CN111738307A - Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium - Google Patents
Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium Download PDFInfo
- Publication number
- CN111738307A CN111738307A CN202010492179.2A CN202010492179A CN111738307A CN 111738307 A CN111738307 A CN 111738307A CN 202010492179 A CN202010492179 A CN 202010492179A CN 111738307 A CN111738307 A CN 111738307A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- image
- power transmission
- foreign
- fast rcnn
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
Abstract
The invention provides a foreign matter identification method and system in a power transmission line environment based on fast RCNN and a computer readable storage medium. The identification method comprises the following steps: constructing a training sample: acquiring an environment image of the power transmission line containing the foreign matters, marking frame coordinates of the foreign matters in the image, and adding a classification label to each frame to obtain a sample image; building a fast RCNN model, and training the fast RCNN model by using a sample image until the value of the loss function reaches a preset threshold condition; and acquiring the environmental image of the power transmission line again, and inputting the newly acquired environmental image of the power transmission line into the trained fast RCNN network model to obtain the classification result of the foreign matters in the image. The invention can automatically identify the foreign matters in the acquired transmission line environment image, does not need a transmission line maintainer to monitor the transmission line environment monitoring screen for a long time at the background, and saves the workload of the transmission line maintainer.
Description
Technical Field
The invention relates to the technical field of power transmission lines, in particular to a foreign matter identification method and system in a power transmission line environment based on fast RCNN and a computer readable storage medium.
Background
The breadth of our country is broad, the coverage of high-voltage transmission lines is wide, the number of points is large, and the lines are long, so that the maintenance work of the transmission lines is the key point for guaranteeing the normal work of the transmission lines. Among factors damaging the power transmission line, more bird damage, ice coating, winding of sundries such as garbage and the like, scraping of tall construction vehicles and the like can cause the power transmission line to be broken down or even damaged. Usually can only in time discover these hidden dangers through patrolling and examining many times, in the past through artifical patrol, nevertheless because the position that has some erects in the transmission line is more special, difficult artifical observation, consequently gradually replaces artifical patrol through the machine in recent years, for example install the camera on the power transmission tower pole, perhaps cruises through unmanned aerial vehicle and gathers transmission line environmental information. However, in the above manner, the collected environmental information still needs to be distinguished by manpower, the workload is still large, if the automatic identification and distinguishing of the foreign matters can be realized according to the collected environmental information of the power transmission line, the workload of power transmission line maintenance personnel can be greatly saved, and in addition, compared with manual detection, the automatic detection can improve the detection accuracy.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a scheme capable of automatically identifying foreign matters in a power transmission line environment, and particularly relates to a foreign matter identification method, a foreign matter identification system and a computer readable storage medium in the power transmission line environment based on fast RCNN.
The technical scheme is as follows: in order to achieve the purpose, the invention provides the following technical scheme:
a foreign matter identification method in a power transmission line environment based on fast RCNN comprises the following steps:
(1) constructing a training sample: acquiring an environment image of the power transmission line containing the foreign matters, marking frame coordinates of the foreign matters in the image, and adding a classification label to each frame to obtain a sample image;
(2) building a fast RCNN model, and training the fast RCNN model by using a sample image until the value of the loss function reaches a preset threshold condition;
(3) and acquiring the environmental image of the power transmission line again, and inputting the newly acquired environmental image of the power transmission line into the trained fast RCNN network model to obtain the classification result of the foreign matters in the image.
Further, in the method for identifying the foreign matters in the power transmission line environment based on the fast RCNN, the foreign matters comprise construction vehicles, flying birds and floating objects.
Further, the Faster RCNN network model comprises a feature extraction network, a region generation network and a target detector; extracting a feature image feature map of the input power transmission line environment image by a feature extraction network; the area generation network generates a foreign matter candidate frame according to the feature image feature map; the ROI pooling layer in the target detector maps the foreign matter candidate frame to a feature image feature map to obtain the low-dimensional feature of each foreign matter candidate frame; and sending the low-dimensional features into a full-connection layer of the target detector for regression and classification to obtain the frame coordinates and classification results of the foreign matters.
Further, the loss function is:
wherein ImginRepresenting an input image, NclsIs the total number of foreground, piIndicating the probability that the ith foreign object candidate box is predicted to correspond to the category,
to predict the probability that the ith foreign object candidate frame is the corresponding true frame, tiCoordinate information indicating the ith foreign substance candidate frame,
coordinate information of the corresponding real frame;
in order to classify the function of the loss,
λ is the balance parameter for the bounding box regression loss function.
A computer readable storage medium storing computer executable instructions which, when executed by a processor, identify a foreign object in an image of a power transmission line environment via the trained fast RCNN network model.
Foreign matter identification system in transmission line environment based on fast RCNN includes: the system comprises an image acquisition module and a processor; the image acquisition module acquires an environmental image of the power transmission line and then sends the environmental image to the processor, the processor stores a computer executable instruction, and when the processor executes the computer executable instruction, the processor identifies foreign matters in the received environmental image of the power transmission line through the trained fast RCNN network model.
Has the advantages that: compared with the prior art, the invention has the following advantages:
the invention trains the neural network through the images with different foreign body marks, extracts the characteristics of different foreign bodies by using the memory characteristic of the neural network and adopting the trained neural network, classifies the characteristics and outputs the outlines and the classes of the different foreign bodies. According to the technical scheme provided by the invention, the foreign matters in the acquired transmission line environment image can be automatically identified, a transmission line maintainer does not need to monitor a transmission line environment monitoring screen for a long time at the background, and the workload of the transmission line maintainer is greatly saved.
And the neural network trained by adopting a plurality of samples has higher accuracy, and compared with the method of manually observing and detecting the visual screen and finding problems, the neural network has higher accuracy of classification and judgment results, and can reduce the conditions of misjudgment, missed judgment and misjudgment to a great extent.
Drawings
FIG. 1 is a flow chart of a method for identifying a foreign object in a power transmission line environment based on fast RCNN according to the present invention;
FIG. 2 is a flow chart of the operation of the Faster RCNN involved in an embodiment;
fig. 3 is a block diagram of a foreign object recognition system in a power transmission line environment based on fast RCNN according to an embodiment.
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific embodiments. It is to be understood that the present invention may be embodied in various forms, and that there is no intention to limit the invention to the specific embodiments illustrated, but on the contrary, the intention is to cover some exemplary and non-limiting embodiments shown in the attached drawings and described below.
It is to be understood that the features listed above for the different embodiments may be combined with each other to form further embodiments within the scope of the invention, where technically feasible. Furthermore, the particular examples and embodiments of the invention described are non-limiting, and various modifications may be made in the structure, steps, and sequence set forth above without departing from the scope of the invention.
Fig. 1 is a flowchart of a foreign object identification method in a power transmission line environment based on fast RCNN according to the present invention, and as shown in the drawing, the foreign object identification method in the power transmission line environment based on fast RCNN includes the following steps:
(1) constructing a training sample: acquiring an environment image of the power transmission line containing the foreign matters, marking frame coordinates of the foreign matters in the image, and adding a classification label to each frame to obtain a sample image;
(2) building a fast RCNN model, and training the fast RCNN model by using a sample image until the value of the loss function reaches a preset threshold condition;
(3) and acquiring the environmental image of the power transmission line again, and inputting the newly acquired environmental image of the power transmission line into the trained fast RCNN network model to obtain the classification result of the foreign matters in the image.
In an embodiment of the method for identifying foreign matters in the power transmission line environment based on fast RCNN, the foreign matters include construction vehicles, birds and floats, and may be set according to requirements, and other settable options are also included in the protection scope of the present invention.
In an embodiment of the foreign object identification method in the power transmission line environment based on the fast RCNN, a fast RCNN network model includes a feature extraction network, a region generation network, and a target detector, and a workflow of the fast RCNN is as shown in fig. 2: extracting a feature image featuremap of the input power transmission line environment image by a feature extraction network; the area generation network generates a foreign matter candidate frame according to the feature image feature map; the ROI pooling layer in the target detector maps the foreign matter candidate frame to a feature image feature map to obtain the low-dimensional feature of each foreign matter candidate frame; and sending the low-dimensional features into a full-connection layer of the target detector for regression and classification to obtain the frame coordinates and classification results of the foreign matters.
The training process of the Faster RCNN network model is as follows:
data collection: selecting 10000 pictures from the shot environment image of the power transmission line, normalizing the pictures to the size specified by the input layer of the Faster RCNN network, framing out the foreign matters in the pictures on the normalized pictures, and adding a mark, wherein the mark comprises the coordinates of the foreign matter frame and the category of the foreign matters;
training a neural network: the tagged pictures are fed into the Faster RCNN network and the network is trained through the tensoflow framework until the value of the loss function meets the threshold condition. In this embodiment, the loss function is:
wherein ImginRepresenting an input image, NclsIs the total number of foreground, piIndicating the probability that the ith foreign object candidate box is predicted to correspond to the category,
to predict the probability that the ith foreign object candidate frame is the corresponding true frame, tiCoordinate information indicating the ith foreign substance candidate frame,
coordinate information of the corresponding real frame;
in order to classify the function of the loss,
λ is the balance parameter for the bounding box regression loss function.
Further, the present embodiment also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the processor identifies a foreign object in an environmental image of a power transmission line through the trained fast RCNN network model.
Further, this embodiment also provides a foreign object identification system in the power transmission line environment based on fast RCNN, including: the system comprises an image acquisition module 1 and a processor 2; the image acquisition module 1 acquires an environmental image of the power transmission line and then sends the environmental image to the processor 2, the processor 2 stores a computer executable instruction, and when the processor 2 executes the computer executable instruction, the foreign matters in the received environmental image of the power transmission line are identified through the trained fast RCNN network model.
The above-described embodiments, particularly any "preferred" embodiments, are possible examples of implementations, and are presented merely for a clear understanding of the principles of the invention. Many variations and modifications may be made to the above-described embodiments without departing substantially from the spirit and principles of the technology described herein, and such variations and modifications are to be considered within the scope of the invention.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (6)
1. A foreign matter identification method in a power transmission line environment based on fast RCNN is characterized by comprising the following steps:
(1) constructing a training sample: acquiring an environment image of the power transmission line containing the foreign matters, marking frame coordinates of the foreign matters in the image, and adding a classification label to each frame to obtain a sample image;
(2) building a fast RCNN model, and training the fast RCNN model by using a sample image until the value of the loss function reaches a preset threshold condition;
(3) and acquiring the environmental image of the power transmission line again, and inputting the newly acquired environmental image of the power transmission line into the trained FasterRCNN network model to obtain the classification result of the foreign matters in the image.
2. The method for identifying foreign objects in the power transmission line environment based on fast RCNN according to claim 1, wherein the foreign objects include construction vehicles, flying birds and floating objects.
3. The method for identifying a foreign object in a power transmission line environment based on the Faster RCNN according to claim 1, wherein the Faster RCNN network model includes a feature extraction network, a region generation network, and an object detector; extracting a feature image feature map of the input power transmission line environment image by a feature extraction network; the area generation network generates a foreign matter candidate frame according to the feature image feature map; the ROI pooling layer in the target detector maps the foreign matter candidate frame to a feature image feature map to obtain the low-dimensional feature of each foreign matter candidate frame; and sending the low-dimensional features into a full-connection layer of the target detector for regression and classification to obtain the frame coordinates and classification results of the foreign matters.
4. The method of claim 1, wherein the loss function is:
wherein ImginRepresenting an input image, NclsIs the total number of foreground, piIndicating the probability that the ith foreign object candidate box is predicted to correspond to the category,
to predict the probability that the ith foreign object candidate frame is the corresponding true frame, tiCoordinate information indicating the ith foreign substance candidate frame,
coordinate information of the corresponding real frame;
in order to classify the function of the loss,
λ is the balance parameter for the bounding box regression loss function.
5. A computer readable storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a processor, identify a foreign object in an image of a power transmission line environment through the trained fasterncn network model according to any one of claims 1 to 4.
6. Foreign matter identification system in transmission line environment based on fast RCNN, its characterized in that includes: the system comprises an image acquisition module and a processor; the image acquisition module acquires an environmental image of the power transmission line and then sends the environmental image to the processor, computer-executable instructions are stored in the processor, and when the processor executes the computer-executable instructions, foreign matters in the received environmental image of the power transmission line are identified through the trained Faster RCNN network model according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010492179.2A CN111738307A (en) | 2020-06-02 | 2020-06-02 | Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010492179.2A CN111738307A (en) | 2020-06-02 | 2020-06-02 | Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738307A true CN111738307A (en) | 2020-10-02 |
Family
ID=72648207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010492179.2A Pending CN111738307A (en) | 2020-06-02 | 2020-06-02 | Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738307A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651337A (en) * | 2020-12-25 | 2021-04-13 | 国网黑龙江省电力有限公司电力科学研究院 | Sample set construction method applied to training line foreign object target detection model |
| CN112909824A (en) * | 2021-03-24 | 2021-06-04 | 南方电网电力科技股份有限公司 | Method and device for identifying suspended foreign matters of power transmission line |
| CN113392803A (en) * | 2021-06-30 | 2021-09-14 | 广东电网有限责任公司 | Method and device for identifying suspended foreign matters of power transmission line, terminal and storage medium |
| CN113449769A (en) * | 2021-05-18 | 2021-09-28 | 内蒙古工业大学 | Power transmission line icing identification model training method, identification method and storage medium |
| CN113486865A (en) * | 2021-09-03 | 2021-10-08 | 国网江西省电力有限公司电力科学研究院 | Power transmission line suspended foreign object target detection method based on deep learning |
| CN115586792A (en) * | 2022-09-30 | 2023-01-10 | 三峡大学 | Iron tower parameter-based unmanned aerial vehicle power inspection system and method |
| CN117237363A (en) * | 2023-11-16 | 2023-12-15 | 国网山东省电力公司曲阜市供电公司 | Method, system, medium and equipment for identifying external broken source of power transmission line |
-
2020
- 2020-06-02 CN CN202010492179.2A patent/CN111738307A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651337A (en) * | 2020-12-25 | 2021-04-13 | 国网黑龙江省电力有限公司电力科学研究院 | Sample set construction method applied to training line foreign object target detection model |
| CN112909824A (en) * | 2021-03-24 | 2021-06-04 | 南方电网电力科技股份有限公司 | Method and device for identifying suspended foreign matters of power transmission line |
| CN113449769A (en) * | 2021-05-18 | 2021-09-28 | 内蒙古工业大学 | Power transmission line icing identification model training method, identification method and storage medium |
| CN113392803A (en) * | 2021-06-30 | 2021-09-14 | 广东电网有限责任公司 | Method and device for identifying suspended foreign matters of power transmission line, terminal and storage medium |
| CN113486865A (en) * | 2021-09-03 | 2021-10-08 | 国网江西省电力有限公司电力科学研究院 | Power transmission line suspended foreign object target detection method based on deep learning |
| CN115586792A (en) * | 2022-09-30 | 2023-01-10 | 三峡大学 | Iron tower parameter-based unmanned aerial vehicle power inspection system and method |
| CN117237363A (en) * | 2023-11-16 | 2023-12-15 | 国网山东省电力公司曲阜市供电公司 | Method, system, medium and equipment for identifying external broken source of power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738307A (en) | Foreign matter identification method and system in power transmission line environment based on fast RCNN and computer readable storage medium | |
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| CN112884931B (en) | Unmanned aerial vehicle inspection method and system for transformer substation | |
| CN109376605B (en) | Electric power inspection image bird-stab-prevention fault detection method | |
| CN111784685A (en) | Power transmission line defect image identification method based on cloud edge cooperative detection | |
| CN108038424B (en) | Visual automatic detection method suitable for high-altitude operation | |
| CN104881865A (en) | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis | |
| CN112241692B (en) | Channel foreign matter intelligent detection and classification method based on aerial image super-pixel texture | |
| CN112541372B (en) | Difficult sample screening method and device | |
| CN111739184A (en) | Power transmission line inspection system based on power transmission line tower pole | |
| CN112666553B (en) | Road ponding identification method and equipment based on millimeter wave radar | |
| CN115359239A (en) | Wind power blade defect detection and positioning method and device, storage medium and electronic equipment | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN112487894A (en) | Automatic inspection method and device for rail transit protection area based on artificial intelligence | |
| CN111898444A (en) | Aircraft landing gear state determination method based on image recognition | |
| CN111738312B (en) | Power transmission line state monitoring method and device based on GIS and virtual reality fusion and computer readable storage medium | |
| CN111753610A (en) | Weather identification method and device | |
| CN113657151A (en) | Water traffic violation detection method based on YOLO target detection algorithm | |
| CN111597939B (en) | High-speed rail line nest defect detection method based on deep learning | |
| US20200250443A1 (en) | Information processing device, server, and traffic management system | |
| CN105574490A (en) | Vehicle brand identification method and system based on headlight image characteristics | |
| CN115620047A (en) | Target object attribute information determination method and device, electronic equipment and storage medium | |
| CN112241691B (en) | Channel ice condition intelligent identification method based on unmanned aerial vehicle inspection and image characteristics | |
| CN114187568A (en) | Road sign breakage detection method, apparatus and storage medium | |
| CN113052820A (en) | Circuit equipment defect identification method based on neural network technology |
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 |