Fire monitoring method and system based on internet of vehicles

Abstract

The application discloses a fire monitoring method and system based on Internet of Vehicles, and belongs to the technical field of Internet of Vehicles. The method comprises the following steps: acquiring an environment image based on a preset time mode; wherein the environment image is collected by a driving recorder; processing the environment image through a preset smoke identification model to obtain a smoke identification result; if the smoke identification result is suspected smoke or suspected flame, acquiring an environment image sequence within a preset time range and sending the sequence to an alarm platform, so that the alarm platform performs image recognition on the environment image sequence through a preset fire identification model to obtain a fire identification result; and if the smoke identification result is smoke or flame, sending alarm information and vehicle position information to a user terminal and the alarm platform. The application can improve the coverage range and timeliness of fire monitoring, reduce the risk of fire expansion, and solve the problems that the comprehensiveness and real-time performance of the existing fire monitoring need to be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire monitoring, in particular to a fire monitoring method and system based on Internet of Vehicles. BACKGROUND

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

[0003] Fire monitoring refers to monitoring a specific area through various technical means and management measures so as to timely discover and take corresponding actions in case of fire. The existing fire monitoring technical means are mainly to realize fire identification and early warning through smoke detectors, temperature detectors, smoke alarms, video monitoring systems and other devices.

[0004] However, for road surfaces, green belts on both sides of roads, ground parking lots, residences and other places, on the one hand, the coverage of the monitoring devices is often not complete, and there are often monitoring dead angles, which become potential risk areas and affect the comprehensiveness and real-time performance of fire monitoring. On the other hand, the monitoring devices may sometimes produce false alarms due to environmental factors (such as dust, steam, insects, etc.), increasing the work burden and cost of maintenance personnel.

[0005] In addition, there are often vehicles driving or parked in the above-mentioned places, and once a fire risk occurs, it will also pose a threat to the safety of the vehicles. Although the existing vehicles have a high degree of intelligence, they only focus on vehicle self-protection and self-fire monitoring, ignoring the influence of the surrounding environment on the vehicles. Once the alarm is triggered, the vehicle itself is usually at risk of fire, which has a certain lag and is easy to cause property loss. SUMMARY

[0006] In order to solve the problems of the prior art, the present application provides a fire monitoring method and system based on Internet of Vehicles, an electronic device, a computer readable storage medium and a computer program product, which use the car's on-board vehicle event data recorder to collect environmental images, identify smoke and identify fire, so as to timely discover the fire risks in the surrounding environment.

[0007] In a first aspect, the present application 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, comprising:

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

[0010] The environmental image is processed by a preset smoke identification model to obtain a smoke identification result;

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

[0012] If the smoke identification result is smoke or flame, alarm information and vehicle position information are sent to a user terminal and the alarm platform.

[0013] In some embodiments, while acquiring the environmental image sequence in the preset time range, the method further includes:

[0014] The smoke identification result and the vehicle position information are sent to the alarm platform, so that the alarm platform determines a fire risk value according to the smoke identification result, the vehicle position information and the corresponding receiving time of different vehicle nodes in the same region.

[0015] In some embodiments, the determination of the fire risk value according to the smoke identification result, the vehicle position information and the corresponding receiving time of different vehicle nodes in the same region specifically includes:

[0016] The position similarity is calculated according to the vehicle position information of different vehicle nodes in the same region, and the time similarity is calculated according to the corresponding receiving time of different vehicle nodes.

[0017] The fire risk value is determined according to the position similarity and the time similarity.

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

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

[0020] In some embodiments, when the vehicle node is in a parking state, if the smoke preliminary identification result is suspected smoke or suspected flame, a control instruction is sent to a power supply system to make it supply power for a driving record instrument to collect an environmental image sequence in a preset time range.

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

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

[0023] An acquisition module is configured to acquire an environmental image based on a preset time mode, wherein the environmental image is collected by a driving record instrument.

[0024] The smoke identification module is configured to process the environment image through a preset smoke identification model to obtain a smoke identification result.

[0025] The fire identification module is configured to: if the smoke identification result is suspected smoke or suspected flame, acquire an environment image sequence within a preset time range and send the environment image sequence to an alarm platform, so that the alarm platform performs image identification on the environment image sequence through a preset fire identification model to obtain a fire identification result; and if the smoke identification result is smoke or flame, send alarm information and vehicle position information to a user terminal and the alarm platform.

[0026] In a third aspect, the present application provides an electronic device.

[0027] An electronic device includes a memory, a processor, and a computer program stored on the memory, and 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 application provides a computer readable storage medium.

[0029] A computer readable storage medium has a computer program / instruction stored thereon, and the computer program / instruction is executed by a processor to implement the steps of the above-mentioned fire monitoring method based on vehicle networking.

[0030] In a fifth aspect, the present application provides a computer program product.

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

[0032] Compared with the prior art, the present application has the following advantages:

[0033] 1. The technical solution provided by the present application is based on the existing vehicle monitoring system for fire monitoring, which expands the coverage of fire monitoring and the use range of the vehicle monitoring system, reduces the risk of fire occurrence or expansion of the surrounding environment, and further protects the personal and property safety of the vehicle owner.

[0034] 2. The technical solution provided by the present application uses a lightweight smoke identification model deployed on a vehicle node to efficiently process the collected environment model, ensuring the timeliness of initial fire identification; for the case where the smoke identification result is suspected smoke or suspected flame, a fire identification model with higher identification accuracy deployed by the alarm platform is used for identification to avoid false positives; for the case where the smoke identification result is smoke or flame, alarm information and vehicle position information are sent to the alarm platform in a timely manner to avoid delaying the rescue opportunity.

[0035] 3、 The technical scheme provided by the present application can reduce the false alarm and wrong report probability, the alarm platform can comprehensively evaluate the fire risk by combining the smoke identification results of different vehicle nodes in the same area, vehicle position information and corresponding receiving time in the vehicle networking system, and then the potential fire risk can be found in time. BRIEF DESCRIPTION OF DRAWINGS

[0036] The drawings accompanying the specification of this application form a part thereof, serve to provide further understanding of the application, and together with the description of the exemplary embodiments of the application, serve to explain the application, and do not limit the application.

[0037] Figure 1 The flowchart provided for the embodiments of the present application;

[0038] Figure 2 The system framework diagram provided for the embodiments of the present application. DETAILED DESCRIPTION

[0039] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application pertains.

[0040] It should be noted that the terms used herein are only for the purpose of describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form, and in addition, it should be understood that the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0041] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0042] Embodiment one

[0043] Existing fire monitoring relies on installed monitoring sensors or video monitoring systems, but for outdoor open scenes (such as roads, green belts) or indoor enclosed scenes (such as underground parking lots), there are likely to be monitoring dead angles and false alarms; therefore, the present application provides a fire monitoring method based on vehicle networking, which uses the vehicle monitoring system of the vehicle node and the vehicle networking system to monitor fire, and improves the comprehensiveness and real-time performance of fire monitoring.

[0044] Next, combined with Figure 1A vehicle networking-based fire monitoring method is disclosed in the embodiment. The vehicle networking-based fire monitoring method is applied to a vehicle node and includes the following steps.

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

[0046] A driving recorder can record video images and sound in the whole process of driving, and provide video and image information for vehicle abnormal conditions such as traffic accidents. In the parking state, the driving recorder can be used for parking monitoring, and the driving recorder can capture the road surface in the case of collision and other abnormal conditions.

[0047] Therefore, in the embodiment, the driving recorder is used to collect environment images for fire monitoring. In the driving state, the environment images collected by the driving recorder in real time can be called based on a preset time mode; in the parking state, the driving recorder is started based on a preset time mode to collect environment images. Here, the preset time mode refers to the time interval set by the vehicle owner for fire monitoring.

[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, perform S3; if the smoke recognition result is smoke or flame, perform S4.

[0049] Considering the hardware configuration performance of the vehicle node and the real-time requirement of preliminary smoke recognition, in the embodiment, a trained YOLOv5s network is used as a smoke recognition model, and the light weight feature of the YOLOv5s network is used to improve the speed of smoke recognition.

[0050] Specifically, the environment images collected by the driving recorder in the past are collected and labeled with smoke recognition results to construct a training set, and the YOLOv5s network is trained through the training set. The input of the YOLOv5s network is an environment image, and the output is an environment image containing a smoke recognition result. The smoke recognition result includes none, suspected smoke, suspected flame, smoke, and flame.

[0051] S3. Obtain an environment image sequence in a preset time range and send it to an alarm platform to make the alarm platform perform image recognition on the environment 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, the environment image sequence of the related time period (such as one minute before and after) of the environment image is obtained and sent to the alarm platform, so that the alarm platform can further identify the fire according to the environment image sequence.

[0053] When the vehicle node is in a parking state, if the preliminary smoke identification result is suspected smoke or suspected flame, a control instruction is sent to the power supply system to make it supply power for the driving recorder, and then the environmental image sequence in the preset time range is collected.

[0054] In this embodiment, the fire identification model is an improved YOLOv8 network, the input of the improved YOLOv8 network is an environmental image sequence, and the output is a fire identification result. The improved YOLOv8 network includes 1 GhostConv layer, 4 groups of stacked GhostConv layers and C2f layers, a CBAM module and a classification layer connected in turn.

[0055] In order to improve the data processing speed of the fire identification 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 make the model automatically adjust the attention degree to different regions, ensure the priority processing of key features, and then improve the accuracy of fire identification.

[0056] Specifically, the GhostConv layer includes a depth separable convolution layer, a Cheap Operation layer and a Concat layer connected in turn, the output of the depth separable convolution layer and the output of the Cheap Operation layer are jump connected, and the Cheap Operation 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 positives of the smoke identification model and the identification of potential fire risks, as an implementation, it also includes: sending the smoke identification result and the vehicle position information to the alarm platform, so that the alarm platform determines the fire risk value according to the smoke identification result, the vehicle position information and the corresponding receiving time of different vehicle nodes in the same area. The specific process is as follows:

[0059] (1) Calculate the position similarity according to the vehicle position information of different vehicle nodes in the same area, and calculate the time similarity according to the receiving time corresponding to different vehicle nodes.

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

[0061]

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

[0063] The time similarity is represented as:

[0064]

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

[0066] (2) According to the position similarity and the time similarity, a fire risk value is determined; the fire risk value is represented as:

[0067] ρ=S P *S T .

[0068] If the fire risk value exceeds a preset threshold value, it indicates that the vehicle nodes close to the warning site in the same area have all sent out fire warnings within a certain time range, and the warning site has a safety hazard; even if the further fire identification result is that there is no fire, fire personnel should be sent out for safety hazard investigation.

[0069] S4, sending alarm information and vehicle position information to a user terminal and an alarm platform.

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

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

[0072] Further, a control instruction is sent out to wake up the vehicle voice control system to notify the on-site alarm, the alarm horn reminds the nearby personnel of the possible risk, synchronously notifies the on-site personnel to evacuate through voice broadcast and the like, and the personnel safety is preferentially ensured. The vehicle owner or the property department, the fire department and the like can remotely shout to timely remind the nearby personnel to leave.

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

[0074] Embodiment Two

[0075] In combination Figure 2 , the embodiment discloses a fire monitoring system based on Internet of Vehicles, which comprises:

[0076] An acquisition module is configured to acquire an environment image based on a preset time mode, wherein the environment image is collected by a driving recorder.

[0077] A smoke identification module is configured to process the environment image by a preset smoke identification model to obtain a smoke identification result.

[0078] A fire identification module is configured to, if the smoke identification result is suspected smoke or suspected flame, acquire an environment image sequence in a preset time range and send the environment image sequence to an alarm platform, so that the alarm platform performs image recognition on the environment image sequence by a preset fire identification model to obtain a fire identification result; and if the smoke identification result is smoke or flame, send alarm information and vehicle position information to a user terminal and the alarm platform.

[0079] It should be noted that the above acquisition module, smoke identification module and fire identification module correspond to the steps in Embodiment One, and the above modules have the same examples and application scenarios as the corresponding steps, but are not limited to the content disclosed in Embodiment One. 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 Three

[0081] Embodiment Three of the present application provides an electronic device, which includes a memory and a processor, and computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, the steps of the above fire monitoring method based on vehicle networking are completed.

[0082] Embodiment Four

[0083] Embodiment Four of the present application provides a computer readable storage medium for storing computer instructions, wherein the computer instructions are executed by a processor to complete the steps of the above fire monitoring method based on vehicle networking.

[0084] Embodiment Five

[0085] Embodiment Five of the present application provides a computer program product, which includes a computer program / instruction, wherein the computer program / instruction is executed by a processor to implement the steps of the above fire monitoring method based on vehicle networking.

[0086] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0087] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0088] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0089] The above description of the various embodiments can have emphasized certain aspects of the various embodiments, which have not been described in detail. One skilled in the art will readily understand that the various embodiments can be practiced with the elements, acts, and functions not expressly described herein. Applicant has not limited the various embodiments to the specific embodiments disclosed herein.

[0090] The above description is only preferred embodiments of the present application and is not intended to limit the present application. The present application can be variously changed and modified by those skilled in the art without departing from the spirit and scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the present application.

Claims

1. A fire monitoring method based on Internet of Vehicles, characterized in that, The application is applied to a vehicle node, comprising: acquiring an environment image based on a preset time mode, wherein the environment image is collected by a driving recorder; processing the environment image through a preset smoke identification model to obtain a smoke identification result; if the smoke identification result is suspected smoke or suspected flame, acquiring an environment image sequence within a preset time range and sending it to an alarm platform to enable the alarm platform to perform image recognition on the environment image sequence through a preset fire identification model to obtain a fire identification result; while acquiring the environment image sequence within the preset time range, also comprising: sending the smoke identification result and vehicle location information to the alarm platform to enable the alarm platform to determine a fire risk value according to the smoke identification results, vehicle location information and corresponding receiving times of different vehicle nodes in the same area; the determination of the fire risk value according to the smoke identification results, vehicle location information and corresponding receiving times of different vehicle nodes in the same area specifically comprises: calculating a location similarity according to the vehicle location information of different vehicle nodes in the same area and calculating a time similarity according to the corresponding receiving times of different vehicle nodes; determining the fire risk value according to the location similarity and the time similarity; wherein the location similarity is represented as: ； wherein, denotes the maximum distance between different vehicle nodes within the same region, denotes the vehicle node position corresponding to the latest reception time, denotes the position coordinates of the i-th vehicle node, denotes the total number of vehicle nodes; the time similarity is represented as: ; In the formula, denotes the reception time corresponding to the i-th vehicle node, denotes the latest reception time; the fire risk value is determined according to the location similarity and the time similarity; the fire risk value is represented as: 。 2.The vehicle-to-everything based fire monitoring method of claim 1, wherein, the fire risk value is used in combination with the fire identification result to formulate a fire response strategy. 3.The vehicle-to-everything based fire monitoring method of claim 1, wherein, the smoke identification model is a YOLOv5s network and the fire identification model is an improved YOLOv8 network. 4.The vehicle-to-everything based fire monitoring method of claim 1, wherein, when the vehicle node is in a parking state, if the smoke preliminary identification result is suspected smoke or suspected flame, a control instruction is sent to a power supply system to enable it to supply power to the driving recorder to collect an environment image sequence within a preset time range.

5. A fire monitoring system based on Internet of Vehicles, characterized in that, comprising: an acquisition module configured to acquire an environment image based on a preset time mode, wherein the environment image is collected by a driving recorder; a smoke identification module configured to process the environment image through a preset smoke identification model to obtain a smoke identification result; a fire identification module configured to, if the smoke identification result is suspected smoke or suspected flame, acquire an environment image sequence within a preset time range and send it to an alarm platform to enable the alarm platform to perform image recognition on the environment image sequence through a preset fire identification model to obtain a fire identification result; while acquiring the environment image sequence within the preset time range, also comprising: sending the smoke identification result and vehicle location information to the alarm platform to enable the alarm platform to determine a fire risk value according to the smoke identification results, vehicle location information and corresponding receiving times of different vehicle nodes in the same area; the determination of the fire risk value according to the smoke identification results, vehicle location information and corresponding receiving times of different vehicle nodes in the same area specifically comprises: calculating a location similarity according to the vehicle location information of different vehicle nodes in the same area and calculating a time similarity according to the corresponding receiving times of different vehicle nodes; According to the position similarity and the time similarity, a fire risk value is determined; The position similarity is expressed as: ； wherein, denotes the maximum distance between different vehicle nodes within the same region, denotes the vehicle node position corresponding to the latest reception time, denotes the position coordinates of the i-th vehicle node, denotes the total number of vehicle nodes; The time similarity is expressed as: ; In the formula, denotes the reception time corresponding to the i-th vehicle node, denotes the latest reception time; According to the position similarity and the time similarity, a fire risk value is determined; the fire risk value is expressed as: 。 6. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, causes the electronic device to perform the method of any one of claims 1 to 5. The processor executes the computer program to implement the steps of the fire monitoring method based on the Internet of Vehicles in any one of claims 1-4.

7. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the fire monitoring method based on the Internet of Vehicles in any one of claims 1-4.

8. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the fire monitoring method based on the Internet of Vehicles in any one of claims 1-4.

Images