CN109246424A - Failure video camera method for rapidly positioning based on space-time analysis technology - Google Patents
Failure video camera method for rapidly positioning based on space-time analysis technology Download PDFInfo
- Publication number
- CN109246424A CN109246424A CN201810937927.6A CN201810937927A CN109246424A CN 109246424 A CN109246424 A CN 109246424A CN 201810937927 A CN201810937927 A CN 201810937927A CN 109246424 A CN109246424 A CN 109246424A
- Authority
- CN
- China
- Prior art keywords
- time
- video camera
- space
- camera
- video
- 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
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention belongs to video fault detection technique fields, and in particular to a kind of failure video camera method for rapidly positioning based on space-time analysis technology.The present invention and is stored in temporary data table the following steps are included: from being read needed for calculating analysis in database wait diagnose the space-time data in video monitoring camera, establishes the video fault detection system of space-time foundation；Rule is identified and handled using data exception to being identified and being marked extremely existing for above-mentioned video monitoring camera, marks the video camera of preliminary exception；The Space Lorentz Curve between video camera is obtained, binding time syntople obtains the adjacent relation matrix between space-time object；Judge target video camera Ci whether failure；It alarms failure video camera.The accuracy rate of diagnosis of video failure can be not only greatly improved in the present invention, and reduces the rate of false alarm of fault diagnosis.
Description
Technical field
The invention belongs to video fault detection technique fields, and in particular to a kind of failure camera shooting based on space-time analysis technology
Machine method for rapidly positioning.
Background technique
The video surveillance applications in current China are very universal, and traffic, public security, finance, army, prison etc. are all or just
In construction video fault diagnosis system, distinctive timeliness, accuracy and intuitive are provided to people's lives and property
It ensures, so that monitoring system has been to be concerned by more and more people and approves.However as the rapid growth of video monitoring service,
Its there are the problem of be also gradually exposed, as video fault diagnosis system frequently occurs, malfunction monitoring difficulty is big, processing is too late
When, the situations such as O&M amount is big, while monitor camera be also usually because cannot timely safeguard, repair and replace so that
The using effect of video fault diagnosis system is had a greatly reduced quality.In existing video quality diagnosis system, one side maintenance work
It is all mainly manually to detect and handle；On the other hand also occur similar failure on current monitor supervision platform and the function such as detect automatically
Can, but these functions only rest on and simply judge that the simple failures such as equipment drawing picture whether there is, whether network is connected to are sentenced
It is disconnected；Simultaneously from time and space dimensional analysis monitor camera there are certain difficulty, also all to the applications of video camera monitoring data
Not enough sufficiently.Whether can develop a kind of while consider the time of monitor camera and the analysis method of space characteristics, thus
It can be according to the preliminary abnormal camera data detected in video fault detection system, with statistical principle and space-time analysis side
Method identification rain, snow, the space-time characterisation of hail, group greasy weather gas or power failure etc. fault of camera in special circumstances, from
And the rate of false alarm of fault diagnosis is significantly reduced while the accuracy rate of diagnosis of video failure is greatly improved, in recent years for this field
Technical problem urgently to be resolved.
Summary of the invention
The purpose of the present invention is overcoming above-mentioned the deficiencies in the prior art, a kind of failure based on space-time analysis technology is provided and is taken the photograph
Camera method for rapidly positioning, based on space and time self-correlation theory, with mathematical statistics basic theories, according to video
The preliminary abnormal video camera detected in fault detection system, analyze rain, snow, the feelings of hail, group's greasy weather gas or power failure
Under condition, the Emergence and Development and evanishment of fault of camera.With point of the different video camera of this method statistic on space-time
Cloth feature can identify and judge abnormal video camera from the time and spatially, so that further support video fault diagnosis is implemented.
The accuracy rate of diagnosis of video failure can be not only greatly improved in the present invention, while also can significantly reduce the rate of false alarm of fault diagnosis.
To achieve the above object, the invention adopts the following technical scheme:
A kind of failure video camera method for rapidly positioning based on space-time analysis technology, it is characterised in that the following steps are included:
(1), it from being read in database needed for calculating analysis wait diagnose the space-time data in video monitoring camera, and deposits
Storage establishes the video fault detection system of space-time foundation in temporary data table；
(2), the data in the temporary data table that read step (1) generates, it is regular right to be identified and handled using data exception
It is identified and is marked extremely existing for above-mentioned video monitoring camera, mark the video camera of preliminary exception, process is as follows:
1) video camera position is obtained according to diagnosis target, the sequence of positions along video camera chooses n location point, is formed
Position point sequence L1, L2 ..., Ln, wherein n be natural number；
2) it is promoted along the position, position sequence described in order traversal, in each location point Lx, executes step 3),
In 1≤x≤n；
3) according to the diagnosis target selection corresponding time, n time point is chosen along time shaft sequence, forms time point sequence
T1,T2,…,Tn；Wherein n is natural number；
4) it is promoted along the time shaft, time point sequence described in order traversal, in each time point Tx, executes step
5), wherein 1≤x≤n；
5) configuration file with the presence or absence of target video camera Ci is started to query from video camera C1, is imaged if there is no target
6) configuration file of machine Ci thens follow the steps, then follow the steps 7) if there is the configuration file of target video camera Ci；
6) algorithm adaptation, adaptation procedure are carried out to target video camera Ci are as follows: with adaptation algorithm Fj to target video camera Ci
The photo of all time point shootings carries out fault diagnosis operation, wherein 1≤j≤m, m are failure item number, calculates to calculate adaptation
The best adaptation times point Tj of method Fj, at the same according to the location point Lj where target video camera Ci and determining its position whether there is
It rains, snow, hail, rolling into a ball the case where greasy weather gas or power failure, to obtain above-mentioned time point Tj, location point Lj and adaptation algorithm
Fj forms corresponding relationship；The result that target video camera Ci algorithm is adapted to is saved, obtains in target video camera Ci institute sometimes
Between point, location point and adaptation algorithm corresponding relationship configuration file, the configuration file of abbreviation target video camera Ci；Execute step
7)；
7) as there are the corresponding adaptation algorithm of time point Tx, then it is suitable executed this in the configuration file of the target video camera Ci
Video diagnosis is carried out with algorithm；Execute step 8)；
8) if diagnostic result is video camera that is fuzzy or going offline, labeled as preliminary abnormal video camera；
(3), the Space Lorentz Curve between video camera is obtained, binding time syntople obtains between space-time object
Adjacent relation matrix, detailed process are as follows:
A, the syntople between the spatial object where target video camera Ci is obtained, what spatial object herein referred to is exactly
The point of monitor camera around target video camera Ci spatially in a certain range；The number phase of two monitor cameras
It is adjacent, then it represents that they are adjacent, otherwise non-conterminous；
B, the neighbouring relations between the time object where acquisition target video camera Ci, herein due to video monitoring camera
In space-time data be all be uniformly distributed within a certain range by certain time interval, therefore by the time range of research by number
Be divided into many periods according to acquisition time interval, the time daily, week, the moon or season statistics；If two times in adjacent time interval,
Then show that two time objects are adjacent；
C, the space-time syntople between space-time object is determined according to the Space Lorentz Curve of acquisition and time syntople,
If two Camera objects spatially and temporally on it is all adjacent, then they in time-space relationship just it is adjacent；For any two
A Camera object all obtains their syntople by step a and b, to obtain space-time adjacency matrix；
(4), the space-time object adjacency matrix obtained according to the space-time data of video camera in step (2) and step (3), judgement
Target video camera Ci whether failure, specifically:
Video fault diagnosis is carried out to other video cameras in target video camera Ci environs；If its in environs
His video camera detecting state is equally also fuzzy or goes offline, then separately marks, detect again after a time；If in environs
Other video cameras are detected as normal condition, the state of other video cameras of repetition measurement Tj time, if state is the fuzzy or state that goes offline,
It then separately marks, detects again after a time；If other video cameras detect still in the Tj time as normal condition, the target is judged just now
Video camera Ci is abnormality machine namely failure video camera；
(5), it alarms the failure video camera obtained in the step (4), achievees the effect that video fault detection.
Preferably, the reading process wait diagnose the space-time data in video monitoring camera in the step 1) is as follows:
A, querying condition is arranged to parameter to be arranged by user individual, as from date and time, the date of expiry and when
Between, the range of monitor camera position, position range allows user to directly select from map, either directly input position or
Directly input the number of monitor camera；
B, database is connected, the querying condition that user inputs is nested in input database in query statement and carries out data
Inquiry operation, inquiry the data obtained are stored in an interim tables of data, the base as subsequent anomalous identification and processing operation
Plinth data.
The beneficial effects of the present invention are:
1), the present invention solves the using effect difference of existing video fault diagnosis flow scheme and judges precision difference or even miss
The high problem of rate is examined, and provides a kind of method for improving video fault detection accuracy using space-time analysis technology.
Specifically, the present invention is to define some video camera based on spatial autocorrelation and time self-correlation theory
As soon as state at a time is a space-time object, then temporal correlation refers to that a certain attribute value of space-time object is adjacent thereto
All space-time objects same attribute value between correlativity.Using the space-time to relationship, the present invention is first according to the time
The image difference opposite sex of each video camera of different time points on axis carries out algorithm adaptation, so that it is special to find each video camera adaptation
Determine the best adaptation times point of algorithm, then the location of target video camera Ci point of arranging in pairs or groups, thus forgo it is rainy, snow, hail,
Group's greasy weather gas or the factor of power failure, just can be carried out video fault diagnosis at this time.And it is taken the photograph in video fault diagnosis, then with target
The location of camera Ci point is basic point, using the space-time to relationship, is carried out to video camera neighbouring on the space-time arround it same
Walk video fault diagnosis.Neighbouring video camera is asked in the image nothing of above-mentioned best adaptation times point on space-time only arround
When topic, can make a definite diagnosis target video camera Ci is failure video camera.Practice have shown that: the present invention is right by above-mentioned multiple reinspection mode
Clarity is abnormal, the abnormal failure phenomenon that goes offline accuracy rate of diagnosis is up to 99%.
To sum up, the present invention is based on space and time self-correlation theory, with mathematical statistics basic theories, according to video
The preliminary abnormal video camera detected in fault detection system, analyze rain, snow, the feelings of hail, group's greasy weather gas or power failure
Under condition, the Emergence and Development and evanishment of fault of camera.With point of the different video camera of this method statistic on space-time
Cloth feature can identify and judge abnormal video camera from the time and spatially, so that further support video fault diagnosis is implemented.
The accuracy rate of diagnosis of video failure can be not only greatly improved in the present invention, and reduces the rate of false alarm of fault diagnosis.
Detailed description of the invention
Fig. 1 is the method flow schematic block diagram of this method；
Fig. 2 is the diagnostic process block diagram of embodiment 1.
Specific embodiment
For ease of understanding, here in connection with attached drawing, specific structure and working method of the invention are made described further below:
As shown in Figs. 1-2, this method is main including the following steps:
(1), from being read in database needed for calculating analysis wait diagnose the space-time data in video monitoring camera.
This space-time data has different observations not only for each monitor camera, for same position when different
Also there is different observations at quarter, has typical space-time double properties.
Detailed process is as follows for above-mentioned reading data:
1, in order to the empty data of real-time query video monitoring camera as needed, by querying condition be arranged to parameter by
User individual setting, such as the range of from date and time, date of expiry and time, monitor camera position, position range
Allow user to directly select from map, directly inputs position, or directly input the number of monitor camera；
2, database is connected, the querying condition that user inputs is nested in input database in query statement and carries out data
Inquiry operation, inquiry the data obtained are stored in an interim tables of data, the base as subsequent anomalous identification and processing operation
Plinth data.
(2), rule is identified and handles using data exception to be identified and marked extremely to existing for video monitoring camera
Note.
The data in temporary data table that read step (1) generates, judge in data according to the recognition rule of abnormal data
The video monitoring camera of existing failure, and labeled as preliminary abnormal video camera.Make labeled as preliminary abnormal video camera
The foundation of the calculating of temporal and spatial correlations index is carried out for subsequent step.
(3), the Space Lorentz Curve between video camera is obtained, binding time syntople obtains between space-time object
Adjacent relation matrix；
According to the connotation of temporal and spatial correlations index, definition on a space-time object adjacent space position, adjacent time point
All space-time objects are the space-time neighborhood of the space-time object, then space-time syntople can be adjacent by Space Lorentz Curve and time
Connect relationship acquisition.
Therefore, the step of calculating the space-time syntople of two space-time objects is as follows:
A, the syntople between the spatial object where target video camera Ci is obtained, what spatial object herein referred to is exactly
The point of monitor camera around target video camera Ci spatially in a certain range；The number phase of two monitor cameras
It is adjacent, then it represents that they are adjacent, otherwise non-conterminous；
B, the neighbouring relations between the time object where acquisition target video camera Ci, herein due to video monitoring camera
In space-time data be all be uniformly distributed within a certain range by certain time interval, therefore by the time range of research by number
Be divided into many periods according to acquisition time interval, the time daily, week, the moon or season statistics；If two times in adjacent time interval,
Then show that two time objects are adjacent；
C, the space-time syntople between space-time object is determined according to the Space Lorentz Curve of acquisition and time syntople,
If two Camera objects spatially and temporally on it is all adjacent, then they in time-space relationship just it is adjacent；For any two
A Camera object all obtains their syntople by step a and b, to obtain space-time adjacency matrix；
(4), the space-time object adjacency matrix obtained according to the space-time data of video camera in step (2) and step (3), judgement
Target video camera Ci whether failure, specifically:
By space-time adjacency matrix, other video cameras in target video camera Ci environs are carried out sometime putting
Video fault diagnosis；If other video camera detecting states in environs are equally also fuzzy or go offline, separately mark,
It detects again after a time, this kind of situation, probably due to influence caused by group's mist phenomenon occur or going offline.If in environs
Other video cameras are detected as normal condition, then the state of other video cameras when repetition measurement is located at other times, if at this time other
Camera status is the fuzzy or state that goes offline, then separately marks, detect again after a time.This kind of situation, probably due to occurring
Influence caused by rolling into a ball mist phenomenon or going offline.If other video cameras are detected as normal condition in the Tj time, the target is judged
Video camera Ci is failure video camera.
(5), it alarms failure video camera, to achieve the effect that video fault detection.
Above-mentioned steps (2), (3), (4) are core of the invention, are made below with reference to 1 pair of embodiment diagnosis process of the invention
It is further to be described in detail.
Embodiment 1:
Video fault diagnosis system be equipped with n platform video camera, formed camera sequence C1, C2 ..., Cn；N in the present embodiment 1
=20000, that is, there are 20000 video cameras.
The video failure is preset m kind failure, is correspondingly matched with the preset adaptation algorithm of m kind, is formed suitable
With sequence of algorithms.Video failure described in the present embodiment 1 includes clarity exception and go offline totally 2 kinds, i.e. m=2 such as abnormal, phase
The adaptation algorithm answered is that adaptation algorithm is clarity exception diagnosis algorithm and the exception diagnosis algorithm that goes offline.
In the present embodiment as shown in Figure 2, comprising the following steps:
According to the diagnosis corresponding time location of target selection, the light filling video camera that Yi Yitai is mounted on underground parking is
Example, using natural light plus the period of general light filling is usually 6:00 to 19:00 in morning, remaining time Duan Zewei reinforcement property
Light filling.Since its image failure has cyclically-varying within the time, select 24 hours in 1 day for time change
Change.According to the light change rate in one day, since 0 point, every 1 hour is a time point, i.e., the described time point is along time shaft
Be uniformly distributed, and formed time point sequence T1, T2 ..., Tn；Wherein n is natural number 24 in the present embodiment.According to diagnosis target choosing
Selecting corresponding time shaft is the prior art, can carry out appropriate adjustment according to the result of a period of time when practical operation, for example select
Week, the moon, season etc., and can correspondingly adjustment time interval.
1) video camera position is obtained according to diagnosis target, the sequence of positions along video camera chooses n location point, is formed
Position point sequence L1, L2 ..., Ln, wherein n be natural number；
2) it is promoted along the position, position sequence described in order traversal, in each location point Lx, executes step 3),
In 1≤x≤n；
3) according to the diagnosis target selection corresponding time, n time point is chosen along time shaft sequence, forms time point sequence
T1,T2,…,Tn；Wherein n is natural number；
4) it is promoted along the time shaft, time point sequence described in order traversal, in each time point Tx, executes step
5), wherein 1≤x≤n；
5) configuration file with the presence or absence of target video camera Ci is started to query from video camera C1, is imaged if there is no target
6) configuration file of machine Ci thens follow the steps, then follow the steps 7) if there is the configuration file of target video camera Ci；
6) algorithm adaptation, adaptation procedure are carried out to target video camera Ci are as follows: with adaptation algorithm Fj to target video camera Ci
The photo of all time point shootings carries out fault diagnosis operation, wherein 1≤j≤m, m are failure item number, calculates to calculate adaptation
The best adaptation times point Tj of method Fj, at the same according to the location point Lj where target video camera Ci and determining its position whether there is
It rains, snow, hail, rolling into a ball the case where greasy weather gas or power failure, to obtain above-mentioned time point Tj, location point Lj and adaptation algorithm
Fj forms corresponding relationship；The result that target video camera Ci algorithm is adapted to is saved, obtains in target video camera Ci institute sometimes
Between point, location point and adaptation algorithm corresponding relationship configuration file, the configuration file of abbreviation target video camera Ci；Execute step
7)；
7) as there are the corresponding adaptation algorithm of time point Tx, then it is suitable executed this in the configuration file of the target video camera Ci
Video diagnosis is carried out with algorithm；Execute step 8)；
8) if diagnostic result is video camera that is fuzzy or going offline, labeled as preliminary abnormal video camera.
9) syntople between the spatial object where the acquisition target video camera Ci object, spatial object herein
What is referred to is exactly the point of the monitor camera in a certain range spatially, and the number of two monitor cameras is adjacent, then it represents that
They are adjacent, otherwise non-conterminous；
10) neighbouring relations between the time object where the acquisition target video camera Ci, herein due to video monitoring
Space-time data in video camera is all to be uniformly distributed within a certain range by certain time interval, therefore by the time model of research
Enclose and be divided into many periods by data collection interval, the time daily, week, the moon or season statistics.If two times are adjacent
In period, then show that two time objects are adjacent；
11) video fault diagnosis is carried out to other video cameras in target video camera Ci environs.If in environs
Other video camera detecting states be equally also it is fuzzy or go offline, then separately mark, detect again after a time.This kind of situation,
Probably due to influence caused by group's mist phenomenon occur or going offline.If other video cameras in environs are detected as normal shape
State performs the next step rapid later.
12) state for detecting other video cameras of Tj time is separately marked if state is the fuzzy or state that goes offline, mistake
The section time is detected again.This kind of situation, probably due to influence caused by group's mist phenomenon occur or going offline.If other video cameras are in Tj
Time is detected as normal condition, then judges that the target video camera Ci is abnormality machine namely failure video camera.
13) i+1 is assigned to i, to realize that Zhuge of video camera checks；It needs to return to step 3) at this time, Zhi Daosuo
Some camera processes finish；
14) i+1 is assigned to i, returns to step 2), is disposed until all time points；
15) i+1 is assigned to i, returned to step 1), until all location points are disposed；
After the completion of the time series and position sequence traverse, video fault diagnosis is completed.
Claims (2)
1. a kind of failure video camera method for rapidly positioning based on space-time analysis technology, it is characterised in that the following steps are included:
(1), it from being read in database needed for calculating analysis wait diagnose the space-time data in video monitoring camera, and is stored in
In temporary data table, the video fault detection system of space-time foundation is established；
(2), the data in the temporary data table that read step (1) generates identify using data exception and handle rule to above-mentioned
It is identified and is marked extremely existing for video monitoring camera, mark the video camera of preliminary exception, process is as follows:
1) video camera position is obtained according to diagnosis target, the sequence of positions along video camera chooses n location point, forming position
Point sequence L1, L2 ..., Ln, wherein n be natural number；
2) it is promoted along the position, position sequence described in order traversal, in each location point Lx, executes step 3), wherein 1≤
x≤n；
3) according to diagnosis the target selection corresponding time, along time shaft sequence choose n time point, formation time point sequence T1,
T2,…,Tn；Wherein n is natural number；
4) it is promoted along the time shaft, time point sequence described in order traversal, in each time point Tx, executes step 5),
In 1≤x≤n；
5) configuration file with the presence or absence of target video camera Ci is started to query from video camera C1, if there is no target video camera Ci
Configuration file then follow the steps 6), thened follow the steps 7) if there is the configuration file of target video camera Ci；
6) algorithm adaptation, adaptation procedure are carried out to target video camera Ci are as follows: all to target video camera Ci with adaptation algorithm Fj
The photo of time point shooting carries out fault diagnosis operation, wherein 1≤j≤m, m are failure item number, to calculate adaptation algorithm Fj
Best adaptation times point Tj, while under determining that its position whether there is according to the location point Lj where target video camera Ci
Rain snows, hail, rolls into a ball the case where greasy weather gas or power failure, to obtain above-mentioned time point Tj, location point Lj and adaptation algorithm Fj
Form corresponding relationship；The result that target video camera Ci algorithm is adapted to is saved, institute's having time in target video camera Ci is obtained
The configuration file of point, location point and adaptation algorithm corresponding relationship, the configuration file of abbreviation target video camera Ci；Execute step 7)；
7) there are the corresponding adaptation algorithms of time point Tx such as in the configuration file of the target video camera Ci, then execute adaptation calculation
Method carries out video diagnosis；Execute step 8)；
8) if diagnostic result is video camera that is fuzzy or going offline, labeled as preliminary abnormal video camera；
(3), the Space Lorentz Curve between video camera is obtained, binding time syntople obtains the adjoining between space-time object
Relational matrix, detailed process are as follows:
A, the syntople between the spatial object where acquisition target video camera Ci, what spatial object herein referred to is exactly space
On target video camera Ci around monitor camera in a certain range point；The number of two monitor cameras is adjacent, then
Indicate that they are adjacent, it is otherwise non-conterminous；
B, the neighbouring relations between the time object where acquisition target video camera Ci, herein due in video monitoring camera
Space-time data is all to be uniformly distributed within a certain range by certain time interval, therefore the time range of research is adopted by data
Collection time interval is divided into many periods, the time daily, week, the moon or season statistics；If two times in adjacent time interval, table
Bright two time objects are adjacent；
C, the space-time syntople between space-time object is determined according to the Space Lorentz Curve of acquisition and time syntople, if two
A Camera object spatially and temporally on it is all adjacent, then they in time-space relationship just it is adjacent；Any two are taken the photograph
Camera object all obtains their syntople by step a and b, to obtain space-time adjacency matrix；
(4), the space-time object adjacency matrix obtained according to the space-time data of video camera in step (2) and step (3), judges target
Video camera Ci whether failure, specifically:
Video fault diagnosis is carried out to other video cameras in target video camera Ci environs；If other in environs are taken the photograph
Camera detecting state equally also to obscure or going offline, is then separately marked, is detected again after a time；If other in environs
Video camera is detected as normal condition, the state of other video cameras of repetition measurement Tj time, if state is the fuzzy or state that goes offline, separately
It marks, detects again after a time；If other video cameras detect still in the Tj time as normal condition, judge that the target images just now
Machine Ci is abnormality machine namely failure video camera；
(5), it alarms the failure video camera obtained in the step (4), achievees the effect that video fault detection.
2. a kind of failure video camera method for rapidly positioning based on space-time analysis technology according to claim 1, feature
Be: the reading process wait diagnose the space-time data in video monitoring camera in the step 1) is as follows:
A, querying condition is arranged to parameter to be arranged by user individual, such as from date and time, date of expiry and time, prison
The range of camera position is controlled, position range allows user to directly select from map, either directly inputs position or direct
The number of input monitoring video camera；
B, database is connected, the querying condition that user inputs is nested in the inquiry that input database in query statement carries out data
Operation, inquiry the data obtained are stored in an interim tables of data, the basic number as subsequent anomalous identification and processing operation
According to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810937927.6A CN109246424A (en) | 2018-08-17 | 2018-08-17 | Failure video camera method for rapidly positioning based on space-time analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810937927.6A CN109246424A (en) | 2018-08-17 | 2018-08-17 | Failure video camera method for rapidly positioning based on space-time analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109246424A true CN109246424A (en) | 2019-01-18 |
Family
ID=65070805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810937927.6A Pending CN109246424A (en) | 2018-08-17 | 2018-08-17 | Failure video camera method for rapidly positioning based on space-time analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109246424A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111157223A (en) * | 2019-12-31 | 2020-05-15 | 华为技术有限公司 | Equipment fault detection method, device and system |
| CN111787311A (en) * | 2020-07-17 | 2020-10-16 | 江苏中州科技有限公司 | Fault detection system and method for security monitoring camera |
| CN114095725A (en) * | 2022-01-19 | 2022-02-25 | 上海兴容信息技术有限公司 | Method and system for judging whether camera is abnormal |
| CN114302065A (en) * | 2022-03-07 | 2022-04-08 | 广东电网有限责任公司东莞供电局 | Self-adaptive operation and maintenance method for transformer substation video |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103050005A (en) * | 2012-11-16 | 2013-04-17 | 北京交通大学 | Method and system for space and time analysis of urban road traffic states |
| US20140071281A1 (en) * | 2012-09-12 | 2014-03-13 | Xerox Corporation | Intelligent use of scene and test pattern analyses for traffic camera diagnostics |
| CN105357518A (en) * | 2015-11-26 | 2016-02-24 | 江苏省电力公司南京供电公司 | Video fault diagnosis method for video monitoring system |
| CN105974356A (en) * | 2016-07-22 | 2016-09-28 | 国网浙江省电力公司电力科学研究院 | Fault diagnosis method for electric power metering automatic verification assembly line |
-
2018
- 2018-08-17 CN CN201810937927.6A patent/CN109246424A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140071281A1 (en) * | 2012-09-12 | 2014-03-13 | Xerox Corporation | Intelligent use of scene and test pattern analyses for traffic camera diagnostics |
| CN103050005A (en) * | 2012-11-16 | 2013-04-17 | 北京交通大学 | Method and system for space and time analysis of urban road traffic states |
| CN105357518A (en) * | 2015-11-26 | 2016-02-24 | 江苏省电力公司南京供电公司 | Video fault diagnosis method for video monitoring system |
| CN105974356A (en) * | 2016-07-22 | 2016-09-28 | 国网浙江省电力公司电力科学研究院 | Fault diagnosis method for electric power metering automatic verification assembly line |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111157223A (en) * | 2019-12-31 | 2020-05-15 | 华为技术有限公司 | Equipment fault detection method, device and system |
| CN111157223B (en) * | 2019-12-31 | 2022-05-10 | 华为技术有限公司 | Fault detection method, device and system |
| CN111787311A (en) * | 2020-07-17 | 2020-10-16 | 江苏中州科技有限公司 | Fault detection system and method for security monitoring camera |
| CN111787311B (en) * | 2020-07-17 | 2021-08-03 | 江苏中州科技有限公司 | Fault detection system and method for security monitoring camera |
| CN114095725A (en) * | 2022-01-19 | 2022-02-25 | 上海兴容信息技术有限公司 | Method and system for judging whether camera is abnormal |
| CN114302065A (en) * | 2022-03-07 | 2022-04-08 | 广东电网有限责任公司东莞供电局 | Self-adaptive operation and maintenance method for transformer substation video |
| CN114302065B (en) * | 2022-03-07 | 2022-06-03 | 广东电网有限责任公司东莞供电局 | Self-adaptive operation and maintenance method for transformer substation video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109246424A (en) | Failure video camera method for rapidly positioning based on space-time analysis technology | |
| CN100596192C (en) | An intelligent digital system based on video and its processing method | |
| CN105425123B (en) | A kind of ultraviolet imagery and the method and system of infrared imaging cooperation detection electrical equipment fault | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN109915736B (en) | Thermal pipe network system and leakage detection method thereof | |
| CN111882810B (en) | Fire identification and early warning method and system | |
| CN108955900A (en) | A kind of booster stations temperature measurement early warning system and method based on infrared thermal imaging | |
| CN117220441A (en) | Information monitoring intelligent early warning method based on panoramic monitoring | |
| CN111383429A (en) | Method, system, device and storage medium for detecting dress of workers in construction site | |
| CN106681300A (en) | Data clustering analysis method and system of power devices | |
| CN111787189A (en) | Gridding automatic monitoring system for integration of augmented reality and geographic information | |
| CN109145796A (en) | A kind of identification of electric power piping lane fire source and fire point distance measuring method based on video image convergence analysis algorithm | |
| CN112083000A (en) | Intelligent identification method and system for appearance defects of substation equipment | |
| CN111461078A (en) | Anti-fishing monitoring method based on computer vision technology | |
| CN104112140A (en) | Casting blank image accurate positioning device and positioning method | |
| CN115081957B (en) | Useless management platform of danger of keeping in and monitoring useless | |
| CN112906674A (en) | Mine fire identification and fire source positioning method based on binocular vision | |
| CN103888731A (en) | Structured description device and system for mixed video monitoring by means of gun-type camera and dome camera | |
| CN108416969A (en) | A kind of no dead angle underground space fire detection method | |
| CN110031152B (en) | Thermal heating system and method for detecting temperature deviation accumulation leakage of adjacent days | |
| Han et al. | Research and application of substation intelligent inspection technology based on multi spectral image recognition | |
| CN116452961A (en) | Industrial equipment state judging method and device | |
| CN112712604A (en) | Machine vision-based on-site inspection quality non-inductive detection method | |
| LiPing et al. | The Application and Research of navigation-aids inspection and maintenance based on video surveillance | |
| CN115457457B (en) | Safety detection method and device for perimeter area of aviation oil depot and safety operation and maintenance 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |