CN113271457B - Video data abnormality determination method and apparatus, storage medium, and control apparatus - Google Patents
Video data abnormality determination method and apparatus, storage medium, and control apparatus Download PDFInfo
- Publication number
- CN113271457B CN113271457B CN202110524370.5A CN202110524370A CN113271457B CN 113271457 B CN113271457 B CN 113271457B CN 202110524370 A CN202110524370 A CN 202110524370A CN 113271457 B CN113271457 B CN 113271457B
- Authority
- CN
- China
- Prior art keywords
- video data
- frame
- image
- image blocks
- abnormal
- 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.)
- Active
Links
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
Abstract
The invention relates to the field of video data processing, and aims to prevent the phenomena that a camera is damaged to different degrees, video data cannot be acquired or cannot be acquired perfectly during behavior occurrence and the like due to malicious attack (especially) of the camera or intervention of other factors. In view of this, the invention specifically provides a method and an apparatus for determining an abnormality of video data, a storage medium, and a control apparatus. One embodiment of the present invention provides a method for determining an abnormality of video data, including: the judging method comprises the following steps: selecting one frame as a target image every other preset frame from the images of the video data; analyzing a plurality of frames of the target images in a set mode; judging whether the video data is abnormal or not according to the analysis result; and the frame numbers of the preset frames between the adjacent target images are the same or different. By such an arrangement, the accuracy of abnormality determination can be improved by analyzing the images of a plurality of frames.
Description
Technical Field
The invention relates to the field of video data processing, in particular to a method and a device for judging the abnormity of video data, a computer readable storage medium and a control device.
Background
The acquisition module (e.g., camera) of the monitoring device may record the complete video data during the occurrence of the event. In this way, not only the event can be effectively monitored during the occurrence period, but also the related event can be traced and restored later by calling the video data if necessary. With the development of video technology, cameras are widely deployed in places such as roads, shopping malls, non-self-service/self-service checkout supermarkets, residential buildings/office buildings, and the like. Based on the acquisition of video data, from the perspective of supervision, the security of the corresponding place can be well guaranteed, such as: under the condition that a camera is configured in a self-service checkout supermarket, a consumer can automatically complete a complete shopping step comprising commodity selection, registration and settlement on the premise of no salesperson; under the condition that the cameras are configured in residential buildings/office buildings, functions such as face gating, face attendance checking and the like can be realized.
When the cameras are arranged in different places, the installation positions of the cameras are often different. In some locations, the camera is generally mounted at a low position (e.g., a supermarket, a portion of a road, etc.), so that a person (e.g., a pedestrian corresponding to the road location, a consumer corresponding to the supermarket location, etc.) can physically contact the capture location of the camera. Under this premise, there is a possibility that the camera is maliciously attacked, such as being strongly slammed/bumped, being intentionally shielded, and the like. In the case of the above-mentioned behaviors, for example, the camera may be damaged to different degrees (for example, a strong slapping behavior causes the lens of the camera to be broken, and the viewing angle range of the camera to be changed), video data distortion during a partial behavior (for example, after the lens is intentionally blocked by a foreign object, effective video data cannot be acquired until the foreign object is removed), or partial distortion (for example, the camera is partially blocked, and the video data shakes due to the strong slapping/bumping) may occur.
Accordingly, there is a need in the art for a new solution to the above problems.
Disclosure of Invention
In order to prevent, at least to a certain extent or at least to a part, the camera from being damaged in different extents due to malicious attack (especially) or intervention of other factors, and video data cannot be acquired or cannot be acquired perfectly during behavior occurrence, the invention provides an abnormality judgment method and device for video data, and a computer-readable storage medium.
A first aspect of the present invention provides a method for determining an abnormality of video data, where the method includes: selecting one frame as a target image every other preset frame from the images of the video data; analyzing a plurality of frames of the target images in a set mode; judging whether the video data is abnormal or not according to the analysis result; and the frame numbers of the preset frames between the adjacent target images are the same or different.
By such an arrangement, it is possible to improve the accuracy of abnormality determination by analyzing the images of a plurality of frames in the video data.
It is understood that a person skilled in the art can select a specific form of the setting employed when analyzing the plurality of frames of images according to actual situations. Such as may be:
1) on the premise of selecting a plurality of frames of images, further screening partial images according to a certain rule, then independently analyzing a single frame of image to respectively obtain analysis results, integrating the analysis results corresponding to each frame of image, and determining whether the video data is abnormal or not based on the analysis results;
2) taking the selected multiple (M) frames of images as effective images, obtaining multiple (M-1) analysis results by comparing the images of adjacent frames, taking one or more of the multiple analysis results as a core judgment mechanism, and determining whether the video data is abnormal or not based on the core judgment mechanism;
3) by analyzing the selected multi-frame images and using a portion of the selected multi-frame images as representative images, each representative image may participate in multiple comparisons (e.g., a and B, A and C) to determine whether the video data is abnormal.
Illustratively, the multi-frame target image may be selected at intervals of preset frames having the same number of frames, for example. The number of frames of the preset frame may also be adjusted in conjunction with the analysis of the target image. As may be seen, in the case where a certain feature (e.g., data missing) is included in a certain frame target image, the number of frames of the preset frame is appropriately adjusted down before and/or after the frame target image, e.g., after the frame target image.
In one possible embodiment, the method for determining an abnormality of video data includes: dividing a target image into a plurality of image blocks; analyzing a plurality of the image blocks; correspondingly, the step of judging whether the video data is abnormal according to the analysis result comprises the following steps: calculating a frame difference between image blocks of the target image of adjacent frames; comparing each frame difference with a first threshold corresponding to the frame difference; determining whether the video data is abnormal or not according to the comparison result; wherein the first threshold is determined from at least one of the two target images associated with each frame difference.
With this arrangement, it is possible to better specify whether or not the video data is abnormal.
Specifically, by introducing data related to the attributes of the single-frame images, an adaptive threshold corresponding to each frame difference operation is obtained, so that whether the video data is abnormal or not can be better determined through the frame difference comparison of the auxiliary multi-frame images through the analysis of the single-frame images. If the attribute of one frame of image is introduced into the judging mechanism for judging whether the video data is abnormal or not, the attributes of two frames of images can be directly introduced into the judging mechanism for judging whether the video data is abnormal or not, or reasonable intermediate operation can be carried out on the attributes of the two frames of images, and the operation result is introduced into the judging mechanism.
In one possible implementation manner of the above method for determining an abnormality of video data, the first threshold is determined by: calculating statistical parameters of a plurality of image blocks in one of the target images related to each frame difference; and determining a first threshold corresponding to a corresponding image block in the plurality of image blocks according to the frame difference of the plurality of image blocks and the statistical parameter.
With such an arrangement, a specific way of determining the adaptive first threshold is given.
For example, the statistical parameters of the single-frame image may include a mean, a variance, an integral map, and the like of a plurality of image blocks in the single-frame image. Based on comparing different statistical parameters with corresponding thresholds. Illustratively, the first threshold is calculated by the frame difference and the mean, variance of the previous frame image related to the frame difference. Specifically, it is assumed that both the front frame image and the rear frame image are divided into m × n image blocks, m × n difference values corresponding to the m × n image blocks are obtained through frame difference operation, the m × n difference values correspond to m × n first thresholds, and each first threshold is determined by a corresponding difference value and a mean value and a variance of the front frame image.
In one possible embodiment, the method for determining an abnormality of video data includes: dividing a target image into a plurality of image blocks; analyzing a plurality of the image blocks; accordingly, the "determining whether the video data is abnormal by analyzing the plurality of image blocks" includes: calculating statistical parameters of a plurality of image blocks in a single-frame image; comparing the statistical parameter with a preset second threshold value; and determining whether the video data is abnormal or not according to the comparison result.
As described above, the single frame image is divided into m × n image blocks, and the statistical parameters of the single frame image may include a mean, a variance, an integral map, and the like of the image blocks. Taking the statistical parameters as the mean and variance of a plurality of image blocks as an example, the mean and variance of m × n image blocks are respectively corresponding to a preset second threshold, and the abnormality of a single frame image can be determined by comparing different statistical parameters with corresponding thresholds. For example, if the video data is abnormal due to the camera being blocked, the brightness is reduced in the case that the video data is blocked. Based on this, the normal brightness interval of the un-occluded video data can be determined. On the basis of this, a boundary corresponding to the statistical parameter of the single frame image is determined, on the basis of which a corresponding second threshold value can further be determined. Therefore, under the condition that the camera is shielded, the image can be accurately judged to be the shielded image by directly comparing the statistical parameters with the corresponding second threshold value.
In a possible implementation manner of the above method for determining an abnormality of video data, the determining whether the video data is abnormal according to an analysis result includes: selecting a target image block group from the plurality of image blocks, wherein the target image block group comprises a plurality of target image blocks; and judging whether the video data is abnormal or not by analyzing the plurality of target image blocks.
With this arrangement, it is possible to determine whether or not video data is abnormal by analyzing a part of image blocks in a single-frame image.
In principle, analyzing all image blocks should be able to reflect the attributes of the image. However, there may be a problem of a large amount of data and also a problem of interference with the result due to the introduction of some data itself. Moreover, depending on the specific application scenario of the camera, there are situations: when the camera has abnormal phenomena such as occlusion, shake, occlusion + shake, etc., some local data (data of image blocks in a local area) of the camera inevitably has abnormality, or the local data has more obvious changes when the video data has abnormality. On the basis, on the premise of proper local data analysis, a more accurate abnormal judgment result can be obtained on the premise of less data quantity by only reasonably intercepting the image.
In one possible embodiment, the method for determining an abnormality of video data includes: performing a plurality of analyses on the image; correspondingly, the step of judging whether the video data is abnormal according to the analysis result comprises the following steps: judging whether the video data are abnormal or not according to the multiple analysis results; in case of an anomaly of the video data, feedback information is selectively given.
By such an arrangement, it is possible to enhance the robustness of the determination result based on a plurality of results.
Taking the example of analyzing multiple frame images in a set manner as performing frame difference operation on the images of adjacent frames, it is possible to perform (N-1) times of frame difference operation on N target images and correspondingly calculate (N-1) sets of adaptive thresholds, and determine whether the video data is abnormal according to the final comparison result. For example, assuming that 40% of the tiles indicate an anomaly, the video data may be determined to be anomalous.
The generation of the feedback information can inform the corresponding side (such as a user side, a monitoring side and the like) of the abnormity of the data in time. Such as may be: the process of analyzing the multi-frame image comprises multiple analyses, each analysis has a preliminary judgment about whether the multi-frame image is abnormal or not, and when the conclusion of the preliminary judgment that the multi-frame image is abnormal reaches M times, feedback information can be given.
The feedback information may be, for example, sound (e.g., alarm, voice, etc.) and/or light (text, flashing) and/or information directly corresponding to the operating instructions (e.g., directly shutting down the camera or activating a second camera capable of capturing current video data, etc.). The way of giving feedback information may be, for example: the abnormality may include various kinds, and feedback information is given only in a case where some of the abnormalities occur; the anomalies can comprise a plurality of types, and different anomalies give different feedback information; different levels may be included for the same anomaly, e.g. corresponding to a light beat and a strong beat, the degree of anomaly of the video data is often more different, and different feedback information may be given for different levels.
A second aspect of the present invention provides an abnormality determination apparatus for video data, the determination apparatus comprising: a selection module configured to: selecting one frame as a target image every other preset frame from the images of the video data; an analysis module configured to: analyzing a plurality of frames of the target images in a set mode; and a determination module configured to: judging whether the video data is abnormal or not according to the analysis result; and the frame numbers of the preset frames between the adjacent target images are the same or different.
It can be understood that the apparatus for determining an abnormality of video data has all the technical effects of any one of the foregoing methods for determining an abnormality of video data, and details thereof are not repeated herein.
In the description of the present invention, each module (hereinafter, referred to as a control module) corresponding to the implementation of the abnormality determination method of video data may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, may comprise software components such as program code, or may be a combination of software and hardware. The processor may be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and/or signal processing functionality. The processor may be implemented in software, hardware, or a combination thereof. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random-access memory, and the like.
Further, it should be understood that, since the settings of each control module are only for explaining the functional units in the system corresponding to the video data abnormality judgment method of the present invention, the physical device corresponding to the control module may be the processor itself, or a part of software, a part of hardware, or a part of a combination of software and hardware in the processor. Thus, the number of control modules is only exemplary. Those skilled in the art will appreciate that the control module may be adaptively split according to the actual situation. The specific splitting of the control module does not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solution after splitting will fall into the protection scope of the present invention.
For the above apparatus for determining an abnormality of video data, in a possible implementation, the analysis module is further configured to: calculating a frame difference between image blocks of the target image of adjacent frames; comparing each frame difference with a first threshold corresponding to the frame difference; determining whether the video data is abnormal or not according to the comparison result; wherein the first threshold is determined from at least one of the two target images associated with each frame difference.
With such an arrangement, a specific manner is given in which it can be determined that video data has an abnormal phenomenon corresponding to camera occlusion, shake + occlusion.
For the above apparatus for determining an abnormality of video data, in a possible implementation, the analysis module is further configured to: calculating statistical parameters of a plurality of image blocks in a single-frame image; comparing the statistical parameter with a preset second threshold value; and determining whether the video data is abnormal or not according to the comparison result.
With such an arrangement, a specific manner is given in which at least an abnormal phenomenon of the video data corresponding to the camera being occluded or a shake containing the occlusion can be determined.
A third aspect of the present invention provides a computer readable storage medium adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by a processor to perform the method of determining an abnormality of video data according to any one of the preceding claims.
It can be understood that the computer-readable storage medium has all the technical effects of any one of the foregoing methods for determining an abnormality of video data, and details are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the method for determining the present invention can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the above-mentioned method embodiments when the computer program is executed by a processor. The computer program includes a computer program code, and it is understood that the program code includes, but is not limited to, a program code for executing the above-mentioned method for determining an abnormality of video data. For convenience of explanation, only portions relevant to the present invention are shown. The computer program code may be in source code form, object code form, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying said computer program code, media, usb disk, removable hard disk, magnetic diskette, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunication signals, software distribution media, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
A fourth aspect of the present invention provides a control apparatus comprising a memory and a processor, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the method of determining an abnormality in video data according to any one of the preceding claims.
It can be understood that the control device has all the technical effects of any one of the foregoing methods for determining an abnormality of video data, and details are not repeated herein. The control device may be a control device apparatus formed including various electronic apparatuses.
Drawings
The present invention is described below with reference to the accompanying drawings by taking as an example a scene in which a camera acquiring video data is only occluded and only shaken. In the drawings:
fig. 1 is a schematic diagram illustrating a first principle of an anomaly determination method for video data according to an embodiment of the present invention, where a camera acquiring video data is merely shaken;
fig. 2 is a schematic flow chart illustrating a method for determining an anomaly of video data according to an embodiment of the present invention, where a scene corresponding to the embodiment is a situation where a camera that acquires video data is merely shaken; and
fig. 3 is a schematic diagram illustrating a second principle of a method for determining video data anomalies according to an embodiment of the present invention, where a scene corresponding to the embodiment is a situation where a camera that acquires video data is only blocked.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention. It should be noted that, although in the present embodiment, whether video data is abnormal due to being occluded is determined by the scheme corresponding to fig. 3, obviously, the scheme corresponding to fig. (1, 2) may be directly adopted for determination.
It should be noted that in the description of the present invention, the term "a and/or B" indicates all possible combinations of a and B, such as a alone, B alone, or a and B. The term "at least one A or B" or "at least one of A and B" means similar to "A and/or B" and may include only A, only B, or both A and B. The singular forms "a", "an" and "the" may include the plural forms as well. The terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Furthermore, while numerous specific details are set forth in the following description in order to provide a better understanding of the invention, it will be apparent to those skilled in the art that the invention may be practiced without some of these specific details. In some instances, cooktop principles and the like well known to those skilled in the art have not been described in detail in order to highlight the subject matter of the invention.
In a specific embodiment, the video data acquisition module is a monitoring device (monitoring camera) applied to the roadside, and the corresponding road monitoring function can be realized by acquiring the video data of the person-vehicle-road in the visual field range. Due to the fact that the monitoring device is low in installation height, adjustable in view angle and installed in an outdoor environment, abnormal phenomena related to blocking, shaking, blocking + shaking and the like of video data collected by the monitoring device can occur due to uncontrollable factors (bad weather) or man-made malicious attacks.
The server has a control module corresponding to the monitoring apparatus, the control module being configured to execute the following abnormality determination method of video data. Under the condition that the video data is judged to be abnormal, the control module can give feedback information such as alarm and voice prompt, so that the fact that the video data is abnormal is informed to related personnel (such as the personnel who manage the film area of the monitoring device), the abnormal removal work of the video data can be timely arranged, and the integrity of the video data is further ensured.
Example 1
Referring to fig. 1, fig. 1 is a schematic diagram illustrating a first principle of an anomaly determination method for video data according to an embodiment of the present invention. As shown in fig. 1, in the case where the video data is abnormal due to the beat, the abnormality of the video data can be determined by selecting a plurality of frame images from the video stream, performing a block operation on the plurality of frame images, performing a frame difference operation on adjacent frames after the block operation, calculating an adaptive threshold for the frame difference operation, and comparing the result of the frame difference operation with the adaptive threshold for a plurality of times.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for determining an anomaly of video data according to an embodiment of the present invention. As shown in fig. 2, in a possible embodiment, the method for determining an abnormality of video data of the present invention mainly includes the following steps:
s201, selecting one frame of image from the video stream every 20-30 frames, and segmenting the image.
If YUV bare stream of video data is obtained, a gray image channel of the image is taken for processing. For example, an image with 1920 × 1080 pixels is divided into 16 × 9 image blocks, each image block has 120 × 120 pixels), and the mean value and the variance of each image block in the frame image are counted, and the mean value and the variance each have a corresponding threshold, for example, the threshold is a fixed threshold, such as the brightness of an image acquired in a case where the camera is blocked is significantly reduced compared with an unblocked image. Therefore, as long as the threshold value is reasonably selected, whether the single-frame image is blocked or not can be judged. The image can be determined to be shielded according to the judgment results of the single-frame images, so that the robustness of a judgment mechanism can be better enhanced. If the consecutive k images are determined to be occluded, it is confirmed that the video data is abnormal due to occlusion, and an alarm may be issued.
S203, comparing the adjacent frames selected in S201, calculating the frame difference of the adjacent frames, and on the basis, calculating an adaptive threshold value according to the frame difference and the statistical data of the single image calculated in S103, such as a mean value/variance, an integral graph and the like, and recording the adaptive threshold value as a first threshold value. Such as may be: and calculating the self-adaptive threshold corresponding to the frame difference of each image block according to the frame difference of the adjacent frames and the mean value and the variance of each image block in the previous frame image in the adjacent frames.
In one possible embodiment, a frame of image is sliced into rows ×. cols image blocks, rows being the total number of rows of image blocks and cols being the total number of columns corresponding to image blocks. For example, 1920 × 1080 image blocks are sliced into 16 × 9 image blocks, each of which is 120 × 120. i is the number of rows where a certain image block is located, i is greater than or equal to 1 and less than or equal to rows, j is the number of columns where a certain image block is located, and j is greater than or equal to 1 and less than or equal to cols. X (i, j) is the value of the image block of the image in the ith row and the jth column.
The mean value u of the image can be expressed as:
the variance Var of the image can be expressed as:
in one possible embodiment, the adaptive first threshold is determined by:
in the formula (3), TH1、TH2A preset value determined by one skilled in the art based on test experience. U shape0A preset cut point, empirically determined by one skilled in the art, is the mean of the image based on the preset cut point. It can be roughly distinguished that the time at which the image is acquired is day or night. Of course, the first threshold may be determined in other manners based on the average value of the image, such as threshold K ═ u, where the coefficient K is a constant value or a variable value determined empirically by those skilled in the art.
Of course, the first threshold may be determined in other manners, such as by introducing two elements of the mean and the variance of the image when calculating the first threshold. And on the premise of introducing the two elements, a first threshold corresponding to the frame difference of the image block is calculated according to the frame difference of the corresponding image block. Namely: and f (u, var (x)), FD, where FD is a frame difference between corresponding image blocks in two adjacent frames of images, and a specific form of f may be selected by a person skilled in the art according to actual conditions on the premise that the calculated adaptive first threshold can better reflect the image abnormality.
S205, comparing each corresponding image block in the adjacent frames with the corresponding first threshold, and judging whether the video data shakes according to the result. For example, if 60% of the 16 × 9 image blocks have comparison results corresponding to an abnormality, it may be determined that the video data is jittered;
and S207, repeating the steps S201-S205, and determining whether the video data has jitter according to the judgment result of the frame difference operation for a plurality of times. If a frame of image is selected from the video stream every 20-30 frames, based on the selected 9 frames of images, based on the foregoing S201-S205, 8 times of judgment based on frame difference operation are performed, and in 8 times of judgment, when the judgment result of 5 consecutive times is that the video data is jittered, a conclusion that the video data is jittered can be given;
and S209, sending feedback information to the management department of the monitoring device locally and respectively.
For example, the local (installation location) feedback information may be an alarm, and text or voice information including an abnormal situation may be sent to the management department. For example, the corresponding feedback information can be sent to the mobile phones of the related personnel of the management department.
It can be seen that in the determination method of the embodiment, the adaptive first threshold corresponding to each frame difference operation is determined by introducing statistical data reflecting the attributes of the single-frame image. And the attribute of the single-frame image can accurately reflect the abnormal shielding of the video data. That is, by introducing factors related to occlusion anomalies to determine a threshold value related to a shake anomaly, a shake anomaly of video data can be determined more accurately.
Example 2
Referring to fig. 3, fig. 3 is a schematic diagram illustrating a principle of an anomaly determination method for video data according to an embodiment of the present invention. As shown in fig. 3, in the case where the video data is abnormal due to a simple process, the abnormality of the video data can be determined by selecting a plurality of frame images from the video stream, slicing the plurality of frame images, calculating statistical data (such as the aforementioned mean/variance) of each frame image after slicing, and comparing the statistical data with a preset threshold.
The present embodiment is different from embodiment 1 mainly in whether S203 is introduced or not. Specifically, the introduction of the frame difference is more suitable for judging the jitter abnormality, and for the occlusion abnormality, the judgment can be more accurately performed directly through a single frame image. Therefore, for the occlusion anomaly, a preset threshold value can be configured for the statistical data of the single-frame image, and is recorded as a second threshold value. On the basis, a plurality of judgment results can be obtained based on the selected multi-frame images, and the abnormal shielding of the video data can be more accurately determined by analyzing the plurality of judgment results.
The video data abnormity judgment method can simultaneously realize judgment of two attacks, namely beating and shielding, of the camera. For example, for flapping or slight dithering (similar to flapping) attack, more than 90% accuracy can be achieved; for shielding attack, the accuracy can reach more than 80%.
It should be noted that, although the foregoing embodiments describe each step in a specific sequence, those skilled in the art may understand that, in order to achieve the effect of the present invention, different steps do not have to be executed in such a sequence, and may be executed simultaneously or in other sequences, and some steps may be added, replaced or omitted, and these changes are within the protection scope of the present invention. Such as may be: after the image is divided into a plurality of image blocks, a part of the image blocks which can better characterize the abnormality is selected as the target image block, and the analysis as in embodiment 1 and embodiment 2 is performed on the basis of the selected part of the image blocks.
It should be noted that, although the control method configured in the above-described specific manner is described as an example, those skilled in the art will appreciate that the present invention should not be limited thereto. In fact, the user can flexibly adjust the relevant steps and parameters in the steps according to the situations such as actual application scenes.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (8)
1. An abnormality determination method for video data, the method comprising:
selecting one frame as a target image every other preset frame from the images of the video data;
analyzing a plurality of frames of the target images in a set mode;
judging whether the video data is abnormal or not according to the analysis result;
the frame numbers of preset frames between adjacent target images are the same or different;
the step of analyzing a plurality of frames of the target images in a set mode comprises the following steps:
dividing a target image into a plurality of image blocks;
analyzing a plurality of the image blocks;
the step of judging whether the video data is abnormal according to the analysis result comprises the following steps:
calculating a frame difference between corresponding image blocks of the adjacent target images;
comparing each frame difference with a first threshold corresponding to the frame difference;
determining whether the video data is abnormal or not according to the comparison result;
wherein the first threshold is determined in the following manner:
calculating statistical parameters of a plurality of image blocks in one of the target images related to each frame difference;
and determining a first threshold corresponding to each frame difference according to each frame difference and the statistical parameters.
2. The method of claim 1, wherein said determining whether the video data is abnormal according to the analysis result further comprises:
calculating statistical parameters of a plurality of image blocks in each frame of target image;
comparing the statistical parameters of a plurality of image blocks in each frame of the target image with a preset second threshold;
and determining whether the video data is abnormal or not according to the comparison result.
3. The method for determining an abnormality in video data according to claim 1 or 2, wherein said analyzing the plurality of image blocks includes:
selecting a target image block group from the plurality of image blocks, wherein the target image block group comprises a plurality of target image blocks;
and analyzing a plurality of target image blocks.
4. The method of determining an abnormality in video data according to claim 1, wherein after the step of determining whether the video data is abnormal based on the analysis result, the method includes:
in case of an anomaly of the video data, feedback information is selectively given.
5. An abnormality determination device for video data, characterized in that said determination device comprises:
a selection module configured to: selecting one frame as a target image every other preset frame from the images of the video data;
the frame numbers of preset frames between adjacent target images are the same or different;
an analysis module configured to: analyzing a plurality of frames of the target images in a set mode, specifically:
dividing a target image into a plurality of image blocks;
analyzing a plurality of the image blocks;
a determination module configured to: according to the analysis result, judging whether the video data is abnormal, specifically:
calculating a frame difference between corresponding image blocks of the adjacent target images;
comparing each frame difference with a first threshold corresponding to the frame difference;
determining whether the video data is abnormal or not according to the comparison result;
wherein the first threshold is determined in the following manner:
calculating statistical parameters of a plurality of image blocks in one of the target images related to each frame difference;
and determining a first threshold corresponding to each frame difference according to each frame difference and the statistical parameters.
6. The apparatus for determining an abnormality in video data according to claim 5, wherein said analysis module is further configured to:
calculating statistical parameters of a plurality of image blocks in each frame of the target image;
comparing the statistical parameters of a plurality of image blocks in each frame of the target image with a preset second threshold;
and determining whether the video data is abnormal or not according to the comparison result.
7. A computer-readable storage medium, characterized in that the storage medium is adapted to store a plurality of program codes, said program codes being adapted to be loaded and run by a processor to perform the method for anomaly determination of video data according to any one of claims 1 to 4.
8. A control apparatus, characterized in that the control apparatus comprises a memory and a processor, said memory being adapted to store a plurality of program codes, said program codes being adapted to be loaded and run by said processor to perform the method of anomaly determination of video data according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524370.5A CN113271457B (en) | 2021-05-13 | 2021-05-13 | Video data abnormality determination method and apparatus, storage medium, and control apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524370.5A CN113271457B (en) | 2021-05-13 | 2021-05-13 | Video data abnormality determination method and apparatus, storage medium, and control apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113271457A CN113271457A (en) | 2021-08-17 |
| CN113271457B true CN113271457B (en) | 2022-03-15 |
Family
ID=77230701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110524370.5A Active CN113271457B (en) | 2021-05-13 | 2021-05-13 | Video data abnormality determination method and apparatus, storage medium, and control apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113271457B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7639873B2 (en) * | 2005-07-28 | 2009-12-29 | Microsoft Corporation | Robust shot detection in a video |
| CN105430384B (en) * | 2015-12-10 | 2018-05-29 | 青岛海信网络科技股份有限公司 | A kind of video quality diagnosing method and system |
| CN108492287B (en) * | 2018-03-14 | 2020-06-02 | 罗普特（厦门）科技集团有限公司 | Video jitter detection method, terminal equipment and storage medium |
| CN109698906B (en) * | 2018-11-24 | 2021-01-26 | 四川鸿景润科技有限公司 | Image-based jitter processing method and device and video monitoring system |
-
2021
- 2021-05-13 CN CN202110524370.5A patent/CN113271457B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113271457A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10070053B2 (en) | Method and camera for determining an image adjustment parameter | |
| CN110769246B (en) | Method and device for detecting faults of monitoring equipment | |
| EP3104327B1 (en) | Anomalous pixel detection | |
| US7751647B2 (en) | System and method for detecting an invalid camera in video surveillance | |
| CN107240092B (en) | Image ambiguity detection method and device | |
| JP5127883B2 (en) | Network camera error detection and notification method | |
| CN110399831A (en) | A kind of method for inspecting and device | |
| CN112784738A (en) | Moving object detection alarm method, device and computer readable storage medium | |
| CN115174861A (en) | Method and device for automatically tracking moving target by pan-tilt camera | |
| JP5356302B2 (en) | Smoke detector | |
| CN113271457B (en) | Video data abnormality determination method and apparatus, storage medium, and control apparatus | |
| KR20190026625A (en) | Image displaying method, Computer program and Recording medium storing computer program for the same | |
| US7424167B1 (en) | Tide filtering for video surveillance system | |
| US9395887B2 (en) | Image processing apparatus and method for removing noise from a frame group | |
| KR20180089249A (en) | Method for diagnosing fault of camera | |
| CN112927178A (en) | Occlusion detection method, occlusion detection device, electronic device, and storage medium | |
| CN116051477A (en) | Image noise detection method and device for ultra-high definition video file | |
| US20070217655A1 (en) | Image detection device | |
| KR101248154B1 (en) | Method and apparatus for estimating moving object using variable area size, and computer readable record medium with moving estimating program for the same | |
| CN113329171A (en) | Video processing method, device, equipment and storage medium | |
| EP1944963B1 (en) | Image Sensor Systems Having Improved Noise Performance | |
| CN115514955B (en) | Camera picture quality abnormality detection and identification method | |
| CN117011288B (en) | Video quality diagnosis method and system | |
| CN117635937A (en) | Method, system and medium for judging shielding alarm of patrol robot camera | |
| CN116626046A (en) | Relay protection cabinet terminal defect detection method, system, equipment and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |