Image recognition method and system based on power transmission service scene

Abstract

The embodiment of the invention provides an image recognition method and system based on a power transmission service scene, and relates to the technical field of image recognition. The image recognition method comprises the following steps: training a convolutional neural network model for executing an image recognition task by adopting a training image; acquiring an image of a to-be-identified power transmission service scene; and inputting the image of a to-be-identified power transmission service scene into the convolutional neural network model, and outputting an image identification result. According to the image recognition method and system, learning is carried out through the convolutional neural network, and the learning model of power transmission service scene image recognition is constructed, so that power transmission service scene image recognition is more accurate and efficient.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to an image recognition method and system based on a power transmission business scenario. Background Art

[0002] In the power system, the safe operation of transmission lines is of vital importance. However, due to factors such as long lines, large spans, and complex environments, traditional inspection methods have problems such as low efficiency, high cost, and difficulty in timely detection of hidden dangers. Therefore, the transmission business scene monitoring technology based on image recognition has emerged. It uses advanced image processing and recognition algorithms to monitor and analyze the transmission lines and their surrounding environment in real time to improve the efficiency and accuracy of inspections. In the existing technology, the accuracy of image recognition is not high enough, and the judgment of problems generated during inspections is not accurate enough. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide an image recognition method and system based on a power transmission business scenario. The image recognition method and system learn through a convolutional neural network to construct a learning model for image recognition in power transmission business scenarios, so that image recognition in power transmission business scenarios is more accurate and efficient.

[0004] In order to achieve the above object, an embodiment of the present invention provides an image recognition method based on a power transmission business scenario, the image recognition method comprising:

[0005] Using training images to train a convolutional neural network model that performs image recognition tasks;

[0006] Acquire an image of a power transmission business scene to be identified;

[0007] The image of the power transmission business scene to be identified is input into the convolutional neural network model, and the image recognition result is output.

[0008] Optionally, a convolutional neural network model for performing an image recognition task is trained using a training image, including:

[0009] Initialize the convolutional neural network model;

[0010] Using a training set to train the convolutional neural network model;

[0011] Using a test set to test the trained convolutional neural network model;

[0012] Determine whether the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold;

[0013] When it is determined that the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold, the convolutional neural network model is output.

[0014] Optionally, inputting the image of the power transmission business scene to be identified into the convolutional neural network model, and outputting the image recognition result, comprises:

[0015] Deploy the convolutional neural network model to a business machine;

[0016] Inputting the image of the power transmission business scene to be identified into the convolutional neural network model, and the convolutional neural network model outputs a prediction result of the image;

[0017] The prediction result with the largest number of occurrences among the prediction results is obtained as the final recognition result of the image.

[0018] Optionally, the image recognition method further includes:

[0019] Scaling the image size of the power transmission business scene to be identified to the same size and normalizing the image pixel value size;

[0020] The edge of the image of the power transmission business scene to be identified is padded with 0 pixels and then cropped, and the image is randomly flipped horizontally.

[0021] Optionally, the image recognition method further includes:

[0022] According to formula (1), the loss function is determined:

[0023]

[0024] Among them, loss is the loss function, p i is the predicted value, y i is the actual observed value, and n is the total number of samples.

[0025] On the other hand, the present invention further provides an image recognition system based on a power transmission business scenario, wherein the image recognition system comprises a processor for executing any of the above-mentioned image recognition methods.

[0026] In yet another aspect, the present invention further provides an electronic terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to execute any of the above-described methods when executing the program.

[0027] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which is used to execute any of the above methods when executed by a processor.

[0028] Through the above technical solution, the embodiment of the present invention provides an image recognition method and system based on the power transmission business scenario. By using training images to train a convolutional neural network model that performs image recognition tasks, an image of the power transmission business scenario to be identified is obtained, the image of the power transmission business scenario to be identified is input into the convolutional neural network model, and the image recognition result is output. The image recognition method and system learns through a convolutional neural network to construct a learning model for image recognition of power transmission business scenarios, so that image recognition of power transmission business scenarios is more accurate and efficient.

[0029] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0031] Figure 1 is a flow chart of an image recognition method according to an embodiment of the present invention;

[0032] Figure 2 is a flow chart of training a convolutional neural network model according to an embodiment of the present invention;

[0033] Figure 3 is a flow chart of outputting image recognition results according to one embodiment of the present invention;

[0034] Figure 4 The flowchart of processing an image of a power transmission service scene to be identified according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0036] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0037] like Figure 1 The figure is a flow chart of an image recognition method according to an embodiment of the present invention. Figure 1 In the method, the image recognition method comprises:

[0038] In step S10, a convolutional neural network model for performing an image recognition task is trained using a training image;

[0039] In step S20, an image of a power transmission service scene to be identified is acquired;

[0040] In step S30, the image of the power transmission business scene to be identified is input into the convolutional neural network model, and the image recognition result is output.

[0041] In this Figure 1 In the method shown, step S10 is used to train a convolutional neural network model for performing an image recognition task using a training image. The specific method for training the convolutional neural network model may be in various forms known to those skilled in the art. In one example of the present invention, training the convolutional neural network model may include: Figure 2 The steps shown in this Figure 2 middle,

[0042] In step S11, the convolutional neural network model is initialized;

[0043] In step S12, the convolutional neural network model is trained using a training set;

[0044] In step S13, the trained convolutional neural network model is tested using a test set;

[0045] In step S14, it is determined whether the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold;

[0046] In step S15, when it is determined that the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold, the convolutional neural network model is output.

[0047] Step S20 may be used to obtain an image of a power transmission business scene to be identified. Step S30 may be used to input the image of the power transmission business scene to be identified into a convolutional neural network model and output an image recognition result. The specific manner of outputting the image recognition result may be in various forms known to persons skilled in the art. In one example of the present invention, the specific manner of outputting the image recognition result may include: Figure 3 The steps shown in this Figure 3 middle,

[0048] In step S21, the convolutional neural network model is deployed on the business machine;

[0049] In step S22, the image of the power transmission business scene to be identified is input into the convolutional neural network model, and the convolutional neural network model outputs a prediction result of the image;

[0050] In step S23, the prediction result with the largest number of predictions is obtained as the final recognition result of the image.

[0051] In this embodiment, the image recognition method also includes the following steps for image processing: Figure 4 The steps shown in this Figure 4 middle,

[0052] In step S31, the image size of the power transmission business scene to be identified is scaled to the same size and the image pixel value size is normalized;

[0053] In step S32, the edge of the image of the power transmission business scene to be identified is padded with 0 pixels and then cropped, and the image is randomly flipped horizontally.

[0054] In this embodiment, in order to improve the recognition accuracy, the image recognition method determines the loss function through formula (1):

[0055]

[0056] Among them, loss is the loss function, p i is the predicted value, y i is the actual observed value, and n is the total number of samples.

[0057] On the other hand, the present invention also provides an image recognition system based on a power transmission business scenario, wherein the image recognition system includes a processor for executing any of the above-mentioned image recognition methods. The image recognition method may include: Figures 1 to 4 The steps shown. Figure 1 In the method, the image recognition method comprises:

[0058] In step S10, a convolutional neural network model for performing an image recognition task is trained using a training image;

[0059] In step S20, an image of a power transmission service scene to be identified is acquired;

[0060] In step S30, the image of the power transmission business scene to be identified is input into the convolutional neural network model, and the image recognition result is output.

[0061] In this Figure 1 In the method shown, step S10 is used to train a convolutional neural network model for performing an image recognition task using a training image. The specific method for training the convolutional neural network model may be in various forms known to those skilled in the art. In one example of the present invention, training the convolutional neural network model may include: Figure 2 The steps shown in this Figure 2 middle,

[0062] In step S11, the convolutional neural network model is initialized;

[0063] In step S12, the convolutional neural network model is trained using a training set;

[0064] In step S13, the trained convolutional neural network model is tested using a test set;

[0065] In step S14, it is determined whether the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold;

[0066] In step S15, when it is determined that the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold, the convolutional neural network model is output.

[0067] Step S20 may be used to obtain an image of a power transmission business scene to be identified. Step S30 may be used to input the image of the power transmission business scene to be identified into a convolutional neural network model and output an image recognition result. The specific manner of outputting the image recognition result may be in various forms known to persons skilled in the art. In one example of the present invention, the specific manner of outputting the image recognition result may include: Figure 3 The steps shown in this Figure 3 middle,

[0068] In step S21, the convolutional neural network model is deployed on the business machine;

[0069] In step S22, the image of the power transmission business scene to be identified is input into the convolutional neural network model, and the convolutional neural network model outputs a prediction result of the image;

[0070] In step S23, the prediction result with the largest number of predictions is obtained as the final recognition result of the image.

[0071] In this embodiment, the image recognition method also includes the following steps for image processing: Figure 4 The steps shown in this Figure 4 middle,

[0072] In step S31, the image size of the power transmission business scene to be identified is scaled to the same size and the image pixel value size is normalized;

[0073] In step S32, the edge of the image of the power transmission business scene to be identified is padded with 0 pixels and then cropped, and the image is randomly flipped horizontally.

[0074] In this embodiment, in order to improve the recognition accuracy, the image recognition method determines the loss function through formula (1):

[0075]

[0076] Among them, loss is the loss function, p i is the predicted value, y i is the actual observed value, and n is the total number of samples.

[0077] In yet another aspect, the present invention further provides an electronic terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to execute any of the above-described methods when executing the program.

[0078] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which is used to execute any of the above methods when executed by a processor.

[0079] Through the above technical solution, the embodiment of the present invention provides an image recognition method and system based on the power transmission business scenario. By using training images to train a convolutional neural network model that performs image recognition tasks, an image of the power transmission business scenario to be identified is obtained, the image of the power transmission business scenario to be identified is input into the convolutional neural network model, and the image recognition result is output. The image recognition method and system learns through a convolutional neural network to construct a learning model for image recognition of power transmission business scenarios, so that image recognition of power transmission business scenarios is more accurate and efficient.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0082] 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.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions 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.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0088] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An image recognition method based on a power transmission business scenario, characterized in that: The image recognition method comprises: Using training images to train a convolutional neural network model that performs image recognition tasks; Acquire an image of a power transmission business scene to be identified; The image of the power transmission business scene to be identified is input into the convolutional neural network model, and the image recognition result is output.

2. The image recognition method according to claim 1, characterized in that: The convolutional neural network model that performs image recognition tasks is trained using training images, including: Initialize the convolutional neural network model; Using a training set to train the convolutional neural network model; Using a test set to test the trained convolutional neural network model; Determine whether the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold; When it is determined that the prediction accuracy of the convolutional neural network model is greater than or equal to a preset accuracy threshold, the convolutional neural network model is output.

3. The image recognition method according to claim 1, characterized in that: Inputting the image of the power transmission business scene to be identified into the convolutional neural network model, and outputting the image recognition result, including: Deploy the convolutional neural network model to a business machine; Inputting the image of the power transmission business scene to be identified into the convolutional neural network model, and the convolutional neural network model outputs a prediction result of the image; The prediction result with the largest number of occurrences among the prediction results is obtained as the final recognition result of the image.

4. The image recognition method according to claim 1, characterized in that: The image recognition method further comprises: Scaling the image size of the power transmission business scene to be identified to the same size and normalizing the image pixel value size; The edge of the image of the power transmission business scene to be identified is padded with 0 pixels and then cropped, and the image is randomly flipped horizontally.

5. The image recognition method according to claim 1, characterized in that: The image recognition method further comprises: According to formula (1), the loss function is determined: Among them, loss is the loss function, p i is the predicted value, y i is the actual observed value, and n is the total number of samples.

6. An image recognition system based on power transmission business scenarios, characterized in that: The image recognition system comprises a processor, configured to execute the image recognition method according to any one of claims 1 to 5.

7. An electronic terminal comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, it is used to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it is used to execute the method described in any one of claims 1 to 5.

Images