CN114359836A - Automatic-identification monitoring system and monitoring method based on computer - Google Patents
Automatic-identification monitoring system and monitoring method based on computer Download PDFInfo
- Publication number
- CN114359836A CN114359836A CN202210023242.7A CN202210023242A CN114359836A CN 114359836 A CN114359836 A CN 114359836A CN 202210023242 A CN202210023242 A CN 202210023242A CN 114359836 A CN114359836 A CN 114359836A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- information
- abnormal
- substances
- 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
Links
Images
Landscapes
- Alarm Systems (AREA)
- Hardware Redundancy (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
Abstract
The invention provides an automatic identification monitoring system and a monitoring method based on a computer, which comprises the following steps: the method comprises the following steps: monitoring processing is carried out through monitoring equipment, and first monitoring data are obtained; step two: carrying out monitoring data difference detection on the first monitoring data, acquiring an abnormal value of the monitoring data, carrying out abnormal judgment and generating abnormal information; step three: automatically identifying according to the abnormal information to obtain identification information; step four: matching a corresponding monitoring mode according to the identification information, monitoring according to the monitoring mode, and acquiring second monitoring data; step five: generating a monitoring result by performing feature extraction on the second monitoring data; through carrying out the data layering to the monitored data first monitored data and second monitored data, filter effective monitoring information, when guaranteeing the control coverage, improve monitoring efficiency, through judging the abnormal value, subdivide the abnormal condition of difference, reduce the control and omit.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an automatic identification monitoring system and a monitoring method based on a computer.
Background
At present, with the development of computers, more and more application scenes are provided, and higher requirements are provided for monitoring which is closely related to urban management and daily travel of people; generally, monitoring is widely applied to scenes such as streets, enterprises, banks, universities and the like, but aiming at different use scenes, the monitoring functions are not very different, and the application characteristics of each scene cannot be considered; meanwhile, monitoring is surrounded by collecting images, analyzing the images, processing the images and generating processing results, and the invention aims to improve the automatic identification capability of monitoring based on a computer, thereby improving the monitoring efficiency and realizing monitoring processing with different functions aiming at different regions; the ' 202010952582.9 application number ' massive computing node resource monitoring and management method facing high-performance computers ' calls judgment information through a rule base, calls operation data in a storage library at the same time, and performs alarm judgment according to the judgment information and the operation data; the method is an efficient early warning judgment method, but new data needs to be continuously extracted, then the extracted new data is compared with the data of the storage library, and the comparison judgment is not accompanied by the monitoring process all the time, so that the method can not better cope with complex conditions except possibly generating redundant data; the invention sets normal monitoring and abnormal processing monitoring at the same time by limiting the monitoring mode, is tightly connected with automatic identification, maximizes the monitoring efficiency by detailed dynamic monitoring and static monitoring, and is suitable for various monitoring application scenes.
Disclosure of Invention
The invention provides an automatic identification computer-based monitoring system and a monitoring method, which are used for solving the problems that different monitoring modes cannot be adopted for carrying out segmented monitoring aiming at various monitoring scenes, and the monitoring cannot be carried out by effectively combining dynamic and static characteristics through early warning difference analysis.
The invention provides an automatic identification monitoring method based on a computer, which comprises the following steps:
the method comprises the following steps: monitoring processing is carried out through monitoring equipment, and first monitoring data are obtained;
step two: carrying out monitoring data difference detection on the first monitoring data, acquiring an abnormal value of the monitoring data, carrying out abnormal judgment and generating abnormal information;
step three: automatically identifying according to the abnormal information to obtain identification information;
step four: matching a corresponding monitoring mode according to the identification information, monitoring according to the monitoring mode, and acquiring second monitoring data;
step five: and generating a monitoring result by performing feature extraction on the second monitoring data.
As an embodiment of the present invention, the first step includes:
monitoring in a preset condition through monitoring equipment to generate initial monitoring information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
performing data screening on the initial monitoring information according to preset screening conditions to obtain first monitoring data; wherein the content of the first and second substances,
the data screening comprises the following steps: type screening, data size screening, time period screening and region screening;
the first monitoring data includes: monitoring scene data, monitoring path data, monitoring time data and monitoring area data.
As an embodiment of the present technical solution, the second step includes:
detecting and judging the first monitoring data through a preset monitoring data interval table; wherein the content of the first and second substances,
when the first monitoring data is within a preset interval range, the first monitoring data is normal monitoring data;
when the first monitoring data is not in the preset interval range, the first monitoring data is abnormal monitoring data;
performing difference calculation on the abnormal monitoring data to generate a data abnormal value, and judging to obtain abnormal information; wherein the content of the first and second substances,
the abnormality information includes: first abnormal data and second abnormal data;
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
and when the data abnormal value is not in the preset threshold range, determining the data abnormal value is second abnormal data.
As an embodiment of the present technical solution, in the third step, the method includes the following steps:
step S01: capturing information according to the abnormal information to obtain captured data, identifying and judging the captured data, and determining data to be identified; wherein the content of the first and second substances,
the capturing data includes: the method comprises the steps of capturing information type, capturing information size, capturing information parameter and capturing information characteristic carrier;
step S02: classifying and analyzing the data to be recognized to obtain an automatic recognition type, and determining an automatic recognition technology according to the automatic recognition type and the data to be recognized; wherein the content of the first and second substances,
the automatic identification technology comprises the following steps: bar code identification, magnetic identification, optical character identification, radio frequency identification and biological identification;
step S03: and monitoring and identifying according to the automatic identification technology to obtain identification information.
As an embodiment of the present technical solution, in the step four, the method includes:
screening and analyzing the identification information through preset conditions, and extracting matching characteristic data; wherein the content of the first and second substances,
the matching feature data includes: identifying the number of subjects, the types of the subjects and main scenes;
monitoring mode matching is carried out according to the matched characteristic data, a corresponding monitoring mode is obtained, monitoring is carried out, and second monitoring data are obtained; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
the monitoring pattern matching comprises: extracting monitoring characteristics of the identification information, acquiring the monitoring characteristics, and judging; wherein the content of the first and second substances,
the monitoring features include: static features, dynamic features;
when the monitoring feature is a static feature, using a static monitoring mode;
when the monitoring feature is a dynamic feature, using a dynamic monitoring mode; wherein the content of the first and second substances,
the static monitoring mode is used for obtaining static characteristic information by analyzing the characteristic category of the static characteristic and carrying out static monitoring according to the static characteristic information to obtain static monitoring data; wherein the content of the first and second substances,
the static feature information includes: static scene information, static segmentation point information and static object information;
the dynamic monitoring mode obtains dynamic characteristic information by analyzing the characteristic category of the dynamic characteristics, and dynamically monitors according to the dynamic characteristic information to obtain dynamic monitoring data;
the dynamic characteristic information includes: dynamic scene information, dynamic classification information and dynamic track information.
As an embodiment of the present technical solution, the step five includes:
according to the second monitoring data, extracting the second monitoring data characteristics to obtain second monitoring data characteristics; wherein the content of the first and second substances,
the second monitoring data characteristic comprises: biological characteristics, dynamic characteristics, static characteristics, monitoring distribution characteristics;
performing mimicry analysis on the second monitoring data characteristics to generate a monitoring result; wherein the content of the first and second substances,
the monitoring result comprises: monitoring safety value, monitoring time, monitoring image information and mimicry image information.
The invention provides an automatic identification monitoring system based on a computer, which comprises:
an automatic identification module: the system is used for carrying out automatic identification according to preset conditions to obtain identification information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
the intelligent monitoring module: the system is used for carrying out grading monitoring and carrying out monitoring analysis according to the identification information to generate monitoring data; wherein the content of the first and second substances,
acquiring hierarchical monitoring data through the hierarchical monitoring; wherein the content of the first and second substances,
the hierarchical monitoring data includes: first monitoring data and second monitoring data;
the monitoring analysis comprises: monitoring data difference detection and data automatic identification;
a mimicry analysis module: and the simulation analysis is carried out according to the monitoring data to generate a monitoring result.
As an embodiment of the present invention, the automatic identification module unit includes:
a detection unit: the monitoring system is used for carrying out state detection on the first monitoring data to obtain a monitoring state; wherein the content of the first and second substances,
the monitoring state includes: normal state monitoring data and abnormal state monitoring data;
an abnormality analysis unit: the abnormal monitoring data processing device is used for carrying out difference analysis on the abnormal monitoring data and calculating a data abnormal value; wherein the content of the first and second substances,
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
and when the data abnormal value is not in the preset threshold range, determining the data abnormal value is second abnormal data.
As an embodiment of the present technical solution, the intelligent monitoring module includes:
a pattern matching unit: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for performing characteristic extraction processing on identification information to obtain matched characteristic data, and performing monitoring mode matching according to the matched characteristic data to obtain a monitoring mode; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
a monitoring and analyzing unit: the monitoring system is used for analyzing monitoring characteristics according to the monitoring mode, generating monitoring characteristic information and acquiring monitoring data; wherein the content of the first and second substances,
the monitoring characteristic information comprises: static scene information, static segmentation point information, static object information, dynamic scene information, dynamic classification information and dynamic track information;
the monitoring data includes: monitoring mode, monitoring characteristics, monitoring information.
As an embodiment of the present technical solution, the mimicry analysis module includes:
a mimic feature analysis unit: the characteristic extraction module is used for extracting the characteristics of the second monitoring data to generate mimicry characteristics, and performing characteristic analysis to obtain a monitoring result; wherein the content of the first and second substances,
the mimicry features include: biometric, object features; wherein the content of the first and second substances,
the biometric features include: portrait features, animal features;
the object features include: static object features, dynamic object features; wherein the content of the first and second substances,
the static object features include: static object distribution data, static object parameters and static object contact degree;
the dynamic object features include: dynamic object distribution data, dynamic object moving tracks and dynamic object track connecting nodes;
a safety monitoring unit: the security analysis and calculation is carried out according to the mimicry characteristics to generate a monitoring security value; wherein the content of the first and second substances,
when the monitoring safety value is within a preset threshold range, the monitoring safety value is a safety scene;
and when the monitoring safety value is not within the preset threshold range, determining the monitoring safety value is a dangerous scene, and carrying out dangerous early warning processing.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of an automatic identification computer-based monitoring method in an embodiment of the present invention;
FIG. 2 is a flow chart of step three of an auto-identification computer-based monitoring method in an embodiment of the present invention;
FIG. 3 is a functional diagram of an auto-id computer-based monitoring system in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly or indirectly connected to the other element.
It will be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like, as used herein, refer to an orientation or positional relationship indicated in the drawings that is solely for the purpose of facilitating the description and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and is therefore not to be construed as limiting the invention.
Moreover, it is noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions, and "a plurality" means two or more unless specifically limited otherwise. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Example 1:
the embodiment of the invention provides an automatic identification computer-based monitoring method, which comprises the following steps:
the method comprises the following steps: monitoring processing is carried out through monitoring equipment, and first monitoring data are obtained;
step two: carrying out monitoring data difference detection on the first monitoring data, acquiring an abnormal value of the monitoring data, carrying out abnormal judgment and generating abnormal information;
step three: automatically identifying according to the abnormal information to obtain identification information;
step four: matching a corresponding monitoring mode according to the identification information, monitoring according to the monitoring mode, and acquiring second monitoring data;
step five: generating a monitoring result by performing feature extraction on the second monitoring data;
the working principle of the technical scheme is as follows: in the prior art, generally, monitoring is directly performed according to a time period or a fixed scene, and in the '201410033761.7 application number' monitoring method and device for monitoring method execution time, a monitoring object is determined first, and then a monitoring task is started, when the monitoring object appears, the monitoring method is executed, so that the pollution to the monitored method is avoided, the error probability of the on-line of the monitored method is reduced, however, when a plurality of monitoring objects are provided, or a new target which is homologous with the monitoring object appears, effective monitoring cannot be performed, and when monitoring target detection is performed in a set time period, whether other conditions exist in a monitoring part is difficult to analyze; in the technical scheme, first monitoring data is obtained, the first monitoring data is initial monitoring data, then difference detection is carried out, an abnormal value is calculated, abnormal information is obtained, automatic identification is completed according to the abnormal information, monitoring is carried out according to the identified information and a proper monitoring mode is matched, second monitoring data is obtained, finally characteristic data of the second monitoring data is extracted, and a monitoring result is generated after analysis;
in an example application: the monitoring can be carried out dynamically and statically according to time periods and scenes, for example, the warehouse storage can be subjected to static monitoring, the warehouse storage amount is counted, the safety of the warehouse storage can be analyzed, and a suburban warehouse can also be used for preventing biohazards such as mice, weasels and other animals by using dynamic monitoring;
the beneficial effects of the above technical scheme are: through carrying out the data layering to monitored data first monitored data and second monitored data, filter effective monitoring information, when guaranteeing that the control range covers comprehensively, improve monitoring efficiency, through judging abnormal value, subdivide the abnormal condition of difference, reduce the control and omit, through multiple automatic identification classification, improved control accuracy and pertinence.
Example 2:
in one embodiment, the first step comprises:
monitoring in a preset condition through monitoring equipment to generate initial monitoring information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
performing data screening on the initial monitoring information according to preset screening conditions to obtain first monitoring data; wherein the content of the first and second substances,
the data screening comprises the following steps: type screening, data size screening, time period screening and region screening;
the first monitoring data includes: monitoring scene data, monitoring path data, monitoring time data and monitoring area data;
the working principle of the technical scheme is as follows: firstly, according to the monitoring scene and the monitoring requirement, according to the preset region and the preset time, carrying out initial monitoring, secondly, carrying out data screening on the initial monitoring information, including: type screening, data size screening, time quantum screening, regional screening obtain first monitoring data, include: monitoring scene data, monitoring path data, monitoring time data and monitoring area data;
the beneficial effects of the above technical scheme are: the monitoring data screening breadth is guaranteed by comprehensively screening the initial monitoring information, the monitoring relevancy of the initial monitoring data is improved according to screening processing of different types, and the overall monitoring processing efficiency is improved by acquiring comprehensive first monitoring data.
Example 3:
in one embodiment, the second step includes:
detecting and judging the first monitoring data through a preset monitoring data interval table; wherein the content of the first and second substances,
when the first monitoring data is within a preset interval range, the first monitoring data is normal monitoring data;
when the first monitoring data is not in the preset interval range, the first monitoring data is abnormal monitoring data;
performing difference calculation on the abnormal monitoring data to generate a data abnormal value, and judging to obtain abnormal information; wherein the content of the first and second substances,
the abnormality information includes: first abnormal data and second abnormal data;
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
when the data abnormal value is not within the preset threshold range, the data abnormal value is second abnormal data;
the working principle of the technical scheme is as follows: in the prior art, if "a monitoring method and apparatus for monitoring execution time of a method" sets a designated monitoring target in advance, and performs analysis when the monitoring target appears, the monitoring is more targeted, but the monitoring target is limited, in the above technical scheme, the method includes the steps of determining monitoring data by using first monitoring data obtained by initial monitoring, analyzing normal monitoring data and abnormal monitoring data, performing difference calculation on the abnormal monitoring data, and analyzing the type of the abnormal monitoring data, wherein the method includes: first abnormal data and second abnormal data;
the beneficial effects of the above technical scheme are: by comprehensively analyzing the initial data, normal monitoring data and abnormal monitoring data are obtained, the monitoring and monitoring range is improved, the monitoring leakage rate is reduced, and meanwhile, the scene applicability is enlarged by analyzing the initial data.
Example 4:
in one embodiment, the third step includes the following steps:
step S01: capturing information according to the abnormal information to obtain captured data, identifying and judging the captured data, and determining data to be identified; wherein the content of the first and second substances,
the capturing data includes: the method comprises the steps of capturing information type, capturing information size, capturing information parameter and capturing information characteristic carrier;
step S02: classifying and analyzing the data to be recognized to obtain an automatic recognition type, and determining an automatic recognition technology according to the automatic recognition type and the data to be recognized; wherein the content of the first and second substances,
the automatic identification technology comprises the following steps: bar code identification, magnetic identification, optical character identification, radio frequency identification and biological identification;
step S03: monitoring and identifying according to the automatic identification technology to obtain identification information;
the working principle of the technical scheme is as follows: in the prior art, a preset identification method is generally used in monitoring or identification, and this method makes the application scenario of the method too fixed to face a complex monitoring or identification situation, and in the above technical scheme, capturing abnormal information is first used to determine captured data, including: the method comprises the steps of capturing information type, capturing information size, capturing information parameter and capturing information characteristic carrier, then carrying out identification judgment, obtaining data to be identified, then carrying out classification analysis on the data to be identified, and determining an automatic identification technology, comprising the following steps: bar code identification, magnetic identification, optical character identification, radio frequency identification, biological identification and finally obtaining identification information;
the beneficial effects of the above technical scheme are: by carrying out network type division on the captured data and carrying out comprehensive identification according to different automatic identification technologies, the automatic identification application range is enriched, and the automatic identification precision and the identification efficiency are improved.
Example 5:
in one embodiment, the fourth step includes:
screening and analyzing the identification information through preset conditions, and extracting matching characteristic data; wherein the content of the first and second substances,
the matching feature data includes: identifying the number of subjects, the types of the subjects and main scenes;
monitoring mode matching is carried out according to the matched characteristic data, a corresponding monitoring mode is obtained, monitoring is carried out, and second monitoring data are obtained; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
the monitoring pattern matching comprises: extracting monitoring characteristics of the identification information, acquiring the monitoring characteristics, and judging; wherein the content of the first and second substances,
the monitoring features include: static features, dynamic features;
when the monitoring feature is a static feature, using a static monitoring mode;
when the monitoring feature is a dynamic feature, using a dynamic monitoring mode; wherein the content of the first and second substances,
the static monitoring mode is used for obtaining static characteristic information by analyzing the characteristic category of the static characteristic and carrying out static monitoring according to the static characteristic information to obtain static monitoring data; wherein the content of the first and second substances,
the static feature information includes: static scene information, static segmentation point information and static object information;
the dynamic monitoring mode obtains dynamic characteristic information by analyzing the characteristic category of the dynamic characteristics, and dynamically monitors according to the dynamic characteristic information to obtain dynamic monitoring data;
the dynamic characteristic information includes: dynamic scene information, dynamic classification information and dynamic track information;
the working principle of the technical scheme is as follows: in the prior art, the monitoring of different scenes generally adopts a dynamic monitoring mode, which means that dynamic monitoring is carried out on required time in a monitoring range to capture dynamic information, and meanwhile, while paying attention to dynamic capturing, potential risks and monitored attributes brought by a static main body are ignored; in the above technical solution, the extracting the matching feature data includes: the main part quantity of discernment, discernment main part type, main scene of discernment, then the monitoring mode that matches corresponds monitors, acquires second monitoring data, and the monitoring mode includes: the monitoring mode matching comprises the steps of extracting monitoring characteristics of the identification information, obtaining the monitoring characteristics, judging, and using the obtained static information for security analysis;
the beneficial effects of the above technical scheme are: through analyzing the identification information and matching the corresponding monitoring mode, the monitoring efficiency and the monitoring accuracy are improved, the corresponding characteristic information is quickly acquired through selection of the monitoring mode, and the instantaneity of monitoring processing is improved.
Example 6:
in one embodiment, the step five includes:
according to the second monitoring data, extracting the second monitoring data characteristics to obtain second monitoring data characteristics; wherein the content of the first and second substances,
the second monitoring data characteristic comprises: biological characteristics, dynamic characteristics, static characteristics, monitoring distribution characteristics;
performing mimicry analysis on the second monitoring data characteristics to generate a monitoring result; wherein the content of the first and second substances,
the monitoring result comprises: monitoring a safety value, monitoring time, monitoring image information and mimicry image information;
the working principle of the technical scheme is as follows: obtaining a second monitoring data feature by extracting the second monitoring data feature, including: biological characteristics, dynamic characteristics, static characteristics and monitoring distribution characteristics, then performing mimicry analysis on the second monitoring data characteristics to generate a monitoring result, and the method comprises the following steps: monitoring a safety value, monitoring time, monitoring image information and mimicry image information;
the beneficial effects of the above technical scheme are: by carrying out feature on the second monitoring data and carrying out feature classification, the accuracy of the obtained monitoring result and the matching degree with the scene are improved, and the monitoring efficiency is enhanced.
Example 7:
the embodiment of the invention provides an automatic identification monitoring system based on a computer, which comprises:
an automatic identification module: the system is used for carrying out automatic identification according to preset conditions to obtain identification information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
the intelligent monitoring module: the system is used for carrying out grading monitoring and carrying out monitoring analysis according to the identification information to generate monitoring data; wherein the content of the first and second substances,
acquiring hierarchical monitoring data through the hierarchical monitoring; wherein the content of the first and second substances,
the hierarchical monitoring data includes: first monitoring data and second monitoring data;
the monitoring analysis comprises: monitoring data difference detection and data automatic identification;
a mimicry analysis module: the simulation analysis is carried out according to the monitoring data to generate a monitoring result;
the working principle of the technical scheme is as follows: in the prior art, for example, the monitoring system of application No. 201780062799.9 for improving image quality adopts a controller to control monitoring imaging equipment arranged in advance, controls monitoring according to frame interpolation of an imaging picture, adjusts an illumination device located in a monitoring acquisition part to obtain a best monitoring angle in consideration of night safety, judges a monitoring result from an image according to information such as color, exposure and the like, but is limited to behavior control of a human figure at night, and is difficult to monitor and analyze each element when moving objects including animals and complex scenes are faced, in the technical scheme, identification information is obtained by automatic identification according to preset conditions through an automatic identification module, wherein the automatic identification comprises static characteristic identification and dynamic characteristic identification, and then hierarchical monitoring and monitoring analysis are performed through an intelligent monitoring module, generating monitoring data, wherein the monitoring analysis comprises: monitoring data difference detection, data automatic identification, and finally performing mimicry analysis to generate a monitoring result;
the beneficial effects of the above technical scheme are: through the automatic identification module, the analysis speed of intelligent monitoring is improved, hierarchical monitoring is carried out through the intelligent monitoring module, mimicry analysis is combined, all elements in a monitoring scene are monitored, monitoring samples are enriched, and monitoring safety is improved.
Example 8:
in one embodiment, the automatic identification module unit includes:
a detection unit: the monitoring system is used for carrying out state detection on the first monitoring data to obtain a monitoring state; wherein the content of the first and second substances,
the monitoring state includes: normal state monitoring data and abnormal state monitoring data;
an abnormality analysis unit: the abnormal monitoring data processing device is used for carrying out difference analysis on the abnormal monitoring data and calculating a data abnormal value; wherein the content of the first and second substances,
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
when the data abnormal value is not within the preset threshold range, the data abnormal value is second abnormal data;
the anomaly analysis comprises the following steps:
step S100: get exceptionsMonitoring data set { p1,p2,…,pnAnd fourthly, calculating and establishing a regularization parameter equation
Wherein the content of the first and second substances,
for regularizing the parameter, λhMonitoring for anomalies the anomaly value, p, of the h-th data in the data sethH is a variable, h is more than or equal to 1 and less than or equal to n, n is a constant, and 1<n, tau is the clustering center of the abnormal data class, epsilon is a regularization first influence parameter, and sigma is a regularization second influence parameter;
step S200: calculating an abnormal value lambda of abnormal monitoring data according to the regularization parameter equationh：
Wherein theta is an abnormal index parameter, theta belongs to (0, infinity), and kappa is a clustering center influence parameter;
the working principle of the technical scheme is as follows: carrying out state detection on the first monitoring data through the detection unit to obtain a monitoring state, wherein the monitoring state comprises: performing difference analysis on the abnormal monitoring data through an abnormal analysis unit to calculate a data abnormal value, wherein the data abnormal value is first abnormal data when being in a preset threshold range, and is second abnormal data otherwise;
the beneficial effects of the above technical scheme are: by adjusting the monitoring state, the coping ability of complex conditions in the monitoring process is enhanced, the state is classified, invalid data is reduced for follow-up monitoring analysis, and the monitoring analysis efficiency is improved.
Example 9:
in one embodiment, the intelligent monitoring module comprises:
a pattern matching unit: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for performing characteristic extraction processing on identification information to obtain matched characteristic data, and performing monitoring mode matching according to the matched characteristic data to obtain a monitoring mode; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
a monitoring and analyzing unit: the monitoring system is used for analyzing monitoring characteristics according to the monitoring mode, generating monitoring characteristic information and acquiring monitoring data; wherein the content of the first and second substances,
the monitoring characteristic information comprises: static scene information, static segmentation point information, static object information, dynamic scene information, dynamic classification information and dynamic track information;
the monitoring data includes: monitoring mode, monitoring characteristics and monitoring information;
the working principle of the technical scheme is as follows: the characteristic extraction processing is carried out on the identification information through the pattern matching unit, and the monitoring pattern is matched, wherein the method comprises the following steps: static monitoring mode, dynamic monitoring mode, rethread control analysis unit, monitor characteristic analysis, generate control characteristic information to acquire the monitoring data, control characteristic information includes: static scene information, static segmentation point information, static object information, dynamic scene information, dynamic classification information, dynamic track information, the monitoring data includes: monitoring mode, monitoring characteristics and monitoring information;
the beneficial effects of the above technical scheme are: by extracting the characteristics of the identification information and matching the corresponding monitoring modes, the applicability and the monitoring efficiency of the monitoring method are improved, the difficulty of specific analysis on specific monitoring contents is reduced by analyzing the monitoring characteristic information, and the monitoring completion degree is improved.
Example 10:
in one embodiment, the mimicry analysis module comprises:
a mimic feature analysis unit: the characteristic extraction module is used for extracting the characteristics of the second monitoring data to generate mimicry characteristics, and performing characteristic analysis to obtain a monitoring result; wherein the content of the first and second substances,
the mimicry features include: biometric, object features; wherein the content of the first and second substances,
the biometric features include: portrait features, animal features;
the object features include: static object features, dynamic object features; wherein the content of the first and second substances,
the static object features include: static object distribution data, static object parameters and static object contact degree;
the dynamic object features include: dynamic object distribution data, dynamic object moving tracks and dynamic object track connecting nodes;
a safety monitoring unit: the security analysis and calculation is carried out according to the mimicry characteristics to generate a monitoring security value; wherein the content of the first and second substances,
when the monitoring safety value is within a preset threshold range, the monitoring safety value is a safety scene;
when the monitoring safety value is not within the preset threshold range, determining the monitoring safety value is a dangerous scene, and carrying out dangerous early warning treatment;
the mimicry analysis comprises the following steps:
step S10: obtaining a first movement time delta consumed in the moving process of the dynamic body by extracting the second monitoring data1And obtaining second moving time delta consumed by the same type of optimal moving process according to the preset database and the moving trace of the moving main body2Calculating the safe moving time delta0：
Wherein the content of the first and second substances,
in order to secure the moving time weighting coefficients,
to move safelyA dynamic time negative influence parameter;
step S20: acquiring data set { alpha ] of monitoring movement trace points of dynamic body1,α2,…,αsAnd performing node connection optimization on the mobile trace points according to a preset database to obtain a data set { beta } of the optimized trace points1,β2,…,βsAnd performing dynamic track prediction according to the second monitoring data to obtain a data set { gamma } of predicted trace points1,γ2,…,γsThe safe movement time delta is combined0Establishing a safe moving target function R:
wherein, betaiFor optimizing the ith trace point data, gamma, in the trace point data setiFor the ith predictor point data, alpha, in the predictor trace point data setiI is variable, i is more than or equal to 1 and less than or equal to s, s is constant and is 1<s，δ2Second shift time, delta, consumed for the same type of optimal shift process1The first moving time consumed in the moving process of the dynamic main body is u ', and the u' is a trace point weighting coefficient;
step S30: establishing a safety constraint equation system according to the safety movement objective function R (delta, alpha):
wherein, γi' is the first abscissa of the ith predicted trace point in the data set of the predicted trace points, e is a natural base number, iμFor the first distribution angle, gamma, of the ith predicted trace point in the data set of predicted trace pointsi"is the second abscissa, i, of the ith predicted trace point in the dataset of predicted trace pointsρA second distribution angle, t, of the ith predicted trace point in the data set of predicted trace points1To predictFirst weighting factor, t, of trace points2Second weighting factor, xi, for predicting trace pointsiThe prediction angle of the ith predicted trace point in the data set of the predicted trace points, omega is the weighting coefficient of the prediction angle of the predicted trace points, and gammaj' is the first ordinate, gamma, of the ith predicted trace point in the dataset of predicted trace pointsj"is the second ordinate of the ith predicted trace point in the data set of predicted trace points;
step S40: calculating according to the safety constraint equation set to obtain a monitoring safety weight and a monitoring safety value;
the working principle of the technical scheme is as follows: performing feature extraction on the second monitoring data through a mimicry feature analysis unit to generate a mimicry feature, and performing mimicry feature analysis to obtain a monitoring result, wherein the mimicry feature comprises: biometric, object features, biometric including: portrait characteristics, animal characteristic, object characteristics include: static object characteristics, dynamic object characteristics, static object characteristics include: static object distribution data, static object parameters, static object contact degree, and dynamic object characteristics include: the dynamic object distribution data, the dynamic object moving track and the dynamic object track connecting nodes are subjected to safety analysis and calculation through a safety monitoring unit according to the mimicry characteristics to generate a monitoring safety value, and when the monitoring safety value is within a preset threshold range, a safety scene is formed; otherwise, carrying out danger early warning treatment on the dangerous scene;
the beneficial effects of the above technical scheme are: through the mimicry analysis, specific characteristic analysis is carried out on the monitoring information, the usability of the monitoring information is improved, monitoring personnel can use the monitoring data conveniently, the monitoring efficiency is improved through the specific dynamic and static characteristic analysis, the safety analysis is carried out according to the mimicry characteristics, the safety of a monitoring scene is ensured, and the monitoring processing frequency is improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. An automatically identified computer-based monitoring method, comprising the steps of:
the method comprises the following steps: monitoring processing is carried out through monitoring equipment, and first monitoring data are obtained;
step two: carrying out monitoring data difference detection on the first monitoring data, acquiring an abnormal value of the monitoring data, carrying out abnormal judgment and generating abnormal information;
step three: automatically identifying according to the abnormal information to obtain identification information;
step four: matching a corresponding monitoring mode according to the identification information, monitoring according to the monitoring mode, and acquiring second monitoring data;
step five: and generating a monitoring result by performing feature extraction on the second monitoring data.
2. An automatically identifiable computer-based monitoring method as claimed in claim 1, wherein said first step comprises:
monitoring in a preset condition through monitoring equipment to generate initial monitoring information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
performing data screening on the initial monitoring information according to preset screening conditions to obtain first monitoring data; wherein the content of the first and second substances,
the data screening comprises the following steps: type screening, data size screening, time period screening and region screening;
the first monitoring data includes: monitoring scene data, monitoring path data, monitoring time data and monitoring area data.
3. An automatically identifying computer-based monitoring method according to claim 1, wherein said second step comprises:
detecting and judging the first monitoring data through a preset monitoring data interval table; wherein the content of the first and second substances,
when the first monitoring data is within a preset interval range, the first monitoring data is normal monitoring data;
when the first monitoring data is not in the preset interval range, the first monitoring data is abnormal monitoring data;
performing difference calculation on the abnormal monitoring data to generate a data abnormal value, and judging to obtain abnormal information; wherein the content of the first and second substances,
the abnormality information includes: first abnormal data and second abnormal data;
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
and when the data abnormal value is not in the preset threshold range, determining the data abnormal value is second abnormal data.
4. An automatically identifying computer-based monitoring method according to claim 1, wherein said step three, comprises the steps of:
step S01: capturing information according to the abnormal information to obtain captured data, identifying and judging the captured data, and determining data to be identified; wherein the content of the first and second substances,
the capturing data includes: the method comprises the steps of capturing information type, capturing information size, capturing information parameter and capturing information characteristic carrier;
step S02: classifying and analyzing the data to be recognized to obtain an automatic recognition type, and determining an automatic recognition technology according to the automatic recognition type and the data to be recognized; wherein the content of the first and second substances,
the automatic identification technology comprises the following steps: bar code identification, magnetic identification, optical character identification, radio frequency identification and biological identification;
step S03: and monitoring and identifying according to the automatic identification technology to obtain identification information.
5. An automatically identifying computer-based monitoring method according to claim 1, wherein said step four comprises:
screening and analyzing the identification information through preset conditions, and extracting matching characteristic data; wherein the content of the first and second substances,
the matching feature data includes: identifying the number of subjects, the types of the subjects and main scenes;
monitoring mode matching is carried out according to the matched characteristic data, a corresponding monitoring mode is obtained, monitoring is carried out, and second monitoring data are obtained; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
the monitoring pattern matching comprises: extracting monitoring characteristics of the identification information, acquiring the monitoring characteristics, and judging; wherein the content of the first and second substances,
the monitoring features include: static features, dynamic features;
when the monitoring feature is a static feature, using a static monitoring mode;
when the monitoring feature is a dynamic feature, using a dynamic monitoring mode; wherein the content of the first and second substances,
the static monitoring mode is used for obtaining static characteristic information by analyzing the characteristic category of the static characteristic and carrying out static monitoring according to the static characteristic information to obtain static monitoring data; wherein the content of the first and second substances,
the static feature information includes: static scene information, static segmentation point information and static object information;
the dynamic monitoring mode obtains dynamic characteristic information by analyzing the characteristic category of the dynamic characteristics, and dynamically monitors according to the dynamic characteristic information to obtain dynamic monitoring data;
the dynamic characteristic information includes: dynamic scene information, dynamic classification information and dynamic track information.
6. An automatically identifying computer-based monitoring method according to claim 1, wherein said step five comprises:
according to the second monitoring data, extracting the second monitoring data characteristics to obtain second monitoring data characteristics; wherein the content of the first and second substances,
the second monitoring data characteristic comprises: biological characteristics, dynamic characteristics, static characteristics, monitoring distribution characteristics;
performing mimicry analysis on the second monitoring data characteristics to generate a monitoring result; wherein the content of the first and second substances,
the monitoring result comprises: monitoring safety value, monitoring time, monitoring image information and mimicry image information.
7. An automatically identified computer-based monitoring system, comprising:
an automatic identification module: the system is used for carrying out automatic identification according to preset conditions to obtain identification information; wherein the content of the first and second substances,
the preset conditions include: presetting a region, presetting time and presetting a monitoring method;
the intelligent monitoring module: the system is used for carrying out grading monitoring and carrying out monitoring analysis according to the identification information to generate monitoring data; wherein the content of the first and second substances,
acquiring hierarchical monitoring data through the hierarchical monitoring; wherein the content of the first and second substances,
the hierarchical monitoring data includes: first monitoring data and second monitoring data;
the monitoring analysis comprises: monitoring data difference detection and data automatic identification;
a mimicry analysis module: and the simulation analysis is carried out according to the monitoring data to generate a monitoring result.
8. An auto-id computer-based monitoring method according to claim 1, wherein the auto-id module unit comprises:
a detection unit: the monitoring system is used for carrying out state detection on the first monitoring data to obtain a monitoring state; wherein the content of the first and second substances,
the monitoring state includes: normal state monitoring data and abnormal state monitoring data;
an abnormality analysis unit: the abnormal monitoring data processing device is used for carrying out difference analysis on the abnormal monitoring data and calculating a data abnormal value; wherein the content of the first and second substances,
when the data abnormal value is within a preset threshold value range, the data abnormal value is first abnormal data;
and when the data abnormal value is not in the preset threshold range, determining the data abnormal value is second abnormal data.
9. An automatically identified computer-based monitoring method according to claim 1, wherein said intelligent monitoring module comprises:
a pattern matching unit: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for performing characteristic extraction processing on identification information to obtain matched characteristic data, and performing monitoring mode matching according to the matched characteristic data to obtain a monitoring mode; wherein the content of the first and second substances,
the monitoring mode comprises the following steps: a static monitoring mode and a dynamic monitoring mode;
a monitoring and analyzing unit: the monitoring system is used for analyzing monitoring characteristics according to the monitoring mode, generating monitoring characteristic information and acquiring monitoring data; wherein the content of the first and second substances,
the monitoring characteristic information comprises: static scene information, static segmentation point information, static object information, dynamic scene information, dynamic classification information and dynamic track information;
the monitoring data includes: monitoring mode, monitoring characteristics, monitoring information.
10. An automatically identifying computer-based monitoring method according to claim 1, wherein said mimicry analysis module comprises:
a mimic feature analysis unit: the characteristic extraction module is used for extracting the characteristics of the second monitoring data to generate mimicry characteristics, and performing characteristic analysis to obtain a monitoring result; wherein the content of the first and second substances,
the mimicry features include: biometric, object features; wherein the content of the first and second substances,
the biometric features include: portrait features, animal features;
the object features include: static object features, dynamic object features; wherein the content of the first and second substances,
the static object features include: static object distribution data, static object parameters and static object contact degree;
the dynamic object features include: dynamic object distribution data, dynamic object moving tracks and dynamic object track connecting nodes;
a safety monitoring unit: the security analysis and calculation is carried out according to the mimicry characteristics to generate a monitoring security value; wherein the content of the first and second substances,
when the monitoring safety value is within a preset threshold range, the monitoring safety value is a safety scene;
and when the monitoring safety value is not within the preset threshold range, determining the monitoring safety value is a dangerous scene, and carrying out dangerous early warning processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023242.7A CN114359836B (en) | 2022-01-10 | 2022-01-10 | Automatic-identification monitoring system and monitoring method based on computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023242.7A CN114359836B (en) | 2022-01-10 | 2022-01-10 | Automatic-identification monitoring system and monitoring method based on computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114359836A true CN114359836A (en) | 2022-04-15 |
| CN114359836B CN114359836B (en) | 2022-09-13 |
Family
ID=81108322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210023242.7A Active CN114359836B (en) | 2022-01-10 | 2022-01-10 | Automatic-identification monitoring system and monitoring method based on computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114359836B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845890A (en) * | 2016-12-23 | 2017-06-13 | 济南博图信息技术有限公司 | A kind of storage monitoring method and device based on video monitoring |
| CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
| CN110379108A (en) * | 2019-08-19 | 2019-10-25 | 铂纳思(东莞)高新科技投资有限公司 | A kind of method and its system of unmanned shop anti-thefting monitoring |
| CN111223260A (en) * | 2020-01-19 | 2020-06-02 | 上海智勘科技有限公司 | Method and system for intelligently monitoring goods theft prevention in warehousing management |
| CN112329691A (en) * | 2020-11-17 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Monitoring video analysis method and device, electronic equipment and storage medium |
-
2022
- 2022-01-10 CN CN202210023242.7A patent/CN114359836B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845890A (en) * | 2016-12-23 | 2017-06-13 | 济南博图信息技术有限公司 | A kind of storage monitoring method and device based on video monitoring |
| CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
| CN110379108A (en) * | 2019-08-19 | 2019-10-25 | 铂纳思(东莞)高新科技投资有限公司 | A kind of method and its system of unmanned shop anti-thefting monitoring |
| CN111223260A (en) * | 2020-01-19 | 2020-06-02 | 上海智勘科技有限公司 | Method and system for intelligently monitoring goods theft prevention in warehousing management |
| CN112329691A (en) * | 2020-11-17 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Monitoring video analysis method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李心雨等: "面向城市应急事件管理的监控视频智能解析", 《计算机工程与应用》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114359836B (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109684916B (en) | Method, system, equipment and storage medium for detecting data abnormity based on path track | |
| US7136524B1 (en) | Robust perceptual color identification | |
| Usha Nandini et al. | Efficient shadow detection by using PSO segmentation and region-based boundary detection technique | |
| Amorim et al. | Evaluating the faithfulness of saliency maps in explaining deep learning models using realistic perturbations | |
| Vijayan et al. | A fully residual convolutional neural network for background subtraction | |
| Li et al. | Coarse-to-fine salient object detection based on deep convolutional neural networks | |
| CN117094184B (en) | Modeling method, system and medium of risk prediction model based on intranet platform | |
| Zhang et al. | Rethinking unsupervised texture defect detection using PCA | |
| Karayiannis et al. | Automated detection of videotaped neonatal seizures of epileptic origin | |
| Erciyas et al. | Improving detection and classification of diabetic retinopathy using CUDA and Mask RCNN | |
| CN114359836B (en) | Automatic-identification monitoring system and monitoring method based on computer | |
| CN110543364A (en) | Medical image rapid loading method and system | |
| CN112732690B (en) | Stabilizing system and method for chronic disease detection and risk assessment | |
| Shang et al. | Real-time Accurate Object Counting for Smart Farms | |
| Yuan et al. | Edgemixup: improving fairness for skin disease classification and segmentation | |
| Kesarwani et al. | Non-invasive haemoglobin estimation using different colour and texture features of palm | |
| CN112200010A (en) | Face acquisition quality evaluation strategy in community monitoring scene | |
| Zabary et al. | A MATLAB pipeline for spatiotemporal quantification of monolayer cell migration | |
| Deniziak et al. | Iot-based smart monitoring system using automatic shape identification | |
| Altulea et al. | Fractional Hölder mean-based image segmentation for mouse behavior analysis in conditional place preference test | |
| Adonias et al. | Towards automatic rat’s gait analysis under suboptimal illumination conditions | |
| Bontempo et al. | Enhancing PFI Prediction with GDS-MIL: A Graph-based Dual Stream MIL Approach | |
| CN115831339B (en) | Medical system risk management and control pre-prediction method and system based on deep learning | |
| Faruk et al. | Walking path images from real-time location data predict degree of cognitive impairment | |
| Venugopal et al. | An Effective Feature Extraction Based Classification Model Using Canonical Particle Swarm Optimization with Convolutional Neural Network for Glaucoma Diagnosis 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |