CN112749656A - Air switch state detection method and device based on ORB feature matching and yolo - Google Patents
Air switch state detection method and device based on ORB feature matching and yolo Download PDFInfo
- Publication number
- CN112749656A CN112749656A CN202110017776.4A CN202110017776A CN112749656A CN 112749656 A CN112749656 A CN 112749656A CN 202110017776 A CN202110017776 A CN 202110017776A CN 112749656 A CN112749656 A CN 112749656A
- Authority
- CN
- China
- Prior art keywords
- image
- air switch
- yolo
- data set
- standard template
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
-
- 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
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention provides an air switch state detection method based on ORB feature matching and yolo, which comprises the following steps: A. taking an image sample of the device containing the air switch to create a data set; B. training and exporting a yolo model; C. manufacturing a standard template; D. shooting an equipment image containing an air switch to be detected, and carrying out ORB feature point extraction on the equipment image and generating a corresponding feature vector; E. d, performing characteristic matching to position the air switch to be detected, and correcting the equipment image in the step D; F. obtaining a to-be-detected switch image basically consistent with the standard template; G. b, inputting the image of the switch to be detected into the yolo model processed in the step B to obtain the number of the switches and the state of each switch; F. and judging whether the air switch state is abnormal or not and giving an alarm. The invention has strong anti-interference performance, low false detection rate and high accuracy, and can also reduce the workload.
Description
Technical Field
The invention relates to an ORB feature matching and yolo-based air switch state detection method and device.
Background
The stability of the power communication system directly affects the reliability and stability of the power grid operation, so that the maintenance of the power communication equipment is very important, and the air switch is a very important electric appliance and integrates control and various protection functions. The air switch can not only complete the contact and the breaking of the circuit, but also protect the short circuit, the serious overload, the undervoltage and the like of the circuit or the electrical equipment, so that the detection and the maintenance of the air switch are indispensable links of an electric power communication machine room. At present, the detection mode of manual detection or fixed camera monitoring is generally adopted in the detection of electric power communication computer lab equipment, and these two kinds of modes all have the defect: the manual detection mode easily causes false detection, false detection or missing detection due to self subjective factors of personnel; the detection mode of fixed camera monitoring, its detection range is limited, when the equipment that needs to detect increases, its detection cost also can increase, and the detection mode of fixed camera monitoring adopts the template matching algorithm to carry out air switch state detection mostly moreover, and this method is easily influenced by external environment, and its robustness is poor.
Disclosure of Invention
The invention aims to provide an air switch state detection method and device based on ORB feature matching and yolo, aiming at the defects of the prior art, and the air switch state detection method and device are strong in anti-interference performance, low in false detection rate, high in accuracy rate and capable of reducing workload.
The invention is realized by the following technical scheme:
the air switch state detection method based on ORB feature matching and yolo comprises the following steps:
A. controlling the inspection robot to shoot equipment image samples containing an air switch at a specified place in a specified posture so as to establish a data set, and recording the position and the posture when each image sample is shot;
B. training and exporting a yolo model according to the equipment image sample of the data set;
C. manufacturing standard templates corresponding to the air switches according to the equipment image samples of the data set, and extracting feature points of the standard templates and generating corresponding feature vectors;
D. b, controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the position and the posture recorded in the step A, and carrying out ORB feature point extraction on the equipment image and generating a corresponding feature vector;
E. performing RANSAC feature matching on the feature points and the feature vectors in the step D and the feature points and the feature vectors of the corresponding standard template in the step C respectively to position the air switch to be detected in the equipment image, and acquiring a perspective transformation matrix to correct the equipment image in the step D;
F. according to the feature matching result, performing ROI deduction on the equipment image obtained in the step E to obtain a to-be-detected switch image basically consistent with the standard template;
G. b, inputting the image of the switch to be detected into the yolo model processed in the step B to obtain the position and the state of each switch, and determining the number of the air switches according to the number of the positions;
H. and G, comparing the number and the state of the air switches obtained in the step G with the power company management background data, judging whether the states of the air switches are abnormal or not and whether missing detection exists or not, and giving an alarm if the states of the air switches are abnormal or missing detection exists.
Further, the step a further includes: and performing image processing operations of mirror image inversion, translation transformation, affine transformation, random noise addition and random brightness change on the equipment image sample, and then establishing a data set.
Further, the step B includes:
b1, carrying out data labeling on the air switch area in each equipment image sample in the data set through a rectangular frame, wherein the data labeling is to record the position (x, y, w, h) of the air switch area in the image and the state (on and off) of the air switch, wherein (x, y) represents the coordinates of the upper left corner of the image, and w and h represent the width and height of the air switch area respectively;
b2, dividing the data set processed in the step B1 into a training set and a testing set;
b3, setting yolo model parameters, training by using a training set, and exporting the yolo model when the accuracy of the test set reaches 99%.
Further, the step C includes:
c1, respectively deducting each air switch in each equipment image sample in the data set as a standard template;
c2, respectively extracting OEB feature points of each standard template, and generating corresponding feature vectors according to the feature points;
and C3, numbering and recording each standard template according to the position information corresponding to the standard template.
Further, in the step E, a corresponding standard template is selected according to the position in the step D.
Further, step H further comprises: when the air state of the switch is abnormal, a background alarm is given; and when the missing detection exists, sending a verification signal to the staff.
Further, the invention is realized by the following technical scheme:
air switch state detection device based on ORB feature matching and yolo includes:
a dataset creation module: the inspection robot is used for controlling the inspection robot to shoot equipment image samples containing the air switch at a specified place in a specified posture so as to establish a data set, and recording the position and the posture when each image sample is shot;
a preprocessing module: training and deriving a yolo model from the device image samples of the data set; standard templates corresponding to the air switches are manufactured according to the equipment image samples of the data set, feature point extraction is carried out on the standard templates, and corresponding feature vectors are generated;
a characteristic point acquisition module: the inspection robot is used for controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the recorded position and posture, and extracting characteristic points of the equipment image and generating a corresponding characteristic vector;
a feature matching module: the device comprises a characteristic point acquisition module, a standard template acquisition module, a transmission transformation matrix acquisition module and a characteristic point acquisition module, wherein the characteristic point acquisition module is used for acquiring characteristic points and characteristic vectors of the standard template and performing RANSAC characteristic matching on the characteristic points and the characteristic vectors respectively to position an air switch to be detected in the device image, acquire the transmission transformation matrix to correct the device image, and then perform ROI (region of interest) deduction on the corrected device image according to a characteristic matching result to obtain a switch image to be detected which is basically consistent with the standard template;
the identification and alarm module: the system comprises a yolo model, a position acquisition module and a position acquisition module, wherein the yolo model is used for inputting images of switches to be detected into the preprocessed yolo model to obtain the position and the state of each switch, and the number of the air switches is determined according to the number of the positions; and comparing the number and the state of the switches with the management background data of the power company, judging whether the state of the air switch is abnormal or not and whether the detection is missed or not, and giving an alarm if the state is abnormal or the detection is missed.
Further, before the data set is established, the data set establishing module performs image processing operations of mirror image inversion, translation transformation, affine transformation, random noise addition and random brightness change on the device image sample, and then establishes the data set.
Furthermore, be provided with the industry camera that can reciprocate on the robot patrols and examines.
Further, the feature point obtaining module specifically includes:
a deduction module: the air switches are used for respectively deducting the air switches in the image samples of the equipment in the data set and used as standard templates;
an extraction module: the system comprises a standard template, a data processing module and a data processing module, wherein the standard template is used for extracting OEB characteristic points of the standard template and generating corresponding characteristic vectors according to the characteristic points;
a numbering module: and the system is used for numbering and recording each standard template according to the position information corresponding to the standard template.
The invention has the following beneficial effects:
1. the invention combines ORB characteristic matching and yolo model to detect the air switch state on the power equipment, can quickly and accurately judge the state of each air switch, in practical application, a panel of the equipment is usually provided with a plurality of groups of air switches, if the yolo model is directly used for state recognition, because of the movement error of the inspection robot, the relative position of each air switch can not be determined, whether the detected target is the target needing to be detected or not can not be judged, error detection is easy to occur, therefore, before the yolo model is used, the air switch group needing to be detected at this time is positioned through ORB characteristic matching, the image is corrected through perspective transformation, the air switch group needing to be detected is basically consistent with the standard template, then the yolo model is used, namely, the interference of factors such as distance, angle, illumination and the like caused by the movement error of the robot can be avoided, the false detection rate is further reduced, the accuracy is improved, the detection accuracy of the method can reach 98.8 percent, the highest detection accuracy of a single yolo model is about 94 percent, and the accuracy of template matching is lower; furthermore, if the ORB feature matching is not used first, if the interference of factors such as distance and angle is to be avoided, more data are needed to train the yolo model, the workload for preparing training data is not small, and satisfactory effect cannot be guaranteed.
Drawings
The present invention will be described in further detail with reference to the accompanying drawings.
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a standard template corresponding to the air switch to be detected.
Fig. 3 is an image of an apparatus containing an air switch to be tested.
Fig. 4 is an image of the feature point matching and perspective transformation process.
Fig. 5 is an image of the corrected air switch to be tested after being taken out.
Detailed Description
As shown in fig. 1, the air switch state detection method based on ORB feature matching and yolo includes the following steps:
A. controlling an inspection robot to shoot equipment image samples containing an air switch at a specified place in a specified posture, carrying out image processing operations of mirror image overturning, translation transformation, affine transformation, random noise addition and random brightness change on the equipment image samples, establishing a data set, and recording the positions and postures of shooting the image samples; the inspection robot is provided with an industrial camera which can move up and down, so that the posture of the inspection robot when the image sample is shot is the specific position of the industrial camera on the inspection robot; the structure of the inspection robot, the arrangement structure of the industrial camera, the control of the inspection robot and the specific operation of the image processing are all the prior art;
B. training and deriving a yolo model (in the present embodiment, specifically, the yolo3 model) from the device image samples of the data set; the method specifically comprises the following steps:
b1, carrying out data labeling on the air switch area in each equipment image sample in the data set through a rectangular frame, wherein the data labeling is to record the position (x, y, w, h) of the air switch area in the image and the state (on and off) of the air switch, wherein (x, y) represents the coordinates of the upper left corner of the image, and w and h represent the width and height of the air switch area respectively;
b2, randomly dividing the data set processed in the step B1 according to the ratio of 2:8 to form a training set and a testing set, wherein the training set is used for training a yolo3 model, and the testing set is used for performance testing of a yolo3 model;
b3, setting parameters of a yolo3 model, training by using a training set, and exporting the yolo3 model when the accuracy of a test set reaches 99%;
the parameter setting specifically comprises: scaling the picture size to 416 × 416 × 3, setting the batch training sample number batch to 64, setting the learning rate learning _ rate to 0.001, setting the maximum number of iterations to 100000, and taking loss (object) as a loss function, which is calculated as follows:
wherein the content of the first and second substances,
indicates whether the ith mesh jth anchor box is responsible for this object, if so
Otherwise 0, the loss function is prior art;
C. as shown in fig. 2, a standard template corresponding to each air switch is made according to an equipment image sample of the data set, and feature point extraction and corresponding feature vector generation are performed on each standard template; the method specifically comprises the following steps:
c1, manually deducting each air switch in each equipment image sample in the data set respectively, and storing the air switches as standard templates;
c2, respectively extracting OEB feature points of each standard template, and generating corresponding feature vectors according to the feature points;
c3, numbering and recording each standard template according to the position information corresponding to the standard template;
D. b, controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the position and the posture recorded in the step A, and performing ORB feature point extraction on the equipment image and generating a corresponding feature vector, wherein the feature vector is shown in FIG. 3;
E. as shown in fig. 4, selecting a corresponding standard template according to the position in step D, and performing RANSAC feature matching on the feature points and the feature vectors in step D and the feature points and the feature vectors of the corresponding standard template in step C, respectively, to locate the air switch to be detected in the device image, and acquiring a perspective transformation matrix to correct the device image in step D; although the inspection robot is controlled to shoot the equipment image according to the recorded position and posture, the factors such as shooting angle, distance, illumination and the like are complex and changeable due to the large error existing in the movement of the robot, so that the shot equipment image and the equipment image in the data set have large errors, and feature point matching and perspective transformation are required to be firstly carried out; the RANSAC feature matching and perspective transformation matrix is the prior art;
F. according to the feature matching result, performing ROI deduction on the equipment image obtained in the step E to obtain a to-be-detected switch image basically consistent with the standard template, as shown in FIG. 5;
G. b, inputting the image of the switch to be detected into the yolo model processed in the step B to obtain the position and the state of each switch, and determining the number of the air switches according to the number of the positions;
H. and G, comparing the number and the state of the air switches obtained in the step G with the management background data of the power company, judging whether the state of the air switches is abnormal or not and whether missing detection exists or not, and if the state is abnormal or missing detection exists, giving an alarm, specifically:
when the air state of the switch is abnormal, a background alarm is given; and when the missing detection exists, sending a verification signal to the staff.
Air switch state detection device based on ORB feature matching and yolo includes:
a dataset creation module: the inspection robot is used for controlling the inspection robot to shoot equipment image samples containing an air switch at a specified place in a specified posture, carrying out image processing operations of mirror image overturning, translation transformation, affine transformation, random noise addition and random brightness change on the equipment image samples, establishing a data set for the processed equipment image samples, and recording the positions and postures of shooting the image samples;
a preprocessing module: training and deriving a yolo model from the device image samples of the data set; standard templates corresponding to the air switches are manufactured according to the equipment image samples of the data set, feature point extraction is carried out on the standard templates, and corresponding feature vectors are generated;
a characteristic point acquisition module: the inspection robot is used for controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the recorded position and posture, and extracting characteristic points of the equipment image and generating a corresponding characteristic vector; this module specifically includes: a deduction module: the air switches are used for respectively deducting the air switches in the image samples of the equipment in the data set and used as standard templates;
an extraction module: the system comprises a standard template, a data processing module and a data processing module, wherein the standard template is used for extracting OEB characteristic points of the standard template and generating corresponding characteristic vectors according to the characteristic points;
a numbering module: and the system is used for numbering and recording each standard template according to the position information corresponding to the standard template.
A feature matching module: the device comprises a characteristic point acquisition module, a standard template acquisition module, a transmission transformation matrix acquisition module and a characteristic point acquisition module, wherein the characteristic point acquisition module is used for acquiring characteristic points and characteristic vectors of the standard template and performing RANSAC characteristic matching on the characteristic points and the characteristic vectors respectively to position an air switch to be detected in the device image, acquire the transmission transformation matrix to correct the device image, and then perform ROI (region of interest) deduction on the corrected device image according to a characteristic matching result to obtain a switch image to be detected which is basically consistent with the standard template;
the identification and alarm module: the system comprises a yolo model, a position acquisition module and a position acquisition module, wherein the yolo model is used for inputting images of switches to be detected into the preprocessed yolo model to obtain the position and the state of each switch, and the number of the air switches is determined according to the number of the positions; and comparing the number and the state of the switches with the management background data of the power company, judging whether the state of the air switch is abnormal or not and whether the detection is missed or not, and giving an alarm if the state is abnormal or the detection is missed.
The above description is only a preferred embodiment of the present invention, and therefore should not be taken as limiting the scope of the invention, which is defined by the appended claims and their equivalents and modifications within the scope of the description.
Claims (10)
1. Air switch state detection method based on ORB feature matching and yolo, its characterized in that: the method comprises the following steps:
A. controlling the inspection robot to shoot equipment image samples containing an air switch at a specified place in a specified posture so as to establish a data set, and recording the position and the posture when each image sample is shot;
B. training and exporting a yolo model according to the equipment image sample of the data set;
C. manufacturing standard templates corresponding to the air switches according to the equipment image samples of the data set, and extracting feature points of the standard templates and generating corresponding feature vectors;
D. b, controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the position and the posture recorded in the step A, and carrying out ORB feature point extraction on the equipment image and generating a corresponding feature vector;
E. performing RANSAC feature matching on the feature points and the feature vectors in the step D and the feature points and the feature vectors of the corresponding standard template in the step C respectively to position the air switch to be detected in the equipment image, and acquiring a perspective transformation matrix to correct the equipment image in the step D;
F. according to the feature matching result, performing ROI deduction on the equipment image obtained in the step E to obtain a to-be-detected switch image basically consistent with the standard template;
G. b, inputting the image of the switch to be detected into the yolo model processed in the step B to obtain the position and the state of each switch, and determining the number of the air switches according to the number of the positions;
H. and G, comparing the number and the state of the air switches obtained in the step G with the power company management background data, judging whether the states of the air switches are abnormal or not and whether missing detection exists or not, and giving an alarm if the states of the air switches are abnormal or missing detection exists.
2. The ORB feature matching and yolo based air switch state detection method of claim 1, wherein: the step A further comprises the following steps: and performing image processing operations of mirror image inversion, translation transformation, affine transformation, random noise addition and random brightness change on the equipment image sample, and then establishing a data set.
3. The ORB feature matching and yolo based air switch state detection method of claim 2, wherein: the step B comprises the following steps:
b1, carrying out data labeling on the air switch area in each equipment image sample in the data set through a rectangular frame, wherein the data labeling is to record the position (x, y, w, h) of the air switch area in the image and the state (on and off) of the air switch, wherein (x, y) represents the coordinates of the upper left corner of the image, and w and h represent the width and height of the air switch area respectively;
b2, dividing the data set processed in the step B1 into a training set and a testing set;
b3, setting yolo model parameters, training by using a training set, and exporting the yolo model when the accuracy of the test set reaches 99%.
4. The ORB feature matching and yolo based air switch state detection method of claim 1, 2 or 3, wherein: the step C comprises the following steps:
c1, respectively deducting each air switch in each equipment image sample in the data set as a standard template;
c2, respectively extracting OEB feature points of each standard template, and generating corresponding feature vectors according to the feature points;
and C3, numbering and recording each standard template according to the position information corresponding to the standard template.
5. The ORB feature matching and yolo-based air switch state detection method of claim 4, wherein: and in the step E, selecting a corresponding standard template according to the position in the step D.
6. The ORB feature matching and yolo based air switch state detection method of claim 1, 2 or 3, wherein: step H also includes: when the air state of the switch is abnormal, a background alarm is given; and when the missing detection exists, sending a verification signal to the staff.
7. Air switch state detection device based on ORB characteristic matching and yolo, its characterized in that: the method comprises the following steps:
a dataset creation module: the inspection robot is used for controlling the inspection robot to shoot equipment image samples containing the air switch at a specified place in a specified posture so as to establish a data set, and recording the position and the posture when each image sample is shot;
a preprocessing module: training and deriving a yolo model from the device image samples of the data set; standard templates corresponding to the air switches are manufactured according to the equipment image samples of the data set, feature point extraction is carried out on the standard templates, and corresponding feature vectors are generated;
a characteristic point acquisition module: the inspection robot is used for controlling the inspection robot to shoot an equipment image containing the air switch to be detected according to the recorded position and posture, and extracting characteristic points of the equipment image and generating a corresponding characteristic vector;
a feature matching module: the device comprises a characteristic point acquisition module, a standard template acquisition module, a transmission transformation matrix acquisition module and a characteristic point acquisition module, wherein the characteristic point acquisition module is used for acquiring characteristic points and characteristic vectors of the standard template and performing RANSAC characteristic matching on the characteristic points and the characteristic vectors respectively to position an air switch to be detected in the device image, acquire the transmission transformation matrix to correct the device image, and then perform ROI (region of interest) deduction on the corrected device image according to a characteristic matching result to obtain a switch image to be detected which is basically consistent with the standard template;
the identification and alarm module: the system comprises a yolo model, a position acquisition module and a position acquisition module, wherein the yolo model is used for inputting images of switches to be detected into the preprocessed yolo model to obtain the position and the state of each switch, and the number of the air switches is determined according to the number of the positions; and comparing the number and the state of the switches with the management background data of the power company, judging whether the state of the air switch is abnormal or not and whether the detection is missed or not, and giving an alarm if the state is abnormal or the detection is missed.
8. The ORB feature matching and yolo based air switch state detection apparatus of claim 7, wherein: before the data set is established, the data set establishing module is used for establishing the data set after image processing operations of mirror image overturning, translation transformation, affine transformation, random noise adding and random brightness change are carried out on the image samples of the equipment.
9. The ORB feature matching and yolo based air switch state detection apparatus of claim 7, wherein: be provided with the industry camera that can reciprocate on patrolling and examining the robot.
10. The ORB feature matching and yolo based air switch state detection apparatus of claim 7, wherein: the feature point obtaining module specifically includes:
a deduction module: the air switches are used for respectively deducting the air switches in the image samples of the equipment in the data set and used as standard templates;
an extraction module: the system comprises a standard template, a data processing module and a data processing module, wherein the standard template is used for extracting OEB characteristic points of the standard template and generating corresponding characteristic vectors according to the characteristic points;
a numbering module: and the system is used for numbering and recording each standard template according to the position information corresponding to the standard template.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110017776.4A CN112749656B (en) | 2021-01-07 | 2021-01-07 | ORB feature matching and yolo-based air switch state detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110017776.4A CN112749656B (en) | 2021-01-07 | 2021-01-07 | ORB feature matching and yolo-based air switch state detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112749656A true CN112749656A (en) | 2021-05-04 |
| CN112749656B CN112749656B (en) | 2023-06-20 |
Family
ID=75650252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110017776.4A Active CN112749656B (en) | 2021-01-07 | 2021-01-07 | ORB feature matching and yolo-based air switch state detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749656B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191350A (en) * | 2021-06-03 | 2021-07-30 | 河南科技大学 | Method and equipment for detecting state of switch knob of aircraft cockpit |
| CN113674352A (en) * | 2021-07-28 | 2021-11-19 | 浙江大华技术股份有限公司 | Switch state detection method, electronic device and storage medium |
| CN115578630A (en) * | 2022-11-09 | 2023-01-06 | 广东科凯达智能机器人有限公司 | Method and system for judging working gear of air switch |
| CN116935079A (en) * | 2023-09-07 | 2023-10-24 | 深圳金三立视频科技股份有限公司 | Linear switch state monitoring method and terminal based on vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
| CN110059556A (en) * | 2019-03-14 | 2019-07-26 | 天津大学 | A kind of transformer substation switch division condition detection method based on deep learning |
| CN110570392A (en) * | 2019-07-26 | 2019-12-13 | 深圳供电局有限公司 | method, device, system, equipment and medium for detecting on-off state of substation equipment |
| CN111738109A (en) * | 2020-06-09 | 2020-10-02 | 杭州古德微机器人有限公司 | Van-type cargo vehicle carriage door state identification method based on deep learning |
-
2021
- 2021-01-07 CN CN202110017776.4A patent/CN112749656B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957325A (en) * | 2010-10-14 | 2011-01-26 | 山东鲁能智能技术有限公司 | Substation equipment appearance abnormality recognition method based on substation inspection robot |
| CN110059556A (en) * | 2019-03-14 | 2019-07-26 | 天津大学 | A kind of transformer substation switch division condition detection method based on deep learning |
| CN110570392A (en) * | 2019-07-26 | 2019-12-13 | 深圳供电局有限公司 | method, device, system, equipment and medium for detecting on-off state of substation equipment |
| CN111738109A (en) * | 2020-06-09 | 2020-10-02 | 杭州古德微机器人有限公司 | Van-type cargo vehicle carriage door state identification method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 许志瑜;章海兵;: "一种变电站智能巡检机器人的仪表图像空间变换算法", 电工技术 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191350A (en) * | 2021-06-03 | 2021-07-30 | 河南科技大学 | Method and equipment for detecting state of switch knob of aircraft cockpit |
| CN113674352A (en) * | 2021-07-28 | 2021-11-19 | 浙江大华技术股份有限公司 | Switch state detection method, electronic device and storage medium |
| CN115578630A (en) * | 2022-11-09 | 2023-01-06 | 广东科凯达智能机器人有限公司 | Method and system for judging working gear of air switch |
| CN116935079A (en) * | 2023-09-07 | 2023-10-24 | 深圳金三立视频科技股份有限公司 | Linear switch state monitoring method and terminal based on vision |
| CN116935079B (en) * | 2023-09-07 | 2024-02-20 | 深圳金三立视频科技股份有限公司 | Linear switch state monitoring method and terminal based on vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112749656B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112749656A (en) | Air switch state detection method and device based on ORB feature matching and yolo | |
| CN112766103B (en) | Machine room inspection method and device | |
| CN112131936B (en) | Inspection robot image recognition method and inspection robot | |
| CN109308447A (en) | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN111144401A (en) | Touch screen control operation method for deep learning and visual servo of power plant centralized control room | |
| CN113822882A (en) | Circuit board surface defect detection method and device based on deep learning | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN113343998A (en) | Reading monitoring system and method for electric power mechanical meter, computer equipment and application | |
| CN111740699A (en) | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle | |
| CN111597868A (en) | SSD-based substation disconnecting switch state analysis method | |
| CN117119170A (en) | Camera holder testing method | |
| CN112304965A (en) | Multi-scene fuse box visual detection system | |
| CN116840240A (en) | Visual detection system of power supply distributor | |
| CN111951161A (en) | Target identification method and system and inspection robot | |
| CN114594102B (en) | Machine vision-based data line interface automatic detection method | |
| CN110909653B (en) | Method for automatically calibrating screen cabinet of distribution room by indoor robot | |
| CN106846302B (en) | Detection method for correctly taking tool and examination table based on method | |
| CN113139541B (en) | Power distribution cabinet dial nixie tube visual identification method based on deep learning | |
| CN112927222B (en) | Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN | |
| CN111652055B (en) | Intelligent switch instrument identification method based on two-stage positioning | |
| CN115147591A (en) | Transformer equipment infrared image voltage heating type defect diagnosis method and system | |
| CN114792328A (en) | Infrared thermal imaging image processing and analyzing method | |
| CN113012125A (en) | Automatic pincard checking method and system for semiconductor CP (content provider) equipment based on image recognition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |