CN116704218A - Power industry target detection method and device - Google Patents
Power industry target detection method and device Download PDFInfo
- Publication number
- CN116704218A CN116704218A CN202310636391.5A CN202310636391A CN116704218A CN 116704218 A CN116704218 A CN 116704218A CN 202310636391 A CN202310636391 A CN 202310636391A CN 116704218 A CN116704218 A CN 116704218A
- Authority
- CN
- China
- Prior art keywords
- target detection
- power industry
- training data
- training
- scene image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 135
- 238000012549 training Methods 0.000 claims abstract description 97
- 238000002372 labelling Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims description 43
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000005457 optimization Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of power industry target detection, and particularly provides a power industry target detection method and device, comprising the following steps: acquiring a scene image to be detected; taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model; the detection result comprises at least one of the following: the location and class of the target. The technical scheme provided by the invention solves the problems of large labeling quantity and low training accuracy in the target detection task of the power industry, has wider applicability, provides a more efficient and accurate target detection solution, and promotes the intelligent development of the power industry and other fields.
Description
Technical Field
The invention relates to the technical field of power industry target detection, in particular to a power industry target detection method and device.
Background
In the power industry, a target detection task plays an important role and is used for realizing intelligent application in key fields such as equipment monitoring, fault diagnosis, safety management and the like.
However, conventional target detection methods typically require a large amount of annotation data for model training. In such a large-scale application scenario in the power industry, it is a great challenge to obtain a sufficient amount and quality of annotation data. The manual labeling process is tedious and time-consuming, subjectivity and inconsistency exist, and the requirement of labeling quantity becomes a bottleneck for limiting the application range and iterative optimization of the target detection model.
The low training accuracy is also another key problem in the task of target detection. The conventional method trains the target detection model directly from scratch, and does not fully utilize the existing large-scale data and knowledge. There are two main problems with this direct training approach: firstly, the model needs to be trained on limited labeling data, so that the training is insufficient and the accuracy is low; secondly, the object detection model lacks sufficient semantic understanding and visual characteristic characterization capability, cannot accurately capture complex shape and context information of the object, and further limits the accuracy and generalization capability of the model.
Disclosure of Invention
In order to overcome the defects, the invention provides a method and a device for detecting targets in the power industry.
In a first aspect, a power industry target detection method is provided, including:
acquiring a scene image to be detected;
taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
wherein the detection result comprises at least one of the following: the location and class of the target.
Preferably, the category includes at least one of: power equipment category, preset facilities and scenario category, preset fault and abnormal scenario category.
Preferably, the process of obtaining the pre-trained power industry target detection model includes:
taking the scene image without the detection result as the input of the Segment analysis model to obtain a semantic segmentation image output by the Segment analysis model;
labeling the segmentation box of the semantic segmentation image to obtain first training data;
and training an initial target detection model by using the first training data.
Further, after training the initial target detection model by using the training data, the method includes:
constructing second training data by using the scene image marked with the detection result;
and training the pre-trained power industry target detection model by using the second training data to obtain the pre-trained power industry target detection model.
Further, the data size of the second training data is smaller than the data size of the first training data.
Further, the method comprises the steps of:
and carrying out data enhancement on the first training data and the second training data.
Further, the data enhancement of the first training data and the second training data includes:
and respectively carrying out random overturning in the horizontal direction and the vertical direction on the first training data and the second training data according to the probability of 0.5, carrying out image random rotation operation of an angle of-20 degrees to 20 degrees and a step distance of 1 degree, carrying out fixed angle random rotation operation of 90 degrees, 180 degrees and 270 degrees, and carrying out random scaling operation of the image size of 0.25 to 4 times.
Further, an algorithm adopted in the process of obtaining the scene image of the labeling detection result is as follows: rectangular box labeling algorithm or instance segmentation labeling algorithm.
In a second aspect, there is provided a power industry target detection apparatus, the power industry target detection apparatus comprising:
the acquisition module is used for acquiring the scene image to be detected;
the analysis module is used for taking the scene image to be detected as the input of a pre-trained power industry target detection model to obtain the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
wherein the detection result comprises at least one of the following: the location and class of the target.
In a third aspect, there is provided a computer device comprising: one or more processors;
the processor is used for storing one or more programs;
the power industry target detection method is implemented when the one or more programs are executed by the one or more processors.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored, which when executed, implements the power industry target detection method.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
the invention provides a method and a device for detecting a target in the power industry, comprising the following steps: acquiring a scene image to be detected; taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model; the detection result comprises at least one of the following: the location and class of the target. The technical scheme provided by the invention solves the problems of large labeling quantity and low training accuracy in the target detection task of the power industry, has wider applicability, provides a more efficient and accurate target detection solution, promotes the intelligent development of the power industry and other fields, and is specific:
firstly, the method and the device remarkably reduce the labeling quantity requirement of the target detection model, so that first-line staff can easily acquire labeling data with sufficient quantity and quality. This reduces the workload and time consumption of the first line personnel, enabling them to focus more on site work and task execution.
Secondly, by introducing the pre-trained power industry target detection model, the accuracy and generalization capability of the target detection model are improved. This enables a first line of personnel to accurately identify and locate objects in electrical equipment, facilities and scenes, such as malfunctions, abnormal situations, etc. This helps to find problems in time, reduce potential risks, and improve the work efficiency and safety of first-line personnel.
In addition, the method has wide applicability and can be applied to different power industry scenes and task demands. Whether it is power equipment inspection, fault detection or safety monitoring, first-line personnel can benefit from the efficient, accurate target detection solution provided by the invention.
Drawings
FIG. 1 is a flow chart of main steps of a power industry target detection method according to an embodiment of the present invention;
fig. 2 is a main structural block diagram of a power industry target detection apparatus according to an embodiment of the present invention.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As disclosed in the background art, in the power industry, a target detection task plays an important role, and is used for realizing intelligent application in key fields such as equipment monitoring, fault diagnosis, safety management and the like.
However, conventional target detection methods typically require a large amount of annotation data for model training. In such a large-scale application scenario in the power industry, it is a great challenge to obtain a sufficient amount and quality of annotation data. The manual labeling process is tedious and time-consuming, subjectivity and inconsistency exist, and the requirement of labeling quantity becomes a bottleneck for limiting the application range and iterative optimization of the target detection model.
The low training accuracy is also another key problem in the task of target detection. The conventional method trains the target detection model directly from scratch, and does not fully utilize the existing large-scale data and knowledge. There are two main problems with this direct training approach: firstly, the model needs to be trained on limited labeling data, so that the training is insufficient and the accuracy is low; secondly, the object detection model lacks sufficient semantic understanding and visual characteristic characterization capability, cannot accurately capture complex shape and context information of the object, and further limits the accuracy and generalization capability of the model.
In order to improve the above problems, the present invention provides a method and an apparatus for detecting a target in the power industry, including: acquiring a scene image to be detected; taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model; the detection result comprises at least one of the following: the location and class of the target. The technical scheme provided by the invention solves the problems of large labeling quantity and low training accuracy in the target detection task of the power industry, has wider applicability, provides a more efficient and accurate target detection solution, promotes the intelligent development of the power industry and other fields, and is specific:
firstly, the method and the device remarkably reduce the labeling quantity requirement of the target detection model, so that first-line staff can easily acquire labeling data with sufficient quantity and quality. This reduces the workload and time consumption of the first line personnel, enabling them to focus more on site work and task execution.
Secondly, by introducing the pre-trained power industry target detection model, the accuracy and generalization capability of the target detection model are improved. This enables a first line of personnel to accurately identify and locate objects in electrical equipment, facilities and scenes, such as malfunctions, abnormal situations, etc. This helps to find problems in time, reduce potential risks, and improve the work efficiency and safety of first-line personnel.
In addition, the method has wide applicability and can be applied to different power industry scenes and task demands. Whether it is power equipment inspection, fault detection or safety monitoring, first-line personnel can benefit from the efficient, accurate target detection solution provided by the invention.
The above-described scheme is explained in detail below.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a power industry target detection method according to an embodiment of the present invention. As shown in fig. 1, the method for detecting the target in the power industry in the embodiment of the invention mainly comprises the following steps:
step S101: acquiring a scene image to be detected;
step S102: taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
wherein the detection result comprises at least one of the following: the location and class of the target.
In this embodiment, the category includes at least one of the following: the power equipment category, the preset facilities and scene category, the preset faults and abnormal scene category, for example, the fault and abnormal scene category is the loss of bolts of the transmission line and the appearance damage of the metering device.
In this embodiment, the process of obtaining the pre-trained power industry target detection model includes:
taking the scene image without the detection result as the input of the Segment analysis model to obtain a semantic segmentation image output by the Segment analysis model;
labeling the segmentation box of the semantic segmentation image to obtain first training data;
and training an initial target detection model by using the first training data.
In one embodiment, after training the initial target detection model using the training data, the training method includes:
constructing second training data by using the scene image marked with the detection result;
and training the pre-trained power industry target detection model by using the second training data to obtain the pre-trained power industry target detection model.
In one embodiment, the second training data has a smaller data size than the first training data.
In one embodiment, the method comprises:
performing data enhancement on the first training data and the second training data;
in one embodiment, the data enhancing the first training data and the second training data includes:
and respectively carrying out random overturning in the horizontal direction and the vertical direction on the first training data and the second training data according to the probability of 0.5, carrying out image random rotation operation of an angle of-20 degrees to 20 degrees and a step distance of 1 degree, carrying out fixed angle random rotation operation of 90 degrees, 180 degrees and 270 degrees, and carrying out random scaling operation of the image size of 0.25 to 4 times.
In one embodiment, the algorithm adopted in the process of obtaining the scene image of the labeling detection result is as follows: rectangular box labeling algorithm or instance segmentation labeling algorithm.
In a specific embodiment, the entire training process is presented in the following flow:
step 1, data preparation
First, an objective detection dataset of the power industry is collected and prepared, including annotated image data and corresponding objective tags. The data set should cover the power equipment, facilities and scenarios, as well as common faults and anomalies.
Step 2, training the pre-training model
Using a large scale unlabeled image dataset, training was performed using a Segment analysis pre-training model. The pre-training model can learn rich semantic information and visual features. The training process may employ self-supervised learning or other suitable unsupervised learning methods. The input of the pre-training model is the original image data and the output is the corresponding semantically segmented image.
Step 3, training the target detection model
And training a downstream task model, namely training a target detection model, on the basis of the pre-training model. And using the marked image data set, taking the pre-training model as an initialization model, and performing supervised object detection model training. A common target detection model may be used, such as fast R-CNN, YOLO, or SSD, etc. The input of the object detection model is the original image data and the output is the position and class information of the object in the image.
Step 4, model optimization and adjustment
And optimizing and adjusting the target detection model obtained through training to further improve accuracy and performance. Various optimization techniques, such as learning rate adjustment, data enhancement, model fusion, etc., may be employed to achieve better results.
Step 5, model evaluation and test
And evaluating and testing the optimized target detection model. And (3) evaluating the performance of the model in the target detection task by using an independent test data set, wherein the performance comprises indexes such as accuracy, recall rate, precision and the like. The performance and accuracy of the target detection model is verified by comparison with standard evaluation indicators, such as average accuracy mean (mAP) and target detection accuracy. Based on the evaluation, necessary adjustments and improvements are made to further optimize the model.
Step 6, model application and deployment
After model training and optimization are completed, the target detection model obtained through training is applied to a target detection task in the actual power industry. By inputting image data to be detected, the model can output the position and type information of the target in the image, thereby realizing target detection of power equipment, facilities and scenes.
Step 7, continuous optimization and iteration
With the continuous accumulation of the power industry data and the appearance of new scenes, the model obtained through training can be continuously optimized and iterated. By periodically updating and retraining the model, new target detection requirements can be accommodated and the performance of the model can be improved.
According to the technical scheme, the target detection task of the power industry is effectively solved by combining the training process of the target detection model through the Segment analysis-based pre-training model method. By reducing the labeling amount requirement, improving the training accuracy and providing wider applicability, the invention can provide a more accurate and efficient target detection solution and promote the intelligent development of the power industry.
Example 2
Based on the same inventive concept, the invention also provides a power industry target detection device, as shown in fig. 2, comprising:
the acquisition module is used for acquiring the scene image to be detected;
the analysis module is used for taking the scene image to be detected as the input of a pre-trained power industry target detection model to obtain the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
the detection result comprises at least one of the following: the location and class of the target.
Preferably, the category includes at least one of: power equipment category, preset facilities and scenario category, preset fault and abnormal scenario category.
Preferably, the process of obtaining the pre-trained power industry target detection model includes:
taking the scene image without the detection result as the input of the Segment analysis model to obtain a semantic segmentation image output by the Segment analysis model;
labeling the segmentation box of the semantic segmentation image to obtain first training data;
and training an initial target detection model by using the first training data.
Further, after training the initial target detection model by using the training data, the method includes:
constructing second training data by using the scene image marked with the detection result;
and training the pre-trained power industry target detection model by using the second training data to obtain the pre-trained power industry target detection model.
Further, the data size of the second training data is smaller than the data size of the first training data.
Further, the method comprises the steps of:
performing data enhancement on the first training data and the second training data;
further, the data enhancement of the first training data and the second training data includes:
and respectively carrying out random overturning in the horizontal direction and the vertical direction on the first training data and the second training data according to the probability of 0.5, carrying out image random rotation operation of an angle of-20 degrees to 20 degrees and a step distance of 1 degree, carrying out fixed angle random rotation operation of 90 degrees, 180 degrees and 270 degrees, and carrying out random scaling operation of the image size of 0.25 to 4 times.
Further, an algorithm adopted in the process of obtaining the scene image of the labeling detection result is as follows: rectangular box labeling algorithm or instance segmentation labeling algorithm.
Example 3
Based on the same inventive concept, the invention also provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application SpecificIntegrated Circuit, ASIC), off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular to load and execute one or more instructions in a computer storage medium to implement the corresponding method flow or corresponding functions, to implement the steps of a power industry target detection method in the above embodiments.
Example 4
Based on the same inventive concept, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a computer device, for storing programs and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of a power industry target detection method in the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (11)
1. A method for power industry target detection, the method comprising:
acquiring a scene image to be detected;
taking the scene image to be detected as the input of a pre-trained power industry target detection model, and obtaining the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
wherein the detection result comprises at least one of the following: the location and class of the target.
2. The method of claim 1, wherein the categories include at least one of: power equipment category, preset facilities and scenario category, preset fault and abnormal scenario category.
3. The method of claim 1, wherein the process of obtaining the pre-trained power industry target detection model comprises:
taking the scene image without the detection result as the input of the Segment analysis model to obtain a semantic segmentation image output by the Segment analysis model;
labeling the segmentation box of the semantic segmentation image to obtain first training data;
and training an initial target detection model by using the first training data.
4. The method of claim 3, wherein after training the initial object detection model using the training data, comprising:
constructing second training data by using the scene image marked with the detection result;
and training the pre-trained power industry target detection model by using the second training data to obtain the pre-trained power industry target detection model.
5. The method of claim 4, wherein the second training data has a smaller data size than the first training data.
6. The method of claim 4, wherein the method comprises:
and carrying out data enhancement on the first training data and the second training data.
7. The method of claim 6, wherein the data enhancing the first training data and the second training data comprises:
and respectively carrying out random overturning in the horizontal direction and the vertical direction on the first training data and the second training data according to the probability of 0.5, carrying out image random rotation operation of an angle of-20 degrees to 20 degrees and a step distance of 1 degree, carrying out fixed angle random rotation operation of 90 degrees, 180 degrees and 270 degrees, and carrying out random scaling operation of the image size of 0.25 to 4 times.
8. The method of claim 4, wherein the algorithm used in the process of obtaining the scene image of the annotation detection result is: rectangular box labeling algorithm or instance segmentation labeling algorithm.
9. An electrical power industry target detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring the scene image to be detected;
the analysis module is used for taking the scene image to be detected as the input of a pre-trained power industry target detection model to obtain the detection result of the scene image to be detected, which is output by the pre-trained power industry target detection model;
wherein the detection result comprises at least one of the following: the location and class of the target.
10. A computer device, comprising: one or more processors;
the processor is used for storing one or more programs;
the power industry target detection method of any one of claims 1 to 8, when the one or more programs are executed by the one or more processors.
11. A computer-readable storage medium, on which a computer program is stored, which, when executed, implements the power industry target detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310636391.5A CN116704218A (en) | 2023-05-31 | 2023-05-31 | Power industry target detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310636391.5A CN116704218A (en) | 2023-05-31 | 2023-05-31 | Power industry target detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116704218A true CN116704218A (en) | 2023-09-05 |
Family
ID=87840321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310636391.5A Pending CN116704218A (en) | 2023-05-31 | 2023-05-31 | Power industry target detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116704218A (en) |
-
2023
- 2023-05-31 CN CN202310636391.5A patent/CN116704218A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111353983B (en) | Defect detection identification method, device, computer readable medium and electronic equipment | |
| CN108593260A (en) | Lightguide cable link fault location and detection method and terminal device | |
| US20230007989A1 (en) | Methods and devices for generating training sample, training model and recognizing character | |
| CN109739904A (en) | A kind of labeling method of time series, device, equipment and storage medium | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| CN113688665A (en) | Remote sensing image target detection method and system based on semi-supervised iterative learning | |
| Jiang et al. | Optimization of intelligent plant cultivation robot system in object detection | |
| CN116664846B (en) | Method and system for realizing 3D printing bridge deck construction quality monitoring based on semantic segmentation | |
| Chen et al. | An improved faster R-CNN transmission line bolt defect detection method | |
| CN109242165A (en) | A kind of model training and prediction technique and device based on model training | |
| Zheng et al. | Wind turbine blades surface crack-detection algorithm based on improved YOLO-v5 model | |
| CN115171045A (en) | YOLO-based power grid operation field violation identification method and terminal | |
| CN114706856A (en) | Fault processing method and device, electronic equipment and computer readable storage medium | |
| CN113902793A (en) | End-to-end building height prediction method and system based on single vision remote sensing image and electronic equipment | |
| CN117372424B (en) | Defect detection method, device, equipment and storage medium | |
| CN116704218A (en) | Power industry target detection method and device | |
| CN118337609A (en) | Network fault tracing method based on large model knowledge enhancement | |
| CN117708720A (en) | Equipment fault diagnosis system based on knowledge graph | |
| CN117331017A (en) | Method and system for studying and judging misconnection of three-phase four-wire electric energy meter | |
| US20230022253A1 (en) | Fast and accurate prediction methods and systems based on analytical models | |
| Sheng et al. | A Method and Implementation of Transmission Line's Key Components and Defects Identification Based on YOLO | |
| Chen et al. | Few-Shot Learning on 3D Surface Defect Detection with PM Networks | |
| Gao et al. | Detection method of potholes on highway pavement based on yolov5 | |
| WO2022036689A1 (en) | Method for fault diagnosis using a fault diagnosis model trained by virtual data | |
| Yang et al. | Weakly supervised collaborative localization learning method for sewer pipe defect detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |