obtaining a video segment to be detected with a preset recording duration in real time; extracting audio data contained in the video segment to be detected; Format information to detect the duration of the audio data; perform duration detection according to the duration of the audio data and the duration of the video segment to be detected to obtain a duration detection result, the duration detection result including duration anomalies and duration anomalies; for the audio data Perform analysis to obtain pulse code modulation data; perform audio quality detection on the pulse code modulation data based on a preset decibel range to obtain audio quality detection results, where the audio quality detection results include audio quality abnormalities and audio quality abnormalities; according to the The duration detection result and the audio quality detection result monitor the video recording.
  • a video quality detection device includes: a recording start detection module, used to obtain a video segment to be detected with a preset recording duration in real time when the start of video recording is detected; an audio data extraction module, used to extract the to-be-detected video segment Detect audio data contained in the video segment; audio data duration acquisition module for detecting the duration of the audio data according to the format information of the audio data; duration detection module for detecting the duration of the audio data and the video segment to be detected Perform a duration detection on the duration of, and obtain duration detection results, the duration detection results include duration abnormalities and duration abnormalities; audio data analysis module for analyzing the audio data to obtain pulse code modulation data; audio quality detection module for Perform audio quality detection on the pulse code modulation data based on a preset decibel range to obtain audio quality detection results.
  • the audio quality detection results include audio quality abnormalities and audio quality abnormalities; a video recording monitoring module is configured to The detection result and the audio quality detection result monitor the video recording.
  • a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the above video quality detection method when the computer program is executed.
  • the video quality detection method includes the following steps: when a video recording is detected At the beginning, obtain the video segment to be detected with the preset recording duration in real time; extract the audio data contained in the video segment to be detected; detect the duration of the audio data according to the format information of the audio data; according to the duration of the audio data Perform duration detection with the duration of the video segment to be detected to obtain duration detection results, the duration detection results including duration abnormalities and duration abnormalities; analyze the audio data to obtain pulse code modulation data; The pulse code modulation data is subjected to audio quality detection to obtain audio quality detection results.
  • the audio quality detection results include audio quality abnormalities and audio quality abnormalities; video recording is monitored according to the duration detection results and the audio quality detection results.
  • This application can promptly remind the recording of abnormal conditions and make timely adjustments to avoid the poor quality of the video recording, leading to the problem of re-recording, and improve the efficiency of video recording.
  • Fig. 1 is an application scenario diagram of a video quality detection method in an embodiment.
  • Fig. 2 is a schematic flowchart of a video quality detection method in an embodiment.
  • Fig. 3 is a structural block diagram of a video quality detection device in an embodiment.
  • Fig. 4 is a structural block diagram of a video quality detection device in another embodiment.
  • Fig. 5 is an internal structure diagram of a computer device in an embodiment.
  • the technical solution of this application can be applied to the fields of artificial intelligence, smart city, blockchain and/or big data technology.
  • the data involved in this application such as the video segment to be detected, the duration detection result, and/or the monitored information, can be stored in a database, or can be stored in a blockchain, such as distributed storage through a blockchain.
  • the application is not limited.
  • the video quality detection method provided in this application can be applied to the application environment as shown in FIG. 1.
  • the video quality detection method involves the recording terminal 102, and may also involve the server 104, where the recording terminal 102 communicates with the server 104 through the network.
  • the recording terminal 102 detects the start of video recording, it obtains the video segment to be detected with the preset recording duration in real time; extracts the audio data contained in the video segment to be detected; detects the duration of the audio data according to the format information of the audio data ; Perform duration detection according to the duration of the audio data and the duration of the video segment to be detected to obtain the duration detection result, which includes duration anomalies and duration anomalies; parse the audio data to obtain pulse code modulation data; pair based on the preset decibel range Pulse code modulation data is used for audio quality detection, and audio quality detection results are obtained.
  • the audio quality detection results include audio quality abnormalities and audio quality abnormalities; video recording is monitored based on the duration detection results and audio quality detection results.
  • the server 104 When it comes to the recording terminal 102 and the server 104, when the server 104 detects the start of video recording, it acquires the video segment to be detected for the preset recording time from the recording terminal 102 in real time; the server 104 extracts the audio data of the video segment to be detected to obtain To the audio data in the video segment to be detected; extract the audio data contained in the video segment to be detected; detect the duration of the audio data according to the format information of the audio data; perform the duration detection according to the duration of the audio data and the duration of the video segment to be detected to obtain the duration Detection results, duration detection results include duration anomalies and duration anomalies; parse the audio data to obtain pulse code modulation data; perform audio quality detection on pulse code modulation data based on the preset decibel range to obtain audio quality detection results and audio quality detection results Including audio quality abnormalities and audio quality abnormalities; the server 104 monitors the video recording according to the duration detection result and the audio quality detection result.
  • the recording terminal 102 may be, but is not limited to
  • a video quality detection method is provided, and the method is applied to the server in FIG. 1 as an example for description, including the following steps.
  • step S220 when the start of video recording is detected, a to-be-detected video segment with a preset recording duration is acquired in real time.
  • the detection of the start of video recording can be to determine that the video recording is started when the recording instruction is received, or it can be to determine that the video recording is started when the recording video function of the recording terminal is turned on, or it can be obtained after the recording instruction is received.
  • the preset recording duration is used to determine the time point to obtain the video segment to be detected.
  • the preset recording duration can be set according to the accuracy and rationality of the detection, such as: the preset recording duration is set to 2 seconds, when the recorded video reaches 2 seconds , Obtain these 2 seconds of video as the video segment to be detected.
  • the recording terminal is controlled to start video shooting. After the video shooting is turned on, the video recording starts, and the server corresponding to the video collection platform records the currently recorded video frame in real time , When the video duration reaches the preset recording duration, the video with the preset recording duration is regarded as the video segment to be detected.
  • Step S240 Extract audio data contained in the video segment to be detected.
  • the audio data contained in the video segment to be detected refers to the digitized sound data in the video segment to be detected.
  • the audio data in the video segment to be detected can be extracted by calling the audio data extraction tool to obtain the audio data in the video segment to be detected.
  • Step S260 Detect the duration of the audio data according to the format information of the audio data.
  • the duration of the audio data can be analyzed based on the format information of the audio file to obtain the duration of the audio data.
  • the header part stores the format information of the audio file, and through this information
  • Step S280 Perform duration detection according to the duration of the audio data and the duration of the video segment to be detected to obtain a duration detection result.
  • the duration detection result includes a duration abnormality and a duration abnormality.
  • the duration of the video segment to be detected is the preset recording duration of the video segment to be detected.
  • the duration of the audio data can be compared with the duration of the video segment to be detected, and the duration detection result can be determined according to the comparison result. It can be based on the difference between the duration of the audio data and the duration of the video segment to be detected to determine the comparison result. For example, when the duration difference exceeds a certain range, the duration detection result is judged to be an abnormal duration, and when it is within the range, the duration detection result is judged to be The duration is normal.
  • Step S300 Analyze the audio data to obtain pulse code modulation data.
  • the pulse code modulation data is the data obtained after sampling the audio data, then quantizing the sample amplitude, and encoding.
  • To analyze the audio data is to sample the audio data first, then quantize the amplitude of the sample, and then encode to obtain pulse code modulation data.
  • Sampling of audio data can be periodic scanning, turning a continuous signal in time into a discrete signal in time. Quantization discretizes the amplitude of the instantaneous value obtained after sampling to obtain a quantized pulse amplitude modulation signal.
  • Encoding can be a set of binary code groups to represent each quantized value with a fixed level to obtain a binary code, that is, PCM data.
  • Step S320 Perform audio quality detection on the pulse code modulation data based on a preset decibel range to obtain an audio quality detection result.
  • the audio quality detection result includes an abnormal audio quality and an abnormal audio quality.
  • the audio quality detection can be volume detection, which can calculate the volume value of the fragmented data by slicing the pulse code modulation data, and perform audio quality detection according to the volume value.
  • the audio quality detection result is that the audio quality is normal.
  • the audio quality detection result is that the audio quality is abnormal.
  • step S340 the video recording is monitored according to the duration detection result and the audio quality detection result.
  • the recorded video is out of sync with the audio and video according to the result of the duration detection, and whether the volume in the recorded video is too large or too low can be determined according to the result of the audio quality detection.
  • the user can be reminded of the abnormality when the detection result of the length of time is detected as abnormal. Or, when an abnormal audio quality test result is detected, the user will be reminded of the abnormality.
  • the recorded video clip is obtained in real time during the video recording process; the audio data in the video clip is subjected to duration detection and audio quality detection, and the recorded video is judged whether the recorded video is synchronized with audio and video based on the result of the duration detection. Determine whether the volume is abnormal based on the audio quality detection results, and monitor the video recording in real time. It can promptly remind the abnormal situation of the recording and make timely adjustments to avoid the poor quality of the video recording, which causes the problem of re-recording, and improves the efficiency of recording the video.
  • the pulse code modulation data is subjected to audio quality detection based on a preset decibel range to obtain an audio quality detection result.
  • the audio quality detection result includes the steps of abnormal audio quality and abnormal audio quality, including: performing the pulse code modulation data Volume detection, obtain the volume information of the pulse code modulation data; detect the volume information according to the preset decibel range; when the decibel value of the volume information is within the preset decibel range, the audio quality detection result is determined to be normal; when the volume information is The decibel value is not within the preset decibel range, and it is determined that the audio quality detection result is abnormal audio quality.
  • the volume information of the pulse code modulation data refers to the decibel value of the audio data, that is, the volume value.
  • the volume detection method for pulse code modulation data can be to segment the acquired pulse code modulation data (PCM data) to obtain pulse code modulation data segments (PCM data segments), and analyze the large and small end of each segment data to obtain The volume information of the pulse code modulation data. Further detection of audio quality can promptly remind the user of low volume or noise when the current video is being shot, and notify the user to make adjustments in time.
  • the step of performing volume detection on the pulse code modulation data to obtain volume information of the pulse code modulation data includes: segmenting the pulse code modulation data to obtain a pulse code modulation data segment; Analyze the large and small ends of each segment data to obtain the volume information of the pulse code modulation data.
  • the specific steps of analyzing the large and small ends of each segment data of the pulse code modulation data segment analyze the sign (signed/unsigned) of each segment data, and obtain each data according to the bit depth (8/16 bits). For the data of the sampling point, calculate the average value of the sampling point. Based on the dBFS formula, the maximum value calculated by the bit depth (16-bit signed 32767, unsigned 65535) is the denominator (Pref), and the sampling point value is the numerator (Prms) through the formula Calculate the decibel, the calculated number is a negative value, and 0 is the maximum value. Signed 16-bit is -93 ⁇ 0, and unsigned 16-bit is -90 ⁇ 0.
  • the decibel calculated by the dBFS formula is in the negative range, the decibel conversion is performed, and the result is mapped to 0 ⁇ 120db to obtain the corresponding decibel value, that is, the volume information of the pulse code modulation data. Further detection of audio quality can promptly remind the user of low volume or noise when the current video is being shot, and notify the user to make adjustments in time.
  • the duration detection is performed according to the duration of the audio data and the duration of the video segment to be detected to obtain a duration detection result.
  • the duration detection result includes the steps of abnormal duration and abnormal duration, including: according to the duration of the audio data and the video to be detected.
  • the duration of the segment is analyzed by the duration difference to obtain the duration difference; when the current duration difference is within the preset duration difference, the duration detection result is determined to be normal; when the current duration difference is not within the preset duration difference range, the duration detection result is determined to be duration abnormal.
  • the duration difference is analyzed to obtain the duration difference, which can be the duration of the audio data minus the duration of the video segment to be detected, and the difference obtained is the duration difference, or
  • the duration of the video segment to be detected is subtracted from the duration of the audio data, and the difference obtained is the duration difference.
  • the preset duration difference range can be determined according to the accuracy of the audio and picture in the video. The higher the accuracy, the smaller the preset duration difference range.
  • the preset duration difference range can be 0. For example, when the duration difference is 0, the duration detection The result is normal, and all other values are abnormal.
  • Time length detection can promptly remind the user that the picture and audio are out of sync when the current video is being shot, and notify the user to make adjustments in time.
  • the step of monitoring the video recording according to the duration detection result and the audio quality detection result includes: triggering a recording abnormality reminder when the detected duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality Instruction: According to the recording abnormal reminder instruction, the recording terminal is controlled to give a video recording abnormal reminder.
  • the recording abnormality reminding instruction is used to trigger the reminding mechanism of the server, so as to control the recording terminal to remind the video recording abnormality. It can be by triggering the server's reminder mechanism to obtain the corresponding reminder message and send it to the recording terminal. By promptly reminding the detected abnormal situation, the user can make timely adjustments to avoid the poor quality of the video recording, leading to the problem of re-recording, and improve the efficiency of recording video.
  • the video quality detection method further includes: triggering a recording pause instruction when the detected duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality; and controlling the recording terminal to pause video recording according to the recording pause instruction .
  • the recording pause instruction is used to trigger the pause mechanism of the server, thereby controlling the recording terminal to pause video recording. It can be by triggering the pause mechanism of the server to generate a corresponding pause instruction and send it to the recording terminal to make the recording terminal pause video recording.
  • the recording terminal to pause the recording in time when abnormal conditions are detected it can save memory space, reduce the amount of server analysis, improve operating efficiency, and attract the attention of users, and make timely adjustments to avoid the quality of video recording. Poor, leading to re-recording problems, improving the efficiency of recording video.
  • the method further includes: marking the video segment for which the detected duration detection result is duration abnormality or the audio quality detection result is abnormal audio quality ; When playing the recorded video, the mark will be displayed on the progress bar.
  • the user can be that after the user sees the reminder abnormality, adjusts, and then resumes recording on the basis of pause, by marking the video segment with abnormal audio quality as the result of the detected duration detection result or the audio quality detection result as abnormal audio quality.
  • the mark is displayed on the progress bar, and the user can find the abnormal video segment in time, and can efficiently process the abnormal video segment.
  • steps in the flowchart of FIG. 2 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in FIG. 2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution of these sub-steps or stages The sequence is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.
  • a video quality detection device including: a recording start detection module 310, an audio data extraction module 320, an audio data duration acquisition module 330, a duration detection module 340, and audio data analysis Module 350, audio quality detection module 360, and video recording monitoring module 370.
  • the recording start detection module 310 is configured to obtain a video segment to be detected with a preset recording duration in real time when the start of video recording is detected.
  • the audio data extraction module 320 is used to extract audio data contained in the video segment to be detected.
  • the audio data duration acquiring module 330 is configured to detect the duration of the audio data according to the format information of the audio data.
  • the duration detection module 340 is configured to perform duration detection according to the duration of the audio data and the duration of the video segment to be detected, and obtain a duration detection result.
  • the duration detection result includes a duration abnormality and a duration abnormality.
  • the audio data analysis module 350 is used to analyze audio data to obtain pulse code modulation data.
  • the audio quality detection module 360 is configured to perform audio quality detection on the pulse code modulation data based on a preset decibel range to obtain audio quality detection results.
  • the audio quality detection results include audio quality abnormalities and audio quality abnormalities.
  • the video recording monitoring module 370 is configured to monitor the video recording according to the duration detection result and the audio quality detection result.
  • the audio quality detection module 360 is further configured to: perform volume detection on the pulse code modulation data to obtain volume information of the pulse code modulation data; detect the volume information according to a preset decibel range; when the decibel value of the volume information Within the preset decibel range, the audio quality detection result is determined to be normal audio quality; when the decibel value of the volume information is not within the preset decibel range, the audio quality detection result is determined to be abnormal audio quality.
  • the audio quality detection module 360 is further used to: segment the pulse code modulation data to obtain pulse code modulation data segments; analyze the large and small ends of each segment data of the pulse code modulation data segments to obtain pulses Encode and modulate the volume information of the data.
  • the duration detection module 340 is further configured to: perform a duration difference analysis according to the duration of the audio data and the duration of the video segment to be detected to obtain the duration difference; when the current duration difference is within the preset duration difference range, determine the duration detection The result is that the duration is normal; when the current length difference is not within the preset duration difference, the duration detection result is determined to be an abnormal duration.
  • the video recording monitoring module 370 is further configured to: when the detected duration detection result is a duration abnormality or the audio quality detection result is an audio quality abnormality, trigger a recording abnormality reminder instruction; control the recording terminal according to the recording abnormality reminder instruction Remind you of abnormal video recording.
  • the video quality detection device further includes a control module 380: for triggering a recording pause instruction when the detected duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality; Control the recording terminal to pause video recording according to the recording pause instruction.
  • the video quality detection device further includes a marking module 390: for marking a video segment whose duration detection result is abnormal duration or audio quality detection result is abnormal audio quality; when the recorded video is played To display the mark on the progress bar.
  • Each module in the above-mentioned video quality detection device can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
  • a computer device is provided.
  • the computer device may be a server, and its internal structure diagram may be as shown in 5.
  • the computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the processor of the computer device is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium (or may be a volatile storage medium, and a non-volatile storage medium is used as an example for description below) and an internal memory.
  • the non-volatile storage medium stores an operating system, a computer program, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
  • the database of the computer equipment is used to store video data.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer program is executed by the processor to realize a video quality detection method.
  • FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
  • a computer device including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program: when the start of video recording is detected, the preset recording is acquired in real time The length of the video segment to be detected; extract the audio data contained in the video segment to be detected; detect the duration of the audio data according to the format information of the audio data; perform the duration detection according to the duration of the audio data and the duration of the video segment to be detected to obtain the duration detection result, Duration detection results include duration anomalies and duration anomalies; analyze audio data to obtain pulse code modulation data; perform audio quality detection on pulse code modulation data based on a preset decibel range to obtain audio quality detection results, which include audio quality Abnormalities and audio quality abnormalities; monitoring the video recording according to the duration detection result and the audio quality detection result.
  • the processor further implements the following steps when executing the computer program: detecting the volume of the pulse code modulation data to obtain the volume information of the pulse code modulation data; detecting the volume information according to the preset decibel range; If the decibel value is within the preset decibel range, it is determined that the audio quality detection result is normal audio quality; when the decibel value of the volume information is not within the preset decibel range, it is determined that the audio quality detection result is abnormal audio quality.
  • the processor further implements the following steps when executing the computer program: segment the pulse code modulation data to obtain the pulse code modulation data segment; analyze the large and small end of each segment data of the pulse code modulation data segment, Obtain the volume information of the pulse code modulation data.
  • the processor further implements the following steps when executing the computer program: perform a time-length difference analysis according to the duration of the audio data and the duration of the video segment to be detected to obtain the time-length difference; when the time-length difference is within the preset time-length difference range, The time length detection result is determined to be normal; when the time length difference is not within the preset time length difference range, the time length detection result is determined to be abnormal time length.
  • the processor further implements the following steps when executing the computer program: when the detected duration detection result is a duration abnormality or the audio quality detection result is an audio quality abnormality, trigger a recording abnormality reminder instruction; control according to the recording abnormality reminder instruction The recording terminal reminds the video recording abnormality.
  • the processor further implements the following steps when executing the computer program: when the detected duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality, trigger a recording pause instruction; control the recording terminal according to the recording pause instruction Pause video recording.
  • the processor when the processor executes the computer program, the processor further implements the following steps: mark a video segment whose duration detection result is abnormal duration or audio quality detection result is abnormal audio quality; when playing the recorded video, The mark is displayed on the progress bar.
  • a computer-readable storage medium on which a computer program is stored.
  • the following steps are implemented: when the start of video recording is detected, the waiting time of the preset recording time is acquired in real time. Detect the video segment; extract the audio data contained in the video segment to be detected; detect the duration of the audio data according to the format information of the audio data; perform the duration detection according to the duration of the audio data and the duration of the video segment to be detected, and obtain the duration detection result and the duration detection result Including duration anomalies and duration anomalies; parse the audio data to obtain pulse code modulation data; perform audio quality detection on pulse code modulation data based on the preset decibel range to obtain audio quality detection results.
  • the audio quality detection results include audio quality abnormalities and audio The quality is abnormal; the video recording is monitored according to the duration detection result and the audio quality detection result.
  • the following steps are also implemented: perform volume detection on the pulse code modulation data to obtain volume information of the pulse code modulation data; detect the volume information according to the preset decibel range; when the volume information If the decibel value of is within the preset decibel range, it is determined that the audio quality detection result is normal audio quality; when the decibel value of the volume information is not within the preset decibel range, it is determined that the audio quality detection result is abnormal audio quality.
  • the following steps are also implemented: segment the pulse code modulation data to obtain pulse code modulation data segments; analyze the large and small end of each segment data of the pulse code modulation data segment , To obtain the volume information of the pulse code modulation data.
  • the following steps are also implemented: perform a time-length difference analysis according to the duration of the audio data and the duration of the video segment to be detected to obtain the time-length difference; when the time-length difference is within the preset time-length difference range , The time length detection result is determined to be normal; when the time length difference is not within the preset time length difference range, the time length detection result is determined to be abnormal time length.
  • the following steps are further implemented: when the detected duration detection result is a duration abnormality or the audio quality detection result is an audio quality abnormality, trigger a recording abnormality reminding instruction; according to the recording abnormality reminding instruction Control the recording terminal to remind the video recording abnormality.
  • the following steps are also implemented: when the detected duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality, trigger a recording pause instruction; control recording according to the recording pause instruction The terminal pauses video recording.
  • the following steps are further implemented: mark the video segment for which the duration detection result is abnormal duration or the audio quality detection result is abnormal audio quality; when the recorded video is played, The mark is displayed on the progress bar.
  • the storage medium involved in this application such as a computer-readable storage medium, may be non-volatile or volatile.
  • Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing For Digital Recording And Reproducing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

本申请涉及一种视频质量检测方法、装置、计算机设备和存储介质。基于音频检测技术，所述方法包括：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取待检测视频段包含的音频数据；根据音频数据的格式信息检测音频数据的时长；根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果；对音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果；根据时长检测结果和音频质量检测结果对视频录制进行监测。能及时对录制的异常情况进行提醒，及时做出调整，避免视频录制的质量不佳，导致重新录制的问题，提高了录制视频效率。

Description

视频质量检测方法、装置和计算机设备
本申请要求于2020年2月26日提交中国专利局、申请号为202010120954.1，发明名称为“视频质量检测方法、装置和计算机设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，特别是涉及一种视频质量检测方法、装置、计算机设备和存储介质。
 背景技术
随着计算机领域的不断发展，用户录制视频也变的很方便，只需要一台手机就可以进行视频录制，也使得很多短视频在很多领域中得到应用，如：用户可以对身边发生的事情进行记录，并进行分享。在需要进行信息采集的时候，也可以通过让被采集者的通过上传短视频的方式，完成视频采集。
而发明人意识到，目前用户在录制视频时，因为各软件的版本或者是终端系统问题，容易出现视频中的视频画面与音频数据对不上，甚至会出现没有录入音频数据的问题。如果用户在上传之前没有手动点击查看录制的视频是否正常的话，很难发现视频的质量存在问题。
发明人发现，目前用户只能在录制完成视频后，点击播放进行检查，若发现视频有异常时，重新开始录制整个视频，导致录制视频的效率普遍低下。
 技术问题
基于此，有必要针对上述技术问题，提供一种提高录制视频效率的视频质量检测方法、装置、计算机设备和存储介质。
 技术解决方案
一种视频质量检测方法，所述方法包括：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取所述待检测视频段包含的音频数据；根据所述音频数据的格式信息检测所述音频数据的时长；根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；对所述音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
一种视频质量检测装置，所述装置包括：录制开始检测模块，用于当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；音频数据提取模块，用于提取所述待检测视频段包含的音频数据；音频数据时长获取模块，用于根据所述音频数据的格式信息检测所述音频数据的时长；时长检测模块，用于根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；音频数据解析模块，用于对所述音频数据进行解析，获得脉冲编码调制数据；音频质量检测模块，用于基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；视频录制监测模块，用于根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现上述视频质量检测方法，该视频质量检测方法包括以下步骤：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取所述待检测视频段包含的音频数据；根据所述音频数据的格式信息检测所述音频数据的时长；根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；对所述音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述视频质量检测方法，该视频质量检测方法包括以下步骤：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取所述待检测视频段包含的音频数据；根据所述音频数据的格式信息检测所述音频数据的时长；根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；对所述音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
 有益效果
本申请可以及时的对录制的异常情况进行提醒，及时做出调整，避免视频录制的质量不佳，导致重新录制的问题，提高了录制视频效率。
 附图说明
图1为一个实施例中视频质量检测方法的应用场景图。
图2为一个实施例中视频质量检测方法的流程示意图。
图3为一个实施例中视频质量检测装置的结构框图。
图4为另一个实施例中视频质量检测装置的结构框图。
图5为一个实施例中计算机设备的内部结构图。
 本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请的技术方案可应用于人工智能、智慧城市、区块链和/或大数据技术领域。可选的，本申请涉及的数据如待检测视频段、时长检测结果和/或监测的信息等可存储于数据库中，或者可以存储于区块链中，比如通过区块链分布式存储，本申请不做限定。
本申请提供的视频质量检测方法，可以应用于如图1所示的应用环境中。视频质量检测方法涉及录制终端102，还可以涉及服务器104，其中，录制终端102通过网络与服务器104通过网络进行通信。当涉及终端102时，录制终端102当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取待检测视频段包含的音频数据；根据音频数据的格式信息检测音频数据的时长；根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常；对音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常；根据时长检测结果和音频质量检测结果对视频录制进行监测。
当涉及到其中录制终端102和服务器104时，服务器104当检测到视频录制开始时，实时向录制终端102获取预设录制时长的待检测视频段；服务器104对待检测视频段进行音频数据提取，获取到待检测视频段中的音频数据；提取待检测视频段包含的音频数据；根据音频数据的格式信息检测音频数据的时长；根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常；对音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常；服务器104根据时长检测结果和音频质量检测结果对视频录制进行监测。录制终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一个实施例中，如图2所示，提供了一种视频质量检测方法，以该方法应用于图1中的服务器为例进行说明，包括以下步骤。
步骤S220，当检测到视频录制开始时，实时获取预设录制时长的待检测视频段。
其中，检测视频录制开始可以是接收到录制指令时，判定视频录制开始，也可以是检测到录制终端的录制视频功能开启时，判定视频录制开始，还可以是在接收到录制指令后，获取到视频段时，判定视频录制开始。预设录制时长用于确定获取待检测视频段的时间点，预设录制时长可以根据检测的准确性、合理性进行设定，如：预设录制时长设置为2秒，录制视频到达2秒时，获取这2秒的视频作为待检测视频段。
在一个场景中，当用户通过录制终端触发视频收集平台的视频拍摄指令时，控制录制终端开启视频拍摄，开启视频拍摄后，则视频录制开始，视频收集平台对应的服务器实时记录当前录制的视频帧，当视频时长到达预设录制时长时，对预设录制时长的视频作为待检测视频段。
步骤S240，提取待检测视频段包含的音频数据。
其中，待检测视频段包含的音频数据指的是待检测视频段中数字化的声音数据，可以通过调用音频数据提取工具对待检测视频段中的音频数据进行提取，获得待检测视频段中的音频数据。如：MediaCoder（媒体转换软件）、AVI MPEG WMV RM o MP3 Converter（视频格式转音频文件的软件）等等。
步骤S260，根据所述音频数据的格式信息检测所述音频数据的时长。
其中，音频数据的时长可以基于音频文件的格式信息对音频数据进行时长分析，获得音频数据的时长，其中，在音频数据的原始数据中，头部部分存储了音频文件的格式信息，通过这些信息可以获得当前音频的位深度、采样位数及通道数，通过计算获得每秒的数据大小，如：每秒数据大小=采样频率×采样位数×通道数，通过该音频数据的总数据大小/每秒的数据大小，获得音频数据时长。
步骤S280，根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常。
其中，待检测视频段的时长即为该待检测视频段的预设录制时长。可以将音频数据的时长和待检测视频段的时长进行比较，根据比较结果判断时长检测结果。可以是根据音频数据的时长和待检测视频段的时长的时长差，确定比较结果，如：时长差超过一定范围内时，判断时长检测结果为时长异常，在范围内时，判断时长检测结果为时长正常。
步骤S300，对音频数据进行解析，获得脉冲编码调制数据。
其中，脉冲编码调制数据即PCM数据，是对音频数据先抽样，再对样值幅度量化，编码的过程后获得的数据。对音频数据进行解析即是对音频数据先抽样，再对样值幅度量化后，进行编码，获得脉冲编码调制数据。对音频数据抽样可以是进行周期性扫描，把时间上连续的信号变成时间上离散的信号。量化把经过抽样得到的瞬时值将其幅度离散，获得已量化的脉冲幅度调制信号。编码可以是通过一组二进制码组来表示每一个有固定电平的量化值，获得二进制码，即PCM数据。
步骤S320，基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常。
其中，音频质量检测可以是音量检测，可以通过对脉冲编码调制数据进行分片，计算分片数据的音量值，根据音量值进行音频质量检测，当音量值在预设分贝范围内时，音频质量检测结果为音频质量正常，当音量值不在预设分贝范围内时，音频质量检测结果为音频质量异常。
步骤S340，根据时长检测结果和音频质量检测结果对视频录制进行监测。
其中，根据时长检测结果可以判断录制的视频是否出现画音不同步，根据音频质量检测结果可以判断录制的视频中的音量是否太大或者太小。可以在检测到时长检测结果为异常时，对用户进行异常提醒。或在检测到音频质量检测结果为异常时，对用户进行异常提醒。
上述视频质量检测方法中，通过在视频录制过程中，实时获取录制的视频片段；对视频片段中的音频数据进行时长检测及音频质量检测，通过时长检测结果判断录制的视频是不是画音同步，通过音频质量检测结果判断是否音量异常，实时对视频录制进行实时监测。可以及时的对录制的异常情况进行提醒，及时做出调整，避免视频录制的质量不佳，导致重新录制的问题，提高了录制视频效率。
在一个实施例中，基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常的步骤，包括：对脉冲编码调制数据进行音量检测，获得脉冲编码调制数据的音量信息；根据预设分贝范围对音量信息进行检测；当音量信息的分贝值在预设分贝范围内，确定音频质量检测结果为音频质量正常；当音量信息的分贝值不在预设分贝范围内，确定音频质量检测结果为音频质量异常。
其中，脉冲编码调制数据的音量信息指的是音频数据的分贝值，即音量值。对脉冲编码调制数据进行音量检测的方式，可以是对获取的脉冲编码调制数据（PCM数据）进行分段，获得脉冲编码调制数据片段（PCM数据片段），分析各分段数据的大小端，获得脉冲编码调制数据的音量信息。进一步对音频质量进行检测，可以及时的对当前拍摄视频时，出现音量低或者有噪音的情况进行提醒，及时通知用户进行调整。
在一个实施例中，对脉冲编码调制数据进行音量检测，获得脉冲编码调制数据的音量信息的步骤，包括：对脉冲编码调制数据进行分段，获得脉冲编码调制数据片段；对脉冲编码调制数据片段的各分段数据的大小端进行分析，获得脉冲编码调制数据的音量信息。
其中，对脉冲编码调制数据片段的各分段数据的大小端进行分析的具体步骤：分析各分段数据的符号（有符号/无符号），根据位深度（8/16位）来获取每个采样点的数据，计算采样点的平均value，基于dBFS公式，位深度计算出来的最大值（16位有符号32767，无符号65535）为分母（Pref），采样点value为分子（Prms）通过公式计算分贝，计算出来的数字为负值，0为最大值。16位有符号为-93~0，16位无符号位-90~0。通过dBFS公式计算出来的分贝为负数范围，进行分贝换算，将结果等比映射到0~120db，获得对应的分贝值，即脉冲编码调制数据的音量信息。进一步对音频质量进行检测，可以及时的对当前拍摄视频时，出现音量低或者有噪音的情况进行提醒，及时通知用户进行调整。
在一个实施例中，根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常的步骤，包括：根据音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；当时长差在预设时长差范围内时，确定时长检测结果为时长正常；当时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
其中，根据音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差，可以是通过音频数据的时长减去待检测视频段的时长，获得的差值为时长差，也可以是待检测视频段的时长减去音频数据的时长，获得的差值为时长差。预设时长差范围可以根据视频中的音频和画面的精确程度进行确定，精确度越高，预设时长差范围越小，预设时长差范围可以是0，如时长差为0时，时长检测结果为正常，其他值都为异常。也可以是一个区间，如0~2秒之间，也可以是0~2毫秒之间，还可以是0~10毫秒之间等等。通过时长检测可以及时的对当前拍摄视频时，出现画音不同步的情况进行提醒，及时通知用户进行调整。
在一个实施例中，根据时长检测结果和音频质量检测结果对视频录制进行监测的步骤，包括：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制异常提醒指令；根据录制异常提醒指令控制录制终端进行视频录制异常提醒。
其中，录制异常提醒指令用于触发服务器的提醒机制，从而控制录制终端进行视频录制异常提醒。可以是通过触发服务器的提醒机制，获取对应的提醒消息，向录制终端发送。通过对监测到异常情况及时进行提醒，使用户可以及时做出调整，避免视频录制的质量不佳，导致重新录制的问题，提高了录制视频效率。
在一个实施例中，该视频质量检测方法还包括：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制暂停指令；根据录制暂停指令控制录制终端暂停视频录制。
其中，录制暂停指令用于触发服务器的暂停机制，从而控制录制终端暂停视频录制。可以是通过触发服务器的暂停机制，生成对应的暂停指令，向录制终端发送，使录制终端暂停视频录制。通过对监测到异常情况及时控制录制终端暂停录制，可以节省内存空间的占用，还可以减少服务器的分析量，提高运行效率，也可以更引起用户的注意，及时做出调整，避免视频录制的质量不佳，导致重新录制的问题，提高了录制视频效率。
在一个实施例中，在根据录制异常提醒指令控制录制终端进行视频录制异常提醒的步骤之后，还包括：对检测到时长检测结果为时长异常或音频质量检测结果为音频质量异常的视频段进行标记；在播放录制完成的视频时，在进度条上显示该标记。
其中，可以是用户在看到提醒异常，进行调整之后，在暂停的基础上接着录制时，通过对检测到时长检测结果为时长异常或音频质量检测结果为音频质量异常的视频段进行标记，在播放录制完成的视频时，在进度条上显示该标记，用户可以及时找到异常的视频段，可以高效的对异常的视频段进行处理。
应该理解的是，虽然图2的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中，如图3所示，提供了一种视频质量检测装置，包括：录制开始检测模块310、音频数据提取模块320、音频数据时长获取模块330、时长检测模块340、音频数据解析模块350、音频质量检测模块360和视频录制监测模块370。
录制开始检测模块310，用于当检测到视频录制开始时，实时获取预设录制时长的待检测视频段。
音频数据提取模块320，用于提取待检测视频段包含的音频数据。
音频数据时长获取模块330，用于根据音频数据的格式信息检测音频数据的时长。
时长检测模块340，用于根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常。
音频数据解析模块350，用于对音频数据进行解析，获得脉冲编码调制数据。
音频质量检测模块360，用于基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常。
视频录制监测模块370，用于根据时长检测结果和音频质量检测结果对视频录制进行监测。
在一个实施例中，音频质量检测模块360还用于：对脉冲编码调制数据进行音量检测，获得脉冲编码调制数据的音量信息；根据预设分贝范围对音量信息进行检测；当音量信息的分贝值在预设分贝范围内，确定音频质量检测结果为音频质量正常；当音量信息的分贝值不在预设分贝范围内，确定音频质量检测结果为音频质量异常。
在一个实施例中，音频质量检测模块360还用于：对脉冲编码调制数据进行分段，获得脉冲编码调制数据片段；对脉冲编码调制数据片段的各分段数据的大小端进行分析，获得脉冲编码调制数据的音量信息。
在一个实施例中，时长检测模块340还用于：根据音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；当时长差在预设时长差范围内时，确定时长检测结果为时长正常；当时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
在一个实施例中，视频录制监测模块370还用于：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制异常提醒指令；根据录制异常提醒指令控制录制终端进行视频录制异常提醒。
在一个实施例中，请参阅图4，该视频质量检测装置还包括控制模块380：用于当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制暂停指令；根据录制暂停指令控制录制终端暂停视频录制。
在一个实施例中，该视频质量检测装置还包括标记模块390：用于对检测到时长检测结果为时长异常或音频质量检测结果为音频质量异常的视频段进行标记；在播放录制完成的视频时，在进度条上显示该标记。
关于视频质量检测装置的具体限定可以参见上文中对于视频质量检测方法的限定，在此不再赘述。上述视频质量检测装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如5所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质（或者可以为易失性存储介质，下文以非易失性存储介质为例进行说明）、内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储视频数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种视频质量检测方法。
本领域技术人员可以理解，图5中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，该存储器存储有计算机程序，该处理器执行计算机程序时实现以下步骤：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取待检测视频段包含的音频数据；根据音频数据的格式信息检测音频数据的时长；根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常；对音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常；根据时长检测结果和所述音频质量检测结果对视频录制进行监测。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：对脉冲编码调制数据进行音量检测，获得脉冲编码调制数据的音量信息；根据预设分贝范围对音量信息进行检测；当音量信息的分贝值在预设分贝范围内，确定音频质量检测结果为音频质量正常；当音量信息的分贝值不在预设分贝范围内，确定音频质量检测结果为音频质量异常。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：对脉冲编码调制数据进行分段，获得脉冲编码调制数据片段；对脉冲编码调制数据片段的各分段数据的大小端进行分析，获得脉冲编码调制数据的音量信息。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：根据音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；当时长差在预设时长差范围内时，确定时长检测结果为时长正常；当时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制异常提醒指令；根据录制异常提醒指令控制录制终端进行视频录制异常提醒。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制暂停指令；根据录制暂停指令控制录制终端暂停视频录制。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：对检测到时长检测结果为时长异常或音频质量检测结果为音频质量异常的视频段进行标记；在播放录制完成的视频时，在进度条上显示该标记。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现以下步骤：当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；提取待检测视频段包含的音频数据；根据音频数据的格式信息检测音频数据的时长；根据音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，时长检测结果包括时长异常和时长异常；对音频数据进行解析，获得脉冲编码调制数据；基于预设分贝范围对脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，音频质量检测结果包括音频质量异常和音频质量异常；根据时长检测结果和所述音频质量检测结果对视频录制进行监测。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：对脉冲编码调制数据进行音量检测，获得脉冲编码调制数据的音量信息；根据预设分贝范围对音量信息进行检测；当音量信息的分贝值在预设分贝范围内，确定音频质量检测结果为音频质量正常；当音量信息的分贝值不在预设分贝范围内，确定音频质量检测结果为音频质量异常。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：对脉冲编码调制数据进行分段，获得脉冲编码调制数据片段；对脉冲编码调制数据片段的各分段数据的大小端进行分析，获得脉冲编码调制数据的音量信息。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：根据音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；当时长差在预设时长差范围内时，确定时长检测结果为时长正常；当时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制异常提醒指令；根据录制异常提醒指令控制录制终端进行视频录制异常提醒。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：当检测到的时长检测结果为时长异常或音频质量检测结果为音频质量异常时，触发录制暂停指令；根据录制暂停指令控制录制终端暂停视频录制。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：对检测到时长检测结果为时长异常或音频质量检测结果为音频质量异常的视频段进行标记；在播放录制完成的视频时，在进度条上显示该标记。
可选的，本申请涉及的存储介质如计算机可读存储介质可以是非易失性的，也可以是易失性的。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器（ROM）、可编程ROM（PROM）、电可编程ROM（EPROM）、电可擦除可编程ROM（EEPROM）或闪存。易失性存储器可包括随机存取存储器（RAM）或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM（SRAM）、动态RAM（DRAM）、同步DRAM（SDRAM）、双数据率SDRAM（DDRSDRAM）、增强型SDRAM（ESDRAM）、同步链路（Synchlink） DRAM（SLDRAM）、存储器总线（Rambus）直接RAM（RDRAM）、直接存储器总线动态RAM（DRDRAM）、以及存储器总线动态RAM（RDRAM）等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种视频质量检测方法，所述方法包括：
    当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；
    提取所述待检测视频段包含的音频数据；
    根据所述音频数据的格式信息检测所述音频数据的时长；
    根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；
    对所述音频数据进行解析，获得脉冲编码调制数据；
    基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；
    根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
  2. 根据权利要求1所述的方法，其中，所述基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常的步骤，包括：
    对所述脉冲编码调制数据进行音量检测，获得所述脉冲编码调制数据的音量信息；
    根据预设分贝范围对所述音量信息进行检测；
    当所述音量信息的分贝值在所述预设分贝范围内，确定所述音频质量检测结果为音频质量正常；
    当所述音量信息的分贝值不在所述预设分贝范围内，确定所述音频质量检测结果为音频质量异常。
  3. 根据权利要求2所述的方法，其中，所述对所述脉冲编码调制数据进行音量检测，获得所述脉冲编码调制数据的音量信息的步骤，包括：
    对所述脉冲编码调制数据进行分段，获得脉冲编码调制数据片段；
    对所述脉冲编码调制数据片段的各分段数据的大小端进行分析，获得所述脉冲编码调制数据的音量信息。
  4. 根据权利要求1所述的方法，其中，所述根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常的步骤，包括：
    根据所述音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；
    当所述时长差在预设时长差范围内时，确定时长检测结果为时长正常；
    当所述时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
  5. 根据权利要求1所述的方法，其中，所述根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测的步骤，包括：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制异常提醒指令；
    根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制暂停指令；
    根据所述录制暂停指令控制录制终端暂停视频录制。
  7. 根据权利要求5所述的方法，其中，在根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒的步骤之后，还包括：
    对检测到时长检测结果为时长异常或所述音频质量检测结果为音频质量异常的视频段进行标记；
    在播放录制完成的视频时，在进度条上显示该标记。
  8. 一种视频质量检测装置，其中，所述装置包括：
    录制开始检测模块，用于当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；
    音频数据提取模块，用于提取所述待检测视频段包含的音频数据；
    音频数据时长获取模块，用于根据所述音频数据的格式信息检测所述音频数据的时长；
    时长检测模块，用于根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；
    音频数据解析模块，用于对所述音频数据进行解析，获得脉冲编码调制数据；
    音频质量检测模块，用于基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；
    视频录制监测模块，用于根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
  9. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其中，所述处理器执行所述计算机程序时实现以下步骤：
    当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；
    提取所述待检测视频段包含的音频数据；
    根据所述音频数据的格式信息检测所述音频数据的时长；
    根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；
    对所述音频数据进行解析，获得脉冲编码调制数据；
    基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；
    根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
  10. 根据权利要求9所述的计算机设备，其中，所述处理器执行所述基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果的步骤，包括：
    对所述脉冲编码调制数据进行音量检测，获得所述脉冲编码调制数据的音量信息；
    根据预设分贝范围对所述音量信息进行检测；
    当所述音量信息的分贝值在所述预设分贝范围内，确定所述音频质量检测结果为音频质量正常；
    当所述音量信息的分贝值不在所述预设分贝范围内，确定所述音频质量检测结果为音频质量异常。
  11. 根据权利要求9所述的计算机设备，其中，所述处理器执行所述根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果的步骤，包括：
    根据所述音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；
    当所述时长差在预设时长差范围内时，确定时长检测结果为时长正常；
    当所述时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
  12. 根据权利要求9所述的计算机设备，其中，所述处理器执行所述根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测的步骤，包括：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制异常提醒指令；
    根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒。
  13. 根据权利要求12所述的计算机设备，其中，所述处理器执行所述计算机程序时还用于实现：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制暂停指令；
    根据所述录制暂停指令控制录制终端暂停视频录制。
  14. 根据权利要求12所述的计算机设备，其中，在根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒的步骤之后，所述处理器执行所述计算机程序时还用于实现：
    对检测到时长检测结果为时长异常或所述音频质量检测结果为音频质量异常的视频段进行标记；
    在播放录制完成的视频时，在进度条上显示该标记。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现以下方法：
    当检测到视频录制开始时，实时获取预设录制时长的待检测视频段；
    提取所述待检测视频段包含的音频数据；
    根据所述音频数据的格式信息检测所述音频数据的时长；
    根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果，所述时长检测结果包括时长异常和时长异常；
    对所述音频数据进行解析，获得脉冲编码调制数据；
    基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果，所述音频质量检测结果包括音频质量异常和音频质量异常；
    根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测。
  16. 根据权利要求15所述的计算机可读存储介质，其中，所述基于预设分贝范围对所述脉冲编码调制数据进行音频质量检测，获得音频质量检测结果时，具体实现：
    对所述脉冲编码调制数据进行音量检测，获得所述脉冲编码调制数据的音量信息；
    根据预设分贝范围对所述音量信息进行检测；
    当所述音量信息的分贝值在所述预设分贝范围内，确定所述音频质量检测结果为音频质量正常；
    当所述音量信息的分贝值不在所述预设分贝范围内，确定所述音频质量检测结果为音频质量异常。
  17. 根据权利要求15所述的计算机可读存储介质，其中，所述根据所述音频数据的时长和待检测视频段的时长进行时长检测，获得时长检测结果时，具体实现：
    根据所述音频数据的时长和待检测视频段的时长进行时长差分析，获得时长差；
    当所述时长差在预设时长差范围内时，确定时长检测结果为时长正常；
    当所述时长差不在预设时长差范围内时，确定时长检测结果为时长异常。
  18. 根据权利要求15所述的计算机可读存储介质，其中，所述根据所述时长检测结果和所述音频质量检测结果对视频录制进行监测时，具体实现：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制异常提醒指令；
    根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒。
  19. 根据权利要求18所述的计算机可读存储介质，其中，所述计算机程序被处理器执行时还用于实现：
    当检测到的时长检测结果为时长异常或所述音频质量检测结果为音频质量异常时，触发录制暂停指令；
    根据所述录制暂停指令控制录制终端暂停视频录制。
  20. 根据权利要求18所述的计算机可读存储介质，其中，在根据所述录制异常提醒指令控制录制终端进行视频录制异常提醒的步骤之后，所述计算机程序被处理器执行时还用于实现：
    对检测到时长检测结果为时长异常或所述音频质量检测结果为音频质量异常的视频段进行标记；
    在播放录制完成的视频时，在进度条上显示该标记。
PCT/CN2021/071066 2020-02-26 2021-01-11 视频质量检测方法、装置和计算机设备 WO2021169632A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010120954.1A CN111263189B (zh) 2020-02-26 2020-02-26 视频质量检测方法、装置和计算机设备
CN202010120954.1 2020-02-26

Publications (1)

Publication Number Publication Date
WO2021169632A1 true WO2021169632A1 (zh) 2021-09-02

Family

ID=70954595

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/071066 WO2021169632A1 (zh) 2020-02-26 2021-01-11 视频质量检测方法、装置和计算机设备

Country Status (2)

Country Link
CN (1) CN111263189B (zh)
WO (1) WO2021169632A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114422772A (zh) * 2022-01-24 2022-04-29 腾讯科技（深圳）有限公司 多媒体播放质量评估方法、装置、电子设备及存储介质
US20230217060A1 (en) * 2021-12-30 2023-07-06 Comcast Cable Communications, Llc Systems, methods, and apparatuses for buffer management
CN117793339A (zh) * 2023-12-28 2024-03-29 广州市维博网络信息科技有限公司 基于人工智能的视频质量诊断系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111263189B (zh) * 2020-02-26 2023-03-07 深圳壹账通智能科技有限公司 视频质量检测方法、装置和计算机设备
CN114554004A (zh) * 2020-11-27 2022-05-27 北京小米移动软件有限公司 一种录像方法、装置、电子设备及存储介质
CN113660393A (zh) * 2021-07-08 2021-11-16 上海途悠信息科技有限公司 一种服务窗口双录系统
CN114745497A (zh) * 2022-02-23 2022-07-12 浪潮金融信息技术有限公司 一种基于视觉库的音视频双录方法、系统及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105187909A (zh) * 2015-09-09 2015-12-23 深圳Tcl数字技术有限公司 终端检测录制音视频丢失的方法及装置
CN106534980A (zh) * 2016-11-15 2017-03-22 广州华多网络科技有限公司 音频处理系统的异常检测方法、日志记录方法及装置
CN107371053A (zh) * 2017-08-31 2017-11-21 北京鹏润鸿途科技股份有限公司 音频视频流对比分析方法及装置
CN108877837A (zh) * 2018-06-12 2018-11-23 北京小米移动软件有限公司 音频信号异常识别方法、装置和存储介质
US10368177B2 (en) * 2017-11-29 2019-07-30 Fujitsu Limited Abnormality detecting device, abnormality detection method, and recording medium storing abnormality detection computer program
CN111263189A (zh) * 2020-02-26 2020-06-09 深圳壹账通智能科技有限公司 视频质量检测方法、装置和计算机设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007128097A1 (en) * 2006-05-05 2007-11-15 Mariner Partners, Inc. Transient video anomaly analysis and reporting system
CN102103855B (zh) * 2009-12-16 2013-08-07 北京中星微电子有限公司 一种检测音频片段的方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105187909A (zh) * 2015-09-09 2015-12-23 深圳Tcl数字技术有限公司 终端检测录制音视频丢失的方法及装置
CN106534980A (zh) * 2016-11-15 2017-03-22 广州华多网络科技有限公司 音频处理系统的异常检测方法、日志记录方法及装置
CN107371053A (zh) * 2017-08-31 2017-11-21 北京鹏润鸿途科技股份有限公司 音频视频流对比分析方法及装置
US10368177B2 (en) * 2017-11-29 2019-07-30 Fujitsu Limited Abnormality detecting device, abnormality detection method, and recording medium storing abnormality detection computer program
CN108877837A (zh) * 2018-06-12 2018-11-23 北京小米移动软件有限公司 音频信号异常识别方法、装置和存储介质
CN111263189A (zh) * 2020-02-26 2020-06-09 深圳壹账通智能科技有限公司 视频质量检测方法、装置和计算机设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230217060A1 (en) * 2021-12-30 2023-07-06 Comcast Cable Communications, Llc Systems, methods, and apparatuses for buffer management
US11968417B2 (en) * 2021-12-30 2024-04-23 Comcast Cable Communications, Llc Systems, methods, and apparatuses for buffer management
CN114422772A (zh) * 2022-01-24 2022-04-29 腾讯科技（深圳）有限公司 多媒体播放质量评估方法、装置、电子设备及存储介质
CN117793339A (zh) * 2023-12-28 2024-03-29 广州市维博网络信息科技有限公司 基于人工智能的视频质量诊断系统

Also Published As

Publication number Publication date
CN111263189A (zh) 2020-06-09
CN111263189B (zh) 2023-03-07

Similar Documents

Publication Publication Date Title
WO2021169632A1 (zh) 视频质量检测方法、装置和计算机设备
CN109600564B (zh) 用于确定时间戳的方法和装置
CN105049917B (zh) 录制音视频同步时间戳的方法和装置
WO2020024962A1 (zh) 处理数据的方法和装置
US11114133B2 (en) Video recording method and device
CN109144858B (zh) 流畅度检测方法、装置、计算设备及存储介质
CN109788224B (zh) 视频录制方法、装置、网络摄像器及存储介质
CN112511818B (zh) 视频播放质量检测方法、装置
CN110572617B8 (zh) 一种环境监控的处理方法、装置及存储介质
CN109600665B (zh) 用于处理数据的方法和装置
CN109600661B (zh) 用于录制视频的方法和装置
CN106789209B (zh) 异常处理方法和装置
WO2020024960A1 (zh) 处理数据的方法和装置
CN110912948B (zh) 一种问题上报的方法和装置
CN103929607A (zh) 基于屏幕录制的通信方法及应用客户端
CN109308778B (zh) 移动侦测告警方法、装置、采集设备和存储介质
CN109600563B (zh) 用于确定时间戳的方法和装置
CN109600660B (zh) 用于录制视频的方法和装置
US20120134534A1 (en) Control computer and security monitoring method using the same
CN116233411A (zh) 音视频同步测试的方法、装置、设备及计算机存储介质
CN111385637B (zh) 媒体数据编码方法、装置及电子设备
CN116437068A (zh) 一种唇音同步的测试方法、装置、电子设备和存储介质
US11398091B1 (en) Repairing missing frames in recorded video with machine learning
CN109600562B (zh) 用于录制视频的方法和装置
CN108228829B (zh) 用于生成信息的方法和装置

Legal Events

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

Ref document number: 21759908

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04.01.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21759908

Country of ref document: EP

Kind code of ref document: A1