CN115099760A - Intelligent dangerous article detection and early warning method based on computer machine vision - Google Patents
Intelligent dangerous article detection and early warning method based on computer machine vision Download PDFInfo
- Publication number
- CN115099760A CN115099760A CN202211036835.3A CN202211036835A CN115099760A CN 115099760 A CN115099760 A CN 115099760A CN 202211036835 A CN202211036835 A CN 202211036835A CN 115099760 A CN115099760 A CN 115099760A
- Authority
- CN
- China
- Prior art keywords
- area
- analysis
- normal
- detection
- abnormal
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Alarm Systems (AREA)
Abstract
The invention belongs to the field of hazardous article detection, relates to a data analysis technology, and aims to solve the problem of low abnormal processing efficiency caused by the fact that the conventional hazardous article detection early warning method cannot perform source analysis on a plurality of areas in which abnormality is simultaneously detected, in particular to a hazardous article intelligent detection early warning method based on computer machine vision, which comprises the following steps: the method comprises the steps that regional detection analysis is conducted on a dangerous goods storage warehouse through a region detection module, the dangerous goods storage warehouse is divided into a plurality of monitoring regions, temperature data, humidity data and leakage data of the monitoring regions are obtained, numerical calculation is conducted to obtain environment coefficients, and the monitoring regions are marked as normal regions or abnormal regions according to the numerical values of the environment coefficients; the invention can carry out regional detection and analysis on the dangerous goods storage warehouse, improve the detection precision of the dangerous goods storage environment, and simultaneously can carry out source tracing when an abnormality occurs, thereby improving the safety of dangerous goods storage.
Description
Technical Field
The invention belongs to the field of dangerous goods detection, relates to a data analysis technology, and particularly relates to a dangerous goods intelligent detection early warning method based on computer machine vision.
Background
Dangerous goods are general names of inflammable, explosive, strongly corrosive, toxic and radioactive goods, such as gasoline, explosive, strong acid, strong alkali, benzene, naphthalene, celluloid, peroxide and the like, and should be scientifically and properly treated during production, transportation, storage and destruction.
The existing intelligent dangerous article detection and early warning method can only carry out regional detection and early warning on the storage space of dangerous articles, however, when the storage environment of one region is abnormal, the abnormal environment of the storage region is likely to diffuse along with the rise of temperature or gas leakage, and other originally normal storage regions are affected, and at the moment, the existing dangerous article detection and early warning method cannot carry out source analysis on a plurality of regions which are detected to be abnormal simultaneously, and inspection personnel are required to carry out one-by-one inspection on all abnormal regions to determine the storage region in which the environmental abnormality actually occurs and carry out exception handling, so that the exception handling efficiency is low.
In view of the above technical problem, the present application proposes a solution.
Disclosure of Invention
The invention aims to provide a dangerous goods intelligent detection early warning method based on computer machine vision, which is used for solving the problem of low abnormal processing efficiency caused by the fact that the existing dangerous goods detection early warning method cannot carry out source analysis on a plurality of regions which simultaneously detect abnormal conditions;
the technical problems to be solved by the invention are as follows: how to provide an intelligent dangerous article detection and early warning method capable of carrying out source analysis on a plurality of regions in which abnormality is detected simultaneously.
The purpose of the invention can be realized by the following technical scheme:
a dangerous goods intelligent detection early warning method based on computer machine vision comprises the following steps:
the method comprises the following steps: carrying out regional detection analysis on the dangerous goods storage warehouse through a region detection module, dividing the dangerous goods storage warehouse into a plurality of monitoring regions, acquiring temperature data, humidity data and leakage data of the monitoring regions, carrying out numerical calculation to obtain an environment coefficient, and marking the monitoring regions as normal regions or abnormal regions according to the numerical value of the environment coefficient;
step two: detecting and analyzing the development trend of the storage environment of the normal area through a trend analysis module: judging whether the development trend of the storage environment of the normal area meets the requirement or not by detecting and analyzing results;
step three: performing center analysis on the abnormal areas through a center analysis module to obtain the number of the abnormal areas, and if the number of the abnormal areas is one, marking the corresponding abnormal areas as center areas and sending the center areas to a detection platform; if the number of the abnormal areas is not one, marking the abnormal area with the maximum environmental coefficient value as a diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius, marking the obtained circular area as an analysis area, judging whether the abnormal area exists outside the analysis area, if so, marking the abnormal area with the maximum environmental coefficient value outside the analysis area as the diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius to obtain an analysis area again, and so on until no abnormal area exists outside the analysis area; and if not, performing diffusion analysis on the analysis area to obtain a central area of the analysis area, and sending the central areas of all the analysis areas to the detection platform.
As a preferred embodiment of the present invention, in the step one, the process of marking the monitoring area as a normal area or an abnormal area includes: acquiring an environment threshold value through a storage module, and comparing the environment coefficient HJ of the monitoring area with the environment threshold value:
if the environmental coefficient is smaller than the environmental threshold, judging that the storage environment of the monitoring area meets the requirement, marking the corresponding monitoring area as a normal area, sending the normal area to the detection platform, and sending the normal area to the trend analysis module after the detection platform receives the normal area;
if the environment coefficient is larger than or equal to the environment threshold value, marking the corresponding monitoring area as an abnormal area, sending the abnormal area to the detection platform, and sending the abnormal area to the central analysis module after the detection platform receives the abnormal area.
As a preferred embodiment of the present invention, in the step two, the specific process of detecting and analyzing the trend of the storage environment of the normal area includes: setting the detection time length of a normal region, dividing the detection time length into L1 detection time periods, wherein L1 is a numerical constant, acquiring the maximum value of the environmental coefficient of the normal region in the detection time periods and marking the maximum value as the environmental performance value of the detection time periods, summing the environmental performance values of the detection time periods and averaging to obtain the normal coefficient of the detection time periods, establishing an environmental set of the environmental performance values of the detection time periods, and calculating the variance of the environmental set to obtain the fluctuation coefficient of the normal region in the detection time length; the normal threshold and the fluctuation threshold are obtained through the storage module, the normal coefficient and the fluctuation coefficient of the detection duration are compared with the normal threshold and the fluctuation threshold respectively, and whether the development trend of the storage environment of the normal area meets the requirement or not is judged through the comparison result.
As a preferred embodiment of the present invention, in the step two, the specific process of comparing the normal coefficient and the fluctuation coefficient of the detection duration with the normal threshold and the fluctuation threshold respectively includes:
if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is smaller than the fluctuation threshold, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module;
if the normal coefficient is larger than or equal to the normal threshold, judging that the development trend of the storage environment in the normal area does not meet the requirement, and sending a trend unqualified signal to the detection platform by the trend analysis module; and if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is larger than or equal to the fluctuation threshold, performing depth analysis on the normal area.
As a preferred embodiment of the present invention, in the step two, the specific process of performing depth analysis on the normal region includes: establishing a rectangular coordinate system by taking the detection time as an X axis and the environmental coefficient as a Y axis, marking L1 points in the rectangular coordinate system by taking the end time of the detection time period as a horizontal coordinate and the environmental expression value of the detection time period as a vertical coordinate, marking the points as analysis points, connecting the analysis points from left to right in sequence to obtain analysis broken lines, connecting the end points of the analysis broken lines with the last inflection point to obtain analysis line segments, obtaining the length values and the slope values of the analysis line segments, and obtaining the length threshold value through a storage module;
if the slope value of the analysis line segment is larger than zero and the length value of the analysis line segment is larger than the length threshold, judging that the development trend of the storage environment in the normal area does not meet the requirement, and sending an unqualified trend signal to the detection platform by the trend analysis module;
otherwise, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module.
In a preferred embodiment of the present invention, in step three, the specific process of performing diffusion analysis on the analysis region includes: marking the environmental coefficient of the diffusion region as KS, obtaining a diffusion threshold value KSmin through a formula KSmin = t1 KS, wherein t1 is a proportionality coefficient, t1 is more than or equal to 0.75 and less than or equal to 0.85, forming a diffusion range by the diffusion threshold value KSmin and KS, obtaining the number of abnormal regions of which the environmental coefficients in the analysis region are within the diffusion range, and marking the abnormal regions as diffusion number;
if the diffusion quantity is zero, marking the diffusion area as a central area of the analysis area;
if the diffusion quantity is not zero, marking the abnormal objects and the diffusion objects with the environmental coefficients within the diffusion range as marked objects together, selecting one marked object as a designated object, obtaining the straight-line distances between the center point of the designated object and the center points of all the rest abnormal objects in the analysis area, summing and averaging to obtain the distance table value of the marked object; and taking all the marked objects in the analysis area as designated objects in sequence, acquiring a plurality of distance table values, and marking the abnormal object corresponding to the marked object with the minimum distance table value as the central area of the analysis area.
The invention has the following beneficial effects:
1. the regional detection module can be used for performing regional detection analysis on the dangerous goods storage warehouse, so that the detection precision of the dangerous goods storage environment is improved, meanwhile, the source tracing can be performed when an abnormality occurs, the monitoring of temperature data, humidity data and leakage data is performed on a monitoring region, the storage environment of the dangerous goods can be ensured to meet the requirement, and the storage safety of the dangerous goods is improved;
2. the trend analysis module can be used for detecting and analyzing the development trend of the storage environment of the normal area, and predicting the environment change trend of the normal area by combining the fluctuation degree of the environmental coefficient of the normal area in a period of time aiming at the storage area with the current environment detection result meeting the requirement, so that early warning is carried out before the normal area is abnormal, and the possibility of the abnormal environment phenomenon in the monitoring area is reduced;
3. can carry out central analysis to unusual region through central analysis module, when detecting the unusual monitoring area of a plurality of environment simultaneously, judge the monitoring area that actually appears revealing through central analysis's mode, set for the staff when carrying out exception handling and handle the priority, the staff can be preferably to the monitoring area that most probably appears actually revealing investigate and handle, improves exception handling efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a system according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a method according to a second embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in figure 1, the hazardous article intelligent detection early warning system based on computer machine vision comprises a detection platform, wherein the detection platform is in communication connection with an area detection module, a trend analysis module, a center analysis module and a storage module.
The regional detection module is used for carrying out regional detection analysis on the dangerous goods storage warehouse: dividing the dangerous goods storage warehouse into a plurality of monitoring areas, and acquiring temperature data WD, humidity data SD and leakage data XL of the monitoring areas, wherein the temperature data WD of the monitoring areas are air temperature values detected by temperature sensors in the monitoring areas, the humidity data SD of the monitoring areas are humidity values detected by humidity-sensitive sensors in the monitoring areas, and the leakage data XL of the monitoring areas are total content values of chlorine, carbon monoxide, nitrogen monoxide, sulfur dioxide, propane and methane in the air in the monitoring areas; obtaining an environment coefficient HJ of the monitoring area through a formula HJ = alpha 1 × WD + alpha 2 × SD + alpha 3 × XL, wherein the environment coefficient is a numerical value reflecting the suitability degree of the environment in the monitoring area for dangerous goods storage, and the smaller the numerical value of the environment coefficient is, the higher the suitability degree of the environment in the corresponding monitoring area for dangerous goods storage is; wherein α 1, α 2 and α 3 are all proportionality coefficients, the storage module acquires an environment threshold HJmax, and the environment coefficient HJ of the monitoring region is compared with the environment threshold HJmax: if the environmental coefficient HJ is smaller than the environmental threshold HJmax, judging that the storage environment of the monitoring area meets the requirement, marking the corresponding monitoring area as a normal area, sending the normal area to the detection platform, and sending the normal area to the trend analysis module after the detection platform receives the normal area; if the environmental coefficient HJ is larger than or equal to the environmental threshold HJmax, marking the corresponding monitoring area as an abnormal area, sending the abnormal area to the detection platform, and sending the abnormal area to the central analysis module after the detection platform receives the abnormal area; carry out regional detection and analysis to hazardous articles storage warehouse, when improving hazardous articles storage environment and detecting the precision, can also trace back when appearing unusually in the source, through carrying out temperature data, humidity data and revealing the control of data to the monitoring area, guarantee that the storage environment of hazardous articles can satisfy the demands, improve hazardous articles storage security.
The temperature sensor is a sensor capable of sensing temperature and converting the sensed temperature into a usable output signal; the humidity-sensitive sensor is a device which can sense the change of external humidity and convert the humidity into a useful signal through the change of physical or chemical properties of a device material.
The trend analysis module is used for detecting and analyzing the development trend of the storage environment of the normal area: setting the detection time length of a normal area and dividing the detection time length into L1 detection time periods, wherein L1 is a numerical constant, and the numerical value of L1 is set by a manager; acquiring the maximum value of the environmental coefficient of the normal area in the detection period, marking the maximum value as the environmental performance value of the detection period, summing the environmental performance values of the detection period, averaging to obtain the normal coefficient of the detection period, establishing an environmental set of the environmental performance values of the detection period, and calculating the variance of the environmental set to obtain the fluctuation coefficient of the normal area in the detection period; acquiring a normal threshold and a fluctuation threshold through a storage module, and comparing a normal coefficient and a fluctuation coefficient of the detection duration with the normal threshold and the fluctuation threshold respectively: if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is smaller than the fluctuation threshold, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module; if the normal coefficient is larger than or equal to the normal threshold, judging that the development trend of the storage environment in the normal area does not meet the requirement, and sending a trend unqualified signal to the detection platform by the trend analysis module; if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is larger than or equal to the fluctuation threshold, performing depth analysis on the normal area: establishing a rectangular coordinate system by taking the detection time as an X axis and the environmental coefficient as a Y axis, marking L1 points in the rectangular coordinate system by taking the end time of the detection time period as a horizontal coordinate and the environmental expression value of the detection time period as a vertical coordinate, marking the points as analysis points, sequentially connecting the analysis points from left to right to obtain analysis broken lines, connecting the end points of the analysis broken lines with the last inflection point to obtain analysis line segments, obtaining the length values and the slope values of the analysis line segments, obtaining a length threshold value through a storage module, judging that the development trend of the storage environment in a normal area does not meet the requirement if the slope values of the analysis line segments are greater than zero and the length values of the analysis line segments are greater than the length threshold value, and sending a trend unqualified signal to the detection platform by a trend analysis module; otherwise, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module; the storage environment development trend of the normal area is detected and analyzed, the environmental change trend of the normal area is predicted by combining the environmental coefficient fluctuation degree of the normal area in a period of time aiming at the storage area of which the current environmental detection result meets the requirement, and early warning is further carried out before the normal area is abnormal, so that the possibility of the environmental abnormal phenomenon occurring in the monitoring area is reduced.
The central analysis module is used for carrying out central analysis on the abnormal area after receiving the abnormal area: acquiring the number of abnormal areas, and if the number of the abnormal areas is one, marking the corresponding abnormal areas as central areas and sending the central areas to a detection platform; if the number of the abnormal areas is not one, marking the abnormal area with the largest environmental coefficient value as a diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius, marking the obtained circular area as an analysis area, judging whether the abnormal area exists outside the analysis area, if so, marking the abnormal area with the largest environmental coefficient value outside the analysis area as the diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius to obtain an analysis area again, and so on until no abnormal area exists outside the analysis area; if not, performing diffusion analysis on the analysis area: the method comprises the steps of marking an environmental coefficient of a diffusion area as KS, obtaining a diffusion threshold value KSmin through a formula KSmin = t1 KS, wherein t1 is a proportionality coefficient, t1 is more than or equal to 0.75 and less than or equal to 0.85, and the diffusion threshold value KSmin and KS form a diffusion range; if the diffusion quantity is not zero, marking the abnormal object and the diffusion object with the environmental coefficients in the diffusion range as the marked objects together, selecting one marked object as the designated object, acquiring the straight-line distances between the center point of the designated object and the center points of all the rest abnormal objects in the analysis area, summing and averaging to obtain the distance table value of the marked object; sequentially taking all marked objects in the analysis area as designated objects, acquiring a plurality of distance table values, marking an abnormal object corresponding to the marked object with the minimum distance table value as a central area of the analysis area, and sending the central area of the analysis area to a detection platform; the abnormal areas are subjected to central analysis, when a plurality of monitoring areas with abnormal environment are detected at the same time, the monitoring areas with actual leakage are judged in a central analysis mode, processing priorities are set for workers during abnormal processing, the workers can preferentially investigate and process the monitoring areas with the most possible actual leakage, and the abnormal processing efficiency is improved.
Example two
As shown in fig. 2, a dangerous goods intelligent detection and early warning method based on computer machine vision includes the following steps:
the method comprises the following steps: the method comprises the steps that a regional detection module is used for carrying out regional detection analysis on a dangerous article storage warehouse, the dangerous article storage warehouse is divided into a plurality of monitoring regions, temperature data, humidity data and leakage data of the monitoring regions are obtained, numerical calculation is carried out to obtain an environmental coefficient, the monitoring regions are marked as normal regions or abnormal regions according to the numerical value of the environmental coefficient, the detection precision of the dangerous article storage environment is improved, and meanwhile, source tracing can be carried out when abnormality occurs;
step two: the development trend of the storage environment of the normal area is detected and analyzed through a trend analysis module: whether the development trend of the storage environment of the normal area meets the requirement or not is judged through the detection and analysis result, early warning is carried out before the normal area is abnormal, and the possibility of the abnormal environment phenomenon in the monitoring area is reduced;
step three: performing center analysis on the abnormal areas through a center analysis module to obtain the number of the abnormal areas, and if the number of the abnormal areas is one, marking the corresponding abnormal areas as the center areas and sending the center areas to a detection platform; if the number of the abnormal areas is not one, marking the abnormal area with the maximum environmental coefficient value as a diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius, marking the obtained circular area as an analysis area, judging whether the abnormal area exists outside the analysis area, if so, marking the abnormal area with the maximum environmental coefficient value outside the analysis area as the diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius to obtain an analysis area again, and so on until no abnormal area exists outside the analysis area; if not, performing diffusion analysis on the analysis area to obtain a central area of the analysis area, and sending the central areas of all the analysis areas to the detection platform, so that the worker can preferentially perform troubleshooting and processing on the central area, and the exception handling efficiency is improved.
A dangerous goods intelligent detection early warning method based on computer machine vision comprises the steps that during working, regional detection analysis is conducted on a dangerous goods storage warehouse through a region detection module, the dangerous goods storage warehouse is divided into a plurality of monitoring regions, temperature data, humidity data and leakage data of the monitoring regions are obtained, numerical calculation is conducted to obtain environment coefficients, and the monitoring regions are marked as normal regions or abnormal regions according to the numerical values of the environment coefficients; the development trend of the storage environment of the normal area is detected and analyzed through a trend analysis module: judging whether the development trend of the storage environment of the normal area meets the requirement or not by detecting and analyzing results; the center analysis module is used for performing center analysis on the abnormal area to obtain a center area, and workers can preferentially perform troubleshooting and processing on the center area, so that the abnormal processing efficiency is improved.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
The formulas are obtained by acquiring a large amount of data and performing software simulation, and the coefficients in the formulas are set by the technicians in the field according to actual conditions; such as: formula HJ = α 1 × WD + α 2 × SD + α 3 × XL; collecting multiple groups of sample data and setting corresponding environment coefficients for each group of sample data by a person skilled in the art; substituting the set harmful coefficients and the acquired sample data into formulas, forming a ternary linear equation set by any three formulas, screening the calculated coefficients and taking the mean value to obtain values of alpha 1, alpha 2 and alpha 3 which are 5.28, 2.67 and 2.15 respectively;
the size of the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the coefficient depends on the number of sample data and the corresponding environment coefficient is preliminarily set for each group of sample data by a person skilled in the art; it is sufficient that the proportional relationship between the parameter and the quantized value is not affected, for example, the environmental coefficient is proportional to the value of the temperature data.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (6)
1. A dangerous goods intelligent detection early warning method based on computer machine vision is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that regional detection analysis is conducted on a dangerous goods storage warehouse through a region detection module, the dangerous goods storage warehouse is divided into a plurality of monitoring regions, temperature data, humidity data and leakage data of the monitoring regions are obtained, numerical calculation is conducted to obtain environment coefficients, and the monitoring regions are marked as normal regions or abnormal regions according to the numerical values of the environment coefficients;
step two: the development trend of the storage environment of the normal area is detected and analyzed through a trend analysis module: judging whether the development trend of the storage environment of the normal area meets the requirement or not by detecting and analyzing results;
step three: performing center analysis on the abnormal areas through a center analysis module to obtain the number of the abnormal areas, and if the number of the abnormal areas is one, marking the corresponding abnormal areas as the center areas and sending the center areas to a detection platform; if the number of the abnormal areas is not one, marking the abnormal area with the largest environmental coefficient value as a diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius, marking the obtained circular area as an analysis area, judging whether the abnormal area exists outside the analysis area, if so, marking the abnormal area with the largest environmental coefficient value outside the analysis area as the diffusion area, drawing a circle by taking the central point of the diffusion area as the center of the circle and r1 as the radius to obtain an analysis area again, and so on until no abnormal area exists outside the analysis area; and if not, performing diffusion analysis on the analysis area to obtain a central area of the analysis area, and sending the central areas of all the analysis areas to the detection platform.
2. The intelligent detection and early warning method for dangerous goods based on computer machine vision as claimed in claim 1, wherein in step one, the process of marking the monitoring area as normal area or abnormal area comprises: acquiring an environment threshold value through a storage module, and comparing the environment coefficient HJ of the monitoring area with the environment threshold value:
if the environmental coefficient is smaller than the environmental threshold, judging that the storage environment of the monitoring area meets the requirement, marking the corresponding monitoring area as a normal area, sending the normal area to the detection platform, and sending the normal area to the trend analysis module after the detection platform receives the normal area;
if the environment coefficient is larger than or equal to the environment threshold value, marking the corresponding monitoring area as an abnormal area, sending the abnormal area to the detection platform, and sending the abnormal area to the central analysis module after the detection platform receives the abnormal area.
3. The intelligent detection and early warning method for dangerous goods based on computer machine vision according to claim 1, wherein in the second step, the specific process of detecting and analyzing the development trend of the storage environment in the normal area comprises: setting the detection time length of a normal region, dividing the detection time length into L1 detection time periods, wherein L1 is a numerical constant, acquiring the maximum value of the environmental coefficient of the normal region in the detection time periods and marking the maximum value as the environmental performance value of the detection time periods, summing the environmental performance values of the detection time periods and averaging to obtain the normal coefficient of the detection time periods, establishing an environmental set of the environmental performance values of the detection time periods, and calculating the variance of the environmental set to obtain the fluctuation coefficient of the normal region in the detection time length; the normal threshold and the fluctuation threshold are obtained through the storage module, the normal coefficient and the fluctuation coefficient of the detection duration are respectively compared with the normal threshold and the fluctuation threshold, and whether the development trend of the storage environment in the normal area meets the requirement or not is judged through the comparison result.
4. The intelligent detection and early warning method for dangerous goods based on computer machine vision according to claim 3, wherein in the second step, the specific process of comparing the normal coefficient and the fluctuation coefficient of the detection duration with the normal threshold and the fluctuation threshold respectively comprises:
if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is smaller than the fluctuation threshold, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module;
if the normal coefficient is larger than or equal to the normal threshold, judging that the development trend of the storage environment in the normal area does not meet the requirement, and sending a trend unqualified signal to the detection platform by the trend analysis module; and if the normal coefficient is smaller than the normal threshold and the fluctuation coefficient is larger than or equal to the fluctuation threshold, performing depth analysis on the normal area.
5. The intelligent detection and early warning method for dangerous goods based on computer machine vision according to claim 4, wherein in the second step, the specific process of performing depth analysis on the normal area comprises: establishing a rectangular coordinate system by taking the detection time as an X axis and the environmental coefficient as a Y axis, marking L1 points in the rectangular coordinate system by taking the end time of the detection time period as a horizontal coordinate and the environmental expression value of the detection time period as a vertical coordinate, marking the points as analysis points, connecting the analysis points from left to right in sequence to obtain analysis broken lines, connecting the end points of the analysis broken lines with the last inflection point to obtain analysis line segments, obtaining the length values and the slope values of the analysis line segments, and obtaining the length threshold value through a storage module;
if the slope value of the analysis line segment is larger than zero and the length value of the analysis line segment is larger than the length threshold, judging that the development trend of the storage environment of the normal area does not meet the requirement, and sending an unqualified trend signal to the detection platform by the trend analysis module;
otherwise, judging that the development trend of the storage environment in the normal area meets the requirement, and sending a trend qualified signal to the detection platform by the trend analysis module.
6. The intelligent detection and early warning method for dangerous goods based on computer machine vision as claimed in claim 1, wherein in step three, the specific process of diffusion analysis for the analysis area comprises: the method comprises the steps of marking the environmental coefficients of the diffusion areas as KS, obtaining a diffusion threshold value KSmin through a formula KSmin = t1 KS, wherein t1 is a proportionality coefficient, t1 is more than or equal to 0.75 and less than or equal to 0.85, forming a diffusion range by the diffusion threshold value KSmin and KS, obtaining the number of abnormal areas of the environmental coefficients in the analysis area within the diffusion range, and marking the abnormal areas as diffusion numbers;
if the diffusion quantity is zero, marking the diffusion area as a central area of the analysis area;
if the diffusion quantity is not zero, marking the abnormal objects and the diffusion objects with the environmental coefficients within the diffusion range as marked objects together, selecting one marked object as a designated object, obtaining the straight-line distances between the center point of the designated object and the center points of all the rest abnormal objects in the analysis area, summing and averaging to obtain the distance table value of the marked object; and taking all the marked objects in the analysis area as designated objects in sequence, acquiring a plurality of distance table values, and marking the abnormal object corresponding to the marked object with the minimum distance table value as the central area of the analysis area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211036835.3A CN115099760B (en) | 2022-08-29 | 2022-08-29 | Intelligent dangerous article detection and early warning method based on computer machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211036835.3A CN115099760B (en) | 2022-08-29 | 2022-08-29 | Intelligent dangerous article detection and early warning method based on computer machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115099760A true CN115099760A (en) | 2022-09-23 |
| CN115099760B CN115099760B (en) | 2022-11-25 |
Family
ID=83301600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211036835.3A Active CN115099760B (en) | 2022-08-29 | 2022-08-29 | Intelligent dangerous article detection and early warning method based on computer machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115099760B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619298A (en) * | 2022-10-17 | 2023-01-17 | 广东宏大民爆集团有限公司 | Intelligent prevention and control method and system for emulsion explosive |
| CN115892828A (en) * | 2023-01-06 | 2023-04-04 | 山东复圣化工有限公司 | Storage supervision system for storage device for chemical production |
| CN115979351A (en) * | 2023-03-22 | 2023-04-18 | 青岛市人防建筑设计研究院有限公司 | Unattended people's air defense early warning system based on data analysis |
| CN116070917A (en) * | 2023-03-31 | 2023-05-05 | 南京南瑞信息通信科技有限公司 | Dangerous chemical risk level evaluation system based on artificial intelligent storage |
| CN116381302A (en) * | 2023-04-14 | 2023-07-04 | 杭州中凯通信设备有限公司 | Embedded waterproof electric energy metering box |
| CN116973051A (en) * | 2023-09-22 | 2023-10-31 | 南通友善金属容器有限公司 | Cylinder tightness detection and early warning method and system for concrete mixing |
| CN117193443A (en) * | 2023-11-06 | 2023-12-08 | 山东汇能新材料科技股份有限公司 | Pure benzene storage environment control system based on artificial intelligence |
| CN117789946A (en) * | 2023-12-22 | 2024-03-29 | 中国人民解放军海军第九七一医院 | Anesthetic agent storage management system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542267A (en) * | 2011-12-26 | 2012-07-04 | 哈尔滨工业大学 | Salient region detecting method combining spatial distribution and global contrast |
| CN110543867A (en) * | 2019-09-09 | 2019-12-06 | 北京航空航天大学 | crowd density estimation system and method under condition of multiple cameras |
| US20210169417A1 (en) * | 2016-01-06 | 2021-06-10 | David Burton | Mobile wearable monitoring systems |
| CN114649085A (en) * | 2022-01-20 | 2022-06-21 | 淮安市第二人民医院 | Emergency medical supplies management system based on big data |
| CN114674988A (en) * | 2022-05-25 | 2022-06-28 | 维睿空气系统产品（深圳）有限公司 | Air on-line monitoring system based on wireless network |
-
2022
- 2022-08-29 CN CN202211036835.3A patent/CN115099760B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542267A (en) * | 2011-12-26 | 2012-07-04 | 哈尔滨工业大学 | Salient region detecting method combining spatial distribution and global contrast |
| US20210169417A1 (en) * | 2016-01-06 | 2021-06-10 | David Burton | Mobile wearable monitoring systems |
| CN110543867A (en) * | 2019-09-09 | 2019-12-06 | 北京航空航天大学 | crowd density estimation system and method under condition of multiple cameras |
| CN114649085A (en) * | 2022-01-20 | 2022-06-21 | 淮安市第二人民医院 | Emergency medical supplies management system based on big data |
| CN114674988A (en) * | 2022-05-25 | 2022-06-28 | 维睿空气系统产品（深圳）有限公司 | Air on-line monitoring system based on wireless network |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619298A (en) * | 2022-10-17 | 2023-01-17 | 广东宏大民爆集团有限公司 | Intelligent prevention and control method and system for emulsion explosive |
| CN115892828A (en) * | 2023-01-06 | 2023-04-04 | 山东复圣化工有限公司 | Storage supervision system for storage device for chemical production |
| CN115979351A (en) * | 2023-03-22 | 2023-04-18 | 青岛市人防建筑设计研究院有限公司 | Unattended people's air defense early warning system based on data analysis |
| CN116070917A (en) * | 2023-03-31 | 2023-05-05 | 南京南瑞信息通信科技有限公司 | Dangerous chemical risk level evaluation system based on artificial intelligent storage |
| CN116381302A (en) * | 2023-04-14 | 2023-07-04 | 杭州中凯通信设备有限公司 | Embedded waterproof electric energy metering box |
| CN116381302B (en) * | 2023-04-14 | 2023-11-07 | 杭州中凯通信设备有限公司 | Embedded waterproof electric energy metering box |
| CN116973051A (en) * | 2023-09-22 | 2023-10-31 | 南通友善金属容器有限公司 | Cylinder tightness detection and early warning method and system for concrete mixing |
| CN117193443A (en) * | 2023-11-06 | 2023-12-08 | 山东汇能新材料科技股份有限公司 | Pure benzene storage environment control system based on artificial intelligence |
| CN117193443B (en) * | 2023-11-06 | 2024-01-26 | 山东汇能新材料科技股份有限公司 | Pure benzene storage environment control system based on artificial intelligence |
| CN117789946A (en) * | 2023-12-22 | 2024-03-29 | 中国人民解放军海军第九七一医院 | Anesthetic agent storage management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115099760B (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115099760B (en) | Intelligent dangerous article detection and early warning method based on computer machine vision | |
| CN113783272B (en) | Safety control method based on super capacitor monitoring management system | |
| CN117079428A (en) | Regional early warning system for monitoring leakage of dangerous chemical gas in factory | |
| CN114997682B (en) | Construction site safety monitoring system and method based on big data | |
| CN114994264B (en) | Park digital monitoring platform based on block chain enterprise-level ledger | |
| CN114328075A (en) | Intelligent power distribution room sensor multidimensional data fusion abnormal event detection method and system and computer readable storage medium | |
| CN110889441A (en) | Distance and point density based substation equipment data anomaly identification method | |
| CN117571742B (en) | Method and device for realizing chip quality inspection based on artificial intelligence | |
| CN117079442A (en) | Chemical industry park hazardous chemical gas leakage diffusion monitoring system based on data analysis | |
| CN110186854A (en) | A kind of foodsafety information detecting method | |
| CN117826693A (en) | Intelligent oil depot monitoring and early warning system and method | |
| CN117744945A (en) | Environment monitoring system of hazardous chemical park | |
| CN112881605A (en) | Environmental air quality monitoring method and system | |
| CN109213119B (en) | Complex industry key component fault prediction method and system based on online learning | |
| CN116562712A (en) | System and method for predicting air quality | |
| CN115278390A (en) | Communication base station construction is with synthesizing rack structure and control system thereof | |
| CN114266483A (en) | Dangerous waste monitoring system based on Internet of things | |
| CN113887044A (en) | Data quality monitoring method, device, equipment and readable storage medium | |
| CN117406161B (en) | Metering device magnitude deviation early warning method, system, equipment and medium | |
| CN116878728B (en) | Pressure sensor fault detection analysis processing system | |
| CN116579748B (en) | Safety production management system based on wireless communication technology | |
| CN213715779U (en) | Network control system fault detection system | |
| CN103257206A (en) | Evaluation method of detection result accuracy of rapid organophosphorus and carbamate pesticide residue detector | |
| CN115389707B (en) | SF6 gas monitoring and alarming system and method based on Internet of things | |
| CN117555279B (en) | Remote instant monitoring system and method for dangerous chemical storage warehouse |
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 |