Gas station fire control method, system, readable storage medium and computer

Abstract

The present invention provides a fire control method, system, readable storage medium and computer for a gas station. The method includes: inputting each first fire scene image into a convolutional neural network model for model optimization to obtain an optimized convolutional neural network model; performing model optimization on an image detection model based on each second fire scene image to obtain an optimized image detection model; using an image registration algorithm to perform data processing and fuse data on the feature extraction results of each first fire scene image and each second fire scene image; constructing a corresponding fire control strategy set according to the fire fighting facility information and the fire fighting task set; performing model fusion on the fire control strategy set, the fused data, the optimized convolutional neural network model and the optimized image detection model to construct a fire detection model, and realizing the fire control of the target gas station through the fire detection model. The present invention realizes the fire control of the target gas station through the fire detection model, improves the efficiency of task processing and reduces the allocation cost.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a gas station fire control method, system, readable storage medium and computer. Background Art

[0002] With the rapid development of technology and the improvement of people's living standards, vehicles have become one of the indispensable tools in people's lives. Along with the increase in the vehicle ownership, the number of gas stations is gradually increasing.

[0003] As a new R & D product, a fire fighting robot can be better applied to areas with special properties such as gas stations. On the one hand, it can replace humans to complete fire fighting work to reduce the harm of disasters to rescue personnel. On the other hand, it can quickly detect the fire situation in the gas station and improve the rescue efficiency. However, currently, the control of the fire fighting robot is to collect relevant data manually and process the data in the terminal to control the robot to carry out fire fighting work at the fire scene according to the processing results in the terminal. However, this method has a large error, and in the task allocation of the fire fighting robot, it can only be executed according to the settings of the staff, thus greatly reducing the work efficiency and increasing the use cost. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a gas station fire control method, system, readable storage medium and computer to at least solve the deficiencies in the above technologies.

[0005] The present invention provides a gas station fire control method, including:

[0006] Obtain a plurality of first fire scene images and second fire scene images, and construct a convolutional neural network model. Input each of the first fire scene images into the convolutional neural network model to enable the convolutional neural network model to optimize the model to obtain a convolutional neural network optimized model;

[0007] Construct an image detection model, and optimize the model based on each of the second fire scene images to obtain an image detection optimized model;

[0008] Extract features from each of the first fire scene images and each of the second fire scene images, and use an image registration algorithm to process the feature extraction results to obtain corresponding fusion data;

[0009] Obtain the fire fighting facility information of a plurality of areas where the gas station is located, and construct a fire fighting task set. Construct a corresponding fire fighting strategy set according to the fire fighting facility information and the fire fighting task set;

[0010] Fuse the fire protection strategy set, the fusion data, the optimized convolutional neural network model, and the optimized image detection model to construct a fire detection model, and implement fire control for the target gas station through the fire detection model.

[0011] Further, the steps of inputting each of the first fire scene images into the convolutional neural network model to optimize the convolutional neural network model to obtain an optimized convolutional neural network model include:

[0012] Input each of the first fire scene images into the convolutional neural network model so that the convolutional neural network model extracts features from each of the first fire scene images to obtain corresponding one-dimensional feature maps and two-dimensional feature maps;

[0013] Add a hybrid attention algorithm to the backbone network module of the convolutional neural network model, perform depth convolution on the one-dimensional feature map and the two-dimensional feature map, and use the depth convolution result to optimize the convolutional neural network model to obtain an optimized convolutional neural network model.

[0014] Further, the steps of optimizing the image detection model based on each of the second fire scene images to obtain an optimized image detection model include:

[0015] Perform image processing on each of the second fire scene images to construct a data matrix for each of the second fire scene images;

[0016] Based on the data matrix, calculate weights and perform image segmentation on each of the second fire scene images respectively to obtain a number of segmented images, and perform clustering processing on each of the segmented images to obtain corresponding clustering results;

[0017] Input the clustering results into the image detection model for model optimization to obtain an optimized image detection model.

[0018] Further, the steps of extracting features from each of the first fire scene images and each of the second fire scene images, and using an image registration algorithm to process the feature extraction results to obtain corresponding fusion data include:

[0019] Perform data cleaning and data processing on each of the first fire scene images and each of the second fire scene images to obtain corresponding first processed images and second processed images;

[0020] Use an image registration algorithm to perform image correction and registration on the first processed image and the second processed image, and perform feature fusion on the registered first processed image and second processed image to obtain corresponding fusion data.

[0021] Further, the steps of obtaining the fire-fighting facility information of the areas where several gas stations are located, constructing a fire-fighting task set, and constructing a corresponding fire-fighting strategy set according to the fire-fighting facility information and the fire-fighting task set include:

[0022] Obtain the fire-fighting facility information of the areas where several gas stations are located, where the fire-fighting facility information includes the quantity information and corresponding type information of fire-fighting robots;

[0023] Construct a fire-fighting robot set according to the quantity information and corresponding type information of the fire-fighting robots, construct a task sequence according to the fire-fighting robot set, and perform strategy combination on the constructed task sequence and the fire-fighting robot set to construct a corresponding fire-fighting strategy set.

[0024] The present invention also provides a gas station fire control system, including:

[0025] A first model construction module, configured to obtain several first fire scene images and second fire scene images, construct a convolutional neural network model, and input each of the first fire scene images into the convolutional neural network model to enable the convolutional neural network model to perform model optimization to obtain a convolutional neural network optimized model;

[0026] A second model construction module, configured to construct an image detection model, and perform model optimization on the image detection model based on each of the second fire scene images to obtain an image detection optimized model;

[0027] A data fusion module, configured to extract features from each of the first fire scene images and each of the second fire scene images, and perform data processing on the feature extraction results by using an image registration algorithm to obtain corresponding fusion data;

[0028] A fire-fighting strategy construction module, configured to obtain the fire-fighting facility information of the areas where several gas stations are located, construct a fire-fighting task set, and construct a corresponding fire-fighting strategy set according to the fire-fighting facility information and the fire-fighting task set;

[0029] A fire control module, configured to perform model fusion on the fire-fighting strategy set, the fusion data, the convolutional neural network optimized model, and the image detection optimized model to construct a fire detection model, and implement fire control of a target gas station through the fire detection model.

[0030] Further, the first model construction module includes:

[0031] A feature extraction unit, configured to input each of the first fire scene images into the convolutional neural network model to enable the convolutional neural network model to extract features from each of the first fire scene images to obtain corresponding one-dimensional feature maps and two-dimensional feature maps;

[0032] A model optimization unit, configured to add a hybrid attention algorithm to the backbone network module of the convolutional neural network model, perform depth convolution on the one-dimensional feature map and the two-dimensional feature map, and optimize the processed convolutional neural network model with the depth convolution result to obtain an optimized convolutional neural network model.

[0033] Further, the second model construction module includes:

[0034] An image processing unit, configured to perform image processing on each of the second fire scene images to construct a data matrix of each of the second fire scene images;

[0035] An image segmentation unit, configured to perform weight calculation and image segmentation on each of the second fire scene images based on the data matrix to obtain a number of segmented images, and perform clustering processing on each of the segmented images to obtain corresponding clustering results;

[0036] A clustering processing unit, configured to input the clustering results into the image detection model for model optimization to obtain an optimized image detection model.

[0037] Further, the data fusion module includes:

[0038] Clean and process the data of each of the first fire scene images and each of the second fire scene images to obtain corresponding first processed images and second processed images;

[0039] Use an image registration algorithm to perform image correction and registration on the first processed image and the second processed image, and perform feature fusion on the registered first processed image and second processed image to obtain corresponding fusion data.

[0040] Further, the fire fighting strategy construction module includes:

[0041] Obtain fire fighting facility information of several areas where gas stations are located, where the fire fighting facility information includes the quantity information and corresponding type information of fire fighting robots;

[0042] Construct a fire fighting robot set according to the quantity information and corresponding type information of the fire fighting robots, construct a task sequence according to the fire fighting robot set, and perform strategy combination on the constructed task sequence and the fire fighting robot set to construct a corresponding fire fighting strategy set.

[0043] The present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned gas station fire fighting control method is implemented.

[0044] The present invention also provides a computer, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned gas station fire control method is implemented.

[0045] In the gas station fire control method, system, readable storage medium and computer of the present invention, by obtaining the first fire scene image and the second fire scene image, extracting features from the two different fire scene images, and using the feature extraction results to optimize the constructed convolutional neural network model and image detection model, the accuracy of feature extraction is improved, so that the model can more effectively capture important feature information to improve the perception ability of the model; by processing the fire fighting facility information in the area where the gas station is located, according to the fire fighting facility information and the constructed fire fighting task set, a corresponding fire fighting strategy set is constructed, and the fire fighting strategy set, fusion data, convolutional neural network optimization model and image detection optimization model are fused to construct a fire fighting detection model, and the fire control of the target gas station is realized through the fire fighting detection model, the efficiency of task processing is improved, and the allocation cost is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the gas station fire control method in the first embodiment of the present invention;

[0047] Figure 2 is Figure 1 a detailed flowchart of step S101 in

[0048] Figure 3 is Figure 1 a detailed flowchart of step S102 in

[0049] Figure 4 is Figure 1 a detailed flowchart of step S103 in

[0050] Figure 5 is Figure 1 a detailed flowchart of step S104 in

[0051] Figure 6 is a structural block diagram of the gas station fire control system in the second embodiment of the present invention;

[0052] Figure 7 is a structural block diagram of the computer in the third embodiment of the present invention.

[0053] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0056] Embodiment 1

[0057] Please refer to Figure 1 , which shows the gas station fire control method in the first embodiment of the present invention. The method specifically includes steps S101 to S105:

[0058] S101, obtain a plurality of first fire scene images and second fire scene images, and construct a convolutional neural network model. Input each of the first fire scene images into the convolutional neural network model so that the convolutional neural network model performs model optimization to obtain a convolutional neural network optimized model;

[0059] Further, please refer to Figure 2 , the step S101 specifically includes steps S1011~S1012:

[0060] S1011, input each of the first fire scene images into the convolutional neural network model so that the convolutional neural network model extracts features from each of the first fire scene images to obtain corresponding one-dimensional feature maps and two-dimensional feature maps;

[0061] S1012, add a hybrid attention algorithm to the backbone network module of the convolutional neural network model, perform depth convolution on the one-dimensional feature map and the two-dimensional feature map, and perform model optimization on the processed convolutional neural network model to obtain a convolutional neural network optimized model.

[0062] In specific implementation, fire scene images are collected by a preset image acquisition device. Among them, the image acquisition device includes but is not limited to devices with image acquisition functions such as cameras and infrared image sensors. In this embodiment, visible light images of the fire scene are collected by a camera, and near-infrared images of the same fire scene are collected by an infrared camera;

[0063] Further, a convolutional neural network model is constructed. To avoid the imbalance in the data distribution of the number of samples in visible light images, each first fire scene image is input into the convolutional neural network model, and the channel attention algorithm and spatial attention algorithm in the convolutional neural network model are used to perform image processing on each first fire scene image, so as to obtain the one-dimensional feature map and two-dimensional feature map corresponding to each first fire scene image. It can be understood that by adaptively learning the channel correlation and spatial importance of the input feature map, the accuracy of feature extraction is improved at the same time, so that the model can more effectively capture important feature information to improve the perception ability of the model;

[0064] Specifically, a hybrid attention algorithm (in this application, this algorithm is obtained by optimizing the CBAM algorithm using depthwise separable convolution) is added to the backbone network module of the convolutional neural network model, and deep convolution is performed using the above-obtained one-dimensional feature map and two-dimensional feature map, and the result of the deep convolution is used to optimize the processed convolutional neural network model to obtain a convolutional neural network optimized model. It can be understood that by adding the hybrid attention algorithm, the structure of the backbone network is made richer, and the network can maintain better stability for changes and perturbations of the input image, thereby increasing the generalization ability of the model.

[0065] S102. Construct an image detection model, and optimize the image detection model based on each of the second fire scene images to obtain an optimized image detection model;

[0066] Further, please refer to Figure 3 and the specific steps of step S102 include steps S1021 to S1023:

[0067] S1021. Perform image processing on each of the second fire scene images to construct a data matrix for each of the second fire scene images;

[0068] S1022. Based on the data matrix, calculate the weights and perform image segmentation on each of the second fire scene images respectively to obtain a number of segmented images, and perform clustering processing on each of the segmented images to obtain corresponding clustering results;

[0069] S1023. Input the clustering results into the image detection model for model optimization to obtain an optimized image detection model.

[0070] In specific implementation, an image detection model is pre-constructed, image processing is performed on each second fire scene image, a similarity matrix of the image is constructed using the Euclidean distance, and the similarity matrix is normalized to obtain a corresponding normalized Laplacian matrix, and an adjacency matrix is constructed using the K eigenvector with the largest eigenvalues in the normalized Laplacian matrix;

[0071] Specifically, according to the obtained adjacency matrix, weight calculation is performed on each second fire scene image, and image segmentation is carried out on the images according to the smallest and most uniform weights to cut them into different sub-images. Clustering processing is performed on each sub-image to obtain the corresponding clustering results. The clustering results are input into the above-mentioned constructed image detection model for model optimization. The sparse subspace clustering algorithm is used to combine the clustering results with the image detection model, perform low-dimensional representation on high-dimensional data, and allocate data points to different subspaces through clustering, thereby improving the processing efficiency of the image detection model.

[0072] S103. Extract features from each of the first fire scene images and each of the second fire scene images, and use an image registration algorithm to process the feature extraction results to obtain corresponding fusion data.

[0073] Further, please refer to Figure 4 , and the step S103 specifically includes steps S1031 to S1032:

[0074] S1031. Perform data cleaning and data processing on each of the first fire scene images and each of the second fire scene images to obtain corresponding first processed images and second processed images.

[0075] S1032. Use an image registration algorithm to perform image correction and registration on the first processed image and the second processed image, and perform feature fusion on the registered first processed image and second processed image to obtain corresponding fusion data.

[0076] In specific implementation, data cleaning and data enhancement are performed on each of the first fire scene images and each of the second fire scene images. The purpose is to eliminate redundancy in the data, fill in gaps, improve the quality and reliability of the data, provide better input for subsequent image fusion, and improve the fusion effect and visual perception quality.

[0077] Specifically, an image registration algorithm is used to perform image registration on the first processed image and the second processed image to eliminate distortion and deformation in the images. A reference coordinate system is pre-constructed, and the first processed image and the second processed image are mapped to the same coordinate system in different directions or angles by using the reference coordinate system (in this embodiment, the image registration algorithm includes but is not limited to a feature matching algorithm and a least squares fitting algorithm). The feature regions of the images after image registration are extracted, the feature regions are subjected to feature fusion, the feature space information of the two images is subjected to correlation and complementary feature extraction, and feature-level fusion is performed using the extracted features, thereby making up for the deficiencies of single features, reducing feature redundancy and noise, and improving the robustness and generalization ability of the model.

[0078] Specifically, a multi-channel fusion algorithm is constructed to restore the data samples of the obtained feature regions through a step-by-step denoising process in the multi-channel fusion algorithm, and a diffusion model is generated by the multi-channel fusion algorithm to implement the fusion processing of the data. The obtained feature-level fusion result is integrated with the multi-channel fusion result of this time to obtain the corresponding fusion data.

[0079] S104. Obtain the fire-fighting facility information of the areas where several gas stations are located, and construct a fire-fighting task set, and construct a corresponding fire-fighting strategy set according to the fire-fighting facility information and the fire-fighting task set;

[0080] Further, please refer to Figure 5 , and the step S104 specifically includes steps S1041 to S1042:

[0081] S1041. Obtain the fire-fighting facility information of the areas where several gas stations are located. Among them, the fire-fighting facility information includes the quantity information and the corresponding type information of the fire-fighting robots;

[0082] S1042. Construct a fire-fighting robot set according to the quantity information and the corresponding type information of the fire-fighting robots, and construct a task sequence according to the fire-fighting robot set, and perform a strategy combination on the constructed task sequence and the fire-fighting robot set to construct a corresponding fire-fighting strategy set.

[0083] In specific implementation, obtain the fire-fighting facility information of the areas where several gas stations are located. Among them, the fire-fighting facility information includes the quantity information corresponding to the fire-fighting robots pre-placed in the area, the type information of the fire-fighting robots, and the traveling speed of the fire-fighting robots. Construct a fire-fighting robot set with the quantity information, type information, and traveling speed , where the fire-fighting robot is represented by , , three groups of data. Among them, represents the quantity of the fire-fighting robots, represents the type of the fire-fighting robots, represents the traveling speed of the fire-fighting robots. Construct a corresponding task sequence according to the fire-fighting robot set, generate relevant information such as the quantity, processing level, and execution time of the corresponding rescue tasks for the fire-fighting robot set, and combine various types of information of the rescue tasks to obtain the corresponding task sequence;

[0084] Specifically, define the time set corresponding to the fire-fighting robot set. This time set represents the time when the fire-fighting robots start to execute tasks according to their own preset path sets. Among them, ;

[0085] Define the set of time windows corresponding to the set of fire-fighting robots , , where this set of time windows indicates that the fire-fighting robot can only execute a task within the time period during which the task exists. Among them, represents the time period during which the task exists, and the fire-fighting robot can only execute this task during this time period , represents the end time of the task , represents the start time of the task ;

[0086] Process the constructed task sequence and the set of fire-fighting robots using a bidding algorithm to obtain the corresponding bidding set , where represents the task number currently bid for by the fire-fighting robot that is the owner of this bidding set , represents the number of elements in the bidding set, that is, the number of tasks. For example: indicates that the fire-fighting robot currently bids for the 1st task as task 2.

[0087] Integrate the data obtained above and calculate the total score obtained by the fire-fighting robot after adding the task to the bidding set and completing this task :

[0088] ;

[0089] ;

[0090] In the formula, represents the total score obtained by the fire-fighting robot completing the tasks in the order of the bidding set , , respectively represent the score and cost obtained by the fire-fighting robot after completing the task , which are calculated for this fire-fighting robot through a pre-constructed database represents the task after adding it to the bidding set and the total score obtained by the fire-fighting robot after completing the task.

[0091] After obtaining the total scores of all fire-fighting robots, sort according to the score values to construct the corresponding fire-fighting strategy set.

[0092] S105, fuse the fire protection policy set, the fusion data, the optimized convolutional neural network model, and the optimized image detection model to construct a fire detection model, and implement fire control for the target gas station through the fire detection model.

[0093] In specific implementation, fuse the obtained fire protection policy set, fusion data, optimized convolutional neural network model, and optimized image detection model. Use the fusion data to combine the two models to implement image processing for different fire scene scenarios, improve the processing efficiency, and at the same time improve the accuracy and robustness of the model. Use the combined fire detection model to implement fire control for the target gas station through the fire detection model.

[0094] In summary, for the gas station fire control method in the above embodiments of the present invention, by obtaining the first fire scene image and the second fire scene image, extracting features from the two different fire scene images, and using the feature extraction results to optimize the constructed convolutional neural network model and image detection model, the accuracy of feature extraction is improved, so that the model can capture important feature information more effectively, thereby improving the perception ability of the model; by processing the fire protection facility information in the area where the gas station is located, constructing a corresponding fire protection policy set according to the fire protection facility information and the constructed fire protection task set, fusing the fire protection policy set, fusion data, optimized convolutional neural network model, and optimized image detection model to construct a fire detection model, and implementing fire control for the target gas station through the fire detection model, the efficiency of task processing is improved and the allocation cost is reduced.

[0095] Embodiment 2

[0096] On the other hand, the present invention also proposes a gas station fire control system, please refer to Figure 6 , which shows the gas station fire control system in the second embodiment of the present invention. The system includes:

[0097] The first model construction module 11 is used to obtain a plurality of first fire scene images and second fire scene images, and construct a convolutional neural network model. Input each of the first fire scene images into the convolutional neural network model, so that the convolutional neural network model performs model optimization to obtain an optimized convolutional neural network model;

[0098] Further, the first model construction module 11 includes:

[0099] The feature extraction unit is used to input each of the first fire scene images into the convolutional neural network model, so that the convolutional neural network model performs feature extraction on each of the first fire scene images to obtain corresponding one-dimensional feature maps and two-dimensional feature maps;

[0100] A model optimization unit for adding a hybrid attention algorithm to the backbone network module of the convolutional neural network model, performing depth convolution on the one-dimensional feature map and the two-dimensional feature map, and optimizing the processed convolutional neural network model with the depth convolution result to obtain an optimized convolutional neural network model.

[0101] A second model construction module 12 for constructing an image detection model and optimizing the image detection model based on each of the second fire scene images to obtain an optimized image detection model;

[0102] Further, the second model construction module 12 includes:

[0103] An image processing unit for performing image processing on each of the second fire scene images to construct a data matrix for each of the second fire scene images;

[0104] An image segmentation unit for calculating weights and segmenting each of the second fire scene images based on the data matrix to obtain a number of segmented images, and performing clustering processing on each of the segmented images to obtain corresponding clustering results;

[0105] A clustering processing unit for inputting the clustering results into the image detection model for model optimization to obtain an optimized image detection model.

[0106] A data fusion module 13 for extracting features from each of the first fire scene images and each of the second fire scene images, and performing data processing on the feature extraction results using an image registration algorithm to obtain corresponding fusion data;

[0107] Further, the data fusion module 13 includes:

[0108] Performing data cleaning and data processing on each of the first fire scene images and each of the second fire scene images to obtain corresponding first processed images and second processed images;

[0109] Performing image correction and registration on the first processed image and the second processed image using an image registration algorithm, and performing feature fusion on the registered first processed image and second processed image to obtain corresponding fusion data.

[0110] A fire protection strategy construction module 14 for obtaining fire protection facility information in areas where a number of gas stations are located, constructing a fire protection task set, and constructing a corresponding fire protection strategy set based on the fire protection facility information and the fire protection task set;

[0111] Further, the fire protection strategy construction module 14 includes:

[0112] Obtain the fire-fighting facility information of the areas where several gas stations are located. Among them, the fire-fighting facility information includes the quantity information of fire-fighting robots and the corresponding type information.

[0113] Construct a fire-fighting robot set according to the quantity information of the fire-fighting robots and the corresponding type information, construct a task sequence according to the fire-fighting robot set, and perform a strategy combination of the constructed task sequence and the fire-fighting robot set to construct a corresponding fire-fighting strategy set.

[0114] The fire control module 15 is used to perform model fusion on the fire-fighting strategy set, the fusion data, the convolutional neural network optimization model, and the image detection optimization model to construct a fire detection model, and realize the fire control of the target gas station through the fire detection model.

[0115] The functions or operation steps implemented when the above-mentioned modules and units are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0116] The gas station fire control system provided by the embodiments of the present invention has the same implementation principle and the same technical effects as those in the foregoing method embodiments. For a brief description, for the parts not mentioned in the system embodiments, reference may be made to the corresponding contents in the foregoing method embodiments.

[0117] Embodiment III

[0118] The present invention also proposes a computer. Please refer to Figure 7 , which shows the computer in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned gas station fire control method is realized.

[0119] Among them, the memory 10 includes at least one type of readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 10 may be an internal storage unit of the computer in some embodiments, such as the hard disk of the computer. The memory 10 may also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 may also include both the internal storage unit of the computer and the external storage device. The memory 10 can be used not only to store application software installed on the computer and various types of data, but also to temporarily store data that has been output or will be output.

[0120] Among them, in some embodiments, the processor 20 may be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0121] It should be noted that Figure 7 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0122] An embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the gas station fire control method as described above.

[0123] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0124] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0125] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0126] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0127] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A gas station fire control method, characterized in that: include: Acquire a plurality of first fire scene images and a second fire scene image, and construct a convolutional neural network model, and input each of the first fire scene images into the convolutional neural network model so that the convolutional neural network model is optimized to obtain a convolutional neural network optimization model; Constructing an image detection model, and optimizing the image detection model based on each of the second fire scene images to obtain an image detection optimization model; Extracting features from each of the first fire scene images and each of the second fire scene images, and performing data processing on the feature extraction results using an image registration algorithm to obtain corresponding fused data; Obtaining firefighting facility information of the areas where several gas stations are located, and constructing a firefighting task set, and constructing a corresponding firefighting strategy set according to the firefighting facility information and the firefighting task set, wherein the steps of obtaining firefighting facility information of the areas where several gas stations are located, and constructing a firefighting task set, and constructing a corresponding firefighting strategy set according to the firefighting facility information and the firefighting task set include: Obtaining firefighting facility information in areas where several gas stations are located, wherein the firefighting facility information includes the number of firefighting robots, the type of firefighting robots, and the driving speed of the firefighting robots; A firefighting robot set is constructed based on the number information of the firefighting robots, the type information of the firefighting robots, and the driving speed of the firefighting robots. , among which, fire fighting robot Depend on , , Three sets of data show that represents the number of firefighting robots, Indicates the type of fire fighting robot. Indicates the driving speed of the fire-fighting robot; Constructing a corresponding task sequence according to the fire-fighting robot set, generating the number, processing level and execution time of corresponding rescue tasks for the fire-fighting robot set, and combining various types of information of the rescue tasks to obtain a corresponding task sequence; Define the time set corresponding to the fire fighting robot set , the time set represents the time when the fire-fighting robot starts to perform the task according to its preset path set, where ; Define the time window set corresponding to the fire fighting robot set , , the time window set represents the fire fighting robot A task can only be executed during the time period in which the task exists, where Indicates the task The firefighting robot can only perform the task during this period of time. , Representation Task The end time of Representation Task The start time of The bidding algorithm is used to process the constructed task sequence and the firefighting robot set to obtain the corresponding bidding set. ,in, Indicates the owner of the bidding set, the fire robot The task number obtained by the current bidding, Indicates the number of elements in the bidding set, that is, the number of tasks; The above data are integrated to calculate the fire fighting robot In the task Complete the task after adding it to the bidding set Total score obtained: ； ； In the formula, Fire fighting robot By bidding collection The total score of completing the tasks in order, , Fire fighting robots Complete the task The scores and costs after the fire fighting robot are calculated through the pre-built database. Representation Task Add to Bid Collection Rear fire fighting robot The total score after completing the task; After obtaining the total scores of all firefighting robots, they are sorted according to the scores to construct the corresponding firefighting strategy set; The fire strategy set, the fusion data, the convolutional neural network optimization model and the image detection optimization model are fused to construct a fire detection model, and fire control of the target gas station is achieved through the fire detection model.

2. The fire control method for a gas station according to claim 1, characterized in that: The step of inputting each of the first fire scene images into the convolutional neural network model so as to optimize the convolutional neural network model to obtain a convolutional neural network optimization model comprises: Inputting each of the first fire scene images into the convolutional neural network model, so that the convolutional neural network model performs feature extraction on each of the first fire scene images to obtain a corresponding one-dimensional feature map and a two-dimensional feature map; A hybrid attention algorithm is added to the backbone network module of the convolutional neural network model, and the one-dimensional feature map and the two-dimensional feature map are deeply convolved. The deep convolution result is used to optimize the processed convolutional neural network model to obtain a convolutional neural network optimization model.

3. The fire control method for a gas station according to claim 1, characterized in that: The step of optimizing the image detection model based on each of the second fire scene images to obtain an image detection optimization model includes: Performing image processing on each of the second fire scene images to construct a data matrix of each of the second fire scene images; Based on the data matrix, weight calculation and image segmentation are performed on each of the second fire scene images to obtain a plurality of segmented images, and clustering processing is performed on each of the segmented images to obtain a corresponding clustering result; The clustering results are input into the image detection model for model optimization to obtain an image detection optimization model.

4. The fire control method for a gas station according to claim 1, characterized in that: The steps of extracting features from each of the first fire scene images and each of the second fire scene images, and performing data processing on the feature extraction results using an image registration algorithm to obtain corresponding fused data include: Performing data cleaning and data processing on each of the first fire scene images and each of the second fire scene images to obtain a corresponding first processed image and a second processed image; The first processed image and the second processed image are corrected and registered by using an image registration algorithm, and the registered first processed image and the second processed image are feature fused to obtain corresponding fused data.

5. A gas station fire control system, characterized in that: include: A first model building module is used to obtain a plurality of first fire scene images and a second fire scene image, and to build a convolutional neural network model, and to input each of the first fire scene images into the convolutional neural network model so as to optimize the convolutional neural network model to obtain a convolutional neural network optimization model; A second model building module is used to build an image detection model, and optimize the image detection model based on each of the second fire scene images to obtain an image detection optimization model; A data fusion module, used for extracting features from each of the first fire scene images and each of the second fire scene images, and performing data processing on the feature extraction results using an image registration algorithm to obtain corresponding fused data; The fire strategy building module is used to obtain the fire facility information of the area where several gas stations are located, and to build a fire task set, and to build a corresponding fire strategy set according to the fire facility information and the fire task set, wherein the fire strategy building module is specifically used to: Obtaining firefighting facility information in areas where several gas stations are located, wherein the firefighting facility information includes the number of firefighting robots, the type of firefighting robots, and the driving speed of the firefighting robots; A firefighting robot set is constructed based on the number information of the firefighting robots, the type information of the firefighting robots, and the driving speed of the firefighting robots. , among which, fire fighting robot Depend on , , Three sets of data show that represents the number of firefighting robots, Indicates the type of fire fighting robot. Indicates the driving speed of the fire-fighting robot; Constructing a corresponding task sequence according to the fire-fighting robot set, generating the number, processing level and execution time of corresponding rescue tasks for the fire-fighting robot set, and combining various types of information of the rescue tasks to obtain a corresponding task sequence; Define the time set corresponding to the fire fighting robot set , the time set represents the time when the fire-fighting robot starts to perform the task according to its preset path set, where ; Define the time window set corresponding to the fire fighting robot set , , the time window set represents the fire fighting robot A task can only be executed during the time period in which the task exists, where Representation Task The firefighting robot can only perform the task during this period of time. , Representation Task The end time of Representation Task The start time of The bidding algorithm is used to process the constructed task sequence and the firefighting robot set to obtain the corresponding bidding set. ,in, Indicates the owner of the bidding set, the fire robot The task number obtained by the current bidding, Indicates the number of elements in the bidding set, that is, the number of tasks; The above data are integrated to calculate the fire fighting robot In the task Complete the task after adding it to the bidding set Total score obtained: ； ； In the formula, Fire fighting robot By bidding collection The total score of completing the tasks in order, , Fire fighting robots Complete the task The scores and costs after the fire fighting robot are calculated through the pre-built database. Representation Task Add to Bid Collection Rear fire fighting robot The total score after completing the task; After obtaining the total scores of all firefighting robots, they are sorted according to the scores to construct the corresponding firefighting strategy set; The fire control module is used to fuse the fire strategy set, the fusion data, the convolutional neural network optimization model and the image detection optimization model to construct a fire detection model, and realize fire control of the target gas station through the fire detection model.

6. The gas station fire control system according to claim 5, characterized in that: The first model building module includes: A feature extraction unit, used for inputting each of the first fire scene images into the convolutional neural network model, so that the convolutional neural network model performs feature extraction on each of the first fire scene images to obtain a corresponding one-dimensional feature map and a two-dimensional feature map; A model optimization unit is used to add a hybrid attention algorithm to the backbone network module of the convolutional neural network model, and perform deep convolution on the one-dimensional feature map and the two-dimensional feature map, and optimize the processed convolutional neural network model using the deep convolution result to obtain a convolutional neural network optimization model.

7. The gas station fire control system according to claim 5, characterized in that: The second model building module includes: An image processing unit, used for performing image processing on each of the second fire scene images to construct a data matrix of each of the second fire scene images; An image segmentation unit, used for performing weight calculation and image segmentation on each of the second fire scene images based on the data matrix to obtain a plurality of segmented images, and performing clustering processing on each of the segmented images to obtain a corresponding clustering result; A clustering processing unit is used to input the clustering result into the image detection model for model optimization to obtain an image detection optimization model.

8. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the gas station fire control method as described in any one of claims 1 to 4 is implemented.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the gas station fire control method as described in any one of claims 1 to 4 is implemented.

Images