Fire-fighting auxiliary decision-making method and system based on real-time environment monitoring

Abstract

The invention relates to a fire-fighting auxiliary decision-making method and system based on real-time environment monitoring, and the method comprises the steps: setting a plurality of monitoring points in a hazardous chemical substance storage region, and carrying out the real-time monitoring of a plurality of positions of the hazardous chemical substance storage region. When the environmental parameters of any monitoring point are abnormal or smoke characteristics appear in the video data, trend identification is carried out on the environmental parameters of the monitoring points, and if the environmental parameters have a one-way change trend and the change amount is large, the diffusion risk exists. When diffusion risks exist, diffusion analysis is carried out on the diffusion risks, and the diffusion direction and the diffusion speed are determined. And finally, auxiliary decision making is carried out based on the diffusion direction and the diffusion speed. According to the invention, monitoring is carried out based on the dynamic change of the abnormal parameters, the situation without diffusion risk can be accurately identified, and the situation of many false alarms can be reduced. The method has the advantages of being accurate in monitoring, capable of assisting fire-fighting decision and the like.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a fire fighting auxiliary decision-making method and system based on real-time environmental monitoring. Background Art

[0002] At present, most chemical parks still have problems such as imperfect emergency management system and mechanism, unreasonable allocation of various emergency resources, weak emergency rescue capabilities, lack of safety technology supervision platform, lack of professional fire fighting capabilities, etc. Since there are many major hazard sources such as flammable, explosive, and toxic in the park, once an accident occurs, the consequences will be very serious.

[0003] In the existing technology, a monitoring system is set up to monitor fires, toxic gases, etc. However, for special environments such as chemical parks, fog and high temperature conditions at a single point are often generated, which often leads to misjudgment of the system. In addition, simple sensors can only monitor whether there is high temperature, humidity, and toxic gas leakage in an area, but cannot analyze the spread trend of high temperature, humidity, and toxic gases, resulting in the inability to assist the fire protection system in making evacuation and rescue decisions. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a fire fighting decision support method and system based on real-time environmental monitoring to solve the problems in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: The fire fighting auxiliary decision-making method based on real-time environmental monitoring of the present invention comprises the following steps: Obtain environmental monitoring data and surveillance videos of hazardous chemicals storage areas within the park, and obtain a plan of the park, wherein the environmental monitoring data includes values ​​of environmental factors at multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; Determine whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; When there is a preliminary risk in the hazardous chemicals storage area, a trend analysis is performed on the values ​​of the environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area to obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: a unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; Determine the type of the target environmental factor. When the target environmental factor is of the target type, use the monitoring point with the risk diffusion trend as the base point, and perform diffusion direction and diffusion speed analysis based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, perform diffusion direction and diffusion speed analysis based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results; Fire fighting auxiliary decision making is performed based on the diffusion analysis results and the park floor plan.

[0006] In one embodiment of the present application, judging whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point includes: Compare the values ​​of the environmental factors at multiple consecutive time points with the corresponding preset thresholds, and perform smoke recognition on the surveillance video based on the pre-built smoke recognition model; When the value of any environmental factor at any time point is greater than the corresponding preset threshold, or when smoke features exist in the monitoring video, it is determined that there is a preliminary risk in the hazardous chemicals storage area.

[0007] In one embodiment of the present application, trend analysis is performed on the values ​​of environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area to obtain change characteristics of the environmental factors, including: Mapping the values ​​of each environmental factor at each monitoring point at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis and the vertical axis of the two-dimensional coordinate system is the data axis; The pre-built sliding window is slid along the time axis, and at each slide, the average value of all data points in the sliding window is calculated to obtain the average value of each slide. ; The average value of multiple sliding motions satisfies or , it is determined that the value of the environmental factor has a unidirectional change at multiple consecutive time points; the average value of the last sliding is calculated and the average of the initial position of the sliding window The difference , and obtain the changing characteristics of environmental factors.

[0008] In one embodiment of the present application, diffusion direction and diffusion speed analysis is performed based on the values ​​of the target environmental factors of the base point and other monitoring points at multiple consecutive time points to obtain diffusion analysis results, including: Conduct trend analysis on the values ​​of target environmental factors at other monitoring points at multiple consecutive time points; When the target environmental factors at other monitoring points do not contain a one-way change section, the waiting time , and return to the trend analysis of the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points until the target environmental factors of other monitoring points show a unidirectional change section, or the waiting time accumulates to the target time; When the target environmental factors of other monitoring points do not contain a one-way change section when the waiting time accumulates to the target time, it is determined that there is no diffusion risk in the hazardous chemicals storage area; when the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points contain a one-way change section, it is determined that there is a diffusion risk in the hazardous chemicals storage area, and the monitoring point containing the one-way change section is used as the target monitoring point; The diffusion direction is determined based on the position of the base point and the position of the target monitoring point, and the diffusion speed is determined based on the distance between the base point and the target monitoring point and the time of the one-way change section of the target monitoring point.

[0009] In one embodiment of the present application, trend analysis is performed on the values ​​of target environmental factors at other monitoring points at multiple consecutive time points, including: Mapping the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points located in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis and the vertical axis of the two-dimensional coordinate system is the data axis; Slide along the time axis based on the pre-built first sliding window, and calculate the average value of multiple data points in the first sliding window each time it slides. ; Slide along the time axis based on the pre-built second sliding window, and determine multiple average values ​​in the second sliding window each time it slides. Is it satisfied? or , and will satisfy or The section is regarded as a one-way change section.

[0010] In one embodiment of the present application, the diffusion direction and diffusion speed analysis is performed based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results, including: Extract frames from the infrared thermal video or the RGB video to obtain multiple image frames on the time axis ; For the plurality of image frames Perform preprocessing to obtain multiple preprocessed images , where the preprocessing methods include high-pass filtering, contrast enhancement and grayscale conversion; The plurality of pre-processed images are processed based on a preset grayscale threshold range. Binarization is performed separately to obtain multiple binary images , where the binary image The area that meets the preset grayscale threshold range is the abnormal area; Extract the binary image Outline of the abnormal area , get the time series profile sequence; Subtracting any two adjacent contours in the time-series contour sequence to obtain a diffusion region sequence; From the initial contour in the time-series contour sequence Extracting the centroid from the image, and constructing a plurality of fan-shaped direction areas with the centroid; Align the multiple directional regions with each diffusion region in the diffusion region sequence, and extract the centroid of the diffusion part of the diffusion region that falls within the multiple directional regions. ; Calculate the diffusion speed in each direction area, where the diffusion speed is the ratio of the change in the displacement of the center of mass of each direction area to the duration; The diffusion direction and the diffusion speed in the diffusion direction are determined based on the diffusion speed in each directional region.

[0011] In one embodiment of the present application, fire fighting auxiliary decision making is performed based on the diffusion analysis result and the park plan, including: The diffusion direction whose diffusion speed exceeds the preset threshold is taken as the evacuation direction, and the risk area and the emergency operation area are determined based on the evacuation direction; and the type of emergency materials is determined based on the type of the target environmental factor and the type of hazardous chemicals stored in the hazardous chemicals storage area; The evacuation direction, the risk area, the emergency operation area and the type of emergency materials are marked in the park plan, and the park plan with the evacuation direction, the risk area, the emergency operation area and the type of emergency materials marked is sent to the target object.

[0012] In one embodiment of the present application, it also includes: When there is a risk spreading trend at the monitoring point, an alarm message and monitoring video are sent to the target object.

[0013] In one embodiment of the present application, the target type is an environmental factor type that will not cause changes in air temperature and color.

[0014] The present application also provides a fire fighting decision support system based on real-time environmental monitoring, which is characterized by comprising: An acquisition module is used to acquire environmental monitoring data and surveillance videos of hazardous chemicals storage areas in the park, and to acquire a park floor plan, wherein the environmental monitoring data includes values ​​of environmental factors of multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; The risk determination module is used to determine whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; The diffusion risk determination module is used to perform trend analysis on the values ​​of environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area when there is a preliminary risk in the hazardous chemicals storage area, and obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; The diffusion analysis module is used to determine the type of the target environmental factor. When the target environmental factor is of the target type, the monitoring point with a risk diffusion trend is used as the base point, and the diffusion direction and diffusion speed analysis is performed based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, the diffusion direction and diffusion speed analysis is performed based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results; The auxiliary decision-making module is used to make auxiliary fire fighting decisions based on the diffusion analysis results and the park plan.

[0015] The beneficial effects of the present invention are as follows: the fire fighting decision-making support method and system based on real-time environmental monitoring of the present invention sets multiple monitoring points in the hazardous chemicals storage area, and respectively performs real-time monitoring of multiple locations in the hazardous chemicals storage area. When the environmental parameters of any monitoring point are abnormal, or when smoke features appear in the video data, the environmental parameters of the monitoring point are trend identified. If the environmental parameters show a unidirectional change trend, and the amount of change is large, it indicates that there is a risk of diffusion. When there is a risk of diffusion, a diffusion analysis is performed to determine the diffusion direction and diffusion speed. Finally, auxiliary decision-making is performed based on the diffusion direction and diffusion speed. The present application performs monitoring based on the dynamic changes of abnormal parameters, and can accurately identify situations where there is no risk of diffusion, which can reduce many false alarms. The present application has the advantages of accurate monitoring and the ability to assist in fire fighting decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 It is an application scenario diagram of a fire fighting auxiliary decision-making method based on real-time environmental monitoring shown in an embodiment of the present application; Figure 2 is a schematic diagram of the structure of a monitoring unit in an embodiment of the present application; Figure 3 Schematic diagram of the multi-sensor fusion decision structure used in this application; Figure 4 is a flow chart of a fire fighting auxiliary decision-making method based on real-time environmental monitoring shown in an embodiment of the present application; Figure 5 A schematic diagram of determining the diffusion direction in an embodiment of the present application; Figure 6 is a structural diagram of a fire fighting decision support system based on real-time environmental monitoring shown in an embodiment of the present application; Figure 7 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0018] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.

[0019] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.

[0020] Figure 1 is an application scenario diagram of a fire fighting auxiliary decision-making method based on real-time environmental monitoring in an embodiment of the present application, such as Figure 1As shown, this application mainly relies on multiple monitoring units set up in the area where hazardous chemicals exist to realize the real-time collection of environmental parameters. Each monitoring unit is set up in different locations in the area where hazardous chemicals exist, and basic data is collected through a variety of sensors. In addition, considering that the key points of hazardous chemical enterprises have harsh and extremely dangerous environments and a large amount of flammable gases and dust, the design of the industrial television monitoring system can be considered. The on-site monitoring system is responsible for completing the collection, caching, encoding, storage and sending of front-end audio and video information and alarm information, and can accept control instructions from the network. It usually includes the following equipment: embedded DVR, NVR, camera, alarm input and output equipment, voice intercom equipment, etc. Once an accident occurs, it can quickly review the properties of hazardous chemicals and the surrounding environment information, find the best solution, and formulate a treatment plan to minimize the losses caused by the accident.

[0021] Figure 2 is a schematic diagram of the structure of a monitoring unit in an embodiment of the present application, such as Figure 2 As shown, the present application uses remote intelligent control to collect, process and manage multi-point data, and uses a multi-level computer processing system to realize functions. In the present application, the data acquisition device converts the signal obtained by the sensor into a digital signal for preprocessing. First, the data in each data acquisition device is read, and then the corresponding information and commands are transmitted to the corresponding data collection device; secondly, the data is processed and the corresponding file is generated; thirdly, the processed information is transmitted to the workstation, so that the workstation can be connected to the computer network, thereby forming an integrated production management.

[0022] Figure 3 This is a schematic diagram of the multi-sensor fusion decision structure used in this application. Figure 3 As shown, in this application, multiple sensors are used to perform basic data collection. After being transmitted through the network, signal processing and sensor fusion are performed in the analysis host to assist staff in making firefighting decisions. Finally, the plan deployment and specific plan execution are completed.

[0023] Figure 4 is a flow chart of a fire fighting auxiliary decision-making method based on real-time environmental monitoring in an embodiment of the present application, such as Figure 4 As shown: The fire fighting auxiliary decision-making method based on real-time environmental monitoring of this embodiment may include steps S410 to S450: S410, obtaining environmental monitoring data and surveillance videos of hazardous chemicals storage areas in the park, and obtaining a park floor plan, wherein the environmental monitoring data includes values ​​of environmental factors of multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; In this application, the acquisition of environmental monitoring data and surveillance videos, as described above, depends on the constructed information collection system. This application is mainly aimed at scenes such as chemical parks and hazardous chemical production enterprises. Therefore, the main environmental parameters that need to be collected are temperature, humidity, dust concentration, and harmful gas concentration. In addition, if it is necessary to collect water leakage, leakage, etc., you can also add equipment such as current sensors and water immersion sensors.

[0024] S420, judging whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; The initial risk determination is relatively simple, that is, it is determined based on the results of threshold comparison and feature recognition, including: S421, comparing the values ​​of the environmental factors at multiple consecutive time points with the corresponding preset thresholds, and performing smoke recognition on the surveillance video based on the pre-built smoke recognition model; S422: When the value of any environmental factor at any time point is greater than the corresponding preset threshold, or when smoke features exist in the monitoring video, it is determined that there is a preliminary risk in the hazardous chemicals storage area.

[0025] In this application, monitoring identification is performed through a neural network recognition model prepared in advance to extract smoke features. For chemical parks, local high temperatures or water mist often occur during exothermic reactions in the process, operation and maintenance of equipment, and steam discharge. Therefore, the risk of fire is judged to exist only by relying on existing neural network recognition technology. A large number of false alarms are prone to occur, so this application also uses the following analysis process to further analyze the above data.

[0026] S430, when there is a preliminary risk in the hazardous chemicals storage area, a trend analysis is performed on the values ​​of the environmental factors of each monitoring point in the hazardous chemicals storage area at multiple consecutive time points to obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: a unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; In order to exclude some false alarms caused by local high temperature, humidity changes, and harmful gas discharge caused by normal operation. This application also performs trend analysis on the values ​​of environmental factors at multiple consecutive time points for each monitoring point. Determine whether the abnormal value of a single point continues for a long time from the change trend. If it continues for a long time and the situation continues to deteriorate, it means that the environmental parameter abnormality is not caused by normal operation. For example, when a harmful gas leaks, the harmful gas sensor detects an increase in concentration at the first time. At this time, a trend analysis is performed. If the concentration continues to rise within a certain period of time, and the increase is large, it means that it is an abnormal leak. Because if it is normal operation, the emission rate will be controlled and the concentration will not continue to rise. When the environmental parameter abnormality continues, such as high temperature continues and harmful gas continues to leak, it is bound to lead to risk diffusion, so it is determined that there is a risk diffusion trend. Once a risk diffusion trend appears, send an alarm message and monitoring video to the target object. Provide risk prompts and alarms in time.

[0027] Specifically, the trend analysis process in this application is as follows: S431, mapping the values ​​of each environmental factor of each monitoring point at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points located in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis, and the vertical axis of the two-dimensional coordinate system is the data axis; S432, sliding along the time axis based on the pre-built sliding window, and calculating the average value of all data points in the sliding window at each sliding, to obtain the average value of each sliding ; S433, when the average value of multiple sliding motions satisfies or , it is determined that the value of the environmental factor has a unidirectional change at multiple consecutive time points; the average value of the last sliding is calculated and the average of the initial position of the sliding window The difference , and obtain the changing characteristics of environmental factors.

[0028] This application uses a sliding window to filter out the trend analysis impact caused by the sudden change in the value of a single data point. Multiple time points are generally multiple sampling time points within a duration of 3-10 minutes. The window width is set to about 30 seconds, and the step length is about 10 seconds, that is, the average value of the data points within 30 seconds is calculated each time. If the value of the environmental parameter continues to rise or fall, it will cause the average value of the sliding to meet or In addition, it is also necessary to extract the amount of change in this process. If the amount of change is too small, it is not considered to satisfy the one-way change.

[0029] S440, determining the type of the target environmental factor. When the target environmental factor is of the target type, taking the monitoring point with the risk diffusion trend as the base point, performing diffusion direction and diffusion speed analysis based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, performing diffusion direction and diffusion speed analysis based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone, and obtaining the diffusion analysis result; When the risk diffusion trend is met, in addition to issuing an alarm, the application further extracts the diffusion trend to help relevant personnel make fire rescue decisions.

[0030] The medium-risk diffusion trend mentioned above is caused by the continuous generation of abnormal environmental data at one point. For example, the temperature continues to rise due to a fire; the concentration continues to rise and the humidity continues to drop due to a toxic gas leak. In these scenarios, there will be diffusion phenomena, such as the diffusion of high-temperature air and the diffusion of toxic gas. These diffusion data play a very important role in the subsequent evacuation of personnel and the formulation of emergency rescue plans.

[0031] Because some environmental parameter changes cannot be reflected in temperature or visual changes, such as humidity, some colorless toxic gases that do not cause air temperature changes. For this type of target environmental parameters, this application still analyzes based on multiple monitoring points. For harmful gas leaks or fires that can cause air temperature changes and color changes, this application uses infrared thermal sensing or visual images to perform analysis.

[0032] Specifically, based on the values ​​of the target environmental factors of the base point and other monitoring points at multiple consecutive time points, the diffusion direction and diffusion speed analysis are performed to obtain the diffusion analysis results, including: S4401, performing trend analysis on the values ​​of target environmental factors at other monitoring points at multiple consecutive time points; When the target environmental factor is continuously changing, the values ​​of the target environmental factors at other monitoring points will also change unidirectionally due to air flow and heat conduction effects. Therefore, it is necessary to perform trend analysis on the values ​​of the target environmental factors at other monitoring points at multiple consecutive time points.

[0033] Different from the trend analysis in the previous article, the trend analysis of other monitoring points only needs to find the segment with unidirectional change and after the initial time point of multiple consecutive time points. Specifically, it includes: S44011, mapping the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points located in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis, and the vertical axis of the two-dimensional coordinate system is the data axis; S44012, sliding along the time axis based on a pre-constructed first sliding window, and calculating the average value of multiple data points in the first sliding window during each sliding. ; S44013, sliding along the time axis based on the pre-constructed second sliding window, and determining multiple average values ​​in the second sliding window each time the sliding window is slid. Is it satisfied? or , and will satisfy or The section is regarded as a one-way change section.

[0034] In the above process, the average value analysis method of the sliding window is still used. In order to find the section with a unidirectional change trend, a second sliding window is also set. Trend judgment is performed in the second sliding window to find the section with a unidirectional change trend. This section is used as the time period from the base point to the current monitoring point.

[0035] S4402, when the target environmental factors at other monitoring points do not contain a one-way change section, the waiting time , and return to the trend analysis of the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points until the target environmental factors of other monitoring points show a unidirectional change section, or the waiting time accumulates to the target time; S4403, when the target environmental factors of other monitoring points do not contain a one-way change section when the waiting time accumulates to the target time, it is determined that there is no diffusion risk in the hazardous chemicals storage area; when the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points contain a one-way change section, it is determined that there is a diffusion risk in the hazardous chemicals storage area, and the monitoring point containing the one-way change section is used as the target monitoring point; If the target environmental factors of other monitoring points do not contain a one-way change section, it means that the spread speed is slow. In this case, wait for multiple cycles before conducting another analysis. If it still does not contain a one-way change section, then the diffusion risk inferred in the previous article is revised to determine that there is no diffusion risk at this time.

[0036] If a one-way change section of other monitoring points is found, the monitoring point will be marked.

[0037] S4404, determining a diffusion direction based on the position of the base point and the position of the target monitoring point, and determining a diffusion speed based on the distance between the base point and the target monitoring point and the time of a one-way change section of the target monitoring point.

[0038] Specifically, there may be multiple diffusion directions, each with a different speed.

[0039] Diffusion rate ,in, Diffusion direction speed, Indicates the base point and the target monitoring point The distance between It is the time difference between the start time point of the unidirectional change segment of the target monitoring point and the initial time point of multiple consecutive time points.

[0040] Based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone, the diffusion direction and diffusion speed are analyzed to obtain the diffusion analysis results, including: S4411, extracting frames from the infrared thermal video or the RGB video to obtain multiple image frames on the time axis ; In order to reduce the amount of data to be processed later, the present application performs frame extraction on the infrared thermal video or the RGB video. The frame extraction method adopts uniform frame extraction.

[0041] S4412, for the plurality of image frames Perform preprocessing to obtain multiple preprocessed images , where the preprocessing methods include high-pass filtering, contrast enhancement and grayscale conversion; High-pass filtering can retain more high-frequency information, which is convenient for subsequent contour extraction. Contrast enhancement can also enhance the difference between high-temperature areas or areas with different colors and other areas, which is convenient for subsequent contour extraction.

[0042] S4413, based on a preset gray threshold range, the plurality of pre-processed images Binarization is performed separately to obtain multiple binary images , where the binary image The area that meets the preset grayscale threshold range is the abnormal area; In this application, different grayscale threshold ranges are pre-set according to different abnormal parameter types. For example, if it is an infrared thermal video, after converting the red part to grayscale, it will fall into a rough grayscale range. If it is a white gas leak, there will be a lighter area in the RGB image, which will also fall into a rough grayscale range. This range can be used to effectively extract the abnormal area.

[0043] S4414, extracting the binary image Outline of the abnormal area , get the time series profile sequence; S4415, performing subtraction on any two adjacent contours in the time series contour sequence to obtain a diffusion region sequence; Each diffusion region in the diffusion region sequence represents the diffusion range of gas or temperature, and the diffusion direction and diffusion speed can be analyzed based on the diffusion range.

[0044] S4416, Initial profile from a time-series profile sequence Extracting the centroid from the image, and constructing a plurality of fan-shaped direction areas with the centroid; Initial outline The centroid of is the midpoint at the beginning of diffusion, and this midpoint is needed as the base point when judging the diffusion direction and diffusion speed. The direction areas of multiple sectors are reference areas for describing multiple diffusion directions.

[0045] S4417, aligning the multiple directional regions with each diffusion region in the diffusion region sequence, and extracting the centroid of the diffusion portion of the diffusion region that falls within the multiple directional regions ; Figure 5 This is a schematic diagram of determining the diffusion direction in an embodiment of the present application, such as Figure 5 As shown, multiple fan-shaped directional areas divide the diffusion range into multiple directions, and the main diffusion direction can be determined.

[0046] S4418, calculating the diffusion speed in each directional region, wherein the diffusion speed is the ratio of the displacement change of the center of mass of each directional region to the duration; Diffusion rate The displacement change of the center of mass is the sum of the displacements of all adjacent centers of mass in each direction area, and the duration is the time difference between the time corresponding to the current frame and the initial time.

[0047] S4419, determining a diffusion direction and a diffusion speed in the diffusion direction based on the diffusion speed in each directional region.

[0048] Finally, the direction in which the diffusion speed is greater than a preset threshold is taken as the diffusion direction.

[0049] S450, making auxiliary fire fighting decisions based on the diffusion analysis results and the park plan.

[0050] Specifically include: S451, taking the diffusion direction whose diffusion speed exceeds a preset threshold as the evacuation direction, and determining the risk area and the emergency operation area based on the evacuation direction; and determining the type of emergency materials based on the type of the target environmental factor and the type of hazardous chemicals stored in the hazardous chemicals storage area; S452, marking the evacuation direction, the risk area, the emergency operation area and the type of emergency materials in the park plan, and sending the park plan with the evacuation direction, the risk area, the emergency operation area and the type of emergency materials marked to the target object.

[0051] The diffusion direction of harmful gases is one of the key factors in formulating evacuation plans, determining risk areas, and planning emergency operation areas. The evacuation direction should be opposite or perpendicular to the diffusion direction of harmful gases as much as possible to reduce the risk of exposure to high concentrations of harmful gases. The risk area can also be determined by the diffusion path mentioned above, so as to evacuate people in the risk area. The emergency operation area is usually located on the upwind side or crosswind direction, away from the main diffusion path to ensure the safety of rescuers. For harmful gases with higher density, the emergency operation point may be selected at a higher position to avoid the high concentration area near the ground.

[0052] In addition, this application prepares different types of emergency materials in advance for different target environmental parameter types to help firefighters complete emergency rescue work more efficiently.

[0053] The fire fighting decision-making support method based on real-time environmental monitoring of the present invention sets multiple monitoring points in the hazardous chemicals storage area, and respectively monitors multiple locations in the hazardous chemicals storage area in real time. When the environmental parameters of any monitoring point are abnormal, or when smoke features appear in the video data, the environmental parameters of the monitoring point are trend identified. If the environmental parameters show a unidirectional change trend, and the amount of change is large, it means that there is a risk of diffusion. When there is a risk of diffusion, a diffusion analysis is performed to determine the direction and speed of diffusion. Finally, auxiliary decision-making is performed based on the diffusion direction and diffusion speed. The present application monitors based on the dynamic changes of abnormal parameters, and can accurately identify situations where there is no risk of diffusion, which can reduce many false alarms. The present application has the advantages of accurate monitoring and the ability to assist in fire fighting decisions.

[0054] like Figure 6 As shown, the present application also provides a fire fighting decision support system based on real-time environmental monitoring, which is characterized by including: An acquisition module is used to acquire environmental monitoring data and surveillance videos of hazardous chemicals storage areas in the park, and to acquire a park floor plan, wherein the environmental monitoring data includes values ​​of environmental factors of multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; The risk determination module is used to determine whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; The diffusion risk determination module is used to perform trend analysis on the values ​​of environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area when there is a preliminary risk in the hazardous chemicals storage area, and obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; The diffusion analysis module is used to determine the type of the target environmental factor. When the target environmental factor is of the target type, the monitoring point with a risk diffusion trend is used as the base point, and the diffusion direction and diffusion speed analysis is performed based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, the diffusion direction and diffusion speed analysis is performed based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results; The auxiliary decision-making module is used to make auxiliary fire fighting decisions based on the diffusion analysis results and the park plan.

[0055] The fire fighting decision support system based on real-time environmental monitoring of the present invention sets multiple monitoring points in the hazardous chemicals storage area, and respectively performs real-time monitoring of multiple locations in the hazardous chemicals storage area. When the environmental parameters of any monitoring point are abnormal, or when smoke features appear in the video data, the environmental parameters of the monitoring point are trend identified. If the environmental parameters show a unidirectional change trend, and the amount of change is large, it means that there is a risk of diffusion. When there is a risk of diffusion, a diffusion analysis is performed to determine the direction and speed of diffusion. Finally, auxiliary decision making is performed based on the diffusion direction and diffusion speed. The present application performs monitoring based on the dynamic changes of abnormal parameters, and can accurately identify situations where there is no risk of diffusion, which can reduce many false alarms. The present application has the advantages of accurate monitoring and the ability to assist in fire fighting decisions.

[0056] Figure 7 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 7 The computer system 700 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0057] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703, such as executing the method in the above embodiment. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702 and the RAM 703 are connected to each other through the bus 704. The input / output (I / O) interface 705 is also connected to the bus 704.

[0058] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0059] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from a removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, various functions defined in the system of the present application are executed.

[0060] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable computer program. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0061] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0062] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0063] Another aspect of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the above method. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0064] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in each of the above embodiments.

[0065] The above embodiments are only preferred embodiments for fully illustrating the present application, and the protection scope of the present application is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present application is within the protection scope of the present application.

Claims

1. A fire fighting decision-making assistance method based on real-time environmental monitoring, characterized in that: Includes steps: Obtain environmental monitoring data and surveillance videos of hazardous chemicals storage areas within the park, and obtain a plan of the park, wherein the environmental monitoring data includes values ​​of environmental factors at multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; Determine whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; When there is a preliminary risk in the hazardous chemicals storage area, a trend analysis is performed on the values ​​of the environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area to obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: a unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; Determine the type of the target environmental factor. When the target environmental factor is of the target type, use the monitoring point with the risk diffusion trend as the base point, and perform diffusion direction and diffusion speed analysis based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, perform diffusion direction and diffusion speed analysis based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results; Fire fighting auxiliary decision making is performed based on the diffusion analysis results and the park floor plan.

2. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: Based on the environmental monitoring data and surveillance videos of each monitoring point, determine whether there is a preliminary risk in the hazardous chemicals storage area, including: Comparing the values ​​of the environmental factors at multiple consecutive time points with the corresponding preset thresholds, and performing smoke recognition on the monitoring video based on a pre-built smoke recognition model; When the value of any environmental factor at any time point is greater than the corresponding preset threshold, or when smoke features exist in the monitoring video, it is determined that there is a preliminary risk in the hazardous chemicals storage area.

3. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 2 is characterized in that: Perform trend analysis on the values ​​of environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area to obtain the change characteristics of the environmental factors, including: Mapping the values ​​of each environmental factor at each monitoring point at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis and the vertical axis of the two-dimensional coordinate system is the data axis; The pre-built sliding window is slid along the time axis, and at each slide, the average value of all data points in the sliding window is calculated to obtain the average value of each slide. ; The average value of multiple sliding motions satisfies or , it is determined that the value of the environmental factor has a unidirectional change at multiple consecutive time points; the average value of the last sliding is calculated and the average of the initial position of the sliding window The difference , and obtain the changing characteristics of environmental factors.

4. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: Based on the values ​​of the target environmental factors at the base point and other monitoring points at multiple consecutive time points, the diffusion direction and diffusion speed analysis are performed to obtain the diffusion analysis results, including: Conduct trend analysis on the values ​​of target environmental factors at other monitoring points at multiple consecutive time points; When the target environmental factors at other monitoring points do not contain a one-way change section, the waiting time , and return to the trend analysis of the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points until the target environmental factors of other monitoring points show a unidirectional change section, or the waiting time accumulates to the target time; When the target environmental factors of other monitoring points do not contain a one-way change section when the waiting time accumulates to the target time, it is determined that there is no diffusion risk in the hazardous chemicals storage area; when the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points contain a one-way change section, it is determined that there is a diffusion risk in the hazardous chemicals storage area, and the monitoring point containing the one-way change section is used as the target monitoring point; The diffusion direction is determined based on the position of the base point and the position of the target monitoring point, and the diffusion speed is determined based on the distance between the base point and the target monitoring point and the time of the one-way change section of the target monitoring point.

5. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 4 is characterized in that: Conduct trend analysis on the values ​​of target environmental factors at other monitoring points at multiple consecutive time points, including: Mapping the values ​​of the target environmental factors of other monitoring points at multiple consecutive time points into a two-dimensional coordinate system to obtain multiple data points located in the two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is the time axis and the vertical axis of the two-dimensional coordinate system is the data axis; Slide along the time axis based on the pre-built first sliding window, and calculate the average value of multiple data points in the first sliding window each time it slides. ; Slide along the time axis based on the pre-built second sliding window, and determine multiple average values ​​in the second sliding window each time it slides. Is it satisfied? or , and will satisfy or The section is regarded as a one-way change section.

6. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: Based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone, the diffusion direction and diffusion speed are analyzed to obtain the diffusion analysis results, including: Extract frames from the infrared thermal video or the RGB video to obtain multiple image frames on the time axis ; The plurality of image frames Perform preprocessing to obtain multiple preprocessed images , where the preprocessing methods include high-pass filtering and contrast enhancement; The plurality of pre-processed images are processed based on a preset grayscale threshold range. Binarization is performed separately to obtain multiple binary images , where the binary image The area that meets the preset grayscale threshold range is the abnormal area; Extract the binary image Outline of the abnormal area , get the time series profile sequence; Subtracting any two adjacent contours in the time-series contour sequence to obtain a diffusion region sequence; From the initial contour in the time-series contour sequence Extracting the centroid from the image, and constructing a plurality of fan-shaped direction areas with the centroid; Align the multiple directional regions with each diffusion region in the diffusion region sequence, and extract the centroid of the diffusion part of the diffusion region that falls within the multiple directional regions. ; Calculate the diffusion speed in each direction area, where the diffusion speed is the ratio of the change in the displacement of the center of mass of each direction area to the duration; The diffusion direction and the diffusion speed in the diffusion direction are determined based on the diffusion speed in each directional region.

7. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: Based on the diffusion analysis results and the park plan, fire fighting auxiliary decision making is performed, including: The diffusion direction whose diffusion speed exceeds the preset threshold is taken as the evacuation direction, and the risk area and the emergency operation area are determined based on the evacuation direction; and the type of emergency materials is determined based on the type of the target environmental factor and the type of hazardous chemicals stored in the hazardous chemicals storage area; The evacuation direction, the risk area, the emergency operation area and the type of emergency materials are marked in the park plan, and the park plan with the evacuation direction, the risk area, the emergency operation area and the type of emergency materials marked is sent to the target object.

8. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: Also includes: When there is a risk spreading trend at the monitoring point, an alarm message and monitoring video are sent to the target object.

9. The fire fighting decision-making auxiliary method based on real-time environmental monitoring according to claim 1 is characterized in that: The target type is an environmental factor type that does not cause changes in air temperature and color.

10. Fire fighting decision support system based on real-time environmental monitoring, characterized in that: include: An acquisition module is used to acquire environmental monitoring data and surveillance videos of hazardous chemicals storage areas in the park, and to acquire a park floor plan, wherein the environmental monitoring data includes values ​​of environmental factors of multiple monitoring points at multiple consecutive time points before the current time point, and the environmental factors include temperature values, humidity values, dust concentration values, and harmful gas concentration values; The risk determination module is used to determine whether there is a preliminary risk in the hazardous chemicals storage area based on the environmental monitoring data and surveillance video of each monitoring point; The diffusion risk determination module is used to perform trend analysis on the values ​​of environmental factors at multiple consecutive time points at each monitoring point in the hazardous chemicals storage area when there is a preliminary risk in the hazardous chemicals storage area, and obtain the change characteristics of the environmental factors; when the change characteristics of any target environmental factor meet the following conditions: unidirectional change at multiple consecutive time points, and the change rate is greater than a preset change rate threshold, it is determined that there is a risk diffusion trend at the monitoring point; The diffusion analysis module is used to determine the type of the target environmental factor. When the target environmental factor is of the target type, the monitoring point with a risk diffusion trend is used as the base point, and the diffusion direction and diffusion speed analysis is performed based on the values ​​of the target environmental factor at the base point and other monitoring points at multiple consecutive time points; when the target environmental factor is not of the target type, the diffusion direction and diffusion speed analysis is performed based on the infrared thermal video or RGB video of the hazardous chemicals storage area collected by the drone to obtain the diffusion analysis results; The auxiliary decision-making module is used to make auxiliary fire fighting decisions based on the diffusion analysis results and the park plan.

Images