Fire monitoring method and system based on Internet of Vehicles

Abstract

The invention discloses a fire monitoring method and system based on the Internet of Vehicles, and belongs to the technical field of the Internet of Vehicles. Comprising the steps of obtaining an environment image based on a preset time mode; wherein the environment image is collected through an automobile data recorder; processing the environment image through a preset smoke recognition model to obtain a smoke recognition result; if the smoke recognition result is suspected smoke or suspected flame, acquiring an environment image sequence in a preset time range and sending the environment image sequence to an alarm platform, so that the alarm platform performs image recognition on the environment image sequence through a preset fire recognition model to acquire a fire recognition result; and if the smoke identification result is smoke or flame, alarm information and vehicle position information are sent to a user terminal and an alarm platform. The coverage range and the discovery time efficiency of fire monitoring can be improved, and the risk of fire expansion is reduced; the problem that the comprehensiveness and the real-time performance of existing fire monitoring need to be improved is solved.

Description

Technical Field

[0001] The present invention relates to the field of fire monitoring technology, and in particular to a fire monitoring method and system based on Internet of Vehicles. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] Fire monitoring refers to monitoring a specific area through various technical means and management measures so that fires can be discovered and actions can be taken in a timely manner. Existing fire monitoring technologies mostly use smoke detectors, temperature detectors, smoke alarms, video surveillance systems and other equipment to achieve fire identification and early warning.

[0004] However, for places such as roads, green belts on both sides of roads, ground parking lots, and residential areas, on the one hand, the coverage of their monitoring equipment is often incomplete, and there are easy to be blind spots in monitoring, making them potential risk areas, affecting the comprehensiveness and real-time nature of fire monitoring. On the other hand, monitoring equipment may sometimes generate false alarms due to environmental factors (such as dust, steam, insects, etc.), increasing the workload and costs of maintenance personnel.

[0005] In addition, there are often vehicles being driven or parked in the above-mentioned places, which will also pose a threat to vehicle safety once a fire risk occurs. Although existing vehicles are highly intelligent, they only focus on the vehicle's own anti-theft and fire monitoring, ignoring the impact of the surrounding environment on the vehicle. Once the alarm is triggered, the vehicle itself is usually at risk of fire, which has a certain lag and is prone to causing property losses. Summary of the invention

[0006] In order to address the deficiencies in the prior art, the present invention provides a fire monitoring method, system, electronic device, computer-readable storage medium and computer program product based on the Internet of Vehicles, which uses a driving recorder on a car to collect environmental images, identify smoke and fire, so as to facilitate timely detection of fire risks in the surrounding environment.

[0007] In a first aspect, the present invention provides a fire monitoring method based on Internet of Vehicles;

[0008] A fire monitoring method based on Internet of Vehicles, applied to a vehicle node, includes:

[0009] Based on a preset time mode, an environmental image is acquired; wherein the environmental image is acquired by a driving recorder;

[0010] Processing the environment image through a preset smoke recognition model to obtain a smoke recognition result;

[0011] If the smoke recognition result is suspected smoke or suspected flame, an environmental image sequence within a preset time range is obtained and sent to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire recognition model to obtain a fire recognition result;

[0012] If the smoke recognition result is smoke or flame, the alarm information and vehicle location information will be sent to the user terminal and the alarm platform.

[0013] In some embodiments, while acquiring a sequence of environmental images within a preset time range, the method further includes:

[0014] The smoke recognition results and vehicle location information are sent to the alarm platform, so that the alarm platform can determine the fire risk value according to the smoke recognition results, vehicle location information and corresponding reception time of different vehicle nodes in the same area.

[0015] In some implementations, determining the fire risk value according to the smoke recognition results of different vehicle nodes in the same area, the vehicle location information, and the corresponding reception time specifically includes:

[0016] The location similarity is calculated based on the vehicle location information of different vehicle nodes in the same area, and the time similarity is calculated based on the corresponding reception time of different vehicle nodes;

[0017] The fire risk value is determined based on the location similarity and time similarity.

[0018] In some implementations, the fire risk value is used in combination with a fire identification result to formulate a fire response strategy.

[0019] In some embodiments, the smoke recognition model is a YOLOv5s network, and the fire recognition model is an improved YOLOv8 network.

[0020] In some embodiments, when the vehicle node is in a parked state, if the preliminary smoke identification result is suspected smoke or suspected fire, a control instruction is sent to the power supply system to power the driving recorder to collect a sequence of environmental images within a preset time range.

[0021] In a second aspect, the present invention provides a fire monitoring system based on the Internet of Vehicles;

[0022] A fire monitoring system based on Internet of Vehicles, comprising:

[0023] The acquisition module is configured to: acquire an environmental image based on a preset time mode; wherein the environmental image is acquired by a driving recorder;

[0024] The smoke recognition module is configured to: process the environment image through a preset smoke recognition model to obtain a smoke recognition result;

[0025] The fire identification module is configured as follows: if the smoke identification result is suspected smoke or suspected flame, then an environmental image sequence within a preset time range is obtained and sent to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire identification model to obtain a fire identification result; if the smoke identification result is smoke or flame, then an alarm message and vehicle location information are sent to the user terminal and the alarm platform.

[0026] In a third aspect, the present invention provides an electronic device;

[0027] An electronic device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned fire monitoring method based on vehicle networking.

[0028] In a fourth aspect, the present invention provides a computer-readable storage medium;

[0029] A computer-readable storage medium stores a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned fire monitoring method based on the Internet of Vehicles.

[0030] In a fifth aspect, the present invention provides a computer program product;

[0031] A computer program product includes a computer program / instruction, which implements the steps of the above-mentioned fire monitoring method based on vehicle networking when executed by a processor.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The technical solution provided by the present invention performs fire monitoring based on the existing vehicle monitoring system, thereby expanding the coverage of fire monitoring and the scope of use of the vehicle monitoring system. While reducing the risk of fire occurrence or expansion in the surrounding environment, it can also further protect the personal and property safety of vehicle owners.

[0034] 2. The technical solution provided by the present invention utilizes a lightweight smoke recognition model deployed on a vehicle node to efficiently process the collected environmental model, thereby ensuring the timeliness of the initial fire recognition. For situations where the smoke recognition result is suspected smoke or suspected flame, a fire recognition model with higher recognition accuracy deployed on the alarm platform is used for recognition to avoid false alarms. For situations where the smoke recognition result is smoke or flame, the alarm information and vehicle location information are sent to the alarm platform in a timely manner to avoid delays in rescue opportunities.

[0035] 3. The technical solution provided by the present invention is to reduce the probability of false alarms and misreports. The alarm platform can conduct fire risk assessment based on the smoke recognition results, vehicle location information and corresponding reception time of different vehicle nodes in the same area under the Internet of Vehicles system, so as to timely discover potential fire risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0037] Figure 1 A schematic diagram of a process flow provided by an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a system framework provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0040] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0042] Embodiment 1

[0043] Existing fire monitoring mostly relies on installed monitoring sensors or video surveillance systems, but for outdoor open scenes (such as roads and green belts) or indoor claustrophobic scenes (such as underground parking lots), there are prone to monitoring blind spots and false alarms; therefore, the present invention provides a fire monitoring method based on the Internet of Vehicles, which uses the vehicle monitoring system of the vehicle node and the Internet of Vehicles system to perform fire monitoring, thereby improving the comprehensiveness and real-time performance of fire monitoring.

[0044] Next, combine Figure 1A fire monitoring method based on the Internet of Vehicles disclosed in this embodiment is described in detail. The fire monitoring method based on the Internet of Vehicles is applied to a vehicle node and includes the following steps:

[0045] S1. Acquire an environment image based on a preset time mode.

[0046] The driving recorder can record the video images and sounds of the entire process when the car is driving, and provide video and image information for abnormal vehicle conditions such as traffic accidents. When the car is parked, it can be used for parking monitoring, and the driving recorder can be used to record road conditions in abnormal conditions such as collisions.

[0047] Therefore, in this embodiment, the driving recorder is used to collect environmental images for fire monitoring. When the car is in motion, the driving recorder can be used to collect environmental images in real time based on a preset time mode; when the car is parked, the driving recorder is turned on based on a preset time mode to collect environmental images. Here, the preset time mode refers to the time interval for fire monitoring set by the car owner.

[0048] S2. Process the environment image through a preset smoke recognition model to obtain a smoke recognition result; if the smoke recognition result is suspected smoke or suspected flame, execute S3; if the smoke recognition result is smoke or flame, execute S4.

[0049] Taking into account the performance of the vehicle node hardware configuration and the real-time requirements of the initial smoke recognition, in this embodiment, the trained YOLOv5s network is used as the smoke recognition model to improve the speed of smoke recognition by taking advantage of its lightweight characteristics.

[0050] Specifically, the environmental images collected by the dashcam are collected and the smoke recognition results are annotated to construct a training set, and the YOLOv5s network is trained with the training set. The input of the YOLOv5s network is the environmental image, and the output is the environmental image containing the smoke recognition results. The smoke recognition results include none, suspected smoke, suspected flame, smoke and flame.

[0051] S3. Obtain an environmental image sequence within a preset time range and send it to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire recognition model to obtain a fire recognition result.

[0052] In order to further accurately identify the suspected fire area, an environmental image sequence of a time period related to the environmental image (such as one minute before and after) is obtained and sent to the alarm platform, so that it can perform further fire identification based on the environmental image sequence.

[0053] When the vehicle node is in a parked state, if the preliminary smoke recognition result is suspected smoke or suspected flame, a control command is sent to the power supply system to power the driving recorder, thereby collecting a sequence of environmental images within a preset time range.

[0054] In this embodiment, the fire recognition model is an improved YOLOv8 network, the input of the improved YOLOv8 network is an environmental image sequence, and the output is a fire recognition result. The improved YOLOv8 network includes one GhostConv layer connected in sequence, four groups of stacked GhostConv layers and C2f layers, a CBAM module, and a classification layer.

[0055] In order to improve the data processing speed of the fire recognition model, the GhostConv layer is used instead of the traditional Conv layer to reduce the burden of the model. At the same time, the CBAM module is introduced to enable the model to automatically adjust the degree of attention to different areas, ensuring the priority processing of key features, thereby improving the accuracy of fire recognition.

[0056] Specifically, the GhostConv layer includes a depthwise separable convolutional layer, a Cheap Operation layer, and a Concat layer connected in sequence. The output of the depthwise separable convolutional layer and the output of the Cheap Operation layer are jump-connected. The CheapOperation layer is a cheap operation layer, which represents linear calculation.

[0057] The CBAM module includes a channel attention mechanism and a spatial attention mechanism. In the CBAM module, the input feature map is first processed by the channel attention mechanism, and then the output of the channel attention mechanism is input into the spatial attention mechanism to obtain the final feature map.

[0058] Considering the possible false alarms of the smoke recognition model and the identification of potential fire risks, as an implementation method, it also includes: sending the smoke recognition results and vehicle location information to the alarm platform, so that the alarm platform can determine the fire risk value according to the smoke recognition results, vehicle location information and corresponding reception time of different vehicle nodes in the same area. The specific process is as follows:

[0059] (1) The location similarity is calculated based on the vehicle location information of different vehicle nodes in the same area, and the time similarity is calculated based on the corresponding reception time of different vehicle nodes.

[0060] Exemplarily, the position similarity is expressed as:

[0061]

[0062] Where D maxrepresents the maximum distance between different vehicle nodes in the same area, (x, y) represents the vehicle node position corresponding to the latest receiving time, (x i ,y i ) represents the position coordinates of the i-th vehicle node, and n represents the total number of vehicle nodes.

[0063] The temporal similarity is expressed as:

[0064]

[0065] In the formula, t i represents the receiving time corresponding to the i-th vehicle node, and t represents the latest receiving time.

[0066] (2) Determine the fire risk value based on the location similarity and time similarity; the fire risk value is expressed as:

[0067] ρ=S P *S T .

[0068] If the fire risk value exceeds the preset threshold, it means that the vehicle nodes close to the warning location in the same area have all issued fire warnings within a certain time range, and there are safety hazards at the warning location; even if further fire identification results show that there is no fire, firefighters should be dispatched to investigate safety hazards.

[0069] S4. Send alarm information and vehicle location information to the user terminal and alarm platform.

[0070] Specifically, the fire alarm information and vehicle location information are sent to the vehicle owner and the alarm platform for alarm; at the same time, the alarm information and video are synchronously sent to the property department, fire department and other relevant personnel or departments.

[0071] Here, the vehicle position information is read by the vehicle parking positioning system.

[0072] Furthermore, a control command is issued to wake up the vehicle voice control system to notify the scene of the alarm situation. The alarm horn reminds the people nearby of the possible risks, and simultaneously notifies the people on site to evacuate through voice broadcasts, giving priority to ensuring the safety of the people. The owner of the car or the property, fire and other departments can remotely shout to remind nearby people to leave in time.

[0073] At the same time, the alarm information and alarm video are stored in the vehicle's local and cloud database for backup and easy later query.

[0074] Embodiment 2

[0075] Combination Figure 2 This embodiment discloses a fire monitoring system based on Internet of Vehicles, including:

[0076] The acquisition module is configured to: acquire an environmental image based on a preset time mode; wherein the environmental image is acquired by a driving recorder;

[0077] The smoke recognition module is configured to: process the environment image through a preset smoke recognition model to obtain a smoke recognition result;

[0078] The fire identification module is configured as follows: if the smoke identification result is suspected smoke or suspected flame, then an environmental image sequence within a preset time range is obtained and sent to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire identification model to obtain a fire identification result; if the smoke identification result is smoke or flame, then an alarm message and vehicle location information are sent to the user terminal and the alarm platform.

[0079] It should be noted that the acquisition module, smoke identification module and fire identification module above correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in Embodiment 1 above. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0080] Embodiment 3

[0081] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned fire monitoring method based on the Internet of Vehicles are completed.

[0082] Embodiment 4

[0083] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned fire monitoring method based on the Internet of Vehicles are completed.

[0084] Embodiment 5

[0085] Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned fire monitoring method based on the Internet of Vehicles when executed by a processor.

[0086] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fire monitoring method based on Internet of Vehicles, characterized in that: Applied to vehicle nodes, including: Based on a preset time mode, an environmental image is acquired; wherein the environmental image is acquired by a driving recorder; Processing the environment image through a preset smoke recognition model to obtain a smoke recognition result; If the smoke recognition result is suspected smoke or suspected flame, an environmental image sequence within a preset time range is obtained and sent to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire recognition model to obtain a fire recognition result; If the smoke recognition result is smoke or flame, the alarm information and vehicle location information will be sent to the user terminal and the alarm platform.

2. The fire monitoring method based on the Internet of Vehicles according to claim 1, characterized in that: While acquiring the environmental image sequence within the preset time range, it also includes: The smoke recognition results and vehicle location information are sent to the alarm platform, so that the alarm platform can determine the fire risk value according to the smoke recognition results, vehicle location information and corresponding reception time of different vehicle nodes in the same area.

3. The fire monitoring method based on the Internet of Vehicles according to claim 2, characterized in that: Determining the fire risk value according to the smoke recognition results of different vehicle nodes in the same area, the vehicle location information and the corresponding receiving time specifically includes: The location similarity is calculated based on the vehicle location information of different vehicle nodes in the same area, and the time similarity is calculated based on the corresponding reception time of different vehicle nodes; The fire risk value is determined based on the location similarity and time similarity.

4. The fire monitoring method based on the Internet of Vehicles according to claim 2, characterized in that: The fire risk value is used in combination with the fire identification result to formulate a fire response strategy.

5. The fire monitoring method based on the Internet of Vehicles according to claim 1, characterized in that: The smoke recognition model is a YOLOv5s network, and the fire recognition model is an improved YOLOv8 network.

6. The fire monitoring method based on the Internet of Vehicles according to claim 1, characterized in that: When the vehicle node is in a parked state, if the preliminary smoke recognition result is suspected smoke or suspected flame, a control command is sent to the power supply system to power the driving recorder and collect a sequence of environmental images within a preset time range.

7. The fire monitoring system based on the Internet of Vehicles is characterized by: include: The acquisition module is configured to: acquire an environmental image based on a preset time mode; wherein the environmental image is acquired by a driving recorder; The smoke recognition module is configured to: process the environment image through a preset smoke recognition model to obtain a smoke recognition result; The fire identification module is configured as follows: if the smoke identification result is suspected smoke or suspected flame, then an environmental image sequence within a preset time range is obtained and sent to the alarm platform, so that the alarm platform performs image recognition on the environmental image sequence through a preset fire identification model to obtain a fire identification result; if the smoke identification result is smoke or flame, then an alarm message and vehicle location information are sent to the user terminal and the alarm platform.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the fire monitoring method based on the Internet of Vehicles according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the fire monitoring method based on the Internet of Vehicles described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the fire monitoring method based on the Internet of Vehicles described in any one of claims 1 to 6 are implemented.

Images