CN107197233A - Monitor video quality of data evaluating method and device based on edge calculations model - Google Patents
Monitor video quality of data evaluating method and device based on edge calculations model Download PDFInfo
- Publication number
- CN107197233A CN107197233A CN201710486709.0A CN201710486709A CN107197233A CN 107197233 A CN107197233 A CN 107197233A CN 201710486709 A CN201710486709 A CN 201710486709A CN 107197233 A CN107197233 A CN 107197233A
- Authority
- CN
- China
- Prior art keywords
- color
- value
- video
- background picture
- threshold
- 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
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
Abstract
The present invention provides a kind of monitor video quality of data evaluating method based on edge calculations model, it is characterised in that comprise the following steps：Video acquisition step, data processing step and quality inspection steps.Quality inspection steps include blur detection step and/or color detection step；Wherein, blur detection step carries out analysis calculating to the monitor video background picture of extraction, obtains corresponding values of ambiguity；And judge whether image is clear according to default Fuzzy Threshold；Color detection step carries out analysis calculating according to color histogram nomography to the background picture of extraction, obtains color accounting value；And judge whether color of image is normal according to default color threshold.The present invention can accurately judge the quality of video monitoring picture, fundamentally solving artificial judgment video monitoring image quality wastes time and energy and the skimble-scamble technological deficiency of subjective criterion, the present invention can also further Intelligent Recognition internet off-line failure, improve fault detection efficiency.
Description
Technical field
The invention belongs to technical field of video monitoring, and in particular to a kind of monitor video data based on edge calculations model
Quality assessment method and device
Background technology
With the expansion of city size, video monitoring system is in public safety, financial instrument, bank, shop, intelligent building
In terms of effect constantly protrude, especially in terms of public safety.Nowadays monitoring system entire scope is constantly expanding, prison
Density is controlled also to expand.In the larger Video Monitoring Terminal of data scale, malfunctioned for monitoring terminal equipment, we may nothing
Method is accurately positioned and handled all fault messages, it is therefore desirable to which certain manpower is participated in, and checks these fault messages, and at this
During, terminal user judges the content of video by Consumer's Experience, and so the expense to man power and material is also quite huge
Big.So when video monitoring system malfunctions, operation maintenance personnel will take for the substantial amounts of time to be inquired about and error correction, and this is big
Scale video monitoring system can not ensure its real-time, can not also ensure the quality of data of monitor video.Therefore how to manage and regard
Frequency monitoring system, is reduced because monitoring system malfunctions and causes the real-time of video monitoring system to lack, and manpower checks institute
The time of waste and guarantee video monitoring data quality, are technical problems urgently to be resolved hurrily.
The content of the invention
It can not accurately judge the above-mentioned technological deficiency of video monitoring data quality problems to solve video monitoring system, this
Invention provides a kind of monitor video quality of data evaluating method and device based on edge calculations model.
The present invention is achieved by the following technical solutions：
A kind of monitor video quality of data evaluating method based on edge calculations model, it is characterised in that including following step
Suddenly：
Video acquisition step：
According to default time interval, periodically collection obtains one section of video from Video Monitoring Terminal；
Data processing step：
The video of collection is handled, corresponding background picture is therefrom extracted；
Quality inspection steps：
Including blur detection step and/or color detection step；Wherein,
Blur detection step is specially：Analysis calculating is carried out to the background picture of extraction, corresponding values of ambiguity is obtained；And
Judged according to default Fuzzy Threshold, if values of ambiguity is less than Fuzzy Threshold, be judged as image blurring；If values of ambiguity
More than or equal to Fuzzy Threshold, then it is judged as image clearly；
Color detection step is specially：Analysis calculating is carried out to the background picture of extraction according to color histogram nomography, obtained
Obtain color accounting value；And judged according to default color threshold, if color accounting value is more than or equal to color threshold, judge
For color of image mistake；If color accounting value is respectively less than color threshold, it is judged as that color of image is normal.
The present invention is relative to the beneficial effect of prior art：
1. the evaluating method and device of the video monitoring data quality based on edge calculations model that the present invention is provided, can
The accurate quality for judging video monitoring picture, fundamentally solving artificial judgment video monitoring image quality wastes time and energy and subjective
The skimble-scamble technological deficiency of standard.
2. can judge whether video monitoring picture is normal in time, if finding, error message issues the user with alarm in time,
User is timely repaired the Video Monitoring Terminal of damage, reduce mean repair time (MTTR), real-time guarantees video counts
According to quality.
Brief description of the drawings
Fig. 1 is the general flow chart of the evaluating method of the video monitoring data quality based on edge calculations model of embodiment 1；
Fig. 2 is the particular flow sheet of data processing step；
Fig. 3 is the particular flow sheet of blur detection step；
Fig. 4 is the particular flow sheet of color detection step；
Fig. 5 carries out a background picture of blur detection step operation for plan；
Fig. 6 is a kind of result that blur detection step is exported；
Fig. 7 carries out another background picture of blur detection step operation for plan；
Fig. 8 is another result that blur detection step is exported.
Fig. 9 carries out a background picture of color detection step operation for plan；
Figure 10 is a kind of result that color detection step is exported；
Figure 11 carries out another background picture of color detection step operation for plan；
Figure 12 is another result that color detection step is exported.
Figure 13 is the main-process stream of the evaluating method of the video monitoring data quality based on edge calculations model of embodiment 2
Figure；
Figure 14 is the structural frames of the evaluating apparatus of the video monitoring data quality based on edge calculations model of embodiment 3
Figure；
Figure 15 is the structured flowchart of fuzzy detection module；
Figure 16 is the structured flowchart of color detection module；
Figure 17 is the structural frames of the evaluating apparatus of the video monitoring data quality based on edge calculations model of embodiment 4
Figure.
In all of the figs, identical reference is used for representing identical element or structure, including：
Video acquisition unit 1, data processing unit 2, quality testing unit 3, fuzzy detection module 31, values of ambiguity is calculated
Submodule 311, color detection module 32, color accounting value calculating sub module 321, off-line monitoring unit 4.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that embodiment described herein is only to explain the present invention,
It is not intended to limit the present invention.
Embodiment 1：
The present invention is applied to video monitoring system, and video monitoring system mainly includes high in the clouds, marginal end and client three
It is grouped into.The present embodiment can be based on Win7x64, VS2015, opencv3.2.0 environment exploitation.
The hardware environment of recommendation be the core processors of InterCorei5-6500 3.20GHz tetra-, 16GB (Jin Shidun
DDR42400MHz) internal memory, InterHDGraphics530 video cards.
Above hardware environment is only to better illustrate the present invention, by way of example only, is not intended to limit the protection of the present invention
Scope, those skilled in the art can select other suitable hardware environments according to actual needs.
As shown in figure 1, the present embodiment provides a kind of evaluation and test side of the video monitoring data quality based on edge calculations model
Method, comprises the following steps：
Video acquisition step S1：According to default time interval, periodically one section of collection acquisition is regarded from Video Monitoring Terminal
Frequently.Data processing step S2：The video of collection is handled, corresponding background picture is therefrom extracted.
Quality inspection steps S3：Including blur detection step S31 and/or color detection step S32.
Wherein,
Blur detection step S31 is specially：Analysis calculating is carried out to the background picture of extraction, corresponding fuzziness is obtained
Value；And judged according to default Fuzzy Threshold, if values of ambiguity is less than Fuzzy Threshold, it is judged as image blurring；If mould
Paste angle value and be more than or equal to Fuzzy Threshold, be then judged as image clearly.
Color detection step S32 is specially：Analysis calculating is carried out to the background picture of extraction according to color histogram nomography,
Obtain color accounting value；And judged according to default color threshold, if color accounting value is more than or equal to color threshold, sentence
Break as color of image mistake；If color accounting value is respectively less than color threshold, it is judged as that color of image is normal.
In the present embodiment, video acquisition step S1 is specially：Monitoring terminal equipment is called using VideoCapture classes
And gather one section of video of acquisition.
Opencv 3.2.0VideoCapture classes are used in the present embodiment, and such is mainly read video
Extract operation and call camera, and such provides a series of C++API interfaces, mainly realize in the present embodiment to regarding
The function of frequency read operation.
As shown in Fig. 2 in the present embodiment, data processing step S2 specifically includes following steps：
Step S201, the image of each frame of video is obtained by the read methods in VideoCapture classes；
Step S202, foreground mask is obtained by the apply functions in BackgroundSubtractorMOG2 classes；
Step S203, is extracted by the getBackgroundImage functions in BackgroundSubtractorMOG2 classes
Background picture.
Called in above-mentioned steps be Opencv from tape function, wherein：
VideoCapture::The read functions are for reading video file or capture data from decoding and returning just
The frame of capture, were it not for frame of video it is captured (camera do not connect or video file in there is no more frames) will return
false.Main in the present embodiment realize is the function of reading each frame of video.
BackgroundSubtractorMOG2::The apply functions are mainly calculating background mask, in the present embodiment
Background mask is predominantly obtained by background subtraction.
BackgroundSubtractorMOG2::The getBackgroundImage functions are mainly calculating background picture,
Function in the present embodiment is acquisition background picture.
As shown in figure 3, in the present embodiment, the computational methods of values of ambiguity are specially in blur detection step S31：
Step S311, the rgb value that traversal background picture is each put；
Step S312, according to summation and background picture area ratio of the B values in the rgb value of each point by conversion income value
Absolute value, as values of ambiguity.
Specific conversion process is as follows in this step：
0.5 times of B values in the pixel value each put using the picture subtracts the B values of the first pixel value of vertical direction
Plus the B values of the pixel value of 0.5 times of second point of vertical direction, obtain value sum, sum value and add second point of vertical direction
Sum values subtract 0.5 times of the sum values of first point of vertical direction
As shown in figure 4, in the present embodiment, the computational methods of color accounting value are specially in color detection step S32：
Background picture, is first converted to hsv color space by step S321；
Step S322, according to the two-dimensional histogram of CvHistogram classes establishment hsv color space picture, and according to
CvQueryHistValue_2D functions obtain the statistics number of each color, find the maximum of Color Statistical number of times, obtain it
9-16 point around Color Statistical maximum；
Called in above-mentioned steps be Opencv from tape function, wherein：
CvHistogram classes mainly realize that creating 2 ties up histogram to create multi-dimensions histogram, in the present embodiment.
The cvQueryHistValue_2D functions are mainly the designated value for returning to single channel array, in the present embodiment
Function is mainly the height i.e. statistics number for obtaining each color in the picture color histogram.
Step S323, calculate the maximum and take out around several points statistics number and with background picture each color
The ratio of the sum of statistics number, as color accounting value.
It can be selected as the case may be on Fuzzy Threshold and color threshold, generally, Fuzzy Threshold can
To be determined in the range of 0.00001 to 0.0001, color threshold can be determined in the range of 0.7 to 1.Herein
The scope of Fuzzy Threshold and color threshold by way of example only, the protection domain being not intended to limit the present invention, in practical application
In, those skilled in the art can select Fuzzy Threshold and the color threshold being adapted to according to actual conditions.
Blur detection step S31 operation principle and technique effect are further described with reference to instantiation：
Shown in Fig. 5 is that data processing step S2 extracts the background picture obtained, is counted by blur detection step S31
The specific calculating process for calculating the values of ambiguity of the background picture is as follows：
1. each point for traveling through picture by row obtains its pixel value rgb；
2. the value b of the channel B is worth to according to rgb；
The value that 0.5 times of 3.b values subtracts the first channel B of vertical direction adds 0.5 times of vertical direction second
The channel B of point is worth to value sum；
4.sum values subtract the sum of 0.5 times of second point of vertical direction plus the sum values of first point of vertical direction again
Value, obtains value z；
5. calculate the summation total for the z values that the picture is each put；
The absolute value of 6.total values and the ratio of the area of the picture is the fuzzy value of the picture.
In the present embodiment, Fuzzy Threshold is preset as 10-5(can be adjusted according to actual conditions), accordingly, values of ambiguity
Less than Fuzzy Threshold, be determined as it is image blurring, output result as shown in fig. 6, in time notify maintenance personal arrange maintenance.
Shown in Fig. 7 is that data processing step S2 extracts another background picture obtained, passes through blur detection step S31
The specific calculating process for calculating the values of ambiguity of the background picture is as follows：
1. each point for traveling through picture by row obtains its pixel value rgb；
2. the value b of the channel B is worth to according to rgb；
The value that 0.5 times of 3.b values subtracts the first channel B of vertical direction adds 0.5 times of vertical direction second
The channel B of point is worth to value sum；
4.sum values subtract the sum of 0.5 times of second point of vertical direction plus the sum values of first point of vertical direction again
Value, obtains value z；
5. calculate the summation total for the z values that the picture is each put；
The absolute value of 6.total values and the ratio of the area of the picture is the fuzzy value of the picture.
In the present embodiment, Fuzzy Threshold is preset as 10-5(can be adjusted according to actual conditions), accordingly, values of ambiguity
More than Fuzzy Threshold, it is determined as image clearly, output result is as shown in Figure 8.
Color detection step S32 operation principle and technique effect are further described with reference to instantiation：
Shown in Fig. 9 is that data processing step S2 extracts the background picture obtained, is counted by color detection step S32
The specific calculating process for calculating the color accounting value of the background picture is as follows：
1. according to the color histogram of the picture, find the maximum value of statistics number in the color histogram；
2. according to maximum value, find its position m in picture；
3. finding 9-16 point around m, and calculate the summation sum of the statistics number of these points；
4. calculate all colours statistics number in the picture color histogram and total；
5. sum and total ratio are calculated, i.e. color accounting value.
In the present embodiment, color threshold is preset as 0.9 (can be adjusted according to actual conditions), accordingly, color accounting
Value is more than color threshold, is determined as that the blank screen phenomenon shown in Fig. 9, output result such as Figure 10 occur in color of image mistake, i.e. image
It is shown, notify maintenance personal to arrange maintenance in time.
Shown in Figure 11 is that data processing step S2 extracts another background picture obtained, passes through color detection step
S32 calculates the calculating process of the color accounting value of the background picture：
1. according to the color histogram of the picture, find the maximum value of statistics number in the color histogram；
2. according to maximum value, find its position m in picture；
3. finding 9-16 point around m, and calculate the summation sum of the statistics number of these points；
4. calculate all colours statistics number in the picture color histogram and total；
5. sum and total ratio are calculated, i.e. color accounting value.
In the present embodiment, color threshold is preset as 0.9 (can be adjusted according to actual conditions), accordingly, color accounting
Value is less than color threshold, is determined as that color of image is normal, output result is as shown in figure 12.
Understand according to the above description, the video monitoring data quality based on edge calculations model that the present embodiment is provided is commented
Survey method can be recognized effectively because Video Monitoring Terminal is focused the inaccurate fuzzy class problem occurred, and there is white screen, it is black
Screen, green screen class problem, can substantially reduce the plenty of time spent in detecting and safeguarding video monitoring system, human and material resources
And financial resources.
Embodiment 2：
As shown in figure 13, compared with Example 1, difference is the present embodiment：Increase before video acquisition step S1 from
Line monitoring step S0：It is whether offline according to ping command determinations Video Monitoring Terminal.
The ping orders concrete operations are the IP address of ping Video Monitoring Terminals, obtain packet loss, check in result
Packet loss judges whether video terminal is offline.Generally, when packet loss is more than 100%, judge that the video monitoring is whole
Hold as off-line state.
The other technical characteristics of the present embodiment are same as Example 1, will not be repeated here.
Understand according to the above description, the video monitoring data quality based on edge calculations model that the present embodiment is provided is commented
Survey method can effectively monitor the presence of each Video Monitoring Terminal, and the video monitoring in off-line state can be found in time
Terminal, greatly promotes the efficiency for finding and solving abnormal problem.
Embodiment 3：
As shown in figure 14, a kind of monitor video quality of data evaluating apparatus based on edge calculations model, including：
Video acquisition unit 1：For according to default time interval, periodically collection to obtain one section from Video Monitoring Terminal
Video.Data processing unit 2：Handled for the video to collection, therefrom extract corresponding background picture.
Quality testing unit 3：Including fuzzy detection module 31 and/or color detection module 32.
Wherein,
Fuzzy detection module 31 is used to carry out analysis calculating to the background picture of extraction, obtains corresponding values of ambiguity；And
Judged according to default Fuzzy Threshold, if values of ambiguity is less than Fuzzy Threshold, be judged as image blurring；If values of ambiguity
More than or equal to Fuzzy Threshold, then it is judged as image clearly.
Color detection module 32 is used to carry out analysis calculating to the background picture of extraction according to color histogram nomography, obtains
Color accounting value；And judged according to default color threshold, if color accounting value is more than or equal to color threshold, it is judged as
Color of image mistake；If color accounting value is respectively less than color threshold, it is judged as that color of image is normal.
As shown in figure 15, fuzzy detection module 31 includes values of ambiguity calculating sub module 311, values of ambiguity calculating sub module
311 are used to travel through the rgb value that background picture is each put；According in the rgb value of each point B values by conversion income value summation with
The absolute value of background picture area ratio, as values of ambiguity.
As shown in figure 16, color detection module 32 includes color accounting value calculating sub module 321, and color accounts for ratio calculation
Module 321 is used to background picture be converted to hsv color space；Hsv color space picture is created according to CvHistogram classes
Two-dimensional histogram, and according to the statistics number of cvQueryHistValue_2D functions acquisition each color, find Color Statistical
Several maximums, obtains 9-16 point around its Color Statistical maximum；Several points around calculating the maximum and taking out
It is statistics number and with background picture each color statistics number and ratio, as color accounting value.
The video monitoring data quality assessment device that the present embodiment is provided focuses primarily on marginal end i.e. Video Monitoring Terminal and set
In standby, each Video Monitoring Terminal equipment includes a video monitoring data quality assessment device.
The present embodiment is corresponding with the monitor video quality of data evaluating method based on edge calculations model of embodiment 1
Device, its concrete operating principle is substantially the same manner as Example 1, will not be repeated here.
Embodiment 4：
As shown in figure 17, compared with Example 3, difference is the present embodiment：Also include off-line monitoring unit 4：For root
It is whether offline according to ping command determinations Video Monitoring Terminal.
The present embodiment is corresponding with the monitor video quality of data evaluating method based on edge calculations model of embodiment 2
Device, its concrete operating principle is substantially the same manner as Example 2, will not be repeated here.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, it is not used to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the invention etc., it all should include
Within protection scope of the present invention.
Claims (10)
1. a kind of monitor video quality of data evaluating method based on edge calculations model, it is characterised in that comprise the following steps：
Video acquisition step：According to default time interval, periodically collection obtains one section of video from Video Monitoring Terminal；
Data processing step：The video of collection is handled, corresponding background picture is therefrom extracted；
Quality inspection steps：Including blur detection step and/or color detection step；Wherein,
The blur detection step is specially：Analysis calculating is carried out to the background picture of extraction, corresponding values of ambiguity is obtained；And
Judged according to default Fuzzy Threshold, if the values of ambiguity is less than the Fuzzy Threshold, be judged as image mould
Paste；
If the values of ambiguity is more than or equal to the Fuzzy Threshold, it is judged as image clearly；
The color detection step is specially：Analysis calculating is carried out to the background picture of extraction according to color histogram nomography, obtained
Obtain color accounting value；And judged according to default color threshold, if the color accounting value is more than or equal to the color threshold
Value, then be judged as color of image mistake；If the color accounting value is respectively less than the color threshold, it is judged as color of image just
Often.
2. a kind of monitor video quality of data evaluating method based on edge calculations model according to claim 1, it is special
Levy and be, the video acquisition step is specially：
Monitoring terminal equipment is called using VideoCapture classes and gathers one section of video of acquisition.
3. a kind of monitor video quality of data evaluating method based on edge calculations model according to claim 2, it is special
Levy and be, the data processing step is specially：
The image of each frame of the video is obtained by the read methods in VideoCapture classes；
Foreground mask is obtained by the apply functions in BackgroundSubtractorMOG2 classes；
Background picture is extracted by the getBackgroundImage functions in BackgroundSubtractorMOG2 classes.
4. a kind of monitor video quality of data evaluating method based on edge calculations model according to claim 3, it is special
Levy and be, the computational methods of values of ambiguity are specially described in the blur detection step：
Travel through the rgb value that the background picture is each put；
Absolute value according to B values in the rgb value of each point by the summation and the background picture area ratio of conversion income value,
As described values of ambiguity.
5. a kind of monitor video quality of data evaluating method based on edge calculations model according to claim 3, it is special
Levy and be, the computational methods of color accounting value are specially described in the color detection step：
The background picture is first converted to hsv color space；
According to the two-dimensional histogram of CvHistogram classes establishment hsv color space picture, and according to
CvQueryHistValue_2D functions obtain the statistics number of each color, find the maximum of Color Statistical number of times, obtain it
9-16 point around Color Statistical maximum；
Around calculating the maximum and taking out several points statistics number and with the background picture each color statistics number
Sum ratio, as described color accounting value.
6. a kind of monitor video quality of data evaluation and test based on edge calculations model according to any one of claim 1-5
Method, it is characterised in that the scope of the Fuzzy Threshold is 0.00001 to 0.0001, the scope of the color threshold for 0.7 to
1。
7. according to a kind of monitor video quality of data evaluating method based on edge calculations model of claim 1, it is characterised in that
Also include off-line monitoring step：Whether Video Monitoring Terminal is offline according to ping command determinations.
8. a kind of monitor video quality of data evaluating apparatus based on edge calculations model, it is characterised in that including：
Video acquisition unit：For according to default time interval, periodically collection to obtain one section of video from Video Monitoring Terminal；
Data processing unit：Handled for the video to collection, therefrom extract corresponding background picture；
Quality testing unit：Including fuzzy detection module and/or color detection module；Wherein,
The fuzzy detection module is used to carry out analysis calculating to the background picture of extraction, obtains corresponding values of ambiguity；And root
Judged according to default Fuzzy Threshold, if the values of ambiguity is less than the Fuzzy Threshold, be judged as image blurring；If institute
Values of ambiguity is stated more than or equal to the Fuzzy Threshold, then is judged as image clearly；
The color detection module is used to carry out analysis calculating to the background picture of extraction according to color histogram nomography, obtains face
Color accounting value；And judged according to default color threshold, if the color accounting value is more than or equal to the color threshold,
It is judged as color of image mistake；If the color accounting value is respectively less than the color threshold, it is judged as that color of image is normal.
9. a kind of monitor video quality of data evaluating apparatus based on edge calculations model according to claim 8, it is special
Levy and be：
The fuzzy detection module includes values of ambiguity calculating sub module, and the values of ambiguity calculating sub module is described for traveling through
The rgb value that background picture is each put；According to summation and the Background of the B values in the rgb value of each point by conversion income value
The absolute value of piece area ratio, as described values of ambiguity；
The color detection module includes color accounting value calculating sub module, and the color accounting value calculating sub module is used for institute
State background picture and be converted to hsv color space；It is straight according to the two dimension that CvHistogram classes create hsv color space picture
Fang Tu, and according to the statistics number of cvQueryHistValue_2D functions acquisition each color, find Color Statistical number of times most
Big value, obtains 9-16 point around its Color Statistical maximum；The statistics time of several points around calculating the maximum and taking out
It is several and with the background picture each color statistics number and ratio, as described color accounting value.
10. a kind of monitor video quality of data evaluating apparatus based on edge calculations model according to claim 8, it is special
Levy and be, in addition to off-line monitoring unit：It is whether offline for the Video Monitoring Terminal according to ping command determinations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486709.0A CN107197233A (en) | 2017-06-23 | 2017-06-23 | Monitor video quality of data evaluating method and device based on edge calculations model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486709.0A CN107197233A (en) | 2017-06-23 | 2017-06-23 | Monitor video quality of data evaluating method and device based on edge calculations model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107197233A true CN107197233A (en) | 2017-09-22 |
Family
ID=59878700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710486709.0A Pending CN107197233A (en) | 2017-06-23 | 2017-06-23 | Monitor video quality of data evaluating method and device based on edge calculations model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107197233A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280780A (en) * | 2018-01-18 | 2018-07-13 | 深圳市麦斯杰网络有限公司 | The optimization method and device of property quality product control |
| CN109886963A (en) * | 2019-03-28 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of image processing method and system |
| CN110827364A (en) * | 2018-08-07 | 2020-02-21 | 北京优酷科技有限公司 | Method and device for detecting green screen image |
| CN112087509A (en) * | 2020-09-03 | 2020-12-15 | 哈尔滨工业大学 | Task migration method in edge computing platform |
| CN112200807A (en) * | 2020-12-07 | 2021-01-08 | 光谷技术有限公司 | Video quality diagnosis method and system |
| CN112257691A (en) * | 2020-12-21 | 2021-01-22 | 江苏移动信息系统集成有限公司 | Community security implementation method, system and equipment based on 5G edge calculation |
| CN112749645A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Garment color detection method, device and equipment based on monitoring video |
| CN113691801A (en) * | 2021-08-17 | 2021-11-23 | 国网安徽省电力有限公司检修分公司 | Video monitoring equipment fault monitoring method and system based on video image analysis |
| CN114170619A (en) * | 2021-10-18 | 2022-03-11 | 中标慧安信息技术股份有限公司 | Data checking method and system based on edge calculation |
| CN114581857A (en) * | 2022-05-06 | 2022-06-03 | 武汉兑鑫科技实业有限公司 | Intelligent crown block control method based on image analysis |
| CN115841478A (en) * | 2022-12-16 | 2023-03-24 | 浙江科达利实业有限公司 | Quality detection system applied to vehicle-mounted air conditioner hose production management and control |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102006459A (en) * | 2010-11-09 | 2011-04-06 | 中国电信股份有限公司 | Intelligent video image diagnosis system and method |
| CN202085261U (en) * | 2010-12-14 | 2011-12-21 | 广东鑫程电子科技有限公司 | Intelligent video diagnosing and monitoring system |
| CN104123566A (en) * | 2013-04-24 | 2014-10-29 | 信帧电子技术（北京）有限公司 | Video fuzziness-invariable target tracking method and system |
| CN104200475A (en) * | 2014-09-05 | 2014-12-10 | 中国传媒大学 | Novel no-reference image blur degree estimation method |
| CN104537649A (en) * | 2014-12-16 | 2015-04-22 | 厦门雅迅网络股份有限公司 | Vehicle steering judgment method and system based on image ambiguity comparison |
| CN106851263A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | Video quality diagnosing method and system based on timing self-learning module |
-
2017
- 2017-06-23 CN CN201710486709.0A patent/CN107197233A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102006459A (en) * | 2010-11-09 | 2011-04-06 | 中国电信股份有限公司 | Intelligent video image diagnosis system and method |
| CN202085261U (en) * | 2010-12-14 | 2011-12-21 | 广东鑫程电子科技有限公司 | Intelligent video diagnosing and monitoring system |
| CN104123566A (en) * | 2013-04-24 | 2014-10-29 | 信帧电子技术（北京）有限公司 | Video fuzziness-invariable target tracking method and system |
| CN104200475A (en) * | 2014-09-05 | 2014-12-10 | 中国传媒大学 | Novel no-reference image blur degree estimation method |
| CN104537649A (en) * | 2014-12-16 | 2015-04-22 | 厦门雅迅网络股份有限公司 | Vehicle steering judgment method and system based on image ambiguity comparison |
| CN106851263A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | Video quality diagnosing method and system based on timing self-learning module |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280780A (en) * | 2018-01-18 | 2018-07-13 | 深圳市麦斯杰网络有限公司 | The optimization method and device of property quality product control |
| CN110827364A (en) * | 2018-08-07 | 2020-02-21 | 北京优酷科技有限公司 | Method and device for detecting green screen image |
| CN109886963A (en) * | 2019-03-28 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of image processing method and system |
| CN112087509B (en) * | 2020-09-03 | 2022-04-19 | 哈尔滨工业大学 | Task migration method in edge computing platform |
| CN112087509A (en) * | 2020-09-03 | 2020-12-15 | 哈尔滨工业大学 | Task migration method in edge computing platform |
| CN112200807A (en) * | 2020-12-07 | 2021-01-08 | 光谷技术有限公司 | Video quality diagnosis method and system |
| CN112257691A (en) * | 2020-12-21 | 2021-01-22 | 江苏移动信息系统集成有限公司 | Community security implementation method, system and equipment based on 5G edge calculation |
| CN112257691B (en) * | 2020-12-21 | 2021-05-11 | 江苏移动信息系统集成有限公司 | Community security implementation method, system and equipment based on 5G edge calculation |
| CN112749645A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Garment color detection method, device and equipment based on monitoring video |
| CN112749645B (en) * | 2020-12-30 | 2023-08-01 | 成都云盯科技有限公司 | Clothing color detection method, device and equipment based on monitoring video |
| CN113691801A (en) * | 2021-08-17 | 2021-11-23 | 国网安徽省电力有限公司检修分公司 | Video monitoring equipment fault monitoring method and system based on video image analysis |
| CN113691801B (en) * | 2021-08-17 | 2024-04-19 | 国网安徽省电力有限公司超高压分公司 | Video image analysis-based fault monitoring method and system for video monitoring equipment |
| CN114170619A (en) * | 2021-10-18 | 2022-03-11 | 中标慧安信息技术股份有限公司 | Data checking method and system based on edge calculation |
| CN114581857A (en) * | 2022-05-06 | 2022-06-03 | 武汉兑鑫科技实业有限公司 | Intelligent crown block control method based on image analysis |
| CN114581857B (en) * | 2022-05-06 | 2022-07-05 | 武汉兑鑫科技实业有限公司 | Intelligent crown block control method based on image analysis |
| CN115841478A (en) * | 2022-12-16 | 2023-03-24 | 浙江科达利实业有限公司 | Quality detection system applied to vehicle-mounted air conditioner hose production management and control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107197233A (en) | Monitor video quality of data evaluating method and device based on edge calculations model | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN105791774A (en) | Surveillance video transmission method based on video content analysis | |
| CN105303158A (en) | Line-fitting video intelligent analysis algorithm for disconnecting switch of transformer station | |
| CN105957088B (en) | Transformer composite insulator casing monitoring method and system based on computer vision | |
| CN111222478A (en) | Construction site safety protection detection method and system | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN113837991A (en) | Image processing method, device, equipment and storage medium | |
| CN113096158A (en) | Moving object identification method and device, electronic equipment and readable storage medium | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN112396635A (en) | Multi-target detection method based on multiple devices in complex environment | |
| CN112115875A (en) | Forest fire smoke root detection method based on dynamic and static combination area stacking strategy | |
| CN112053322B (en) | Method for segmenting and detecting surface shielding of photovoltaic cell panel | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
| CN112967221A (en) | Shield constructs section of jurisdiction production and assembles information management system | |
| CN103996199A (en) | Movement detection method based on depth information | |
| CN116612355A (en) | Training method and device for face fake recognition model, face recognition method and device | |
| WO2023070955A1 (en) | Method and apparatus for detecting tiny target in port operation area on basis of computer vision | |
| CN105187821A (en) | Video quality intelligent diagnostic analysis system | |
| KR20180129389A (en) | Watt-hour Meter Measurement Data Aggregating Method using Vision Recognition | |
| CN114913370A (en) | State automatic detection method and device based on deep learning and morphology fusion | |
| CN106650546A (en) | Method for automatically identifying substation switchgear equipment object based on two-dimensional code | |
| Mantini et al. | A signal detection theory approach for camera tamper detection | |
| CN111368608A (en) | Face recognition method, device and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170922 |
|
| RJ01 | Rejection of invention patent application after publication |