CN115988181A - Personnel monitoring system and method based on infrared image algorithm - Google Patents
Personnel monitoring system and method based on infrared image algorithm Download PDFInfo
- Publication number
- CN115988181A CN115988181A CN202310215566.5A CN202310215566A CN115988181A CN 115988181 A CN115988181 A CN 115988181A CN 202310215566 A CN202310215566 A CN 202310215566A CN 115988181 A CN115988181 A CN 115988181A
- Authority
- CN
- China
- Prior art keywords
- personnel
- behavior
- monitoring
- abnormal
- infrared
- 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
Images
Abstract
The invention discloses a personnel monitoring system and a method based on an infrared image algorithm, which comprises the following steps: accessing an infrared thermal imager at personnel monitoring management points of different artificial activity areas of an industrial park, adjusting Gaussian noise information of infrared image processing capacity by using a discretization window sliding window convolution method, and accessing a remote cloud personnel monitoring algorithm processing and optimizing control platform; a remote cloud personnel monitoring algorithm processing and optimizing control platform acquires an original image of a monitored personnel; the remote cloud personnel monitoring algorithm processing and optimizing control platform collects information, encrypts the information through unified data and uploads the information to the edge computing server; the uploaded information is gathered to a remote cloud personnel monitoring algorithm processing and optimizing control platform to carry out abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation; the invention can effectively expand the application of the algorithm and the processing of the action amplitude of the behavior of the personnel in the aspect of monitoring the infrared image processing capability.
Description
Technical Field
The invention relates to the field of personnel behavior monitoring, in particular to a personnel monitoring system and a personnel monitoring method based on an infrared image algorithm.
Background
At present, various monitoring devices for industrial park personnel exist on the market, but the devices still have some defects in the use process. Because the system is monitored by personnel in an industrial park, the reliability of the system is very important, otherwise serious consequences can be caused, and the real-time performance, the reliability and the stability of the system are very important.
The existing method for monitoring the behaviors of the industrial park personnel is passive, the anti-disassembly function is realized by adopting a high-strength alloy shell, early warning is not carried out on the dangerous behaviors of the industrial park personnel, certain potential safety hazards are brought, and meanwhile when the monitoring system acquires the position information of the industrial park personnel, the monitoring system is easily interfered, and the information safety problem needs to be considered in communication with a background command management center, so that the position information of the industrial park personnel is prevented from being acquired by other people.
Disclosure of Invention
In order to overcome the defects and shortcomings of the prior art, the invention provides a personnel monitoring system and a personnel monitoring method based on an infrared image algorithm.
The technical scheme adopted by the invention is that a personnel monitoring method based on an infrared image algorithm comprises the following steps:
the method comprises the steps that an infrared thermal imager is connected to personnel monitoring management points of different artificial activity areas of the industrial park, the Gaussian noise information of images of the different artificial activity areas of the industrial park is adjusted by a discretization window sliding window convolution method, and the images are connected to a remote cloud personnel monitoring algorithm processing and optimizing control platform through an edge computing gateway;
the remote cloud personnel monitoring algorithm processing and optimization control platform acquires the original image of the monitored personnel: the terminal normalizes and segments the original image of the monitored person and enhances the target of the original image of the monitored person;
a personnel infrared monitoring image data transmission unit of the remote cloud personnel monitoring algorithm processing and optimizing control platform adopts a remote cloud personnel monitoring algorithm processing and optimizing control platform data transmission channel to normalize and image-divide the terminal on the original image of the monitored personnel, perform target enhancement processing on the original image of the monitored personnel, gather the appearance frequency information of the personnel in unit time, encrypt the information through unified data and upload the information to an edge computing server;
the uploaded terminal normalizes and divides the original image of the monitored person, performs target enhancement on the original image of the monitored person, summarizes the occurrence frequency information of the person in unit time to a remote cloud person monitoring algorithm processing and optimizing control platform to perform abnormal person occurrence and abnormal person behavior non-standard evaluation;
the remote cloud personnel monitoring algorithm processing and optimization control platform carries out abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation, including abnormal personnel behavior dwell time analysis evaluation, abnormal personnel behavior non-standard grade evaluation and calculation and optimization schemes for personnel behavior abnormal infrared image processing capacity.
The remote cloud personnel monitoring algorithm processing and optimization control platform for abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation comprises the following steps:
when the target enhancement processing of the original image of the monitored person is changed, starting a category characteristic analysis evaluation program of abnormal person behaviors;
analyzing the acquired occurrence frequency information of the personnel in unit time by adopting a personnel behavior amplitude characteristic extraction algorithm, and evaluating whether the behavior amplitude of the personnel with the infrared image processing capability acquired in real time has the phenomena of tools, upper half body actions and lower half body actions irregularity; evaluating the fluctuation condition of a thermal sensing part of an infrared monitoring image of a person transmitted by an infrared thermal imager; evaluating the abnormal behavior change condition of part of personnel of the infrared thermal imager and the influence degree of the change condition on the infrared thermal imager;
the method comprises the steps that the behavior action amplitude of people around an infrared thermal imager and the behavior action amplitude change condition of people in an industrial park are divided, target enhancement processing is conducted on original images of monitored people, the monitoring and optimizing time of the infrared thermal imager is comprehensively calculated, the behavior action amplitude of people with abnormal behaviors in the infrared image processing capacity is analyzed and extracted from the behavior action amplitude of the people in the industrial park based on the behavior action amplitude of the people with abnormal behaviors in the infrared image processing capacity and the monitoring and optimizing time, the behavior integral distribution condition of the abnormal behaviors of the people in the infrared thermal imager is calculated by utilizing a behavior action amplitude evaluation algorithm, and the service life of the infrared thermal imager for shooting is evaluated;
and according to the evaluation result, the state of the infrared thermal imager is evaluated in a grading way, and different monitoring period schemes are given.
The personnel behavior action amplitude feature extraction algorithm specifically comprises the following steps:
establishing an infrared thermal imager state database under different seasonal conditions, wherein the infrared thermal imager state database comprises a curve database of normal conditions of different artificial movement area roads in an industrial park, a historical curve database of a tested infrared thermal imager and a defect curve database of various infrared thermal imagers;
carrying out target enhancement processing on the collected information of the action amplitude curves of the personnel behaviors in different artificial activity areas of the industrial park;
carrying out curve analysis and feature extraction on the collected personnel behavior action amplitude curve information of different artificial activity areas of the industrial park;
the method comprises the steps of generating an infrared monitoring image curve of a characteristic person of the infrared thermal imager, matching the characteristic and comparing and analyzing the action amplitude of the person behavior, quantifying the difference degree of a measured curve, a normal curve and a historical curve, evaluating the type state of the behavior of an abnormal person, and matching and evaluating the abnormal defect and reason of the behavior of the person through the characteristic of a defect curve.
The method comprises the following specific steps of calculating the use duration condition shot by the infrared thermal imager by utilizing a personnel behavior action amplitude evaluation algorithm, and evaluating the use duration shot by the infrared thermal imager:
regulating the abnormal times of the behaviors of people and time parameters of the people in the abnormal behavior amplitude infrared image processing capacity of people in the abnormal behavior amplitude of people in different artificial activity areas of the industrial park by using a discretization window sliding window convolution method;
comprehensively calculating the monitoring and optimizing time of the infrared thermal imager by utilizing the occurrence frequency information of personnel in unit time, the behavior and action amplitude change condition of the personnel in the industrial park and performing target enhancement processing on the original image of the monitored personnel;
analyzing and extracting the behavior action amplitude of the abnormal behavior personnel of the infrared image processing ability from the behavior action amplitude of the personnel of the industrial park based on the behavior action amplitude and monitoring and optimizing time of the abnormal behavior personnel of the infrared image processing ability, and calculating the overall distribution condition of the abnormal behavior personnel of the infrared thermal imager by utilizing a personnel behavior action amplitude evaluation algorithm;
and evaluating the use duration of shooting according to the overall distribution condition of abnormal personnel behaviors of the infrared thermal imager, and predicting the remaining duration of the infrared image processing capacity.
The infrared thermal imager utilizes the Gaussian noise information of images of different artificial activity areas of an industrial park regulated by a discretized window sliding window convolution method to convert the personnel behavior action amplitudes at different times into classified personnel behavior action amplitudes through a personnel behavior action amplitude converter, and then the classified personnel behavior action amplitudes are accessed to a remote cloud personnel monitoring algorithm processing and optimization control platform through an edge computing gateway.
A personnel monitoring system based on an infrared image algorithm comprises a regulation module which is arranged on a remote cloud personnel monitoring algorithm processing and optimizing control platform and utilizes a discretization window sliding window convolution method, a remote cloud personnel monitoring algorithm processing and optimizing control platform data transmission channel and the remote cloud personnel monitoring algorithm processing and optimizing control platform;
the adjusting module comprises an infrared thermal imager, a remote cloud personnel monitoring algorithm processing and optimization control platform filtering unit and a target enhancement processing unit, wherein the infrared thermal imager is connected to personnel monitoring management points of different human activity areas of the industrial park, the infrared thermal imager is used for adjusting Gaussian noise information of images of the different human activity areas of the industrial park by using a discretization window sliding convolution method and transmitting the Gaussian noise information to a remote cloud personnel monitoring algorithm processing and optimization control platform through an edge computing gateway, the remote cloud personnel monitoring algorithm processing and optimization control platform filtering unit is used for acquiring a terminal to normalize and image partition an original image of a monitored person, and the target enhancement processing unit is used for acquiring the remote cloud personnel monitoring algorithm processing and optimization control platform to enhance the target of the original image of the monitored person;
the remote cloud personnel monitoring algorithm processing and optimization control platform data transmission channel comprises an information collection module and a 5G signal personnel infrared monitoring image data transmission unit, wherein the information collection module is used for carrying out normalization and image segmentation processing on original images of monitored personnel and carrying out target enhancement processing on the original images of the monitored personnel for gathering Gaussian noise information of images of different artificial activity areas of an industrial park, and the 5G signal personnel infrared monitoring image data transmission unit is used for encrypting adjustment information gathered by the information collection module and obtained by using a discretization window sliding window convolution method, and uploading the adjustment information to an edge computing server to a remote cloud personnel monitoring algorithm processing and optimization control platform after the adjustment information is encrypted by using unified data;
the remote cloud personnel monitoring algorithm processing and optimization control platform is used for analyzing and processing the summarized adjustment information by using a discretization window sliding window convolution method, and giving an evaluation result of abnormal personnel behavior staying time and different monitoring period schemes.
The infrared thermal imager is connected with a personnel behavior action amplitude converter and is used for converting collected Gaussian noise information analog signals of different artificial activity area images of the industrial park into digital signals so as to be transmitted through an edge computing gateway conveniently.
The invention has the technical effects that:
the invention fully utilizes the basic functions of the remote cloud personnel monitoring algorithm processing and optimization control platform, realizes the remote online adjustment and evaluation of the type performance of abnormal personnel behaviors by using the discretization window sliding window convolution method through installing the infrared thermal imager and combining an automatic terminal communication channel to perform target enhancement processing on the original image of the monitored personnel, has high adjustment efficiency and low cost by using the discretization window sliding window convolution method, ensures the safety of the infrared thermal imager, improves the pertinence of equipment calculation and optimization, and effectively expands the application of personnel behavior amplitude algorithm and processing in the aspect of infrared image processing capability monitoring period.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic view of a first process of the method of the present invention;
FIG. 2 is a schematic diagram of a second flow of the process of the present invention;
fig. 3 is a block diagram of the system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
It should be noted that the embodiments and features of the embodiments can be combined with each other without conflict, and the present application will be further described in detail with reference to the drawings and specific embodiments.
As shown in fig. 1, a method for monitoring a person based on an infrared image algorithm includes the following steps:
s1, accessing an infrared thermal imager at personnel monitoring management points of different artificial activity areas of an industrial park, adjusting Gaussian noise information of images of the different artificial activity areas of the industrial park by using a discretization window sliding window convolution method, and accessing a remote cloud personnel monitoring algorithm processing and optimizing control platform through an edge computing gateway;
s2, the remote cloud personnel monitoring algorithm processing and optimization control platform obtains the original image of the monitored personnel: the terminal normalizes and segments the original image of the monitored person and enhances the target of the original image of the monitored person;
s3, a personnel infrared monitoring image data transmission unit of the remote cloud personnel monitoring algorithm processing and optimization control platform adopts a remote cloud personnel monitoring algorithm processing and optimization control platform data transmission channel to normalize and divide the original image of the monitored personnel by the terminal, perform target enhancement processing on the original image of the monitored personnel, collect the occurrence frequency information of the personnel in unit time, encrypt the information through unified data and upload the information to an edge computing server;
s4, the uploaded terminal normalizes and divides the original image of the monitored person, enhances the target of the original image of the monitored person, summarizes the occurrence frequency information of the person in unit time to a remote cloud person monitoring algorithm processing and optimizing control platform to perform abnormal person occurrence and abnormal person behavior non-standard evaluation;
and S5, performing abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation by the remote cloud personnel monitoring algorithm processing and optimizing control platform, wherein the abnormal personnel behavior non-standard evaluation comprises abnormal personnel behavior retention time analysis evaluation, abnormal personnel behavior non-standard grade evaluation and calculation and optimization scheme giving personnel behavior abnormal infrared image processing capacity.
As shown in fig. 2, the remote cloud personnel monitoring algorithm processing and optimization control platform for abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation includes the following steps:
s10, when the target enhancement processing of the original image of the monitored person is changed, starting a category characteristic analysis and evaluation program of abnormal person behaviors;
s20, analyzing the acquired occurrence frequency information of the personnel in unit time by adopting a personnel behavior action amplitude characteristic extraction algorithm, and evaluating whether the real-time acquired infrared image processing capability has the phenomena of tool existence, upper body action and lower body action irregularity; evaluating the fluctuation condition of a thermal sensing part of an infrared monitoring image of a person transmitted by an infrared thermal imager; evaluating the abnormal behavior change condition of part of personnel of the infrared thermal imager and the influence degree of the change condition on the infrared thermal imager;
s30, comprehensively calculating monitoring and optimizing time of the infrared thermal imager by utilizing behavior action amplitude of people around the infrared thermal imager and behavior action amplitude change conditions of people in an industrial park and carrying out target enhancement processing on original images of monitored people, analyzing and extracting behavior action amplitude of people with abnormal behaviors in the infrared image processing capability from the behavior action amplitude of the people in the industrial park based on the behavior action amplitude, the monitoring and optimizing time of the people with abnormal behaviors in the infrared image processing capability, calculating the overall distribution condition of the behaviors of the people with abnormal behaviors in the infrared thermal imager by utilizing a behavior amplitude evaluation algorithm, and evaluating the use time of shooting by the infrared thermal imager;
and S40, according to the evaluation result, carrying out grading evaluation on the state of the infrared thermal imager and providing different monitoring period schemes.
The personnel behavior action amplitude feature extraction algorithm specifically comprises the following steps:
s100, establishing infrared thermal imager state databases under different seasonal conditions, wherein the infrared thermal imager state databases comprise normal condition curve databases of different artificial activity areas of an industrial park, a historical curve database of a tested infrared thermal imager and defect curve databases of various infrared thermal imagers;
s200, carrying out target enhancement processing on collected information of the behavior and action amplitude curves of the personnel in different artificial activity areas of the industrial park;
s300, carrying out curve analysis and feature extraction on collected information of the behavior and action amplitude curves of the personnel in different artificial activity areas of the industrial park;
s400, infrared monitoring image curve generation and feature matching of the infrared thermal imager features are compared and analyzed with the action amplitude of the personnel behavior, the difference degree of the measured curve, a normal curve and a historical curve is quantized, the type state of the abnormal personnel behavior is evaluated, and abnormal defect and reason of the personnel behavior are evaluated by matching with the defect curve features.
The method comprises the following specific steps of calculating the use duration condition shot by the infrared thermal imager by utilizing a personnel behavior action amplitude evaluation algorithm, and evaluating the use duration shot by the infrared thermal imager:
s01, adjusting the times of abnormal personnel behaviors and time parameters of abnormal personnel behaviors in the infrared image processing capacity of the abnormal personnel behaviors and action amplitudes of different human activity areas of the industrial park by using a discretization window sliding window convolution method;
s02, comprehensively calculating monitoring and optimizing time of an infrared thermal imager by utilizing the occurrence frequency information of personnel in unit time and the behavior and action amplitude change condition of personnel in the industrial park and carrying out target enhancement processing on the original image of the monitored personnel;
s03, analyzing and extracting the behavior action amplitude of the person with the abnormal behavior of the person with the infrared image processing capability from the behavior action amplitudes of the person in the industrial park based on the behavior action amplitude and monitoring and optimizing time of the person with the abnormal behavior of the person with the infrared image processing capability, and calculating the overall distribution condition of the abnormal behavior of the person with the infrared thermal imager by utilizing a person behavior action amplitude evaluation algorithm;
and S04, evaluating the use time of shooting through the overall distribution condition of abnormal personnel behaviors of the infrared thermal imager, and predicting the residual time of the infrared image processing capacity.
The formula for calculating the overall distribution condition of abnormal personnel behaviors of the infrared thermal imager is as follows:
wherein the content of the first and second substances,
infrared monitoring image condition function of persons with abnormal behavior, D, representing infrared image processing capability k Representing the abnormal behavior action amplitude R of the k-th infrared image processing capability personnel k Representing the abnormal time of the behavior of the personnel with the kth infrared image processing capability; r k The method is obtained by performing target enhancement processing comprehensive calculation on the original image of the monitored personnel through the behavior action amplitude of personnel around the sub-infrared thermal imager and the behavior action amplitude change condition of the personnel in the industrial park, wherein F represents the total times of abnormal personnel behaviors, Q k RepresentAnd the personnel infrared monitoring image error is generated by abnormal personnel behaviors.
The infrared thermal imager utilizes the Gaussian noise information of images of different artificial activity areas of an industrial park regulated by a discretized window sliding window convolution method to convert the personnel behavior action amplitudes at different times into classified personnel behavior action amplitudes through a personnel behavior action amplitude converter, and then the classified personnel behavior action amplitudes are accessed to a remote cloud personnel monitoring algorithm processing and optimization control platform through an edge computing gateway.
As shown in fig. 3, a personnel monitoring system based on an infrared image algorithm includes a regulation module using a discretization window sliding window convolution method, a data transmission channel of a remote cloud personnel monitoring algorithm processing and optimizing control platform, and a remote cloud personnel monitoring algorithm processing and optimizing control platform, which are arranged on the remote cloud personnel monitoring algorithm processing and optimizing control platform.
The adjusting module comprises an infrared thermal imager, a remote cloud personnel monitoring algorithm processing and optimizing control platform filtering unit and a target enhancement processing unit, wherein the infrared thermal imager is connected into loops of different artificial activity areas of the industrial park, the infrared thermal imager is used for adjusting Gaussian noise information of images of different artificial activity areas of the industrial park by using a discretization window sliding window convolution method and transmitting the Gaussian noise information to an information collecting module of a remote cloud personnel monitoring algorithm processing and optimizing control platform through an edge computing gateway, the remote cloud personnel monitoring algorithm processing and optimizing control platform filtering unit is used for acquiring a terminal to normalize an original image of a monitored personnel and perform image segmentation processing, and the target enhancement processing unit is used for acquiring the remote cloud personnel monitoring algorithm processing and optimizing control platform to perform target enhancement processing on the original image of the monitored personnel;
the remote cloud personnel monitoring algorithm processing and optimization control platform data transmission channel comprises an information collection module and a 5G signal personnel infrared monitoring image data transmission unit, wherein the information collection module is used for carrying out normalization and image segmentation processing on original images of monitored personnel and carrying out target enhancement processing on the original images of the monitored personnel for gathering Gaussian noise information of images of different artificial activity areas of an industrial park, and the 5G signal personnel infrared monitoring image data transmission unit is used for encrypting adjustment information gathered by the information collection module and obtained by using a discretization window sliding window convolution method, and uploading the adjustment information to an edge computing server to a remote cloud personnel monitoring algorithm processing and optimization control platform after the adjustment information is encrypted by using unified data;
the remote cloud personnel monitoring algorithm processing and optimization control platform is used for analyzing and processing the summarized adjustment information by using a discretization window sliding window convolution method, and providing an abnormal personnel behavior residence time evaluation result and different monitoring period schemes.
The infrared thermal imager is connected with a personnel behavior action amplitude converter and is used for converting collected Gaussian noise information analog signals of different artificial activity area images of the industrial park into digital signals so as to be transmitted through an edge computing gateway conveniently.
The invention fully utilizes the basic functions of a remote cloud personnel monitoring algorithm processing and optimizing control platform, carries out target enhancement processing on the original image of the monitored personnel by installing a simple infrared thermal imager and combining an automatic terminal communication channel, realizes remote online adjustment and evaluation of the type performance of abnormal personnel behaviors by using a discretization window sliding window convolution method, has high adjustment efficiency and low cost by using the discretization window sliding window convolution method, ensures the safety of the infrared thermal imager, improves the pertinence of equipment calculation and optimization, and effectively expands the application of personnel behavior action amplitude algorithm and processing in the aspect of infrared image processing capacity monitoring period.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "fixed" are to be construed broadly, e.g., as meaning either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A personnel monitoring method based on an infrared image algorithm is characterized by comprising the following steps:
the method comprises the steps that an infrared thermal imager is connected to personnel monitoring management points of different artificial activity areas of the industrial park, the Gaussian noise information of images of the different artificial activity areas of the industrial park is adjusted by a discretization window sliding window convolution method, and a remote cloud personnel monitoring algorithm processing and optimizing control platform is connected to the personnel monitoring management points through an edge computing gateway;
the remote cloud personnel monitoring algorithm processing and optimization control platform acquires the original image of the monitored personnel: the terminal normalizes and segments the original image of the monitored person and enhances the target of the original image of the monitored person;
a personnel infrared monitoring image data transmission unit of the remote cloud personnel monitoring algorithm processing and optimizing control platform adopts a remote cloud personnel monitoring algorithm processing and optimizing control platform data transmission channel to normalize and image-divide the terminal on the original image of the monitored personnel, perform target enhancement processing on the original image of the monitored personnel, gather the appearance frequency information of the personnel in unit time, encrypt the information through unified data and upload the information to an edge computing server;
the uploaded terminal normalizes and divides the original image of the monitored person, enhances the target of the original image of the monitored person, and summarizes the occurrence frequency information of the person in unit time to a remote cloud person monitoring algorithm processing and optimizing control platform to evaluate the occurrence of abnormal persons and the behavior of the abnormal persons in an irregular way;
the remote cloud personnel monitoring algorithm processing and optimization control platform carries out abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation, including abnormal personnel behavior retention time analysis evaluation, abnormal personnel behavior non-standard grade evaluation and calculation and optimization scheme for personnel behavior abnormal infrared image processing capacity.
2. The personnel monitoring method based on the infrared image algorithm, as claimed in claim 1, wherein said remote cloud personnel monitoring algorithm processing and optimization control platform for abnormal personnel occurrence and abnormal personnel behavior non-standard evaluation comprises the steps of:
when the target enhancement processing of the original image of the monitored person is changed, starting a category characteristic analysis evaluation program of abnormal person behaviors;
adopting a personnel behavior amplitude characteristic extraction algorithm to analyze the acquired occurrence frequency information of the personnel in unit time, and evaluating whether a tool exists in the behavior amplitude of the personnel, the action of the upper half body and the action of the lower half body are irregular or not in the infrared image processing capability acquired in real time; evaluating the fluctuation condition of a thermal sensing part of an infrared monitoring image of a person transmitted by an infrared thermal imager; evaluating the abnormal behavior change condition of part of personnel of the infrared thermal imager and the influence degree of the change condition on the infrared thermal imager;
the method comprises the steps of utilizing behavior and action amplitude of people around an infrared thermal imager and behavior and action amplitude change conditions of people in an industrial park, carrying out target enhancement processing on original images of monitored people, comprehensively calculating monitoring and optimizing time of the infrared thermal imager, analyzing and extracting behavior and action amplitude of people with abnormal behavior and abnormal behavior of the infrared image processing ability from the behavior and action amplitude of the people in the industrial park based on the behavior and action amplitude, monitoring and optimizing time of the people with abnormal behavior of the infrared image processing ability, calculating overall distribution conditions of abnormal behavior of the infrared thermal imager by utilizing a behavior and action amplitude evaluation algorithm, and evaluating service life of shooting of the infrared thermal imager;
and according to the evaluation result, carrying out grading evaluation on the state of the infrared thermal imager and providing different monitoring period schemes.
3. The personnel monitoring method based on the infrared image algorithm as claimed in claim 2, characterized in that the personnel behavior action amplitude feature extraction algorithm comprises the following specific steps:
establishing an infrared thermal imager state database under different seasonal conditions, wherein the infrared thermal imager state database comprises a curve database of normal conditions of different artificial movement area roads in an industrial park, a historical curve database of a tested infrared thermal imager and a defect curve database of various infrared thermal imagers;
carrying out target enhancement processing on the collected information of the action amplitude curves of the personnel behaviors in different artificial activity areas of the industrial park;
carrying out curve analysis and feature extraction on the collected personnel behavior action amplitude curve information of different artificial activity areas of the industrial park;
the infrared monitoring image curve generation and the characteristic matching of the infrared thermal imager characteristic personnel and the comparison analysis of the action amplitude of the personnel behavior evaluate the type state of the behavior of abnormal personnel by quantifying the difference degree of the measured curve and a normal curve and a historical curve, and evaluate the abnormal behavior defect and reason of the personnel by matching with the defect curve characteristic.
4. The personnel monitoring method based on the infrared image algorithm as claimed in claim 2, wherein the action amplitude evaluation algorithm by utilizing personnel behavior comprises the following specific steps:
regulating abnormal times of personnel behaviors and time parameters of the personnel behaviors in the infrared image processing capacity by using a discretized window sliding window convolution method to regulate abnormal personnel behaviors and action amplitudes of different human activity areas in the industrial park;
comprehensively calculating the monitoring and optimizing time of the infrared thermal imager by utilizing the occurrence frequency information of personnel in unit time and the behavior and action amplitude change condition of personnel in the industrial park and carrying out target enhancement processing on the original image of the monitored personnel;
analyzing and extracting the action amplitude of the abnormal behavior of the personnel with the infrared image processing capability from the action amplitude of the personnel with the abnormal behavior of the personnel in the industrial park based on the action amplitude and monitoring and optimizing time of the abnormal behavior of the personnel with the infrared image processing capability, and calculating the overall distribution condition of the abnormal behavior of the personnel in the infrared thermal imager by utilizing a personnel action amplitude evaluation algorithm;
and evaluating the use duration of shooting according to the overall distribution condition of abnormal personnel behaviors of the infrared thermal imager, and predicting the remaining duration of the infrared image processing capacity.
5. The personnel monitoring method based on the infrared image algorithm as claimed in claim 1, characterized in that the Gaussian noise information of the images of different artificial activity areas of the industrial park adjusted by the infrared thermal imager by the discretization window sliding convolution method is converted into classification personnel behavior amplitude by a personnel behavior amplitude converter, and then is accessed to a remote cloud personnel monitoring algorithm processing and optimization control platform through an edge computing gateway.
6. A personnel monitoring system based on an infrared image algorithm is characterized by comprising a discrete window sliding window convolution method adjusting module, a remote cloud personnel monitoring algorithm processing and optimizing control platform data transmission channel and a remote cloud personnel monitoring algorithm processing and optimizing control platform, wherein the discrete window sliding window convolution method adjusting module is arranged on the remote cloud personnel monitoring algorithm processing and optimizing control platform;
the adjusting module comprises an infrared thermal imager, a remote cloud personnel monitoring algorithm processing and optimizing control platform filtering unit and a target enhancement processing unit, wherein the infrared thermal imager is connected to personnel monitoring management points of different artificial activity areas of the industrial park, the remote cloud personnel monitoring algorithm processing and optimizing control platform filtering unit and the target enhancement processing unit are connected to the personnel monitoring management points of the different artificial activity areas of the industrial park, the infrared thermal imager is used for adjusting Gaussian noise information of the images of the different artificial activity areas of the industrial park by using the discretization window sliding window convolution method and transmitting the Gaussian noise information to the remote cloud personnel monitoring algorithm processing and optimizing control platform through an edge computing gateway, the remote cloud personnel monitoring algorithm processing and optimizing control platform filtering unit is used for acquiring a terminal to perform normalization and image segmentation processing on original images of monitored personnel, and the target enhancement processing unit is used for acquiring the remote cloud personnel monitoring algorithm processing and optimizing control platform to perform target enhancement processing on the original images of the monitored personnel.
7. The personnel monitoring system based on infrared image algorithm of claim 6, characterized in that the remote cloud personnel monitoring algorithm processing and optimization control platform data transmission channel comprises an information collection module and a 5G signal personnel infrared monitoring image data transmission unit, wherein the information collection module is used for normalizing and image-dividing original images of monitored personnel and summarizing the original images of monitored personnel with Gaussian noise information of images of different artificial activity areas of an industrial park, and the 5G signal personnel infrared monitoring image data transmission unit is used for summarizing the information collected by the information collection module, and regulating information by a discretized window sliding window convolution method is encrypted by using unified data and then uploaded to an edge computing server to the remote cloud personnel monitoring algorithm processing and optimization control platform.
8. The personnel monitoring system based on the infrared image algorithm as claimed in claim 6, characterized in that the remote cloud personnel monitoring algorithm processing and optimization control platform is used for analyzing and processing the aggregated adjustment information by using the discretized window sliding window convolution method, and providing the evaluation result of the retention time of the abnormal personnel behavior and different monitoring period schemes.
9. The personnel monitoring system based on infrared image algorithm as claimed in claim 6, characterized in that said infrared thermal imaging camera is connected with personnel action amplitude converter for converting the collected Gaussian noise information analog signals of different human activity area images of industrial park into digital signals for transmission through edge computing gateway.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310215566.5A CN115988181A (en) | 2023-03-08 | 2023-03-08 | Personnel monitoring system and method based on infrared image algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310215566.5A CN115988181A (en) | 2023-03-08 | 2023-03-08 | Personnel monitoring system and method based on infrared image algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115988181A true CN115988181A (en) | 2023-04-18 |
Family
ID=85963378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310215566.5A Pending CN115988181A (en) | 2023-03-08 | 2023-03-08 | Personnel monitoring system and method based on infrared image algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115988181A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116456061A (en) * | 2023-06-15 | 2023-07-18 | 四川三思德科技有限公司 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001148077A (en) * | 1999-11-19 | 2001-05-29 | Fujitsu General Ltd | Intruder detecting device |
| JP2006011728A (en) * | 2004-06-24 | 2006-01-12 | Omron Corp | Suspicious person countermeasure system and suspicious person detection device |
| JP2007233660A (en) * | 2006-02-28 | 2007-09-13 | Sogo Keibi Hosho Co Ltd | Security device and method |
| JP2013131153A (en) * | 2011-12-22 | 2013-07-04 | Welsoc Co Ltd | Autonomous crime prevention warning system and autonomous crime prevention warning method |
| CN106600887A (en) * | 2015-10-14 | 2017-04-26 | 山东鲁能智能技术有限公司 | Video monitoring linkage system based on substation patrol robot and method thereof |
| CN109214309A (en) * | 2018-08-15 | 2019-01-15 | 南京信息工程大学 | A kind of tea hill picking personnel's abnormal behaviour monitoring method based on deep learning |
| US20190172329A1 (en) * | 2016-07-22 | 2019-06-06 | Lucis Technologies Holdings Limited | Security system and method |
| CN111815841A (en) * | 2020-09-09 | 2020-10-23 | 杭州绿城信息技术有限公司 | Wisdom garden situation perception system based on thing networking |
| WO2020218409A1 (en) * | 2019-04-25 | 2020-10-29 | 株式会社クロスエッジラボ | Thermosensitive imaging device, watching and monitoring system using thermosensitive imaging device, and watching and monitoring method using thermosensitive imaging device |
| CN112508073A (en) * | 2020-12-01 | 2021-03-16 | 杭州天铂云科光电科技有限公司 | Electric equipment infrared chart identification method combining deep learning with traditional algorithm |
| WO2022022368A1 (en) * | 2020-07-28 | 2022-02-03 | 宁波环视信息科技有限公司 | Deep-learning-based apparatus and method for monitoring behavioral norms in jail |
| CN114115296A (en) * | 2022-01-21 | 2022-03-01 | 南京理工大学 | Intelligent inspection and early warning system and method for key area |
| CN115410055A (en) * | 2022-08-12 | 2022-11-29 | 浙江大学 | Pedestrian intrusion detection system and method based on deep learning |
| CN115620471A (en) * | 2022-09-30 | 2023-01-17 | 浙江安防职业技术学院 | Image identification security system based on big data screening |
| CN115762046A (en) * | 2022-09-05 | 2023-03-07 | 湖州师范学院 | Early warning and intervention device for building top light life person |
-
2023
- 2023-03-08 CN CN202310215566.5A patent/CN115988181A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001148077A (en) * | 1999-11-19 | 2001-05-29 | Fujitsu General Ltd | Intruder detecting device |
| JP2006011728A (en) * | 2004-06-24 | 2006-01-12 | Omron Corp | Suspicious person countermeasure system and suspicious person detection device |
| JP2007233660A (en) * | 2006-02-28 | 2007-09-13 | Sogo Keibi Hosho Co Ltd | Security device and method |
| JP2013131153A (en) * | 2011-12-22 | 2013-07-04 | Welsoc Co Ltd | Autonomous crime prevention warning system and autonomous crime prevention warning method |
| CN106600887A (en) * | 2015-10-14 | 2017-04-26 | 山东鲁能智能技术有限公司 | Video monitoring linkage system based on substation patrol robot and method thereof |
| US20190172329A1 (en) * | 2016-07-22 | 2019-06-06 | Lucis Technologies Holdings Limited | Security system and method |
| CN109214309A (en) * | 2018-08-15 | 2019-01-15 | 南京信息工程大学 | A kind of tea hill picking personnel's abnormal behaviour monitoring method based on deep learning |
| WO2020218409A1 (en) * | 2019-04-25 | 2020-10-29 | 株式会社クロスエッジラボ | Thermosensitive imaging device, watching and monitoring system using thermosensitive imaging device, and watching and monitoring method using thermosensitive imaging device |
| WO2022022368A1 (en) * | 2020-07-28 | 2022-02-03 | 宁波环视信息科技有限公司 | Deep-learning-based apparatus and method for monitoring behavioral norms in jail |
| CN111815841A (en) * | 2020-09-09 | 2020-10-23 | 杭州绿城信息技术有限公司 | Wisdom garden situation perception system based on thing networking |
| CN112508073A (en) * | 2020-12-01 | 2021-03-16 | 杭州天铂云科光电科技有限公司 | Electric equipment infrared chart identification method combining deep learning with traditional algorithm |
| CN114115296A (en) * | 2022-01-21 | 2022-03-01 | 南京理工大学 | Intelligent inspection and early warning system and method for key area |
| CN115410055A (en) * | 2022-08-12 | 2022-11-29 | 浙江大学 | Pedestrian intrusion detection system and method based on deep learning |
| CN115762046A (en) * | 2022-09-05 | 2023-03-07 | 湖州师范学院 | Early warning and intervention device for building top light life person |
| CN115620471A (en) * | 2022-09-30 | 2023-01-17 | 浙江安防职业技术学院 | Image identification security system based on big data screening |
Non-Patent Citations (1)
| Title |
|---|
| 马玉光;籍芳;黄辉;吴淑霞;李冠豪;: "基于四足履带机器人的危险环境检测系统的设计", 电气技术 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116456061A (en) * | 2023-06-15 | 2023-07-18 | 四川三思德科技有限公司 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
| CN116456061B (en) * | 2023-06-15 | 2023-09-08 | 四川三思德科技有限公司 | Intelligent community monitoring management method, system and medium based on dynamic target detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111928888B (en) | Intelligent monitoring and analyzing method and system for water pollution | |
| CN108846585A (en) | A kind of hidden danger of coal mine processing management system | |
| CN115988181A (en) | Personnel monitoring system and method based on infrared image algorithm | |
| CN112418649B (en) | Building stair pedestrian flow estimation system based on multi-dimensional MEMS inertial sensor | |
| CN111626985A (en) | Poultry body temperature detection method based on image fusion and poultry house inspection system | |
| CN111540471A (en) | Health state tracking and early warning method and system based on user health data | |
| CN111223263A (en) | Full-automatic comprehensive fire early warning response system | |
| CN115527203A (en) | Grain drying remote control method and system based on Internet of things | |
| CN116224925B (en) | Intelligent processing management system | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN114518143A (en) | Intelligent environment sensing system | |
| CN117113729A (en) | Digital twinning-based power equipment online state monitoring system | |
| CN113849774A (en) | Intelligent equipment maintenance platform based on life analysis and health monitoring | |
| CN115860579A (en) | Production quality monitoring system for flour processing | |
| CN109063589A (en) | Instrument and equipment on-line monitoring method neural network based and system | |
| CN110659669B (en) | User behavior identification method and system based on encrypted camera video traffic mode change | |
| CN115796608A (en) | Building construction wind control management method and system based on portable interaction | |
| CN114141390A (en) | Remote ICU data network system | |
| CN113420940A (en) | Safe operation supervision system for orchard weeding robot | |
| CN111678558A (en) | Infrared thermal imaging oil level and temperature monitoring system and method applied to oil filling equipment | |
| CN116506205B (en) | Data processing method and system of intelligent medical platform | |
| CN117708552B (en) | Power station operation data real-time monitoring method based on edge calculation | |
| CN114879784A (en) | Big data real-time monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |