A fire disaster intelligent monitoring and early warning system and method based on big data

Abstract

The present invention relates to the field of big data application, and in particular to a fire disaster intelligent monitoring and early warning system based on big data, comprising: an image acquisition module: the image acquisition module is used to acquire image information of a target area; a data processing module: the data processing module is used to acquire image information, aggregate pixel points of the image information, extract the contours of each object in the pixel target area, and identify the image information; a temperature acquisition module: the temperature acquisition module is used to acquire the ambient temperature value of the target area, and is also used to produce thermal imaging maps of the target area and objects according to the temperature; and also relates to a fire disaster intelligent monitoring, prevention and early warning method based on big data, comprising the following steps: S1: acquiring the distribution of objects in the target area through image information; S2: analyzing whether there is a temperature exceeding a threshold in the space according to the thermal imaging image; and solving the problem of low efficiency in discovering fire hazards.

Description

Technical Field

[0001] The present invention relates to the field of big data applications, and in particular to a fire disaster intelligent monitoring and early warning system and method based on big data. Background Art

[0002] Big data is a term in the IT industry. It refers to a collection of data that cannot be captured, managed, and processed by conventional software tools within a certain time frame. It is a massive, high-growth, and diversified information asset that requires a new processing model to have stronger decision-making power, insight discovery, and process optimization capabilities. With the rapid development of the social economy, the construction industry has developed rapidly. The number of community residential buildings has continued to increase, and the number of community residential building fires has also increased, and the fire situation has become more and more severe. How to strengthen fire safety work in community residences and protect the lives and property of residents is a new issue facing today's society. Through multi-sensor perception of environmental changes in the target area, abnormalities can be discovered in a timely manner, blocked in a timely manner, and the impact can be reduced.

[0003] The invention patent with application number 201910212145.0 discloses an intelligent building fire warning system; it includes a computer terminal, a master control module, an internal safety module and an external safety module; the master control module, the internal safety module and the external safety module are all operated based on the computer terminal; the master control module is used to collect information feedback from the internal safety module and the external safety module in real time, and feed the collected information back to the computer terminal; the internal safety module is used to monitor and detect the internal space of the building in real time; the external safety module is used to monitor and detect the external space of the building in real time; the present invention improves the overall safety inside and outside the building through the coordinated use of the master control module, the internal safety module and the external safety module, ensures the safety of people, property and the building itself in the building, eliminates dangers, and prevents the occurrence of disasters.

[0004] The above technology completes the assessment of fire safety and prevents disasters by obtaining the change values ​​of sensor data inside and outside the building. In reality, fire safety is basically caused by the combination of external factors and internal factors. For example, the external factor is the fire source, and the internal factor is the combustion aid. The combination of the fire source and the combustion aid allows the fire to occur. Taking the warehouse as an example, the things stored in the warehouse are placed in order according to the intervals. Each area is relatively independent to prevent cross-influence and reduce fire hazards. However, there is currently a lack of technology that can judge the layout of the furnishings in the target area to achieve a fire safety assessment. Compared with issuing an early warning only when the signs of fire safety are found, it can improve the efficiency of discovering dangerous situations. Summary of the invention

[0005] The present invention provides a fire disaster intelligent monitoring and early warning system and method based on big data, which can improve the efficiency of discovering fire hazards.

[0006] In order to solve the above technical problems, the present application provides the following technical solutions: a fire disaster intelligent monitoring and early warning system based on big data, comprising: an image acquisition module: the image acquisition module is used to acquire image information of the target area; a data processing module: the data processing module is used to acquire image information, aggregate pixel points of the image information, extract the contours of each object in the pixel target area, and identify the image information to obtain the name of each object in the target area, obtain the object display map in the target area, and surround a safe area with each object as the center; after identifying the name of each object, the data processing module generates a to-be-filled list according to the type of object, and the to-be-filled list is used to fill in the material and ignition point of each object; the data processing module acquires the completed to-be-filled list, updates the ignition point data to the corresponding object display map, and arranges them in descending order according to the ignition point data, and uses a color scheme from warm to cold to distinguish the images of objects in the target area; Among them: when the difference in ignition points of two adjacent objects is within the second threshold value, and the safety areas of the two adjacent objects overlap, a movement warning signal is generated; when a new object is placed in the target area, the new object is identified to obtain the name and ignition point of the new object. If the new object is in the safety area of ​​the old object and the difference in ignition points is within the second threshold value, a stop signal is generated; if a fire source appears in the image and the temperature of the fire source is on the rise, if there is a human image in the image, the human image is analyzed, the human head contour is extracted, the head direction is analyzed, and if the person is looking at the fire source, the expression is analyzed, and the human facial expression image is placed in the preset expression Identify in the recognition model and analyze the meaning of the expression. If the expression is panic or fear, a warning signal is generated. The basic principle and beneficial effects of this solution are: by acquiring image information of the target area, analyzing the object layout in the area, and obtaining the material and ignition point of each object. If the difference between the ignition point thresholds of two objects is within the second threshold and the adjacent distance is short, that is, the safety areas of the two objects overlap, a movement signal is generated to rearrange the two objects. If the later placed object is in the safety area of ​​the old object and the difference in ignition point with the old object is within the second threshold, stop placing it in the area.

[0007] This solution uses the ignition point as a condition for distinguishing the placement of objects, avoiding the situation where objects with low ignition points naturally ignite other objects. It can provide safer protection for low ignition point areas, and after distinguishing by ignition point, the objects can be used more freely, reducing the chaos when stacked together and the concerns when using them. If a fire source appears in the target area, through the intuitive perception of the flame by the people on the scene, if they are afraid and panic, the fire is not under control, and an early warning signal is generated to arrange firefighting. If the flame is under control, such as blowing out birthday candles, no alarm information is generated.

[0008] This plan reduces the probability of fire at the source by estimating future fire safety based on the furnishings details of the target area, provides a quicker early warning of fire safety, and improves the efficiency of detecting fire hazards.

[0009] Furthermore, the data processing module is also used to obtain the brightness in the image information. If the brightness of a certain area exceeds the brightness of its nearby areas by more than a third threshold, the area is marked as a bright spot, and the image information of the bright spot in adjacent intervals is compared. If the area of ​​the bright spot area remains unchanged, the bright spot position is offset, and the offset distance is between 3-5cm, a safety signal is generated. It also includes a temperature acquisition module: the temperature acquisition module is used to obtain the ambient temperature value of the target area, and is also used to generate a thermal imaging map of the target area and the object based on the temperature; when the temperature in the thermal imaging map exceeds the first threshold, a first warning signal is generated.

[0010] Beneficial effect: The bright spot may be a flame or a light. By calculating the area of ​​the bright spot, it is found that the flame has the characteristic of spreading when burning, while the area of ​​the light is relatively fixed. If it is judged to be a light, it is safe. The temperature acquisition module performs thermal imaging of the target area to generate a thermal imaging map. If the temperature in the thermal imaging map exceeds the first threshold, that is, the average temperature of the fire, a first warning signal is generated. Furthermore, it also includes a warning broadcast, which is set in the room. If a fire source appears in the room and the person is not facing the direction of the fire source, a prompt warning is generated, and the direction of the fire source is broadcast to the person in question based on the person in question being the center and the direction facing forward.

[0011] Furthermore, it also includes a water pressure detector, which is arranged in the fire water pipe and is used to monitor the water pressure details of the fire water pipe. If the water pressure is lower than the standard value, a water shortage signal is generated and maintenance personnel enter the site for maintenance.

[0012] Furthermore, it also includes a water storage module, the inlet of the water storage module is connected to the tap water pipe, and the outlet is connected to the fire water pipe. The water storage module is arranged on the roof, and after receiving the water outage notice, the water storage module is filled with water.

[0013] Furthermore, the water storage module reserves 1 / 2 of the water level as fire-fighting water.

[0014] Effective effect: Ensure that fire-fighting water is reserved to cope with emergencies.

[0015] A fire disaster intelligent monitoring and early warning method based on big data includes the following steps: S1: obtaining the distribution of objects in the target area through image information; S2: analyzing whether there is a temperature exceeding a threshold in the space based on thermal imaging images; S3: analyzing the ignition point of each object, and generating early warning information if the object temperature exceeds the ignition point temperature; S4: obtaining the water pressure of the fire water pipe, and generating early warning information if the water pressure is less than the standard value. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a structural diagram of a fire disaster intelligent monitoring and early warning system based on big data;

[0017] Figure 2 The figure is a structural diagram of an intelligent monitoring and early warning method for fire disasters based on big data. DETAILED DESCRIPTION

[0018] The following is further described in detail by specific implementation methods: Embodiment 1 is as shown in the attached Figure 1 As shown, a fire disaster intelligent monitoring and early warning system based on big data includes: an image acquisition module: the image acquisition module selects a camera, there are multiple cameras, covering all ranges of the target area, the image acquisition module is used to acquire image information of the target area, and the target area is located in a room in this embodiment; a data processing module: the data processing module is used to acquire image information, aggregate pixel points of the image information, extract the contours of each object in the pixel target area, and identify the image information, obtain the name of each object in the target area, obtain the object display map in the target area, and surround a safe area with each object as the center; after identifying the name of each object, the data processing module generates a list to be filled in according to the type of object, and the list to be filled in is used to fill in the material and ignition point of each object; the data processing module obtains the completed list to be filled in, and updates the ignition point data to the corresponding object display map, and arranges them in descending order according to the ignition point data, and uses a color system from warm to cold to distinguish the images of the objects in the target area; the data processing module selects an i5-1240P CPU and its related components, or other types of CPU processors to meet the computing requirements of this solution.

[0019] Temperature acquisition module: select a thermal imager, the temperature acquisition module is used to obtain the ambient temperature value of the target area, and is also used to generate a thermal imaging map of the target area and the object according to the temperature; wherein: when the temperature in the thermal imaging map exceeds the first threshold, 200°C is selected here, the use conditions of conventional objects are much lower than this temperature, if conventional objects reach this temperature, even if they do not catch fire, they will cause burns, so a first warning signal is generated; when the difference in the ignition point of two adjacent objects is within the second threshold, 50 degrees Celsius is selected here. And the safety areas of the two adjacent objects overlap, and the safety distance is 50cm centered on the object, then a movement warning signal is generated; when a new object is placed in the target area, the new object is identified, and the name and ignition point of the new object are obtained. If the new object is in the safety area of ​​the old object and the difference in the ignition point is within the second threshold, a stop signal is generated.

[0020] The data processing module is also used to obtain the brightness in the image information. If the brightness of a certain area exceeds the brightness of the adjacent area by a value exceeding the third threshold, the area is marked as a bright spot. The image information of the bright spot in the adjacent interval time is compared. If the area of ​​the bright spot area remains unchanged, the bright spot position is offset, and the offset distance is between 3-5cm, a safety signal is generated. After judging that it is a light by the area of ​​the bright spot, the swaying amplitude of the light is driven by the wind. Usually, the wind directly blows the rope-dropping light to shake, and also blows other objects to cause shadows. No matter which one, the probability of fire is small.

[0021] If a fire source appears in the image, that is, the bright spot is the fire source, and the temperature of the fire source is rising. If there is a person in the image, the person's image is analyzed, the person's head contour is extracted, and the head direction is analyzed. If the person is looking at the fire source, the expression is analyzed. The person's facial expression is put into the preset expression recognition model for recognition, and the meaning of the expression is analyzed. If the expression is panic or fear, an early warning signal is generated. A fire source appears in the target area. Through the intuitive perception of the flame by the people present, if fear or panic appears, the fire is not under control, and an early warning signal is generated to arrange firefighting. If the flame is under control, if it is birthday candles, no alarm information is generated. The expression recognition model is a trained neural curl model. The model training is completed through a large number of sample sets, training sets and test sets. When the accuracy of the training results is above 95%, the training is completed. When in a building, the image is used to identify whether there is a fire source and the shape of the fire source is extracted. If it is a circle or an ellipse (annular closed circle), the image is used to identify whether it is a cigarette. If it is a lit cigarette, it is determined based on whether there is anyone within 10 cm around it and the distance of the cigarette from the ground. If it is greater than 20 cm, it is determined to be in smoking, and if it is less than 20 cm, it is determined to be discarded. The image is identified to determine whether there are flammable materials within 50 cm of the cigarette butt. If so, an early warning signal is generated.

[0022] It also includes an early warning broadcast, which is a home broadcast. There is a communication protocol between the data processing module and the corresponding voice broadcast can be completed according to the control signal. The early warning broadcast is set in the room. If a fire source appears in the room and the person is not facing the direction of the fire source, a prompt warning is generated. Based on the person being the center and the direction of the fire source being the front, the person is informed of the direction of the fire source.

[0023] It also includes a water pressure detector, which is arranged in the fire water pipe and is used to monitor the water pressure details of the fire water pipe. If the water pressure is lower than the standard value, a water shortage signal is generated and maintenance personnel enter the site for maintenance.

[0024] It also includes a water storage module, the inlet of which is connected to the tap water pipe, and the outlet is connected to the fire water pipe. The water storage module is set on the roof. After receiving the water outage notice, the water storage module is filled with water. The water storage module reserves 1 / 2 of the water level as fire water. The water storage module is a water tank, which is set on the top floor. The water tank is also connected to the domestic water pipe, which solves the problem of low water pressure for residents on high floors to a certain extent. At the same time, it also reserves water for fire fighting to prevent the occurrence of special situations.

[0025] It also includes a big data-based intelligent fire disaster monitoring and early warning method applied to the above system, including the following steps: S1: obtaining the distribution of objects in the target area through image information; S2: analyzing whether there is a temperature exceeding a threshold in the space based on the thermal imaging image; S3: analyzing the ignition point of each object, and if the temperature of the object exceeds the ignition point temperature, generating early warning information; S4: obtaining the water pressure of the fire water pipe, and if the water pressure is lower than the standard value, generating early warning information.

[0026] Embodiment 2 Embodiment 2 is different from Embodiment 1 in that: the applicable scenario of this solution is at the construction site. If the construction site under construction is warned in the manner of Embodiment 1, many false alarms will be caused. To solve the false alarm problem, in this solution, the image acquisition module is used to obtain the current image information of the construction, and identify the welding gun, goggles, etc. in the image information. If the worker holds a welding gun and the worker's head is observed to be facing a cylinder (a circular steel pipe to be cut) in the image information, the cylinder is marked by a box selection, indicating that the oxygen welding operation will be performed next. At this time, no warning signal is generated. In the image, the worker's head is facing away from the oxygen welding direction. For example, the operator is distracted, or the goggles are damaged and cannot look directly into the oxygen welding range, resulting in a deviation of vision. At this time, the data processing module locks the oxygen pipe and the gas pipe. If the flame is as low as 20cm from the oxygen pipe and the gas pipe. A warning signal is generated, and a broadcast reminder of safe operation specifications is broadcast. Prevent disasters from occurring.

[0027] The above are only embodiments of the present invention. The invention is not limited to the fields involved in this implementation case. The common sense such as the known specific structures and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to explain the content of the claims.

Claims

1. An intelligent fire disaster monitoring and early warning system based on big data, It is characterized in that include: Image acquisition module: The image acquisition module is used to acquire image information of the target area; Data processing module: The data processing module is used to obtain image information, aggregate pixel points of the image information, extract the outline of each object in the pixel target area, and identify the image information to obtain the name of each object in the target area, obtain the object layout map in the target area, and set up a safe area around each object; After identifying the names of the objects, the data processing module generates a list to be filled in according to the object types, and the list to be filled in is used to fill in the material and burning point of each object; the data processing module obtains the completed list to be filled in, and updates the burning point data to the corresponding object display map, and arranges them in descending order according to the burning point data, and uses a color system from warm to cold to distinguish the images of the objects in the target area; Wherein: when the difference between the ignition points of two adjacent objects is within the second threshold value and the safety zones of the two adjacent objects overlap, a movement warning signal is generated; When a new object is placed in the target area, the new object is identified, and the name and ignition point of the new object are obtained. If the new object is in the safe area of ​​the old object and the ignition point difference is within the second threshold, a stop signal is generated; if a fire source appears in the image and the temperature of the fire source is on the rise, if there is a human image in the image, the human image is analyzed, the human head outline is extracted, and the head direction is analyzed. If the person is looking at the fire source, the expression is analyzed, and the human facial expression image is placed in a preset expression recognition model for identification, and the meaning of the expression is analyzed. If the expression is panic or fear, a warning signal is generated; The data processing module is also used to obtain the brightness in the image information. If the brightness of a certain area exceeds the brightness of its nearby areas by more than a third threshold, the area is marked as a bright spot, and the image information of the bright spot in adjacent intervals is compared. If the area of ​​the bright spot area remains unchanged, the bright spot position is offset, and the offset distance is between 3-5cm, a safety signal is generated. It also includes a temperature acquisition module: the temperature acquisition module is used to obtain the ambient temperature value of the target area, and is also used to generate a thermal imaging map of the target area and the object according to the temperature; when the temperature in the thermal imaging map exceeds the first threshold, a first warning signal is generated.

2. According to claim 1, a fire disaster intelligent monitoring and early warning system based on big data, Features: It also includes an early warning broadcast, which is set in the room. If a fire source occurs in the room and people are not facing the direction of the fire source, a prompt warning will be generated to inform the parties of the direction of the fire source based on the person being the center and the direction being forward.

3. According to the big data-based intelligent fire disaster monitoring and early warning system of claim 1, Features: It also includes a water pressure detector, which is arranged in the fire water pipe and is used to monitor the water pressure details of the fire water pipe. If the water pressure is lower than the standard value, a water shortage signal is generated and maintenance personnel enter the site for maintenance.

4. According to claim 3, a fire disaster intelligent monitoring and early warning system based on big data, Features: It also includes a water storage module, the inlet of which is connected to the tap water pipe, and the outlet is connected to the fire water pipe. The water storage module is arranged on the roof, and after receiving the water outage notice, the water storage module is filled with water.

5. According to claim 4, a fire disaster intelligent monitoring and early warning system based on big data, Features: The water storage module reserves 1 / 2 of the water level as fire-fighting water.

6. A fire disaster intelligent monitoring and early warning method based on big data, Features: A system as claimed in any one of claims 1 to 5 is used, comprising the following steps: S1; obtaining the distribution of objects in the target area through image information; S2: Analyze whether there is a temperature exceeding a threshold in the space based on the thermal imaging image; S3: Analyze the ignition point of each object, and if the temperature of the object exceeds the ignition point temperature, generate a warning message; S4: Obtain the water pressure of the fire water pipe. If the water pressure is lower than the standard value, generate an early warning message.

Images