Image-based comprehensive pipe gallery fire warning method, device, equipment and medium

By combining image information from multiple monitoring devices and deep neural network analysis, the problem of low accuracy in fire early warning in existing technologies has been solved, enabling accurate monitoring of fire points and rational allocation of firefighting resources, thereby improving fire suppression efficiency.

CN116246414BActive Publication Date: 2026-04-07SHANGHAI TENSUN TRANSMART
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-20
Publication Date
2026-04-07

AI Technical Summary

Technical Problem

The existing integrated utility tunnel fire early warning system can only warn of the location and range of the fire point, and the accuracy of fire early warning is low.

Method used

By combining image information collected by the first and second monitoring devices in the server, the location and combustion status of the fire point are analyzed. Deep neural networks are used to detect smoke and flame targets, the angle of the monitoring devices is adjusted to obtain more comprehensive fire information, and the number and direction of fire extinguishing devices are matched according to the area of ​​the fire zone.

Benefits of technology

It enables more accurate monitoring and analysis of fire points, avoids inaccurate information caused by obstructions, ensures an appropriate number of fire extinguishing devices, avoids resource waste, and improves the efficiency of fire suppression.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116246414B_ABST
    Figure CN116246414B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of fire alarm, in particular to a comprehensive pipe gallery fire warning method, device, equipment and medium based on images. The comprehensive pipe gallery fire warning method based on images is applied to a server of a comprehensive pipe gallery fire warning system and comprises the following steps: receiving first image information sent by a first monitoring device; calling a second monitoring device based on the first image information, so that the second monitoring device collects second image information; receiving second image information sent by the second monitoring device; and determining a fire condition of a fire point based on the first image information and the second image information. The application uses multiple monitoring devices to jointly detect and send a fire area, analyzes the position and combustion condition of the fire point, effectively avoids the situation that the fire point is blocked by objects in the comprehensive pipe gallery and accurate fire point information cannot be obtained, comprehensively monitors and analyzes the fire point, and more accurately determines the fire condition of the fire point.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of fire alarm technology, specifically to an image-based integrated utility tunnel fire early warning method, device, equipment, and medium. Background Technology

[0002] Integrated utility tunnels are urban infrastructure projects that centrally house various engineering pipelines such as electricity, communications, gas, heating, and water supply and drainage beneath roads. Fires caused by gas and electricity leaks, as well as fires resulting from flammable gases generated within the tunnels, are among the major hazards affecting the safe operation of urban integrated utility tunnels. Once a fire occurs, it can cause enormous economic losses and casualties. Therefore, accurately alarming for fires in integrated utility tunnels and taking timely firefighting measures are crucial aspects of ensuring their safe operation.

[0003] Currently, in order to detect and control fires inside the utility tunnel in a timely manner, staff use physical sensors and thermal imaging cameras to monitor the situation inside the tunnel. When a fire is detected, an alarm is issued to notify firefighters to extinguish it in time or to evacuate nearby personnel.

[0004] Regarding the aforementioned technologies, the inventors believe that integrated utility tunnels contain various types of pipelines and have complex internal conditions. Current fire early warning systems for utility tunnels can only warn of the location and range of the fire point, resulting in low accuracy in fire early warning. Summary of the Invention

[0005] To address the issue that current utility tunnel fire early warning systems can only warn of the location and range of a fire point, resulting in low accuracy, this application provides an image-based integrated utility tunnel fire early warning method, device, equipment, and medium.

[0006] The first aspect of this application provides an image-based method for early warning of fires in integrated utility tunnels, applied in a server of an integrated utility tunnel fire early warning system. The method includes: receiving first image information sent by a first monitoring device, wherein the first image information is image information of a target area, and the target area is an area in the integrated utility tunnel where a fire has occurred; based on the first image information, invoking a second monitoring device to collect second image information; wherein the second monitoring device is an adjacent monitoring device to the first monitoring device, and the second image information is image information of the target area; receiving the second image information sent by the second monitoring device; and based on the first image information and the second image information, determining the fire situation at the ignition point, wherein the fire situation at the ignition point includes the location information of the ignition point and the burning status of the ignition point.

[0007] By adopting the above technical solution, the server combines the first image information collected by the first monitoring device and the second image information collected by the second monitoring device to analyze the location and combustion status of the fire point. This effectively avoids the situation where the fire point is blocked by objects in the integrated utility tunnel, making it impossible to obtain accurate fire point information. This enables more comprehensive monitoring and analysis of the fire point and more accurate determination of the fire situation.

[0008] In one possible implementation, the second monitoring device includes a first adjacent monitoring device, which is a monitoring device that can monitor the target area without turning. The step of calling the second monitoring device based on the first image information to enable the second monitoring device to acquire second image information includes: determining the position information of a first reference object based on the first image information; determining the positional relationship between the fire point and the first monitoring device based on the position information of the first reference object, wherein the positional relationship between the fire point and the first monitoring device includes a first positional relationship and a second positional relationship, wherein the first positional relationship is that the fire point is on the side of the target area closer to the first monitoring device; and the second positional relationship is that the fire point is on the side of the target area farther from the first monitoring device. If the positional relationship between the fire point and the first monitoring device is the first positional relationship, then the first adjacent monitoring device is called to enable the first adjacent monitoring device to acquire the second image information.

[0009] By adopting the above technical solution, when the fire point is on the side of the target area closer to the first monitoring device, which means that the first monitoring device is the monitoring device closest to the fire point, the first adjacent monitoring device is called to assist the first monitoring device in detecting the fire at the fire point. Under the condition of ensuring that the entire area of ​​the integrated utility tunnel can be detected, a more comprehensive fire situation at the fire point is collected.

[0010] In one possible implementation, the second monitoring device further includes a second adjacent monitoring device, which is a monitoring device that needs to be turned to monitor the target area; the step of calling the second monitoring device based on the first image information to enable the second monitoring device to collect the second image information further includes: if the positional relationship between the fire point and the first monitoring device is second positional information, then calling the second adjacent monitoring device to enable the second adjacent monitoring device to collect the second image information.

[0011] By adopting the above technical solution, when the fire point is on the side of the target area away from the first monitoring device, which is reflected as the second adjacent monitoring device being the monitoring device closest to the fire point, the second adjacent monitoring device is called to assist the first monitoring device in detecting the fire point. This avoids the situation where the fire point is far away from the first monitoring device and is blocked by other objects in the first monitoring device's view, resulting in inaccurate fire detection by the server.

[0012] In one possible implementation, if the second monitoring device invoked is the first adjacent monitoring device, then determining the fire situation at the ignition point based on the first image information and the second image information includes: determining the deflection angle of the first monitoring device based on the position information of the first reference object, so that the first monitoring device can collect image information of the target area again; receiving third image information sent by the first monitoring device, wherein the third image information is the image information of the target area collected by the first monitoring device after the angle deflection; determining the position information of the second reference object and the third reference object based on the third image information; determining the position information of the ignition point based on the position information of the second reference object and the third reference object; and determining the burning situation at the ignition point based on the second image information.

[0013] By adopting the above technical solution, the server adjusts the shooting angle of the first monitoring device according to the location of the fire point in the first image information to obtain the third image information, that is, to obtain a more accurate image of the fire point; based on the second and third image information, the fire situation at the fire point is determined, so as to obtain a more comprehensive and accurate fire situation at the fire point as much as possible.

[0014] In one possible implementation, if the second monitoring device invoked is the second adjacent monitoring device, then determining the fire situation at the ignition point based on the first image information and the second image information further includes: determining the position information of the fourth reference object and the position information of the fifth reference object based on the second image information; determining the position information of the ignition point based on the position information of the fourth reference object and the position information of the fifth reference object; and determining the combustion status of the ignition point based on the first image information.

[0015] In one possible implementation, the utility tunnel fire early warning system includes fire-fighting devices. After determining the fire situation at the ignition point, the system further includes: calculating the area of ​​the fire zone; formulating a first fire-fighting plan based on the area of ​​the fire zone, the first fire-fighting plan including the required number of fire-fighting devices; and sending first information to the fire-fighting devices to cause the fire-fighting devices to perform fire-fighting actions, the first information including the first fire-fighting plan.

[0016] By adopting the above technical solution, the server calculates the actual area of ​​the fire area based on the area of ​​the fire area in the image, matches the required number of fire extinguishing devices according to the size of the actual area, and sends information including the required number of fire extinguishing devices to the fire extinguishing devices to activate the corresponding number of fire extinguishing devices. This effectively avoids the situation where the number of activated fire extinguishing devices is insufficient to extinguish the fire in time, as well as the situation where too many fire extinguishing devices are activated, resulting in a waste of fire extinguishing resources.

[0017] In one possible implementation, the utility tunnel fire early warning system includes a fire-fighting device. After determining the fire situation at the ignition point, the system further includes: formulating a second fire-fighting plan based on the fire situation at the ignition point, the second fire-fighting plan including the moving direction, moving distance, and fire-fighting direction of the fire-fighting device; and sending second information to the fire-fighting device to cause the fire-fighting device to perform fire-fighting actions, the second information including the second fire-fighting plan.

[0018] By adopting the above technical solution, after the server determines the location information of the fire point, it determines the moving direction, moving distance, and extinguishing direction of the fire-fighting device; the first information, including the moving direction, moving distance, and extinguishing direction of the fire-fighting device, is sent to the target fire-fighting device so that the target fire-fighting device can extinguish the fire point as accurately as possible.

[0019] A second aspect of this application provides an image-based integrated utility tunnel fire early warning device. The device is a server and includes: a receiving unit for receiving first image information sent by a first monitoring device, wherein the first image information is image information of a target area, and the target area is an area in the integrated utility tunnel where a fire has occurred; a processing unit for invoking a second monitoring device based on the first image information, so that the second monitoring device collects second image information; the second monitoring device is an adjacent monitoring device of the first monitoring device, and the second image information is image information of the target area; the receiving unit is further configured to receive the second image information sent by the second monitoring device; the processing unit is further configured to determine the fire situation at the ignition point based on the first image information and the second image information, wherein the fire situation at the ignition point includes the location information of the ignition point and the burning status of the ignition point.

[0020] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the first aspects of this application.

[0021] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in any of the first aspects of this application.

[0022] In summary, this application includes at least one of the following beneficial technical effects:

[0023] 1. The server combines the first image information collected by the first monitoring device and the second image information collected by the second monitoring device to analyze the location and combustion status of the fire point. This effectively avoids situations where the fire point is obstructed by objects in the integrated utility tunnel, preventing accurate fire point information from being obtained. This enables more comprehensive monitoring and analysis of the fire point, leading to a more accurate determination of the fire situation. 2. The server calculates the actual area of ​​the fire area based on its area in the image. Based on the actual area size, it matches the required number of fire extinguishing devices and sends information including the required number of devices to the fire extinguishing equipment to activate the corresponding number of devices. This effectively avoids situations where insufficient fire extinguishing devices are activated, resulting in the inability to extinguish the fire in time, or where too many fire extinguishing devices are activated, leading to a waste of fire extinguishing resources. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of a module of an integrated utility tunnel fire early warning system according to an embodiment of this application;

[0025] Figure 2 This is a flowchart illustrating an image-based integrated utility tunnel fire early warning method according to an embodiment of this application.

[0026] Figure 3 This is a flowchart illustrating another embodiment of an image-based integrated utility tunnel fire early warning method.

[0027] Figure 4 This is a schematic diagram of the installation location of a comprehensive utility tunnel monitoring device according to an embodiment of this application;

[0028] Figure 5 This is a schematic diagram of a module of an image-based integrated utility tunnel fire early warning device according to an embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0030] Explanation of reference numerals in the attached drawings: 501, acquisition unit; 502, processing unit; 503, transmission unit; 600, electronic device; 601, processor; 602, communication bus; 603, user interface; 604, network interface; 605, memory. Detailed Implementation

[0031] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0032] To address the issue that current utility tunnel fire early warning systems can only warn of the location and range of a fire point, resulting in low accuracy, this application provides an image-based integrated utility tunnel fire early warning method, which is applied to the server of an integrated utility tunnel fire early warning system.

[0033] Reference Figure 1 The fire early warning system for the integrated utility tunnel includes signal acquisition devices, a fire early warning device for the integrated utility tunnel, and fire-fighting equipment. The signal acquisition devices include surveillance cameras, temperature and humidity sensors, oxygen sensors, hydrogen sulfide sensors, methane sensors, and carbon monoxide sensors, which monitor the temperature, humidity, oxygen levels, and toxic gases within the integrated utility tunnel in real time. The fire-fighting equipment includes fine water mist extinguishing devices, suspended ultra-fine dry powder extinguishing devices, and suspended aerosol extinguishing devices. When a fire occurs within the integrated utility tunnel, the fire early warning device sends a control signal to the fire-fighting equipment to instruct them to take fire-fighting measures and extinguish the fire.

[0034] Reference Figure 2 The illustration shows a flowchart of an image-based integrated utility tunnel fire early warning method according to an embodiment of this application, including the following steps S1-S4.

[0035] Step S1: Receive the first image information sent by the first monitoring device. The first image information is the image information of the target area, which is the area in the integrated utility tunnel where the fire occurred.

[0036] In the above steps, the first monitoring device captures images of the interior of the utility tunnel and sends the image information to the server, which then receives the image information. The target area is the area that the first monitoring device is responsible for monitoring. For example, if a monitoring device is installed every 10 meters in the utility tunnel, the area monitored by one monitoring device is a 10-meter section of the utility tunnel within its camera's field of view.

[0037] Based on the SSD (Single Shot MultiBox Detector) concept, the softmax classification function is replaced with the sigmoid function, which is suitable for binary classification. A smoke and flame target detection model is obtained through training, and a single deep neural network is used for image detection. The Caffe deep learning framework is used on a graphics processing unit (GPU) to optimize the algorithm model's parameters using hundreds of thousands of labeled smoke and flame images, resulting in a high-accuracy smoke and flame target detection model. The smoke and flame target detection model detects the presence of fire sources with smoke and / or flame characteristics in images of integrated utility tunnels. The specific calculation formula is as follows:

[0038] L(a, b, c, d) = 1 / N(L conf (a, b) + αL loc(a, c, d)). Where N is the number of true bounding boxes matched; a is whether the matched box belongs to the smoke or flame category, with a value of {0, 1}; b is the confidence score that the selected target belongs to the smoke or flame category, with a value ranging from 0.7 to 0.9; c is the predicted bounding box; d is the true value; and α is the weight relationship used to adjust the classification and localization.

[0039] Step S2: Based on the first image information, invoke the second monitoring device to enable the second monitoring device to collect the second image information; the second monitoring device is an adjacent monitoring device of the first monitoring device, and the second image information is the image information of the target area.

[0040] In the above steps, the server sends a control signal to the second monitoring device adjacent to the first monitoring device based on the location of the fire point shown in the first image information, so that the second monitoring device can capture images of the fire area in the integrated utility tunnel and assist the first monitoring device in monitoring the fire situation at the fire point.

[0041] In one possible implementation, refer to Figure 3 The second monitoring device includes a first adjacent monitoring device, which is a monitoring device that can monitor the target area without turning. Based on the first image information, the second monitoring device is invoked so that the second monitoring device can collect the second image information. The specific steps include the following.

[0042] Step S21: Determine the position information of the first reference object based on the first image information.

[0043] In the above steps, the server identifies the position information of each object in the utility tunnel based on the first image information, and selects the object that is at the same height as the fire point and is closest to the center of the utility tunnel as a reference.

[0044] The internal environment of the integrated utility tunnel is quite complex, with engineering pipelines for electricity, communication, gas, heating, water supply and drainage, etc.; support frames, signs, detection sensors and fire extinguishing devices for various pipelines; and a monitoring device installed at each preset interval.

[0045] After installing various objects inside the integrated utility tunnel, the staff established a three-dimensional rectangular coordinate system with the ground point corresponding to the monitoring camera as the origin of the coordinate axis, the center line of the shooting angle of the monitoring camera as the Y-axis, and the line connecting the monitoring camera and the origin of the coordinate axis as the Z-axis. They measured the height and X-axis coordinates of each pipeline support frame, as well as the coordinates of each sign, sensor, and fire extinguishing device, and input the measured values ​​into the storage server.

[0046] The server identifies and marks each object in the image, determines the orientation and height of the fire point based on the height and X-axis coordinates of each pipeline support frame, and determines the position information of the first reference object based on the coordinates of each object.

[0047] For example, a surveillance camera is installed every 10 meters inside the integrated utility tunnel; the fire point is on a support frame with an X-axis coordinate of -50 cm and a Z-axis coordinate of 100 cm, which means the fire point is to the left of the surveillance camera and at a height of 100 cm; then an object with a negative X-axis coordinate, a Z-axis coordinate close to 100 cm, and a Y-axis coordinate closest to 500 cm is selected as the first reference object.

[0048] Step S22: Based on the position information of the first reference object, determine the positional relationship between the ignition point and the first monitoring device. The positional relationship between the ignition point and the first monitoring device includes a first positional relationship and a second positional relationship. The first positional relationship is that the ignition point is on the side of the target area closer to the first monitoring device; the second positional relationship is that the ignition point is on the side of the target area farther away from the first monitoring device.

[0049] In the above steps, the server determines the positional relationship between the fire point and the first monitoring device based on the positional relationship between the fire point and the first reference object displayed in the first image information.

[0050] Step S231: If the positional relationship between the fire point and the first monitoring device is a first positional relationship, then the first adjacent monitoring device is invoked so that the first adjacent monitoring device can collect the second image information.

[0051] In one possible implementation, the second monitoring device further includes a second adjacent monitoring device, which is a monitoring device that needs to be turned to monitor the target area; the step of calling the second monitoring device based on the first image information to enable the second monitoring device to collect the second image information further includes step S232.

[0052] Step S232: If the positional relationship between the fire point and the first monitoring device is the second positional information, then the second adjacent monitoring device is invoked so that the second adjacent monitoring device can acquire the second image information.

[0053] In the above steps, the area with a Y-axis coordinate less than that of the first reference object is defined as the side of the fire area closer to the monitoring equipment; the area with a Y-axis coordinate greater than that of the first reference object is defined as the side of the fire area farther from the monitoring equipment.

[0054] Taking the fire point as being to the left of the surveillance camera as an example, when the fire point is to the left of the first reference object, it means that the fire point is on the side of the target area closer to the first monitoring device. The first monitoring device is the monitoring device closest to the fire point. The first adjacent monitoring device is selected to assist the first monitoring device in detecting the fire at the fire point.

[0055] When the fire point is to the right of the first reference object, which means the fire point is on the side of the target area away from the first monitoring device, the second adjacent monitoring device is the monitoring device closest to the fire point. The second adjacent monitoring device is selected to assist the first monitoring device in detecting the fire at the fire point.

[0056] Reference Figure 4 Assuming the fire point is within area S, then monitoring device A is the first monitoring device; monitoring device B is the first adjacent monitoring device; and monitoring device C is the second adjacent monitoring device.

[0057] When the first monitoring device is the closest to the fire point, the first adjacent monitoring device is called in to assist the first monitoring device in detecting the fire, ensuring that the integrated utility tunnel fire early warning device can detect images of the entire area of ​​the integrated utility tunnel. However, if the first adjacent monitoring device cannot capture the fire at the target area, such as when there is a turning point in the integrated utility tunnel between the first monitoring device and the first adjacent monitoring device, or when the fire point is obscured by other objects in the image of the first adjacent monitoring device, then the second adjacent monitoring device is called in to assist the first monitoring device in detecting the fire. In this case, only the situation where the second adjacent monitoring device can detect the fire is considered.

[0058] When the second adjacent monitoring device is the closest to the fire point, it is used to assist the first monitoring device in detecting the fire. This avoids situations where the fire point is too far from the first monitoring device and is obstructed by other objects in the first monitoring device's view, leading to inaccurate fire detection by the server. Selecting the second adjacent monitoring device ensures clearer fire location information. However, if neither the first nor the second adjacent monitoring device can detect the fire in the target area (indicating a large amount of smoke and dust in the target area after fire suppression measures are taken, and the first and second monitoring devices are obstructed by smoke and dust due to their proximity to the fire), then the first adjacent monitoring device is used to assist in detecting the fire. In this case, only the scenario where both the first and second adjacent monitoring devices can detect the fire is considered.

[0059] Step S3: Receive the second image information sent by the second monitoring device.

[0060] In the above steps, the server sends a control signal to the second monitoring device so that the second monitoring device can collect image information of the fire area and send the collected image information to the server.

[0061] Step S4: Based on the first image information and the second image information, determine the fire situation at the ignition point, which includes the location information of the ignition point and the burning situation at the ignition point.

[0062] In the above steps, the server combines the first image information collected by the first monitoring device and the second image information collected by the second monitoring device to analyze the location and combustion status of the fire point. This effectively avoids the situation where the fire point is blocked by objects in the integrated utility tunnel, making it impossible to obtain accurate fire point information. This enables more comprehensive monitoring and analysis of the fire point, resulting in a more accurate fire situation.

[0063] It should be noted that the combustion status of the ignition point includes whether the ignition point is burning or has been extinguished. When the server detects the combustion status of the ignition point, it only checks whether there are flame characteristics in the image to determine whether the ignition point has been extinguished and whether it has reignited after being extinguished. If the ignition point reignites, the next fire prevention plan will be formulated based on the situation of the ignition point.

[0064] In one possible implementation, refer to Figure 3 If the second monitoring device invoked is the first adjacent monitoring device, then the fire situation at the ignition point is determined based on the first image information and the second image information, including the following steps S411-S415.

[0065] Step S411: Based on the position information of the first reference object, determine the deflection angle of the first monitoring device so that the first monitoring device can collect image information of the target area again.

[0066] In the above steps, the server determines the location of the fire point based on the X-axis coordinate of the first reference object; that is, if the X-axis coordinate of the first reference object is positive, the fire point is to the right of the first monitoring device; if the X-axis coordinate of the first reference object is negative, the fire point is to the left of the first monitoring device; and the deflection angle of the monitoring camera is determined based on the position of the fire point in the image so that the fire point is on the center line of the camera's shooting angle.

[0067] It should be noted that when adjusting the deflection angle of the first monitoring device, the server detects the horizontal distance between the fire point and the center line of the first monitoring device's shooting angle and sends a shooting angle adjustment signal to the first monitoring device; when the fire point coincides with the center line of the first monitoring device's shooting angle, the adjustment of the first monitoring device's shooting angle stops.

[0068] Step S412: Receive the third image information sent by the first monitoring device. The third image information is the image information of the target area collected by the first monitoring device after the angle is deflected.

[0069] In the above steps, after the shooting angle of the first monitoring device is adjusted, the image information collected again is sent to the server.

[0070] Step S413: Based on the third image information, determine the position information of the second reference object and the position information of the third reference object.

[0071] In the above steps, the server identifies each object in the third image information, determines the coordinates of each object, and selects any two objects as the second and third reference objects.

[0072] Step S414: Determine the location information of the ignition point based on the location information of the second reference object and the location information of the third reference object.

[0073] In the above steps, the server calculates the ratio of the horizontal distance between the second and third reference objects on the image to the actual distance between the second and third reference objects on the Y-axis, as the first ratio; calculates the ratio of the vertical distance between the second and third reference objects on the image to the actual distance between the second and third reference objects on the Z-axis, as the second ratio; and determines the Y-coordinate and Z-coordinate of the ignition point based on the horizontal and vertical distances between the ignition point and the second or third reference object on the image.

[0074] For example, the coordinates of the second reference object are (-20, 100, 100), and the coordinates of the third reference object are (-20, 150, 200). The horizontal distance between the second and third reference objects on the image is 2 cm, and the actual distance between them on the Y-axis is 50 cm. Alternatively, the horizontal distance between the second and third reference objects on the image is 1 cm, and the actual distance between them on the Y-axis is 100 cm. In the third image, the ignition point is located to the lower left of the second reference object, with a horizontal distance of 1 cm and a vertical distance of 0.5 cm. That is, the first ratio is 0.04, and the second ratio is 0.01. This means the Y-axis coordinate of the ignition point is 75 cm, and the Z-axis coordinate is 50 cm.

[0075] Step S415: Based on the second image information, determine the combustion status of the ignition point.

[0076] In the above steps, the server detects whether there is a flame in the image based on the second image information sent by the first adjacent monitoring device, in order to determine whether the flame at the ignition point has been completely extinguished.

[0077] It should be noted that the server calls upon the first adjacent monitoring device to assist the first monitoring device in detecting the combustion status of the fire point, in order to avoid the problem that the monitoring screen of the first monitoring device is blocked by smoke and dust after the fire-fighting device takes fire-extinguishing action, and thus cannot detect the combustion status of the fire point.

[0078] In one possible implementation, refer to Figure 3 If the second monitoring device invoked is the second adjacent monitoring device, then determining the fire situation at the ignition point based on the first image information and the second image information also includes the following steps.

[0079] Step S421: Based on the second image information, determine the position information of the fourth reference object and the position information of the fifth reference object.

[0080] Step S422: Determine the location information of the ignition point based on the location information of the fourth and fifth reference objects.

[0081] In the above steps, the server selects the second adjacent monitoring device to determine the location of the fire point. This means that the second adjacent monitoring device is the monitoring device closest to the fire point. The server sends a shooting angle adjustment signal to the second adjacent monitoring device so that the second adjacent monitoring device turns its monitoring direction. Based on the positional relationship between the fire point and the center line of the shooting angle of the second adjacent monitoring device, the server adjusts the shooting angle of the second adjacent monitoring device so that the center line of the shooting angle of the fire point coincides with that of the second adjacent monitoring device.

[0082] After adjusting the shooting angle of the second adjacent monitoring device, the system receives the second image information sent by the second adjacent monitoring device; identifies each object in the second image information, and selects any two objects as the fourth and fifth reference objects; and determines the Y-axis coordinates and Z-axis coordinates of the fire point based on the positional relationship between the fire point and the third or fourth reference object.

[0083] Step S423: Based on the first image information, determine the combustion status of the ignition point.

[0084] In the above steps, the server detects whether there is a flame in the image based on the first image information sent by the first monitoring device, in order to determine whether the flame at the ignition point has been completely extinguished.

[0085] In one possible implementation, after determining the location information of the fire point, the method further includes: calculating the area of ​​the fire zone; formulating a first fire-fighting plan based on the area of ​​the fire zone, the first fire-fighting plan including the number of required fire-fighting devices; and sending first information to the fire-fighting devices to cause the fire-fighting devices to perform fire-fighting actions, the first information including the first fire-fighting plan.

[0086] In the above steps, the server calculates the actual area of ​​the fire area based on the area of ​​the fire area in the image, matches the required number of fire extinguishing devices according to the size of the actual area, and sends information including the required number of fire extinguishing devices to the fire extinguishing devices to activate the corresponding number of fire extinguishing devices. This effectively avoids the situation where the number of fire extinguishing devices activated is insufficient to extinguish the fire in time, as well as the situation where too many fire extinguishing devices are activated, resulting in a waste of fire extinguishing resources.

[0087] The correspondence between the area of ​​the fire and the number of fire extinguishing devices required was derived by staff through multiple fire drills. The staff stored the number of fire extinguishing devices required for each fire area range in the database.

[0088] In one possible implementation, after determining the location information of the fire point, the method further includes: formulating a second fire-fighting plan based on the location information of the fire point, the second fire-fighting plan including the direction of movement, distance of movement and direction of fire extinguishing of the fire-fighting device; and sending second information to the fire-fighting device to cause the fire-fighting device to perform fire-fighting actions, the second information including the second fire-fighting plan.

[0089] In the above steps, after the server determines the location information of the fire point, it determines the location information of the fire-fighting equipment in the target area, selects the fire-fighting equipment with the smallest difference from the fire point's Y-axis coordinate as the target fire-fighting equipment, and determines the fire-fighting equipment's moving direction, moving distance, and extinguishing direction based on the coordinates of the fire point and the fire-fighting equipment; the first information, including the fire-fighting equipment's moving direction, moving distance, and extinguishing direction, is sent to the target fire-fighting equipment so that the target fire-fighting equipment can extinguish the fire point as accurately as possible.

[0090] For example, based on the first image information, the server determines that the fire point is to the left of the first monitoring device, with a Y-axis coordinate of 75 cm and a Z-axis coordinate of 50 cm. The coordinates of the target fire extinguishing device are (0, 80, 200). Therefore, the second fire extinguishing plan is as follows: the target fire extinguishing device moves 5 cm closer to the first monitoring device, then moves 150 cm downwards, directing the sprinkler head towards the left side of the first monitoring device, and activating the fire extinguishing device. The server then sends the first information, including the fire extinguishing plan, to the target fire extinguishing device.

[0091] When multiple fire extinguishing devices are needed, the fire extinguishing device with the smaller absolute value of the difference between its Y-axis coordinate and the Y-axis coordinate of the fire point should be selected as the target fire extinguishing device.

[0092] Reference Figure 5 This document illustrates an image-based integrated utility tunnel fire early warning device according to an embodiment of this application. The device is a server and includes a receiving unit for receiving first image information sent by a first monitoring device, wherein the first image information is image information of a target area, and the target area is the area in the integrated utility tunnel where a fire has occurred; a processing unit 502 for calling a second monitoring device based on the first image information, so that the second monitoring device can collect second image information; the second monitoring device is an adjacent monitoring device of the first monitoring device, and the second image information is image information of the target area; the receiving unit is also used to receive the second image information sent by the second monitoring device; the processing unit 502 is also used to determine the fire situation at the ignition point based on the first image information and the second image information, wherein the fire situation at the ignition point includes the location information of the ignition point and the burning situation at the ignition point.

[0093] In one possible implementation, the second monitoring device includes a first adjacent monitoring device, which is a monitoring device that can monitor the target area without turning; the processing unit 502 is further configured to determine the position information of a first reference object based on the first image information; determine the positional relationship between the fire point and the first monitoring device based on the position information of the first reference object, the positional relationship between the fire point and the first monitoring device including a first positional relationship and a second positional relationship, the first positional relationship being that the fire point is on the side of the target area closer to the first monitoring device; the second positional relationship being that the fire point is on the side of the target area farther away from the first monitoring device; if the positional relationship between the fire point and the first monitoring device is the first positional relationship, then the first adjacent monitoring device is invoked so that the first adjacent monitoring device can collect the second image information.

[0094] In one possible implementation, the second monitoring device further includes a second adjacent monitoring device, which is a monitoring device that needs to be turned to monitor the target area; the processing unit 502 is also used to call the second adjacent monitoring device if the positional relationship between the fire point and the first monitoring device is the second position information, so that the second adjacent monitoring device can collect the second image information.

[0095] In one possible implementation, if the second monitoring device invoked is the first adjacent monitoring device, the processing unit 502 is further configured to determine the deflection angle of the first monitoring device based on the position information of the first reference object, so that the first monitoring device can collect image information of the target area again; the receiving unit is further configured to receive the third image information sent by the first monitoring device, the third image information being the image information of the target area collected by the first monitoring device after the angle deflection; the processing unit 502 is further configured to determine the position information of the second reference object and the third reference object based on the third image information; determine the position information of the ignition point based on the position information of the second reference object and the third reference object; and determine the combustion status of the ignition point based on the second image information.

[0096] In one possible implementation, if the second monitoring device invoked is a second adjacent monitoring device, the processing unit 502 is further configured to determine the position information of the fourth reference object and the position information of the fifth reference object based on the second image information; determine the position information of the ignition point based on the position information of the fourth reference object and the position information of the fifth reference object; and determine the combustion status of the ignition point based on the first image information.

[0097] In one possible implementation, the device further includes a sending unit 503; a processing unit 502, which is further configured to calculate the area of ​​the fire zone; formulate a first fire-fighting plan based on the area of ​​the fire zone, the first fire-fighting plan including the number of required fire-fighting devices; and a sending unit 503, which is configured to send first information to the fire-fighting devices to cause the fire-fighting devices to perform fire-fighting actions, the first information including the first fire-fighting plan.

[0098] In one possible implementation, the processing unit 502 is further configured to formulate a second fire-fighting plan based on the fire situation at the ignition point. The second fire-fighting plan includes the moving direction, moving distance, and fire-fighting direction of the fire-fighting device. The sending unit 503 is further configured to send second information to the fire-fighting device to enable the fire-fighting device to perform fire-fighting actions. The second information includes the second fire-fighting plan.

[0099] Reference Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 may include: at least one processor 601, at least one network interface 604, a user interface 603, a memory 605, and at least one communication bus 602.

[0100] The communication bus 602 is used to enable communication between these components.

[0101] The user interface 603 may include a display screen and a camera. Optionally, the user interface 603 may also include a standard wired interface and a wireless interface.

[0102] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0103] The processor 601 may include one or more processing cores. The processor 601 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 605, and by calling data stored in the memory 605. Optionally, the processor 601 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 601 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 601 and may be implemented as a separate chip.

[0104] The memory 605 may include random access memory (RAM) or read-only memory. Optionally, the memory 605 may include a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 605 may also be at least one storage device located remotely from the aforementioned processor 601. Figure 6 As shown, the memory 605, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for an image-based integrated utility tunnel fire early warning method.

[0105] exist Figure 6 In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 601 can be used to call an application program stored in the memory 605 for an image-based integrated utility tunnel fire early warning method. When executed by one or more processors, the electronic device performs one or more of the methods described in the above embodiments.

[0106] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0107] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0108] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. An image-based integrated utility tunnel fire early warning method, characterized in that, The method, applied to a server in a comprehensive utility tunnel fire early warning system, includes: Receive first image information sent by the first monitoring device, wherein the first image information is image information of the target area, and the target area is the area in the integrated utility tunnel where the fire occurred; Based on the first image information, a second monitoring device is invoked to collect the second image information; the second monitoring device is a neighboring monitoring device of the first monitoring device, and the second image information is the image information of the target area. Receive the second image information sent by the second monitoring device; Based on the first image information and the second image information, the fire situation at the ignition point is determined, and the fire situation at the ignition point includes the location information of the ignition point and the burning situation at the ignition point. The second monitoring device includes a first adjacent monitoring device, which is a monitoring device that can monitor the target area without turning; the step of calling the second monitoring device based on the first image information to enable the second monitoring device to collect second image information includes: Based on the first image information, the position information of the first reference object is determined; Based on the location information of the first reference object, the positional relationship between the ignition point and the first monitoring device is determined. The positional relationship between the ignition point and the first monitoring device includes a first positional relationship and a second positional relationship. The first positional relationship is that the ignition point is on the side of the target area closer to the first monitoring device; the second positional relationship is that the ignition point is on the side of the target area farther away from the first monitoring device. If the fire point and the first monitoring device have a first positional relationship, then the first adjacent monitoring device is invoked so that the first adjacent monitoring device can collect the second image information; The second monitoring device further includes a second adjacent monitoring device, which is a monitoring device that needs to be turned to monitor the target area; the step of calling the second monitoring device based on the first image information to enable the second monitoring device to collect the second image information further includes: If the location relationship between the ignition point and the first monitoring device is the second location information, then the second adjacent monitoring device is invoked so that the second adjacent monitoring device can collect the second image information.

2. The image-based integrated utility tunnel fire early warning method according to claim 1, characterized in that, If the second monitoring device invoked is the first adjacent monitoring device, then determining the fire situation based on the first image information and the second image information includes: Based on the position information of the first reference object, the deflection angle of the first monitoring device is determined so that the first monitoring device can collect image information of the target area again; Receive third image information sent by the first monitoring device, wherein the third image information is the image information of the target area collected by the first monitoring device after the angle is deflected; Based on the third image information, the position information of the second reference object and the position information of the third reference object are determined; Based on the position information of the second reference object and the position information of the third reference object, the position information of the ignition point is determined; Based on the second image information, the combustion status of the ignition point is determined.

3. The image-based integrated utility tunnel fire early warning method according to claim 1, characterized in that, If the second monitoring device invoked is the second adjacent monitoring device, then determining the fire situation based on the first image information and the second image information further includes: Based on the second image information, the position information of the fourth reference object and the position information of the fifth reference object are determined; Based on the position information of the fourth reference object and the position information of the fifth reference object, the position information of the ignition point is determined; Based on the first image information, the combustion status of the ignition point is determined.

4. The image-based integrated utility tunnel fire early warning method according to claim 1, characterized in that, The utility tunnel fire early warning system includes fire-fighting devices, and after determining the fire location, it also includes: Calculate the area of ​​the fire zone; Based on the area of ​​the fire zone, a first fire-fighting plan is formulated, which includes the required number of fire-fighting devices. Send a first message to the fire-fighting device to cause the fire-fighting device to perform a fire-fighting action, wherein the first message includes the first fire-fighting plan.

5. The image-based integrated utility tunnel fire early warning method according to claim 1, characterized in that, The utility tunnel fire early warning system includes fire-fighting devices, and after determining the fire location, it also includes: Based on the fire situation at the ignition point, a second fire-fighting plan is formulated, which includes the direction of movement, distance of movement, and direction of fire extinguishing of the fire-fighting equipment. Send a second message to the fire-fighting device to cause the fire-fighting device to perform a fire-fighting action, the second message including the second fire-fighting plan.

6. An image-based integrated utility tunnel fire early warning device, employing an image-based integrated utility tunnel fire early warning method as described in any one of claims 1-5, characterized in that, The device is a server, comprising: The receiving unit is used to receive first image information sent by the first monitoring device, wherein the first image information is image information of a target area, and the target area is the area in the integrated utility tunnel where the fire occurred. The processing unit is configured to invoke a second monitoring device based on the first image information, so that the second monitoring device can acquire second image information; the second monitoring device is an adjacent monitoring device of the first monitoring device, and the second image information is image information of the target area; The receiving unit is also used to receive second image information sent by the second monitoring device; The processing unit is further configured to determine the fire situation at the ignition point based on the first image information and the second image information, wherein the fire situation at the ignition point includes the location information of the ignition point and the burning status of the ignition point.

7. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be loaded by a processor and executed as described in any one of claims 1-5.

Citation Information

Patent Citations

  • Comprehensive pipe gallery fire treatment system

    CN109173130A

  • Warehouse fire brewing period early warning and fighting system

    CN115273377A