Electric power operation scene element lightweight detection method

Abstract

The invention relates to an electric power work scene element lightweight detection method comprising the following steps: collecting an electric power work scene image sample, and labeling elements in the image sample; preprocessing the electric power operation scene image sample; carrying out lightweight improvement on the YOLOv5s model, and constructing a lightweight power operation scene element detection model based on the YOLOv5s model after the lightweight improvement; training a lightweight electric power work scene element detection model through the preprocessed image sample to obtain a trained lightweight electric power work scene element detection model; and collecting an electric power operation scene image sample in real time, and carrying out element detection through the trained lightweight electric power operation scene element detection model.

Description

Technical Field

[0001] The invention relates to a lightweight detection method for elements of an electric power operation scene, and belongs to the technical field of safety management and control of electric power operations. Background Art

[0002] There are dangerous factors such as live areas at power operation sites, and power operations require real-time safety management and control by dedicated personnel. With the development of image processing technology, some power operation risk identification algorithms have been proposed, which provide a basis for realizing intelligent safety management and control at power operation sites.

[0003] The key link of intelligent safety control at power operation sites lies in the accurate detection of various elements. The current element detection effect cannot be promoted and applied. The main reasons include:

[0004] The quality of the sample library of power operation scenes is not high. Most of the current samples are collected by fixed cameras, with limited shooting angles, and there are problems such as being unable to face the operators directly and being blocked by live equipment, which affects the detection accuracy; power operation images have high requirements for pre-processing methods such as image enhancement. Power operation scenes are complex and changeable, and there are factors such as dark light environments and high light ratio environments that affect image quality. Appropriate image enhancement measures need to be taken; there is a lack of efficient and lightweight detection algorithms for power operation scene elements. Due to the high real-time requirements for power operation safety management and control, the detection algorithm for power operation scene elements needs to run on the edge side, and related research is not mature enough.

[0005] The invention patent with the publication number "CN116994095A" discloses a pre-training method and system suitable for target detection in power scenes, including: obtaining a clear power scene image dataset, which does not require manual annotation; after performing different pre-processing on the unlabeled images, the pre-processed images are input into multiple encoders, and multiple loss functions are designed to operate on the output of the encoders, so that the encoders can extract features from a large number of unlabeled power scene images, and finally obtain a pre-trained model for target detection tasks in power scenes; after fine-tuning the pre-trained model using a labeled power scene target detection dataset, a target detection model is obtained. This invention greatly reduces the training time of the target detection model, and at the same time obtains better performance compared to training on a single target detection dataset;

[0006] However, the above invention uses a pre-trained model. Due to the large changes in power scenarios, it is impossible to accurately detect elements that appear in small quantities in power scenarios. Summary of the invention

[0007] In order to solve the above problems existing in the prior art, the present invention proposes a lightweight detection method for elements of power operation scenes.

[0008] The technical solution of the present invention is as follows:

[0009] In one aspect, the present invention provides a method for lightweight detection of elements in a power operation scene, comprising the following steps:

[0010] Collect image samples of power operation scenes and annotate the elements in the image samples;

[0011] Preprocessing the power operation scene image samples;

[0012] The YOLOv5s model is lightweighted and improved, and a lightweight power operation scene element detection model is built based on the lightweighted and improved YOLOv5s model;

[0013] The lightweight power operation scene element detection model is trained by using the preprocessed image samples to obtain a trained lightweight power operation scene element detection model;

[0014] Collect power operation scene image samples in real time, and perform element detection through the trained lightweight power operation scene element detection model.

[0015] As a preferred embodiment of the present invention, the elements annotated in the image sample include: various substation equipment, operators, operator protective equipment, and operator working tools.

[0016] As a preferred embodiment of the present invention, image enhancement preprocessing is performed on the image samples of the power operation scene in the dark light environment and the large light ratio environment, and the specific steps are as follows:

[0017] For the image samples of power operation scenes in dark light environments, the images are processed by the multi-scale Retinex algorithm, as shown in the following formula:

[0018]

[0019] Where: K is the total number of Gaussian center surround functions; S(x, y) is the original image; F(x, y) is the Gaussian filter function; w k represents the weighting coefficient of the kth Gaussian center surround function; r(x, y) represents the enhanced image sample of the power operation scene in the dark light environment.

[0020] As a preferred embodiment of the present invention, the image enhancement preprocessing steps of the electric power operation scene image sample in the large light ratio environment are:

[0021] Image enhancement is performed by normalizing the non-complete Beta function, as shown in the following formula:

[0022]

[0023]

[0024] Wherein: B(α, β) represents the incomplete Beta function; F(u) represents the normalized incomplete Beta function; after adaptively adjusting α and β according to different image samples, the function output value is applied to the enhancement processing of the image sample.

[0025] As a preferred embodiment of the present invention, the lightweight improvement steps of the YOLOv5s model are:

[0026] Replace the backbone network in the YOLOv5s model with a lightweight network consisting of several SandGlass modules and Conv modules;

[0027] The SandGlass module consists of two spatial depth convolution layers at the beginning and the end and two point-by-point convolution layers in the middle.

[0028] As a preferred embodiment of the present invention, the original loss function L of the lightweight power operation scene element detection model is EIoU Improved to L Focal-EIoU , as shown in the following formula:

[0029] L Focal-EIoU =IoU γ L EIoU

[0030]

[0031] Where: w c Indicates the width of the minimum bounding rectangle of the predicted bounding box and the true bounding box; h c represents the height of the minimum bounding rectangle between the predicted bounding box and the true bounding box; ρ represents the Euclidean distance; b represents the predicted bounding box; b gt The real bounding box; w represents the width of the predicted bounding box; w gt represents the width of the true bounding box; h represents the height of the predicted bounding box; h gt Represents the height of the true bounding box; IoU represents the intersection over union ratio of the predicted bounding box to the true bounding box; γ is a hyperparameter.

[0032] On the other hand, the present invention also provides a lightweight detection system for power operation scene elements, including a data acquisition module, a model building module, a model training module and a model output module;

[0033] The data acquisition module is used to collect power operation scene image samples, annotate elements in the image samples, and pre-process the power operation scene image samples;

[0034] The model building module is used to perform lightweight improvement on the YOLOv5s model, and to build a lightweight power operation scene element detection model based on the lightweight improved YOLOv5s model;

[0035] The model training module is used to train the lightweight power operation scene element detection model through the preprocessed image samples to obtain a trained lightweight power operation scene element detection model;

[0036] The model output module is used to collect power operation scene image samples in real time, and perform element detection through a trained lightweight power operation scene element detection model.

[0037] As a preferred embodiment of the present invention, the lightweight improvement steps of the YOLOv5s model are:

[0038] Replace the backbone network in the YOLOv5s model with a lightweight network consisting of several SandGlass modules and Conv modules;

[0039] The SandGlass module consists of two spatial depth convolution layers at the beginning and the end and two point-by-point convolution layers in the middle.

[0040] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0041] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0042] The present invention has the following beneficial effects:

[0043] 1. This paper proposes a low-quality image enhancement method in dark light environment and high light ratio environment, which further improves the quality of the data set; improves the YOLOv5s model, improves the lightweight deployment potential of the model by optimizing the backbone network, and improves the effect of the model on the detection of elements in the power operation scene by optimizing the loss function, providing an algorithmic basis for the safe and intelligent management and control of the power operation scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of the method of the present invention;

[0045] Figure 2 This is a schematic diagram of the improved YOLOv5s model structure of the present invention;

[0046] Figure 3This is a schematic diagram of the SandGlass module structure of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be understood that the step numbers used in this article are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0049] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0050] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0051] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0052] Embodiment 1:

[0053] See also Figure 1 , a lightweight detection method for elements in a power operation scene, comprising the following steps:

[0054] Collect image samples of power operation scenes and annotate the elements in the image samples;

[0055] Preprocessing the power operation scene image samples;

[0056] The YOLOv5s model is lightweighted and improved, and a lightweight power operation scene element detection model is built based on the lightweighted and improved YOLOv5s model;

[0057] The lightweight power operation scene element detection model is trained by using the preprocessed image samples to obtain a trained lightweight power operation scene element detection model;

[0058] Collect power operation scene image samples in real time, and perform element detection through the trained lightweight power operation scene element detection model.

[0059] As a preferred implementation of this embodiment, the elements annotated in the image sample include: various substation equipment, operators, protective equipment such as operator helmets, and operator working tools.

[0060] As a preferred implementation of this embodiment, image enhancement preprocessing is performed on the image samples of the power operation scene in the dark light environment and the large light ratio environment. The specific steps are as follows:

[0061] For the image samples of power operation scenes in dark light environments, the images are processed by the multi-scale Retinex algorithm, as shown in the following formula:

[0062]

[0063] Where: K is the total number of Gaussian center surround functions, which is 3 in this embodiment; S(x, y) is the original image; F(x, y) is the Gaussian filter function; w k represents the weighting coefficient of the kth Gaussian center surround function. Since three Gaussian center surround functions are set in this embodiment, r(x,y) represents the enhanced image sample of the power operation scene in the dark light environment.

[0064] As a preferred implementation of this embodiment, the image enhancement preprocessing steps of the power operation scene image sample in the large light ratio environment are:

[0065] Image enhancement is performed by normalizing the non-complete Beta function, as shown in the following formula:

[0066]

[0067]

[0068] Wherein: B(α, β) represents the incomplete Beta function; F(u) represents the normalized incomplete Beta function; after adaptively adjusting α and β according to the image samples in different high-light-ratio environments, the function output value is applied to the enhancement processing of the image samples, specifically, adjusting the grayscale of the image.

[0069] As a preferred implementation of this embodiment, the lightweight improvement steps of the YOLOv5s model are:

[0070] See also Figure 2, the backbone network in the YOLOv5s model is replaced with a lightweight network consisting of several SandGlass modules and Conv modules. Compared with the original backbone network, the use of C3 modules is reduced, achieving the purpose of reducing the amount of calculation;

[0071] See also Figure 3 The SandGlass module consists of two spatial depth convolutional layers at the beginning and the end and two continuous point-by-point convolutional layers in the middle, which can realize the dimension increase and decrease of the feature map.

[0072] As a preferred implementation of this embodiment, the original loss function L of the lightweight power operation scene element detection model is EIoU Improved to L Focal-EIoU , as shown in the following formula:

[0073] L Focal-EIoU =IoU γ L EIoU

[0074]

[0075] Where: w c Indicates the width of the minimum bounding rectangle of the predicted bounding box and the true bounding box; h c represents the height of the minimum bounding rectangle between the predicted bounding box and the true bounding box; ρ represents the Euclidean distance; b represents the predicted bounding box; b gt The real bounding box; w represents the width of the predicted bounding box; w gt represents the width of the true bounding box; h represents the height of the predicted bounding box; h gt Represents the height of the true bounding box; IoU represents the intersection over union ratio of the predicted bounding box to the true bounding box; γ is a hyperparameter with a value of 0.5.

[0076] After experiments, the effects of the lightweight YOLOv5s model used in this embodiment and other models are compared as shown in the following table:

[0077]

[0078] Embodiment 2:

[0079] A lightweight detection system for power operation scene elements, characterized by comprising a data acquisition module, a model building module, a model training module and a model output module;

[0080] The data acquisition module is used to collect power operation scene image samples, annotate elements in the image samples, and pre-process the power operation scene image samples;

[0081] The model building module is used to perform lightweight improvement on the YOLOv5s model, and to build a lightweight power operation scene element detection model based on the lightweight improved YOLOv5s model;

[0082] The model training module is used to train the lightweight power operation scene element detection model through the preprocessed image samples to obtain a trained lightweight power operation scene element detection model;

[0083] The model output module is used to collect power operation scene image samples in real time, and perform element detection through a trained lightweight power operation scene element detection model.

[0084] As a preferred implementation of this embodiment, the lightweight improvement steps of the YOLOv5s model are:

[0085] Replace the backbone network in the YOLOv5s model with a lightweight network consisting of several SandGlass modules and Conv modules;

[0086] The SandGlass module consists of two spatial depth convolution layers at the beginning and the end and two point-by-point convolution layers in the middle.

[0087] This system is used to implement the functions in the first embodiment, which will not be described in detail here.

[0088] Embodiment three:

[0089] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any embodiment of the present invention when executing the program;

[0090] Specifically, in this embodiment, an image acquisition device and an edge computing terminal are included;

[0091] The image acquisition device is movable, and the shooting direction should be facing the power operation area when in use. The image sample should include the operators and all substation equipment they may come into contact with, as well as all scenes of substation power operations.

[0092] A lightweight power operation scene element detection model is deployed inside the edge computing terminal. The image acquisition device transmits the acquired images to the edge computing terminal. The edge computing terminal runs the lightweight power operation scene element detection model to realize intelligent identification of elements in the substation power operation scene.

[0093] Embodiment 4:

[0094] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0095] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0096] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0099] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A lightweight detection method for power operation scene elements, characterized in that: The following steps are involved: Collect image samples of power operation scenes and annotate the elements in the image samples; Preprocessing the power operation scene image samples; The YOLOv5s model is lightweighted and improved, and a lightweight power operation scene element detection model is built based on the lightweighted and improved YOLOv5s model; The lightweight power operation scene element detection model is trained by using the preprocessed image samples to obtain a trained lightweight power operation scene element detection model; Collect power operation scene image samples in real time, and perform element detection through the trained lightweight power operation scene element detection model.

2. A method for lightweight detection of power operation scene elements according to claim 1, characterized in that: The elements annotated in the image sample include: various substation equipment, operators, operator protective equipment, and operator working tools.

3. The method for lightweight detection of power operation scene elements according to claim 1, characterized in that: Image enhancement preprocessing is performed on the image samples of power operation scenes in dark light environment and high light ratio environment. The specific steps are as follows: For the image samples of power operation scenes in dark light environments, the images are processed by the multi-scale Retinex algorithm, as shown in the following formula: Where: K is the total number of Gaussian center surround functions; S(x, y) is the original image; F(x, y) is the Gaussian filter function; w k represents the weighting coefficient of the kth Gaussian center surround function; r(x, y) represents the enhanced image sample of the power operation scene in the dark light environment.

4. A method for lightweight detection of power operation scene elements according to claim 3, characterized in that: The image enhancement preprocessing steps of the power operation scene image sample in the large light ratio environment are as follows: Image enhancement is performed by normalizing the non-complete Beta function, as shown in the following formula: F(u)=B -1 (α,β)*∫0 u t α-1 (1-t) β-1 dt,α>0,β<10 B(α,β)=∫0 1 t α-1 (1-t) β-1 dt Wherein: B(α, β) represents the incomplete Beta function; F(u) represents the normalized incomplete Beta function; after adaptively adjusting α and β according to different image samples, the function output value is applied to the enhancement processing of the image sample.

5. The method for lightweight detection of power operation scene elements according to claim 1 is characterized in that: The lightweight improvement steps of the YOLOv5s model are: Replace the backbone network in the YOLOv5s model with a lightweight network consisting of several SandG]ass modules and Conv modules; The SandGlass module consists of two spatial depth convolution layers at the beginning and the end and two point-by-point convolution layers in the middle.

6. A method for lightweight detection of power operation scene elements according to claim 5, characterized in that: The original loss function L of the lightweight power operation scene element detection model is EIoU Improved to L Focal-EIoU , as shown in the following formula: L Focal-EIoU =IoU γ L EIoU Where: w c Indicates the width of the minimum bounding rectangle of the predicted bounding box and the true bounding box; h c represents the height of the minimum bounding rectangle between the predicted bounding box and the true bounding box; ρ represents the Euclidean distance; b represents the predicted bounding box; b gt The real bounding box; w represents the width of the predicted bounding box; w gt represents the width of the true bounding box; h represents the height of the predicted bounding box; h gt Represents the height of the true bounding box; IoU represents the intersection over union ratio of the predicted bounding box to the true bounding box; γ is a hyperparameter.

7. A lightweight detection system for power operation scene elements, characterized in that: It includes data acquisition module, model building module, model training module and model output module; The data acquisition module is used to collect power operation scene image samples, annotate elements in the image samples, and pre-process the power operation scene image samples; The model building module is used to perform lightweight improvement on the YOLOv5s model, and to build a lightweight power operation scene element detection model based on the lightweight improved YOLOv5s model; The model training module is used to train the lightweight power operation scene element detection model through the preprocessed image samples to obtain a trained lightweight power operation scene element detection model; The model output module is used to collect power operation scene image samples in real time, and perform element detection through a trained lightweight power operation scene element detection model.

8. The lightweight detection system for power operation scene elements according to claim 7 is characterized in that: The lightweight improvement steps of the YOLOv5s model are: Replace the backbone network in the YOLOv5s model with a lightweight network consisting of several SandGlass modules and Conv modules; The SandGlass module consists of two spatial depth convolution layers at the beginning and the end and two point-by-point convolution layers in the middle.

9. An electronic device 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 program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images