CN113411571A - Video frame definition detection method based on sliding window gradient entropy - Google Patents

Video frame definition detection method based on sliding window gradient entropy Download PDF

Info

Publication number
CN113411571A
CN113411571A CN202110665603.3A CN202110665603A CN113411571A CN 113411571 A CN113411571 A CN 113411571A CN 202110665603 A CN202110665603 A CN 202110665603A CN 113411571 A CN113411571 A CN 113411571A
Authority
CN
China
Prior art keywords
video frame
gradient
definition
image
entropy
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.)
Granted
Application number
CN202110665603.3A
Other languages
Chinese (zh)
Other versions
CN113411571B (en
Inventor
徐哲鑫
许智杰
詹仁辉
陈亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian Normal University
Original Assignee
Fujian Normal University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujian Normal University filed Critical Fujian Normal University
Priority to CN202110665603.3A priority Critical patent/CN113411571B/en
Publication of CN113411571A publication Critical patent/CN113411571A/en
Application granted granted Critical
Publication of CN113411571B publication Critical patent/CN113411571B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a video frame definition detection method based on sliding window gradient entropy, aiming at a video stream continuously input by a monitoring camera, triggering a video frame definition abnormity detection algorithm at the initial moment of each period; extracting a reference video frame and a video frame to be detected; performing image blocking on the extracted video frame and constructing a gradient entropy matrix; calculating a gradient entropy matrix reference value of the definition normal video frame in each time interval; calculating the abnormal definition condition of the image block of the video frame to be detected and outputting a definition abnormal measurement matrix; and judging the fuzzy condition of the video frame according to the definition anomaly measurement matrix. The method of the invention can judge the local definition abnormal condition of the video frame to be detected and mark the abnormal position thereof, and can accurately and rapidly detect the video frame with abnormal definition.

Description

Video frame definition detection method based on sliding window gradient entropy
Technical Field
The invention relates to the field of image processing, in particular to a video frame definition detection method based on sliding window gradient entropy.
Background
Video monitoring systems are an important part of security technology prevention systems, but due to the appearance of a large number of blurred images, the video availability is greatly reduced, and even a large number of blurred images can bring wrong information to people. Therefore, it is very important to perform real-time image sharpness detection on the video monitoring system.
Currently, there are two methods for quality evaluation of images. Subjective evaluation and objective evaluation, respectively. Subjective evaluation is to directly judge an image from the visual effect of human beings. The objective evaluation is to judge the image through the establishment of a mathematical model. At present, there are 3 common image objective evaluation methods, which are respectively as follows: full reference quality evaluation, weak reference quality evaluation, no reference quality evaluation.
In the no-reference quality evaluation, based on the traditional digital image definition evaluation method, the most common and representative definition algorithm at present is an evaluation method based on a gradient function, such as a Brenne gradient function method, a Tenengrad gradient function method, a Laplacian gradient function method and an energy gradient function method.
Although these algorithms have good performance, they all have common problems. Because the algorithms are based on the calculation or comparison of the whole image to the gradient thereof, if the image to be judged has local abnormal conditions such as full black or full white of local area pixels, local blurring, local shielding, local brightness abnormality and the like, the traditional algorithm can detect the clear images as abnormal images, resulting in detection errors. For example, if a part of an image is blocked by black, but the definition of the other part is normal, and if the definition of the image is determined to be abnormal by determining the gradient of the whole image, the gradient of the blocked part affects the gradient of the whole image, so that the determined gradient value cannot reflect the gradient value of the whole image, and the result is misdetermined.
Disclosure of Invention
The invention aims to provide a video frame definition detection method based on sliding window gradient entropy, which can judge the local definition abnormal condition of a video frame to be detected and mark the abnormal position of the local definition abnormal condition and can accurately and quickly detect the video frame with abnormal definition.
The technical scheme adopted by the invention is as follows:
a video frame definition detection method based on sliding window gradient entropy comprises the following steps:
s1: aiming at a video stream continuously input by a monitoring camera, triggering video frame definition abnormity detection at the initial moment of each set period cycle;
s2: extracting a reference video frame and a video frame to be detected: continuously extracting a plurality of video frames at the starting moment of each period as reference video frames for calculating a definition measurement characteristic reference value; extracting a plurality of video frames in the video stream according to a set extraction cycle at each time interval to serve as video frames to be detected;
s3: performing image blocking on the extracted video frame and constructing a gradient entropy matrix;
s4: calculating and obtaining the result of averaging the gradient entropy matrix of the reference video frame;
s5: judging whether a reference value exists in the current time period or not; if yes, go to step S6; otherwise, taking the result of averaging the gradient entropy matrixes of the reference video frame as the current reference value and executing the step S7;
s6: comparing each element of the average gradient entropy matrix of the reference video frame with a reference value of the current corresponding time period respectively to judge whether the average gradient entropy matrix is within an allowable variation range; if so, weighting and combining the current reference value with the original element value; otherwise, keeping the original element value as the current reference value;
s7: calculating the abnormal situation of the definition of the image block of the video frame to be detected and outputting a definition abnormal measurement matrix: element-level comparison is carried out on the gradient entropy matrix of the video frame to be detected in each time interval and the reference value of the time interval, and when the element value of the gradient entropy matrix is within the allowable variation interval range of the reference value, the normal image block is judged; otherwise, judging the image block to be an abnormal image block, and establishing a definition abnormality measurement matrix according to whether the image block is abnormal or not and outputting the definition abnormality measurement matrix.
Further, as a preferred embodiment, in S1, each hour is a period cycle.
Further, as a preferred embodiment, S2 specifically includes the following steps:
s2-1: in the t-th period, letExtracting K frames as reference frames to form a reference frame set FK＝{f1,…,fKIn which f1,…,fKThe first K frames of video frames representing the starting time of the period;
s2-2: in the t-th time interval, the interval of the frames to be detected is set to be delta F, namely, one frame is extracted from every delta F frame as the frame to be detected, and then the frame set F to be detected is obtainedD＝{fK+1+Δf,…,fK+1+n·ΔfAnd n represents the extracted nth frame to be detected.
Further, as a preferred embodiment, in S3, converting the video frame into a grayscale image, and performing sliding clipping from left to right and from top to bottom according to a set sliding window to obtain a plurality of image blocks; and calculating the gradient entropy of each image block, and constructing the frame gradient entropy matrix according to the positions of the image blocks in the gray level image of the corresponding video frame.
Further, as a preferred embodiment, S3 specifically includes:
s3-1: for any frame f in the reference frame setk(K-1, …, K) or any frame f in the set of frames to be detectedd(d ═ K +1+ Δ f, …, K +1+ n · Δ f), which is converted into the corresponding grayscale image gkAnd gd；
S3-2: setting the size of a sliding window as h x w pixels, the transverse sliding step length as x, and the longitudinal sliding as y; the grayscale image g is aligned from left to right, top to bottomkAnd gdSliding cutting to obtain M image blocks, wherein each image block is marked as Gk,iAnd Gd,iWherein i ═ 1,2, …, M; the step length of the transverse sliding is x, and the calculation mode of the longitudinal sliding is as follows:
Figure BDA0003117250030000021
Figure BDA0003117250030000022
wherein, alpha and beta are respective step length control coefficients;
s3-3: g is to bek,iAnd GdAnd are uniformly denoted as GiThe Sobel cores in the horizontal and vertical directions are respectively denoted as SxAnd SyCalculating to obtain the gradient d in the horizontal and vertical directionsxAnd dyThen G isiGradient d ofiIs composed of
Figure BDA0003117250030000031
S3-4: image block GiGradient d ofiN kinds of gradient values exist in total, and the proportion of each gradient value is rhon(N-1, 2, …, N), d is calculated according to the following formulaiEntropy xi of gradient ofi：
Figure BDA0003117250030000032
Thereby obtaining Gk,iAnd Gd,iEntropy xi of gradient ofk,i，ξd,i；
S3-5: according to the position of the sliding window Gk,iAnd Gd,iEntropy xi of gradient ofk,iAnd xid,iConstructed as video frames fkAnd fdRespectively denoted xi of the gradient entropy matrixk,Ξd
Figure BDA0003117250030000033
Further, as a preferred embodiment, the xi of the frame of the time period K as the reference frame is calculated in S4kMean xiK：
Figure BDA0003117250030000034
Further, as a preferred embodiment, S6 specifically includes the following steps:
s6-1: let the reference value of the gradient entropy matrix of the normal definition video frame in the t-th period be xic
Figure BDA0003117250030000035
S6-2: judging whether the gradient entropy matrix reference value of the definition normal video frame at the t-th time period is assigned or not; xi when t iscWithout being assigned a value, then xic＝ΞK(ii) a Otherwise, for xicEach element xi inc,iI ═ 1,2, …, M, updated according to the following equation:
Figure BDA0003117250030000036
wherein, γcAs weighting parameter, σcAnd the error tolerance coefficient is a gradient entropy reference value.
Further, as a preferred embodiment, the step S7 includes:
s7-1: defining a video frame f to be detecteddThe sharpness anomaly metric matrix is Ψd
Figure BDA0003117250030000041
Wherein the element psid,iRepresenting video frames fdThe definition of the ith image block is abnormal; when the image of the image block is clear, the element value is 0; otherwise, it is 1;
s7-2: to-be-detected video frame fdThe gradient entropy matrix xi ofdXi and xicElement level comparison is performed and psi is calculated according to the following formulad,iValue of (A)
Figure BDA0003117250030000042
Wherein σdThe image block definition abnormity fault-tolerant coefficient.
By adopting the technical scheme, the method and the device can judge the local definition abnormal condition of the video frame to be detected and mark the abnormal position of the local definition abnormal condition, and can accurately and quickly detect the video frame with abnormal definition.
Drawings
The invention is described in further detail below with reference to the accompanying drawings and the detailed description;
FIG. 1 is a schematic flow chart of a video frame sharpness detection method based on sliding window gradient entropy according to the present invention;
FIG. 2 is a schematic diagram of the gradient entropy matrix reference value calculation according to the present invention;
FIG. 3 is a schematic diagram of a video frame sharpness anomaly metric matrix according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
As shown in one of fig. 1 to fig. 3, the present invention discloses a video frame sharpness detection method based on sliding window gradient entropy, which includes the following steps:
s1: aiming at a video stream continuously input by a monitoring camera, triggering video frame definition abnormity detection at the initial moment of each set period cycle;
further, as a preferred embodiment, in S1, each hour is a period cycle. The input video stream is divided into frames according to 5s, a file is created to record the total video file, and further, the video frames are stored in a designated file, and then pictures are named regularly.
S2: extracting a reference video frame and a video frame to be detected: continuously extracting a plurality of video frames at the starting moment of each period as reference video frames for calculating a definition measurement characteristic reference value; extracting a plurality of video frames in the video stream according to a set extraction cycle at each time interval to serve as video frames to be detected; s2 specifically includes the following steps:
s2-1: in the t-th time interval, K frames are extracted as reference frames to form a reference frame set FK＝{f1,…,fKIn which f1,…,fKIndicating the starting moment of the periodThe first K frames of video;
s2-2: in the t-th time interval, the interval of the frames to be detected is set to be delta F, namely, one frame is extracted from every delta F frame as the frame to be detected, and then the frame set F to be detected is obtainedD＝{fK+1+Δf,…,fK+1+n·ΔfAnd n represents the extracted nth frame to be detected.
S3: performing image blocking on the extracted video frame and constructing a gradient entropy matrix;
specifically, a video frame is converted into a gray image, and a plurality of image blocks are obtained by sliding and cutting from left to right and from top to bottom according to a set sliding window; calculating the gradient entropy of each image block, and constructing a frame gradient entropy matrix according to the position of the image block in the corresponding video frame gray level image; s3 specifically includes the following steps:
s3-1: for any frame f in the reference frame setk(K-1, …, K) or any frame f in the set of frames to be detectedd(d ═ K +1+ Δ f, …, K +1+ n · Δ f), which is converted into the corresponding grayscale image gkAnd gd；
S3-2: setting the size of a sliding window as h x w pixels, the transverse sliding step length as x, and the longitudinal sliding as y; the grayscale image g is aligned from left to right, top to bottomkAnd gdSliding cutting to obtain M image blocks, wherein each image block is marked as Gk,iAnd Gd,iWherein i ═ 1,2, …, M; the step length of the transverse sliding is x, and the calculation mode of the longitudinal sliding is as follows:
Figure BDA0003117250030000051
Figure BDA0003117250030000052
wherein, alpha and beta are respective step length control coefficients;
s3-3: g is to bek,iAnd GdAnd are uniformly denoted as GiThe Sobel cores in the horizontal and vertical directions are respectively denoted as SxAnd SyCalculating to obtain the gradient d in the horizontal and vertical directionsxAnd dyThen G isiGradient d ofiIs composed of
Figure BDA0003117250030000053
S3-4: image block GiGradient d ofiN kinds of gradient values exist in total, and the proportion of each gradient value is rhon(N-1, 2, …, N), d is calculated according to the following formulaiEntropy xi of gradient ofi：
Figure BDA0003117250030000054
Thereby obtaining Gk,iAnd Gd,iEntropy xi of gradient ofk,i，ξd,i；
S3-5: according to the position of the sliding window Gk,iAnd Gd,iEntropy xi of gradient ofk,iAnd xid,iConstructed as video frames fkAnd fdRespectively denoted xi of the gradient entropy matrixk,Ξd
Figure BDA0003117250030000061
S4: calculating and obtaining the result of averaging the gradient entropy matrix of the reference video frame; further, as a preferred embodiment, the xi of the frame of the time period K as the reference frame is calculated in S4kMean value
Figure BDA0003117250030000062
Figure BDA0003117250030000063
S5: as shown in fig. 2, it is determined whether a reference value exists in the current time period; if yes, go to step S6; otherwise, taking the result of averaging the gradient entropy matrixes of the reference video frame as the current reference value and executing the step S7;
s6: comparing each element of the average gradient entropy matrix of the reference video frame with a reference value of the current corresponding time period respectively to judge whether the average gradient entropy matrix is within an allowable variation range; if so, weighting and combining the current reference value with the original element value; otherwise, keeping the original element value as the current reference value;
specifically, S6 includes the steps of:
s6-1: let the reference value of the gradient entropy matrix of the normal definition video frame in the t-th period be xic
Figure BDA0003117250030000064
S6-2: judging whether the gradient entropy matrix reference value of the definition normal video frame at the t-th time period is assigned or not; xi when t iscIs not assigned, then
Figure BDA0003117250030000065
Otherwise, for xicEach element xi inc,iI ═ 1,2, …, M, updated according to the following equation:
Figure BDA0003117250030000066
wherein, γcAs weighting parameter, σcAnd the error tolerance coefficient is a gradient entropy reference value.
S7: calculating the abnormal situation of the definition of the image block of the video frame to be detected and outputting a definition abnormal measurement matrix: element-level comparison is carried out on the gradient entropy matrix of the video frame to be detected in each time interval and the reference value of the time interval, and when the element value of the gradient entropy matrix is within the allowable variation interval range of the reference value, the normal image block is judged; otherwise, judging the image block to be an abnormal image block, and establishing a definition abnormality measurement matrix according to whether the image block is abnormal or not and outputting the definition abnormality measurement matrix.
Further, as shown in fig. 3, as a preferred embodiment, the step S7 includes:
s7-1: defining a video frame f to be detecteddThe sharpness anomaly metric matrix is Ψd
Figure BDA0003117250030000067
Wherein the element psid,iRepresenting video frames fdThe definition of the ith image block is abnormal; when the image of the image block is clear, the element value is 0; otherwise, it is 1;
s7-2: to-be-detected video frame fdThe gradient entropy matrix xi ofdXi and xicElement level comparison is performed and psi is calculated according to the following formulad,iValue of (A)
Figure BDA0003117250030000071
Wherein σdThe image block definition abnormity fault-tolerant coefficient.
S8: and judging the fuzzy condition of the video frame according to the definition anomaly measurement matrix. If the image is a local abnormal image, outputting a local abnormal position; if the image is a global blurred image, the image is output as a blurred image.
By adopting the technical scheme, the method and the device can judge the local definition abnormal condition of the video frame to be detected and mark the abnormal position of the local definition abnormal condition, and can accurately and quickly detect the video frame with abnormal definition.
It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. The embodiments and features of the embodiments in the present application may be combined with each other without conflict. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the present application is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Claims (9)

1. A video frame definition detection method based on sliding window gradient entropy is characterized in that: which comprises the following steps:
s1: aiming at a video stream continuously input by a monitoring camera, triggering video frame definition abnormity detection at the initial moment of each set period cycle;
s2: extracting a reference video frame and a video frame to be detected: continuously extracting a plurality of video frames at the starting moment of each period as reference video frames for calculating a definition measurement characteristic reference value; extracting a plurality of video frames in the video stream according to a set extraction cycle at each time interval to serve as video frames to be detected;
s3: performing image blocking on the extracted video frame and constructing a gradient entropy matrix;
s4: calculating and obtaining the result of averaging the gradient entropy matrix of the reference video frame;
s5: judging whether a reference value exists in the current time period or not; if yes, go to step S6; otherwise, taking the result of averaging the gradient entropy matrixes of the reference video frame as the current reference value and executing the step S7;
s6: comparing each element of the average gradient entropy matrix of the reference video frame with a reference value of the current corresponding time period respectively to judge whether the average gradient entropy matrix is within an allowable variation range; if so, weighting and combining the current reference value with the original element value; otherwise, keeping the original element value as the current reference value;
s7: calculating the abnormal situation of the definition of the image block of the video frame to be detected and outputting a definition abnormal measurement matrix: element-level comparison is carried out on the gradient entropy matrix of the video frame to be detected in each time interval and the reference value of the time interval, and when the element value of the gradient entropy matrix is within the allowable variation interval range of the reference value, the normal image block is judged; otherwise, judging the image block to be an abnormal image block, and establishing a definition abnormality measurement matrix according to whether the image block is abnormal or not and outputting the definition abnormality measurement matrix.
2. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: one period cycle per hour is set in S1.
3. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: s2 specifically includes:
s2-1: in the t-th time interval, K frames are extracted as reference frames to form a reference frame set FK＝{f1,…,fKIn which f1,…,fKThe first K frames of video frames representing the starting time of the period;
s2-2: in the t-th time interval, the interval of the frames to be detected is set to be delta F, namely, one frame is extracted from every delta F frame as the frame to be detected, and then the frame set F to be detected is obtainedD＝{fK+1+Δf,…,fK+1+n·ΔfAnd n represents the extracted nth frame to be detected.
4. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: s3, converting the video frame into a gray image, and cutting the gray image from left to right and from top to bottom according to a set sliding window to obtain a plurality of image blocks; and calculating the gradient entropy of each image block, and constructing the frame gradient entropy matrix according to the positions of the image blocks in the gray level image of the corresponding video frame.
5. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: s3 specifically includes the following steps:
s3-1: for any frame f in the reference frame setkK is 1, …, K; or any frame f in the set of frames to be detecteddD ═ K +1+ Δ f, …, K +1+ n · Δ f; convert it into corresponding gray image gkAnd gd；
S3-2: setting the size of a sliding window as h x w pixels, the transverse sliding step length as x, and the longitudinal sliding as y; the grayscale image g is aligned from left to right, top to bottomkAnd gdSliding cutting to obtain M image blocks, wherein each image block is marked as Gk，iAnd Gd，iWherein i ═ 1,2, …, M; the step length of the transverse sliding is x, and the calculation mode of the longitudinal sliding is as follows:
Figure FDA0003117250020000021
Figure FDA0003117250020000022
wherein, alpha and beta are respective step length control coefficients;
s3-3: g is to bek，iAnd GdAnd are uniformly denoted as GiThe Sobel cores in the horizontal and vertical directions are respectively denoted as SxAnd SyCalculating to obtain the gradient d in the horizontal and vertical directionsxAnd dyThen G isiGradient d ofiComprises the following steps:
Figure FDA0003117250020000023
s3-4: image block GiGradient d ofiN kinds of gradient values exist in total, and the proportion of each gradient value is rhon(N-1, 2, …, N), d is calculated according to the following formulaiEntropy xi of gradient ofi：
Figure FDA0003117250020000024
Thereby obtaining Gk，iAnd Gd，iEntropy xi of gradient ofk,i，ξd,i；
S3-5: according to the position of the sliding window Gk，iAnd Gd，iEntropy xi of gradient ofk,iAnd xid,iConstructed as video frames fkAnd fdRespectively denoted xi of the gradient entropy matrixk，Ξd
Figure FDA0003117250020000025
6. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: calculating xi of the K frame as reference frame in the time period in S4kMean value
Figure FDA0003117250020000026
7. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: s6 specifically includes the following steps:
s6-1: let the reference value of the gradient entropy matrix of the normal definition video frame in the t-th period be xic
Figure FDA0003117250020000031
S6-2: judging whether the gradient entropy matrix reference value of the definition normal video frame at the t-th time period is assigned or not; xi when t iscIs not assigned, then
Figure FDA0003117250020000032
Otherwise, for xicEach element xi inc,iI ═ 1,2, …, M, updated according to the following equation:
Figure FDA0003117250020000033
wherein, γcAs weighting parameter, σcAnd the error tolerance coefficient is a gradient entropy reference value.
8. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: s7 specifically includes the following steps:
s7-1: defining a video frame f to be detecteddThe sharpness anomaly metric matrix is Ψd
Figure FDA0003117250020000034
Wherein the element psid,iRepresenting video frames fdThe definition of the ith image block is abnormal; when the image of the image block is clear, the element value is 0; otherwise, it is 1;
s7-2: to-be-detected video frame fdThe gradient entropy matrix xi ofdXi and xicElement level comparison is performed and psi is calculated according to the following formulad,iValue of (A)
Figure FDA0003117250020000035
Wherein σdThe image block definition abnormity fault-tolerant coefficient.
9. The method for detecting the sharpness of a video frame based on sliding window gradient entropy as claimed in claim 1, wherein: it also includes the following steps:
s8: judging the fuzzy condition of the video frame according to the definition anomaly measurement matrix: when the local abnormal image is judged, outputting a local abnormal position; and when the image is judged to be the global blurred image, outputting the image as the blurred image.
CN202110665603.3A 2021-06-16 2021-06-16 Video frame definition detection method based on sliding window gradient entropy Active CN113411571B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110665603.3A CN113411571B (en) 2021-06-16 2021-06-16 Video frame definition detection method based on sliding window gradient entropy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110665603.3A CN113411571B (en) 2021-06-16 2021-06-16 Video frame definition detection method based on sliding window gradient entropy

Publications (2)

Publication Number Publication Date
CN113411571A true CN113411571A (en) 2021-09-17
CN113411571B CN113411571B (en) 2023-07-14

Family

ID=77684449

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110665603.3A Active CN113411571B (en) 2021-06-16 2021-06-16 Video frame definition detection method based on sliding window gradient entropy

Country Status (1)

Country Link
CN (1) CN113411571B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115687677A (en) * 2022-10-18 2023-02-03 武汉骏信达信息咨询有限公司 Data storage management method and system based on artificial intelligence
CN115866411A (en) * 2023-03-01 2023-03-28 深圳市昂星科技有限公司 Vehicle-mounted monitoring self-adaptive exposure method, device and equipment based on light correction
CN116866665A (en) * 2023-09-05 2023-10-10 中信建投证券股份有限公司 Video playing method and device, electronic equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008106994A1 (en) * 2007-03-07 2008-09-12 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Concept for determining a video quality measure for block coded images
CN104301722A (en) * 2014-11-03 2015-01-21 电子科技大学 Video stream fuzzy detection method based on frequency domain
US9232118B1 (en) * 2015-01-23 2016-01-05 Interra Systems, Inc Methods and systems for detecting video artifacts
JP6578619B1 (en) * 2019-04-11 2019-09-25 株式会社ラムテック Image analysis apparatus and image analysis program
CN112818737A (en) * 2020-12-18 2021-05-18 广州视源电子科技股份有限公司 Video identification method and device, storage medium and terminal

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008106994A1 (en) * 2007-03-07 2008-09-12 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Concept for determining a video quality measure for block coded images
CN104301722A (en) * 2014-11-03 2015-01-21 电子科技大学 Video stream fuzzy detection method based on frequency domain
US9232118B1 (en) * 2015-01-23 2016-01-05 Interra Systems, Inc Methods and systems for detecting video artifacts
JP6578619B1 (en) * 2019-04-11 2019-09-25 株式会社ラムテック Image analysis apparatus and image analysis program
CN112818737A (en) * 2020-12-18 2021-05-18 广州视源电子科技股份有限公司 Video identification method and device, storage medium and terminal

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
A.HERBULOT 等: "SHAPE GRADIENT FOR IMAGE SEGMENTATION USING INFORMATION THEORY", 《 ICASSP 2004》 *
李鹏程: "模糊图像评价及在视频去模糊中的应用", 《硕士学位论文》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115687677A (en) * 2022-10-18 2023-02-03 武汉骏信达信息咨询有限公司 Data storage management method and system based on artificial intelligence
CN115687677B (en) * 2022-10-18 2024-03-22 浙江丰能医药科技有限公司 Data storage management method and system based on artificial intelligence
CN115866411A (en) * 2023-03-01 2023-03-28 深圳市昂星科技有限公司 Vehicle-mounted monitoring self-adaptive exposure method, device and equipment based on light correction
CN116866665A (en) * 2023-09-05 2023-10-10 中信建投证券股份有限公司 Video playing method and device, electronic equipment and storage medium
CN116866665B (en) * 2023-09-05 2023-11-14 中信建投证券股份有限公司 Video playing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN113411571B (en) 2023-07-14

Similar Documents

Publication Publication Date Title
CN113411571A (en) Video frame definition detection method based on sliding window gradient entropy
US11800969B2 (en) Method and device for monitoring colonoscope withdrawal speed
JP5701005B2 (en) Object detection apparatus, object detection method, surveillance camera system, and program
CN109167997B (en) Video quality diagnosis system and method
JP6565600B2 (en) Attention detection device and attention detection method
WO2017047494A1 (en) Image-processing device
CN112367520B (en) Video quality diagnosis system based on artificial intelligence
RU2419150C1 (en) Method to process sequence of images to detect and follow air objects
CN109996063B (en) Video image screen splash detection method and device, computer equipment and storage medium
WO2017107395A1 (en) Image processing method and system
US11393091B2 (en) Video image processing and motion detection
US10728476B2 (en) Image processing device, image processing method, and image processing program for determining a defective pixel
CN114205578A (en) Video fuzzy anomaly detection method and system based on frequency domain skewness and frequency domain peak value
US20220392225A1 (en) Concept for Detecting an Anomaly in Input Data
US11631183B2 (en) Method and system for motion segmentation
CN115953427A (en) Dynamic target real-time tracking method and device for small sample training
CN110309838B (en) Object contour detection preprocessing method for video detection area based on exponential transformation
JP7409606B2 (en) Image processing device, image processing method and program
CN110349133B (en) Object surface defect detection method and device
US10277926B2 (en) Block-base error measure method for object segmentation
JP3994416B1 (en) Abnormality detection device, program, and abnormality detection method
JP7285661B2 (en) Suspicious behavior detector
CN112261386B (en) High-speed frame difference backup system for video
CN112529956B (en) Blackbody position detection method, electronic device and computer readable storage medium
TWI512638B (en) Intelligent area method and automatic camera state judgment method

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