CN114466181A - Video anomaly detection method, device, equipment and system - Google Patents
Video anomaly detection method, device, equipment and system Download PDFInfo
- Publication number
- CN114466181A CN114466181A CN202111643663.1A CN202111643663A CN114466181A CN 114466181 A CN114466181 A CN 114466181A CN 202111643663 A CN202111643663 A CN 202111643663A CN 114466181 A CN114466181 A CN 114466181A
- Authority
- CN
- China
- Prior art keywords
- video
- picture
- frame
- preset
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000012795 verification Methods 0.000 claims abstract description 61
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000000605 extraction Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000012706 support-vector machine Methods 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The invention discloses a video anomaly detection method, a device, equipment and a system. The method comprises the following steps: receiving a preprocessed video, wherein the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance; acquiring a target picture from the preprocessed video according to a preset interval; extracting the pixel information of the specific area in each frame of target picture to generate a check code of the frame of target picture; and generating video abnormal information based on the inconsistency of the check code and the preset original code. The invention can respectively verify each frame of picture in the video, thereby realizing the verification of the condition that the video signal is input, the video format is correct, but the video content is abnormal, finding out the abnormality of the video content in time and sending an alarm, improving the user experience, and avoiding the problem of misjudgment of the user caused by inaccurate displayed video pictures.
Description
Technical Field
The present invention relates to the field of video verification, and in particular, to a method, an apparatus, a device, and a system for detecting video anomalies.
Background
In order to normally display a video image and avoid the situation of video damage or abnormality, the video display terminal needs to detect the video signal when receiving the video signal or after receiving the video signal. In the prior art, there are two main ways of detecting whether a video signal is abnormal at a video display end:
and judging whether a signal is input or not through an interrupt pin provided by a hardware circuit. The hardware circuit of the video input interface may provide an interrupt pin, and a level state of the interrupt pin may indicate whether a PLL (Phase Locked Loop) is Locked, and if not, it is determined that no video signal is currently input, so that it may be determined whether a video signal is input by monitoring the level state of the interrupt pin. However, this method cannot detect a case where a video signal is input but the video content is abnormal.
Whether the video signal meets the format requirement is judged by analyzing the video signal. When receiving video, judging whether the current input video signal is in accordance with the protocol standard through an error detection interface provided by the system, and if so, considering that the format of the received video is normal. However, this method cannot detect a situation where the video format is correct but the video content is abnormal.
Disclosure of Invention
In order to at least partially solve the technical problems in the prior art, the inventor makes the present invention, and provides the following technical solutions through specific embodiments:
in a first aspect, an embodiment of the present invention provides a video anomaly detection method, where the method includes the following steps:
receiving a preprocessed video, wherein the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
acquiring a target picture from the preprocessed video according to a preset interval;
extracting the pixel information of the specific area in each frame of target picture to generate a check code of the frame of target picture;
and generating video abnormal information based on the inconsistency of the check code and the preset original code.
Further, the preset source code is obtained by the following method: extracting pixel information of the specific area of a preset picture to obtain the preset original code; the specific area of the preset picture is provided with the feature identifier.
Further, the algorithm for extracting the pixel information of the specific area specifically includes:
extracting pixel position information and pixel color information of the specific area in the target picture by using a preset extraction matrix; each element in the preset extraction matrix corresponds to each pixel in the target picture one by one, and the element in the preset extraction matrix corresponding to the pixel in the target picture, which is not the specific region, is 0.
Further, the algorithm for extracting the pixel information of the specific area further includes:
converting the extracted pixel color information of the specific region to obtain graphic information formed by non-background pixels in the specific region; the color of each pixel of the feature identifier is divided into a background color and a non-background color.
Further, the converting the extracted pixel color information of the specific region specifically includes:
converting the extracted pixel color information of the specific region, which accords with the non-background color, into first information; alternatively, the first and second electrodes may be,
converting the extracted pixel color information of the specific region, which is in accordance with the non-background color, into first information, and converting the extracted pixel color information of the specific region, which is in accordance with the background color, into second information.
Further, the check code is judged to be inconsistent with the preset original code based on the continuous preset times, and a video error alarm is sent.
In a second aspect, an embodiment of the present invention provides a video anomaly detection method, which is applied to a video editing apparatus, and includes the following steps:
covering a preset feature identifier in a specific area of each frame of picture in an original video to obtain a preprocessed video, wherein the preprocessed video is used for acquiring a target picture from the preprocessed video after being received by a video verification device, extracting pixel information of the specific area in each frame of target picture by the video verification device to generate a verification code of the frame of target picture, and generating video abnormal information based on the fact that the verification code is inconsistent with a preset original code;
and sending the preprocessed video to a video checking device.
In a third aspect, an embodiment of the present invention provides a video verification apparatus, where the video verification apparatus includes:
the video receiving module is used for receiving a preprocessed video, and the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
the picture extraction module is used for acquiring a target picture from the preprocessed video according to a preset interval;
the check code generating module is used for extracting the pixel information of the specific area in each frame of target picture and generating the check code of the array of target pictures;
and the judging module is used for generating video abnormal information based on the inconsistency of the check code and the preset original code.
In a fourth aspect, an embodiment of the present invention provides a video editing apparatus, including:
the identification superposition module is used for covering a preset characteristic identification in a specific area of each frame of picture in an original video to obtain a preprocessed video, the preprocessed video is used for acquiring a target picture from the preprocessed video after being received by a video verification device, the video verification device extracts pixel information of the specific area in each frame of target picture to generate a verification code of the frame of target picture, and video abnormal information is generated based on the fact that the verification code is inconsistent with a preset original code;
the video sending module: and the video processing device is used for sending the preprocessed video to a video checking device.
In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the video anomaly detection method according to any one of the above schemes.
In a sixth aspect, an embodiment of the present invention provides a video playing device, including a memory, a processor, and at least one video verification apparatus as described in any one of the above schemes, stored on the memory and operable on the processor, where the processor implements the video anomaly detection method as described in any one of the above schemes when executing a program in the video verification apparatus.
In a seventh aspect, an embodiment of the present invention provides a video capture device, including a memory, a processor, and at least one video editing apparatus as described in any one of the above aspects, stored on the memory and operable on the processor, where the processor, when executing a program in the video editing apparatus, implements the video anomaly detection method as described in any one of the above aspects.
In an eighth aspect, an embodiment of the present invention provides a video system, including: at least one video playing device according to any one of the above schemes, and at least one video capturing device according to any one of the above schemes;
the video acquisition equipment is connected with the video playing equipment through a network.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the embodiment of the invention receives a preprocessed video, acquires pictures in the preprocessed video for processing according to a preset interval, respectively extracts pixel information of a specific area in each frame of picture to generate a check code corresponding to the picture, judges whether the check code is consistent with a preset original code or not, and generates abnormal video information if the check code is not consistent with the preset original code. The embodiment of the invention judges whether the picture is abnormal or not by respectively verifying the picture in the preprocessed video and comparing whether the pixel in the specific area in the picture is consistent with the pixel covered in the area during preprocessing, and judges whether the video content is abnormal or not by judging whether each frame of picture is abnormal or not, thereby effectively detecting the abnormal condition of the video content.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flowchart illustrating a video anomaly detection method according to a first embodiment of the present invention;
fig. 2 is a schematic flowchart illustrating another video anomaly detection method according to a first embodiment of the present invention;
fig. 3 is a schematic flowchart illustrating another video anomaly detection method according to a first embodiment of the present invention;
fig. 4 is a schematic flowchart illustrating another video anomaly detection method according to a first embodiment of the present invention;
fig. 5 is a schematic flowchart illustrating a video anomaly detection method according to a second embodiment of the present invention;
fig. 6 is a schematic block diagram of a video verification apparatus according to a third embodiment of the present invention;
fig. 7 is a block diagram schematically illustrating a structure of a video editing apparatus according to a third embodiment of the present invention;
fig. 8 is a block diagram illustrating a video system according to a fourth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
The inventor finds that for some scenes needing to accurately display the actual content of the video, such as a surveillance video, a navigation image, a driving image, and the like, even if the video playing device has a video signal input and the video format is correct, the picture content of the video display is still abnormal, which is not favorable for the user experience. Moreover, the user may make a misjudgment because the user cannot detect the abnormality of the video content, which causes adverse consequences. However, in the prior art, a verification method for the situation that the video signal is input, the video format is correct, but the video content is abnormal is lacked.
To this end, an embodiment of the present invention provides a video anomaly detection method, which is applied to a video verification apparatus, as shown in fig. 1, and includes the following steps:
s11, receiving a preprocessed video, wherein the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
s12, acquiring a target picture from the preprocessed video according to a preset interval;
s13, extracting the pixel information of the specific area in each frame of target picture, and generating a check code of the frame of target picture;
and S14, generating video abnormal information based on the inconsistency between the check code and the preset original code.
The preset original code can be obtained by the following method: extracting pixel information of the specific area of a preset picture to obtain the preset original code; the specific area of the preset picture is provided with the feature identifier.
In practical applications, many videos are marked with watermark identifications related to video sources, including logos (logos) or other characters, patterns, etc., when they are produced, the watermark is actually formed by overlaying a corresponding identification pattern on each frame of picture constituting the video, and in most cases, the positions of the identification patterns on each frame of picture in the video are fixed, and these fixed identification patterns are common data of each frame of picture.
In this embodiment, a video in which a fixed position of each frame of picture in a video is covered with the same shape identification pattern is regarded as a pre-processed video. In the subsequent transmission and processing processes of the preprocessed video, errors of video contents, that is, abnormalities of video pictures, such as wrong display sequence of pixels, misplacement of pixels, color change of pixels, and the like may occur, and at this time, the problems cannot be found only by detecting whether a video signal exists or not and detecting whether a video format is correct or not through the prior art.
The inventor finds that, in general, if a pixel in a frame of picture changes, the pixel in the whole picture is likely to be disordered, and the phenomenon of shifting and deforming the whole pixel is caused, so that the position, shape and even color of the same shape identification pattern in the picture also change. Therefore, for the purpose of verification, a part or all of the same shape identification pattern in each frame of picture can be selected as an object for information comparison to verify whether the received picture is in accordance with expectations.
In this embodiment, the selected object to which the information is compared is regarded as a feature identifier; the area in the picture covered by the feature identification is regarded as a specific area. If the verification result of the feature identifier in one frame of picture is normal, the whole pixel in the frame of picture is considered to be normal; or there may be a very small amount of abnormal pixels, and these abnormal pixels do not affect the whole picture of the frame picture, and such abnormal conditions that do not affect the whole picture of the picture have little influence on the viewing and recognition of the user. Therefore, a picture that verifies the feature identifier as normal can be regarded as a normal picture.
It can be understood that, in some videos, the same shape identification pattern occupies a larger area and contains more pixels, and if all verification is performed, the verification calculation amount is larger and the verification time is longer. For example, when the same-shape logo pattern has a large area and contains several independent sub-patterns, one or several of the sub-patterns can be selected as the feature logo.
Of course, if the smaller the selected feature identifier is, the fewer the verifiable pixels are, the poorer the representativeness of the verification result to the whole picture is, and the lower the reliability of the verification result is, so that more pixels can be selected as the feature identifier as much as possible to make the verification result more reliable. In specific application, the feature identifier to be verified can be selected according to the actual verification requirement of the video and the size of the same-shape identifier pattern.
It can be known that when the human eyes watch the video, people usually cannot detect the video abnormality with the display duration within 0.1 second due to the persistence of vision effect and the reaction duration of the human eyes to the picture change. While the display frame rate of video is typically above 24 frames, i.e. at least 24 pictures are displayed per second. Therefore, when the video frame rate is 24 frames, even if one or two continuous frames of pictures are abnormal, the pictures are not easy to be perceived by the user; in the case of a higher video frame rate, there may be more consecutive frames of picture anomalies that will not be perceived by the user.
In this embodiment, in order to reduce the checking workload and improve the checking efficiency of the video, the picture in the preprocessed video may be selected as the target picture according to a certain proportion to check, for example, the picture is obtained according to a preset frame number interval or a preset playing time interval. Specifically, when the frame rate of the preprocessed video is 24 frames, the target picture can be obtained according to a ratio of at least 1/3, that is, at least every two frames, a third frame is selected as the target picture or every 0.12 seconds, a frame is selected as the target picture, so as to ensure that the abnormality of three or more consecutive frames can be detected.
If the requirement on the verification accuracy is high, each frame of picture in the preprocessed video can be verified optionally. In specific application, the picture proportion to be checked can be set according to the actual checking requirement of the video and the video frame rate.
In this embodiment, whether a picture is abnormal is determined by checking whether pixels in the specific area in the target picture are changed, that is, whether the position or color of the feature identifier is changed in the target picture is determined. It can be understood that, when the video is preprocessed, the position covering the feature identifier in each frame of picture is fixed, that is, the position is covered in the specific area, and if the pixel information in the specific area in one frame of picture in the video does not conform to the pixel information of the feature identifier when the preprocessed video is verified, it is indicated that the frame of picture is changed.
The specific process of verifying whether the pixels in the specific area are changed is as follows:
extracting the pixel information of the specific area in one frame of target picture aiming at each frame of target picture, and generating a check code of the frame of target picture; judging whether the check code is consistent with a preset original code or not; if not, the frame picture is considered to be abnormal, and corresponding video abnormal information is generated.
In this embodiment, the preset source code is obtained by extracting pixel information of the specific region of a preset picture, and the specific region of the preset picture is provided with the feature identifier.
The preset picture is a frame of standard picture which is pre-manufactured according to a pre-processing mode for manufacturing the pre-processed video, and in actual operation, the pre-processing mode needs to be known in advance, and can be found by acquiring UI (user interface) design data for manufacturing the pre-processed video. Therefore, the preset source code can be used as a comparison standard of the pixel information in the specific area, and if the pixels in the specific area in one frame of target picture are not changed, the extracted check code of the frame of picture is consistent with the preset source code.
In some embodiments, the color of the feature identifier is the same in each frame of the picture. At this time, the extracted pixel information may include pixel position information and pixel color information; the algorithm for extracting the pixel information of the specific area in the picture can comprise an extraction matrix corresponding to the resolution of the target picture, wherein an element array in the extraction matrix corresponds to a pixel array in the target picture, and each element corresponds to one pixel; in order to extract only pixels within the specific region in the target picture, elements in the extraction matrix corresponding to pixels outside the specific region are set to 0. As shown in fig. 2, step S13 specifically includes:
s131, respectively extracting pixel position information and pixel color information of the specific area in each target picture by using a preset extraction matrix.
In fact, the position of the element in the preset extraction matrix corresponds to the position of the pixel in the picture, and the preset extraction matrix only needs to extract the color information of the corresponding pixel.
It will be appreciated that in some videos, the color of the watermark identification pattern is not fixed, such as some gradient watermarks, and in videos with such watermarks, the position of the watermark identification pattern on each frame of picture is fixed but the color is different. At this time, if the color of the feature identifier selected from such watermark identifier patterns is also changed in each frame of picture, the color information of the pixel cannot be directly used as the verified content.
In some embodiments, the colors of the pixels that make up the feature identifier are divided into a background color and a non-background color. In fact, the background is usually a part of the watermark identification, and is used for highlighting the pattern or text content to be displayed by the watermark identification, when the watermark is of a gradient color, the color of the background in the watermark is usually still fixed, and the color of the content to be highlighted in the watermark is always different from the color of the background. Based on the characteristic, the extracted pixel color information can be continuously processed. As shown in fig. 2, step S13 may further include, after step S131:
and S132, converting the extracted pixel color information of the specific area to obtain the graphic information consisting of the non-background-color pixels in the specific area.
In actual processing, the color of the background needs to be known in advance, and can be obtained by obtaining UI (user interface) design data for making the preprocessed video. At this time, the preset original code is shape information of the non-background color pixels obtained by extracting the pixels of the specific region in the preset picture, and if the shape information obtained by extracting the pixels of the specific region in the target picture is inconsistent with the preset original code, it is indicated that the pixels in the specific region in the target picture are changed, and the target picture is abnormal.
In one embodiment, as shown in fig. 3, step S132 specifically includes:
s1321, converting the extracted pixel color information of the specific region, which accords with the non-background color, into first information. For example to black, or directly to the number 1. For the pixel color information corresponding to the background color, since the color information is fixed, no processing may be performed.
Preferably, as shown in fig. 3, in order to make the comparison between the check code and the original code more efficient, step S132 may further include, after step S1321:
and S1322, converting the extracted pixel color information of the specific region, which accords with the background color, into second information. The second information corresponds to the first information to simplify the comparison process. For example, when the first information is black, the second information is white; when the first information is the number 1, the second information is the number 0.
In an embodiment, the video anomaly detection method provided by this embodiment further includes:
and S15, sending out a video error alarm when the check code of the target picture is judged to be inconsistent with the preset original code. Such as pop-up box prompt, voice prompt, etc., to remind the user to pay attention and avoid the user from misjudging the picture displayed by the video.
Preferably, as shown in fig. 4, instead of alerting every frame of abnormal picture, step S151 is executed:
and S151, judging that the check code of the target picture is inconsistent with the preset original code based on the continuous preset times, and sending a video error alarm.
According to the foregoing description of the capability of human eyes to recognize an abnormal event in a video, it can be understood that human eyes are not easy to recognize a picture change within 0.1 second, and therefore, according to the time interval between the verified target pictures, an alarm can be given only when the cumulative playing time of consecutive abnormal pictures exceeds 0.1 second, so as to screen out an abnormal event which cannot be recognized, and avoid unnecessary alarms. Moreover, the recognizable transient abnormality generally does not cause the misjudgment of the user, so even if the continuous abnormality exceeds 0.1 second, the alarm condition can be selected according to the actual application scene.
In the embodiment, whether the picture is abnormal or not is judged by comparing whether the pixels in the specific area in the picture are consistent with the pixels covered in the area during preprocessing or not, and whether the video content is abnormal or not is judged by judging whether each frame of picture is abnormal or not, so that the abnormal condition of the video content can be effectively detected.
Example two
Based on the first inventive concept of the embodiment, the embodiment of the present invention further provides a video anomaly detection method, which is applied to a video editing apparatus, as shown in fig. 5, and includes the following steps:
s21, covering a preset feature identifier in a specific area of each frame of picture in the original video to obtain a preprocessed video;
and S22, sending the preprocessed video to a video checking device.
It should be noted that, in this embodiment, a process of preprocessing a video is implemented, and through this preprocessing process, a preprocessed video may be correspondingly verified by a subsequent video verification device according to the preprocessing mode. Specifically, after the preprocessed video is received by a subsequent video verification device, the video verification device may obtain a target picture from the preprocessed video, extract pixel information of the specific area in each frame of the target picture, generate a verification code of the frame of the target picture, and generate video abnormal information based on the fact that the verification code is inconsistent with a preset original code.
The preset original code is obtained by the following method: extracting pixel information of the specific area of a preset picture to obtain the preset original code; the specific area of the preset picture is provided with the feature identifier.
In some embodiments, the preset feature identifier includes background color pixels and non-background color pixels to provide richer verification data, so that the verification result is more reliable; and moreover, a subsequent video verification device can verify the video according to the shape information of the non-background color pixels in the specific area, so that a different verification mode is provided.
Because the principles of the problems solved by these methods are similar to the video anomaly detection method in the first embodiment, the implementation of these methods can be referred to the implementation of the video anomaly detection method in the first embodiment, and repeated details are not repeated.
The embodiment obtains the preprocessed video by editing the original video and covering the preset feature identifier on the specific area of each frame of picture of the original video, after the video is received by the subsequent video checking device, the video checking device can judge whether the picture is abnormal or not by comparing whether the pixels in the specific area in the picture are consistent with the pixels covered in the area during preprocessing or not, judge whether the video content is abnormal or not by judging whether each frame of picture is abnormal or not, thereby effectively detecting the abnormal condition of the video content, compared with the prior art, realizing the verification of the abnormal condition of the video content with the video signal input and the correct video format, therefore, the method and the device can send out alarm information and take corresponding measures in time, improve user experience and avoid the problem of misjudgment of users caused by inaccurate displayed video pictures.
EXAMPLE III
Based on the inventive concept of the first embodiment, an embodiment of the present invention further provides a video verification apparatus, as shown in fig. 6, including:
the video receiving module 301 is configured to receive a pre-processed video, where the pre-processed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
a picture extraction module 302, configured to obtain a target picture from the preprocessed video at preset intervals;
a check code generating module 303, configured to extract pixel information of the specific area in each frame of target picture, and generate a check code of the frame of target picture;
the determining module 304 is configured to generate video abnormal information based on the inconsistency between the check code and the preset original code.
In one embodiment, the check code generating module 303 specifically includes:
the pixel extraction module 3031 is configured to extract pixel position information and pixel color information of a specific region in a target picture by using a preset extraction matrix; each element in the preset extraction matrix corresponds to each pixel in the target picture one by one, and the element in the preset extraction matrix corresponding to the pixel in the target picture, which is not the specific region, is 0.
In one embodiment, the check code generating module 303 further includes:
a pixel color conversion module 3032, configured to perform conversion processing on the extracted pixel color information of the specific region to obtain graphic information formed by pixels with non-background colors in the specific region; the color of each pixel of the feature identifier is divided into a background color and a non-background color.
In one embodiment, the video verification apparatus further includes an alarm module 305, configured to send a video error alarm when the verification code is determined to be inconsistent with a preset original code for a preset number of consecutive times.
Based on the inventive concept of the second embodiment, an embodiment of the present invention further provides a video editing apparatus, as shown in fig. 7, including:
the identification superposition module 401 is configured to cover a preset feature identification in a specific area of each frame of picture in an original video to obtain a preprocessed video, where the preprocessed video is used, after being received by a video verification device, the video verification device can obtain a target picture from the preprocessed video, extract pixel information of the specific area in each frame of target picture to generate a verification code of the frame of target picture, and generate video abnormal information based on that the verification code is inconsistent with a preset original code;
a video sending module 402, configured to send the preprocessed video to a video verification apparatus.
As the principles of the problems solved by these video verification apparatuses and video editing apparatuses are similar to the video anomaly detection method in the first embodiment and the video anomaly detection method in the second embodiment, the implementation of the video verification apparatuses and the video editing apparatuses can refer to the implementation of the methods in the first embodiment and the second embodiment, and repeated details are omitted.
There is also provided, according to an embodiment of the present invention, a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing any one of the video anomaly detection methods according to the first embodiment or any one of the video anomaly detection methods according to the second embodiment.
Example four
Based on the inventive concept of the third embodiment, an embodiment of the present invention further provides a video playing device, including a memory, a processor, and at least one video verification apparatus as described in the third embodiment, where the at least one video verification apparatus is stored on the memory and is operable on the processor, and the processor is configured to:
when the program in the video verification device is executed, the video anomaly detection method as described in the first embodiment is implemented.
A video capture device comprising a memory, a processor, and at least one video editing apparatus as described in embodiment three stored on the memory and executable on the processor, wherein the processor is configured to:
the video anomaly detection method as described in embodiment two is implemented when the program in the video editing apparatus is executed.
A video system, including at least one above-mentioned video playback equipment and at least one above-mentioned video gathering equipment; the video acquisition equipment is connected with the video playing equipment through a network.
For example, referring to fig. 8, in an on-board panoramic image System, an SVM (around View Monitor) acquisition device acquires actual conditions around the outside of a vehicle, synthesizes a panoramic image, and transmits the image to an on-board SoC (System on Chip); the image is analyzed and configured by the vehicle-mounted SoC and then transmitted to the display to be displayed.
The SVM acquisition equipment comprises cameras arranged on the periphery of the vehicle and a video editing device used for synthesizing common images shot by the cameras into a panoramic image;
the vehicle-mounted SoC comprises a camera driving module, a display driving module, a video display framework module, a video service module and a video application program. The SVM acquisition equipment transmits the synthesized panoramic image to the camera driving module through a video transmission interface; the camera driving module transmits the panoramic image to a video service module through a video display frame module; and in the video service module, analyzing and configuring the panoramic image by a video application program, sending the configured video to a display driving module through a video display frame module, and controlling the display by the display driving module.
In this embodiment, the SVM acquisition device is further provided with a video editing apparatus as described in the third embodiment, configured to overlay a feature identifier for each frame of picture in the panoramic image when the panoramic image is synthesized; in the video application program of the vehicle-mounted SoC, the video verification apparatus as described in the third embodiment is further provided, and is configured to acquire the panoramic image and verify the panoramic image.
The principle of the verification is as follows:
in the video application program, a segment of original Code is presetcheck，CodecheckAnd comparing the image with each frame of image to determine whether each frame of image is normal.
The generation mode can be represented by the following formula:
Codecheck＝Framedesign*A
wherein, the FramedesignDesigning original data for a UI (user interface) of a video editing device in SVM (support vector machine) acquisition equipment; a is a feature matrix, which is pre-designed according to the UI design original data and is used for extracting fixed data, such as watermark identification and the like, which are given to each frame of picture in the video by the UI design original data, namely, the designed feature matrix A corresponds to the fixed data to be extracted. The specific amount of the fixed data to be extracted can be determined by comprehensively considering the detection efficiency and the detection accuracy.
In the process of playing the image, the video application program converts each acquired frame of picture as follows to obtain the check Code of each frame of pictureactualAnd respectively with CodecheckAnd (3) comparison:
Codeactual＝Frameactual*A
wherein, the FrameactualObtaining a frame of picture; codeactualIs FrameactualAnd (5) the check code is converted by the characteristic matrix A.
Code if check Code of a frame of pictureactualAnd the original CodecheckIf the frame of picture is the same as the frame of picture, judging the frame of picture to be normal, otherwise, judging the frame of picture to be abnormal. If the pictures in the video are judged to be abnormal by the continuous preset times, the current video data are considered to be abnormal, and an alarm signal is sent out.
In the embodiment, a video editing device is arranged in SVM acquisition equipment to cover feature identification on each frame of picture in a video; and arranging a video verification device in a video application program in the vehicle-mounted SoC to verify the panoramic image received by the vehicle-mounted SoC. Compared with the prior art, the embodiment realizes the verification of the video signal input, the correct video format and the abnormal video content, so that the warning information can be sent out in time and the corresponding measures can be taken, the user experience is improved, and the problem of misjudgment of the user caused by the inaccurate displayed video picture is avoided; in addition, in the embodiment, verification is realized by placing the verification program in the upper layer video application program, bottom layer software does not need to be modified, and risks caused by modifying a bottom layer architecture are avoided.
With regard to the video playing device, the video capturing device and the video system in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the video anomaly detection method, and will not be elaborated here.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (13)
1. A video anomaly detection method is characterized by comprising the following steps:
receiving a preprocessed video, wherein the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
acquiring a target picture from the preprocessed video according to a preset interval;
extracting the pixel information of the specific area in each frame of target picture to generate a check code of the frame of target picture;
and generating video abnormal information based on the inconsistency of the check code and the preset original code.
2. The video anomaly detection method according to claim 1, wherein said default source code is obtained by: extracting pixel information of the specific area of a preset picture to obtain the preset original code; the specific area of the preset picture is provided with the feature identifier.
3. The video anomaly detection method according to claim 1 or 2, wherein the algorithm for extracting pixel information of a specific region specifically comprises:
extracting pixel position information and pixel color information of the specific area in the target picture by using a preset extraction matrix; each element in the preset extraction matrix corresponds to each pixel in the target picture one by one, and the element in the preset extraction matrix corresponding to the pixel in the target picture, which is not the specific region, is 0.
4. The video anomaly detection method according to claim 3, wherein said algorithm for extracting pixel information of a specific region further comprises:
converting the extracted pixel color information of the specific region to obtain graphic information formed by non-background pixels in the specific region; the color of each pixel of the feature identifier is divided into a background color and a non-background color.
5. The method for detecting video anomalies according to claim 4, wherein the converting the extracted pixel color information of the specific area includes:
converting the extracted pixel color information of the specific region, which accords with the non-background color, into first information; alternatively, the first and second electrodes may be,
converting the extracted pixel color information of the specific region, which is in accordance with the non-background color, into first information, and converting the extracted pixel color information of the specific region, which is in accordance with the background color, into second information.
6. The video anomaly detection method according to claim 5, further comprising:
and judging that the check code is inconsistent with the preset original code based on the continuous preset times, and sending a video error alarm.
7. A video anomaly detection method is applied to a video editing device and is characterized by comprising the following steps:
covering a preset feature identifier in a specific area of each frame of picture in an original video to obtain a preprocessed video;
and sending the preprocessed video, enabling a video checking device to acquire a target picture from the preprocessed video, extracting pixel information of the specific area in each frame of target picture, generating a checking code of the frame of target picture, and generating video abnormal information based on the inconsistency of the checking code and a preset original code.
8. A video verification apparatus, comprising:
the video receiving module is used for receiving a preprocessed video, and the preprocessed video is obtained by covering a feature identifier in a specific area of each frame of picture in the video in advance;
the picture extraction module is used for acquiring a target picture from the preprocessed video according to a preset interval;
the check code generating module is used for extracting the pixel information of the specific area in each frame of target picture and generating a check code of the frame of target picture;
and the judging module is used for generating video abnormal information based on the inconsistency of the check code and the preset original code.
9. A video editing apparatus, comprising:
the identification superposition module is used for covering a preset characteristic identification in a specific area of each frame of picture in the original video to obtain a preprocessed video;
the video sending module: and the video verification device is used for acquiring a target picture from the preprocessed video after sending the preprocessing, extracting the pixel information of the specific area in each frame of target picture, generating a verification code of the frame of target picture, and generating video abnormal information based on the inconsistency of the verification code and a preset original code.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the video anomaly detection method according to any one of claims 1 to 6 or the video anomaly detection method according to claim 7.
11. A video playback device comprising a memory, a processor and at least one video verification apparatus according to claim 8 stored on the memory and operable on the processor, wherein the processor implements the video anomaly detection method according to any one of claims 1 to 6 when executing a program in the video verification apparatus.
12. A video capture device comprising a memory, a processor, and at least one video editing apparatus as claimed in claim 9 stored on the memory and operable on the processor, wherein the processor, when executing a program in the video editing apparatus, implements the video anomaly detection method as claimed in claim 7.
13. A video system, comprising: at least one video playback device as claimed in claim 11, and at least one video capture device as claimed in claim 12;
the video acquisition equipment is connected with the video playing equipment through a network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111643663.1A CN114466181A (en) | 2021-12-29 | 2021-12-29 | Video anomaly detection method, device, equipment and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111643663.1A CN114466181A (en) | 2021-12-29 | 2021-12-29 | Video anomaly detection method, device, equipment and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114466181A true CN114466181A (en) | 2022-05-10 |
Family
ID=81407841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111643663.1A Pending CN114466181A (en) | 2021-12-29 | 2021-12-29 | Video anomaly detection method, device, equipment and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114466181A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002085033A2 (en) * | 2001-04-09 | 2002-10-24 | Genista Corporation | Watermarking multimedia content with reduced reference information for perceptual quality of service measurements |
| CN1885947A (en) * | 2005-06-25 | 2006-12-27 | 华为技术有限公司 | Multimedia video communication objective quality appraising method based on digital watermark |
| CN101605272A (en) * | 2009-07-09 | 2009-12-16 | 浙江大学 | A kind of method for evaluating objective quality of partial reference type image |
| KR20120068084A (en) * | 2010-10-26 | 2012-06-27 | 한국전자통신연구원 | Video watermarking embedding and detection apparatus and method using temporal modulation and error-correcting code |
| EP2648410A1 (en) * | 2012-04-08 | 2013-10-09 | Broadcom Corporation | Transmission of video utilizing static content information from video source |
| CN107018406A (en) * | 2016-01-27 | 2017-08-04 | 华为技术有限公司 | Video information processing method and device |
| US20180167630A1 (en) * | 2015-05-01 | 2018-06-14 | Verance Corporation | Watermark recovery using audio and video watermarking |
| CN108235004A (en) * | 2018-03-20 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | Video playing performance test methods, device and system |
| CN110264442A (en) * | 2019-05-16 | 2019-09-20 | 苏州科达科技股份有限公司 | A kind of integrity check method of watermark, electronic equipment and readable storage medium storing program for executing |
| CN110971931A (en) * | 2018-09-30 | 2020-04-07 | 北京微播视界科技有限公司 | Video watermark adding method and device, electronic equipment and storage medium |
| CN112019834A (en) * | 2020-07-22 | 2020-12-01 | 北京迈格威科技有限公司 | Video stream processing method, device, equipment and medium |
| CN112883902A (en) * | 2021-03-12 | 2021-06-01 | 百度在线网络技术（北京）有限公司 | Video detection method and device, electronic equipment and storage medium |
| CN113112448A (en) * | 2021-02-25 | 2021-07-13 | 惠州华阳通用电子有限公司 | Display picture detection method and storage medium |
-
2021
- 2021-12-29 CN CN202111643663.1A patent/CN114466181A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002085033A2 (en) * | 2001-04-09 | 2002-10-24 | Genista Corporation | Watermarking multimedia content with reduced reference information for perceptual quality of service measurements |
| CN1885947A (en) * | 2005-06-25 | 2006-12-27 | 华为技术有限公司 | Multimedia video communication objective quality appraising method based on digital watermark |
| CN101605272A (en) * | 2009-07-09 | 2009-12-16 | 浙江大学 | A kind of method for evaluating objective quality of partial reference type image |
| KR20120068084A (en) * | 2010-10-26 | 2012-06-27 | 한국전자통신연구원 | Video watermarking embedding and detection apparatus and method using temporal modulation and error-correcting code |
| EP2648410A1 (en) * | 2012-04-08 | 2013-10-09 | Broadcom Corporation | Transmission of video utilizing static content information from video source |
| US20180167630A1 (en) * | 2015-05-01 | 2018-06-14 | Verance Corporation | Watermark recovery using audio and video watermarking |
| CN107018406A (en) * | 2016-01-27 | 2017-08-04 | 华为技术有限公司 | Video information processing method and device |
| CN108235004A (en) * | 2018-03-20 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | Video playing performance test methods, device and system |
| CN110971931A (en) * | 2018-09-30 | 2020-04-07 | 北京微播视界科技有限公司 | Video watermark adding method and device, electronic equipment and storage medium |
| CN110264442A (en) * | 2019-05-16 | 2019-09-20 | 苏州科达科技股份有限公司 | A kind of integrity check method of watermark, electronic equipment and readable storage medium storing program for executing |
| CN112019834A (en) * | 2020-07-22 | 2020-12-01 | 北京迈格威科技有限公司 | Video stream processing method, device, equipment and medium |
| CN113112448A (en) * | 2021-02-25 | 2021-07-13 | 惠州华阳通用电子有限公司 | Display picture detection method and storage medium |
| CN112883902A (en) * | 2021-03-12 | 2021-06-01 | 百度在线网络技术（北京）有限公司 | Video detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9807300B2 (en) | Display apparatus for generating a background image and control method thereof | |
| JP2007220004A (en) | Television and authentication device | |
| CN102244715B (en) | Image processing apparatus, setting device and method for image processing apparatus | |
| CN103578116A (en) | Apparatus and method for tracking object | |
| US10991340B2 (en) | Image processing apparatus and image processing method | |
| US9369726B2 (en) | Frame block comparison | |
| CN113645494B (en) | Screen fusion method, display device, terminal device and server | |
| US9436996B2 (en) | Recording medium storing image processing program and image processing apparatus | |
| CN113112448A (en) | Display picture detection method and storage medium | |
| US20130050816A1 (en) | Three-dimensional image processing apparatus and three-dimensional image processing method | |
| CN114860182A (en) | Display information processing method and device, storage medium and electronic equipment | |
| US20140068514A1 (en) | Display controlling apparatus and display controlling method | |
| US9542777B2 (en) | Image processing apparatus, image processing method, and storage medium | |
| CN114466181A (en) | Video anomaly detection method, device, equipment and system | |
| CN107992256B (en) | Window control method, device and system | |
| US11494934B2 (en) | Image processing device, image processing method, and monitoring system | |
| JPH07160891A (en) | Picture monitoring device | |
| JP2005316958A (en) | Red eye detection device, method, and program | |
| EP4016450A1 (en) | State determination device and state determination method | |
| KR100860357B1 (en) | Apparatus and method for monitoring output of variable message sign board | |
| JP6909022B2 (en) | Programs, information terminals, information display methods and information display systems | |
| KR20120062436A (en) | Image monitoring system and method | |
| US20230419548A1 (en) | Color adjustment apparatus used for color matching between image capturing apparatuses, color adjustment method, and storage medium storing color adjustment program | |
| US20220366804A1 (en) | Methods and systems for ensuring proper installation of telecommunication equipment | |
| US20230164436A1 (en) | Imaging device, image processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |