CN110335271B - Infrared detection method and device for electrical component fault - Google Patents
Infrared detection method and device for electrical component fault Download PDFInfo
- Publication number
- CN110335271B CN110335271B CN201910619982.5A CN201910619982A CN110335271B CN 110335271 B CN110335271 B CN 110335271B CN 201910619982 A CN201910619982 A CN 201910619982A CN 110335271 B CN110335271 B CN 110335271B
- Authority
- CN
- China
- Prior art keywords
- visible light
- images
- infrared
- image
- electrical component
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Radiation Pyrometers (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
An infrared detection method and device for electrical component faults comprise the following steps: collecting infrared and visible light images of a normal electrical component as standard images, and collecting the infrared and visible light images of an electrical component to be detected during detection; correspondingly processing the infrared images and the visible light images of the normal component and the electrical component to be detected so as to realize the complete matching of the visible light images and the infrared images; registering the processed visible light images of the component to be measured and the normal electrical component to obtain an affine transformation matrix; carrying out graying processing on the infrared images of the to-be-detected and normal electrical components, and completing registration of two grayscale images by utilizing a visible light image matching matrix of the infrared images; carrying out differential comparison analysis on the gray level images of the two completely matched electrical components to be tested and normal to obtain a differential comparison result; and analyzing the difference comparison result to determine the abnormal condition of the electrical component to be tested. The method and the corresponding detection device realize automatic identification of the fault of the electrical component, and overcome the defects of low efficiency, large workload, high requirement on professional skills of detection personnel and the like of infrared manual detection of the fault of the electrical component.
Description
Technical Field
The invention relates to the field of electrical equipment fault detection, in particular to an infrared detection method and device for electrical component faults.
Background
The electrical components mainly comprise a contactor, a relay, a transformer, a fuse and other switches. Due to long-term use and the influence of factors such as external conditions, the problems of aging, wiring looseness, insulation failure and the like easily occur, if the problems are not found in time and solved, the problems further cause the open circuit and short circuit faults of parts, finally cause the whole electric system to be incapable of working, and possibly harm the life safety of people in serious cases.
The infrared detection technology has the advantages of no shutdown, no contact, convenient operation, visual detection result and the like, and is better applied to the fault detection of electrical equipment. However, in the current infrared detection of faults of key components of electrical equipment, a detector holds an infrared thermal imager to collect infrared images of the electrical components, and then judges the fault conditions through artificial comparison and analysis, so that the workload is large, the efficiency is low, and meanwhile, the detector is required to have better professional skills and abundant practical experience.
Disclosure of Invention
The invention provides an infrared detection method and device for electric component faults, and aims to solve the problems that the existing infrared manual detection method for electric component faults is low in efficiency, large in workload, high in professional skill requirement of detection personnel and the like. Meanwhile, the detection method completes the registration of the infrared images by using the affine transformation matrix obtained by the registration of the visible light images, and solves the problems of high error point rate, low matching success rate and the like when the two infrared images are directly registered.
In a first aspect, the present invention provides a method for infrared detection of a fault in an electrical component, comprising:
s101, acquiring infrared and visible light images of a normal electrical component and archiving the images to be used as standard images, and acquiring the infrared and visible light images of an electrical component to be detected during fault detection;
s102, respectively carrying out corresponding processing on the infrared images and the visible light images of the normal and to-be-detected electrical components so as to realize complete matching of the visible light images and the infrared images;
s103, registering the processed visible light images of the to-be-detected and normal electrical components to obtain an affine transformation matrix;
s104, graying the infrared images of the to-be-detected and normal electrical components to obtain grayscale images of the to-be-detected and normal electrical components, and then completing registration of the grayscale images of the to-be-detected and normal electrical components by using the affine transformation matrix of the visible light image;
s105, carrying out differential comparison analysis on the gray level images of the completely matched electrical components to be detected and normal to obtain a differential comparison result;
and S106, analyzing the difference comparison result and determining the abnormal condition of the electrical component to be tested.
Further, before step S101, the method further includes the following steps:
s001, collecting an infrared image by using an infrared thermal imager;
s002, collecting a visible light image by using a visible light camera;
s003, the thermal infrared imager and the visible light camera are relatively fixed in position, and the mirror surfaces are relatively parallel or have a certain included angle, so that the thermal infrared imager can synchronously acquire visible light images while acquiring infrared thermal images;
the field angle of the visible light camera is larger than that of the thermal infrared imager, so that the infrared image collected by the thermal infrared imager is a part of the visible light image.
Further, the certain included angle in step S003 is set as follows: 170 to 180 degrees.
Further, the step S102 includes intercepting a visible light region completely matching an infrared image of the electrical component to be measured from the visible light image to obtain a first visible light image;
and intercepting a visible light region which is completely matched with the infrared image of the normal electric component from the visible light image of the normal electric component to obtain a second visible light image.
Further, the step S105 includes defining an ROI region of the same and unlimited size in the grayscale images of the two, the ROI region including the complete electrical component;
carrying out difference operation on the two ROI areas to obtain a difference image;
converting a preset temperature difference threshold value into a corresponding gray level threshold value;
comparing the gray value of each pixel point in the differential image with a gray threshold, setting the gray value of the pixel point with the gray value larger than the gray threshold as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold as 0 to form a binary image; and calculating the ratio of the total area of the gray value of 255 in the binary image to the total area of the ROI, if the ratio is larger than a preset area threshold value, judging that the electrical component is abnormal, otherwise, judging that the electrical component is normal.
In a second aspect, the present invention provides an apparatus for infrared detection of a fault in an electrical component according to the above infrared detection method for a fault in an electrical component, comprising:
the image acquisition module is used for acquiring visible light images and infrared images of the electrical component to be detected and acquiring visible light images and infrared images of the normal electrical component to be archived as standard images;
the image processing module is used for completing registration of the infrared images of the to-be-detected and normal electrical components by using the affine transformation matrix of the visible light images of the to-be-detected and normal electrical components, and performing differential comparison analysis to obtain a differential comparison result;
the fault alarm module is used for determining the abnormal condition of the electrical component to be detected according to the image difference comparison analysis result, and sending out a warning if the abnormal condition is judged;
and the diagnosis record storage module is used for storing the diagnosis result of the electric component to be detected and storing the coordinates of the abnormal part of the detected abnormal result.
The thermal infrared imager is used for acquiring infrared images;
the visible light camera is used for collecting visible light images;
the infrared thermal imager and the visible light camera are relatively fixed in position, and the mirror surfaces are relatively parallel or have a certain included angle, so that the infrared thermal imager can synchronously acquire visible light images while acquiring infrared thermal images;
the field angle of the visible light camera is larger than that of the thermal infrared imager, so that the infrared image collected by the thermal infrared imager is a part of the visible light image.
Further, the image processing module includes:
the area intercepting module is used for intercepting a visible light area which is completely matched with an infrared image of the to-be-detected and normal electrical component from the visible light image to obtain a first visible light image and a second visible light image;
the registration module is used for extracting and registering the characteristics of the first visible light image and the second visible light image to obtain an affine transformation matrix, and then the affine transformation matrix is used for completing the registration of the infrared images of the electric component to be detected and the normal electric component;
the difference module is used for dividing ROI areas which are the same and are not limited in size in the two registered gray level images, the areas comprise complete electrical components, and the two ROI areas are subjected to difference operation to obtain difference images; converting a preset temperature difference threshold value into a corresponding gray level threshold value; and comparing the gray value of each pixel point in the differential image with the gray threshold value, setting the gray value of the pixel point with the gray value larger than the gray threshold value as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold value as 0 to form a binary image.
Further, the fault alarm module includes: and calculating the ratio of the total area of the gray value of 255 in the binary image to the total area of the ROI, if the ratio is larger than a preset area threshold value, judging that the electrical component is abnormal, otherwise, judging that the electrical component is normal.
The method and the device provided by the invention realize automatic identification of the electric component fault and solve the problems of low efficiency, large workload, high requirement on professional skills of detection personnel and the like of the current infrared manual detection method for the electric component fault.
Drawings
FIG. 1 is a schematic flow chart of a method for infrared detection of electrical component faults in accordance with the present invention;
FIG. 2 is a schematic diagram of an image acquisition method according to the present invention;
FIG. 3 is a schematic diagram of the infrared and visible image matching of the present invention;
fig. 4 is a schematic structural diagram of an infrared detection device for electrical component failure according to the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and examples.
Fig. 1 is a schematic flow chart of an infrared detection method for electrical component faults according to the present invention. Aiming at the defects of low efficiency, large workload, high requirement on professional skills of detection personnel and the like of the current infrared manual detection method for the faults of the electrical components, the invention provides the infrared detection method for the faults of the electrical components, and the automatic identification of the faults of the electrical components is realized. Referring to fig. 1, the method comprises the following specific steps:
s101, collecting infrared and visible light images of the normal electrical component and archiving the images to be used as standard images, and collecting the infrared and visible light images of the electrical component to be detected during fault detection.
Fig. 2 is a schematic diagram of an image acquisition method according to an embodiment of the present invention. In order to collect the infrared image and the visible light image of the electrical component to be measured and normal, the thermal infrared imager and the visible light camera are required to be relatively fixed in position, and the mirror surface is relatively parallel or has a certain included angle. In order to prevent the electrical components in the collected visible light image and the infrared image from having a certain rotation deviation, the included angle range is preferably: 170-180 degrees. The infrared thermal imager and the visible light camera can be on the same horizontal line or not, and the closest distance between the infrared thermal imager and the visible light camera preferably satisfies that the acquired images all contain electrical components.
It should be noted that, in the embodiment of the present invention, the relative position relationship between the thermal infrared imager and the visible light camera is not specifically limited, and those skilled in the art may adjust the relative position relationship according to actual situations.
The field angle of the visible light camera is larger than that of the thermal infrared imager, so that the acquired infrared image is a part of the visible light image, alpha and beta in fig. 2 are respectively the field angle of the visible light camera and the field angle of the thermal infrared imager, and alpha is larger than beta. Meanwhile, the thermal infrared imager can synchronously acquire visible light images while acquiring infrared thermal images.
S102: and respectively carrying out corresponding processing on the infrared images and the visible light images of the normal and to-be-detected electrical components so as to realize the complete matching of the visible light images and the infrared images.
Fig. 3 is a schematic diagram of infrared and visible light image matching used in an embodiment of the present invention. In this embodiment, the collected infrared image is a part of the visible light image. Known from the imaging principle, the infrared thermal imager and the visible light camera with fixed relative positions have fixed matching positions of the acquired infrared image in the visible light image, so that the visible light image and the infrared image are completely matched, and only a visible light image area matched with the infrared thermography is found in the visible light image, and the embodiment provides the following area intercepting method:
let the pixel of the visible light image f (x, y) be M N, and the pixel of the infrared image g (i, j) be M N, where M > M and N > N, the coordinates e (i) of the three corner points of the object (here, the electrical component) in the infrared image are obtainede，je)、f(if，jf)、g(ig，jg) The three points just form a right triangle, and the coordinates E (x) of the points corresponding to the three corner points are also obtained in the visible light imageE，yE)、F(xF，yF)、G(xG，yG) Then the scaling factor of the object in the visible image relative to the object in the infrared image in the directions of the x-coordinate and the y-coordinate is:
because the focal length and the field angle of the visible light camera are different from those of the thermal infrared imager, the actual sizes of the electrical components in the visible light image and the thermal infrared image are different, and the electrical components can be adjusted through the zoom factor. The coordinates of a corresponding point A of an origin a of the infrared thermography in the visible light image are as follows:
xA＝xE-ie×Δx (3)
yA＝yE-je×Δy (4)
the size of the visible light area matched with the infrared thermography in the total area of the visible light image is as follows:
where w is the width of the region and h is the height of the region.
The fixed point A (x) in the visible light image can be determined through the first calibrationA，yA) And the width w and the height h of the rectangular area, so that the specific position and the area of the visible light area matched with the infrared thermography in the visible light image can be obtained, and then the visible light image collected each time is only required to be intercepted in the area and reduced (or amplified) to the pixel size of the infrared thermography, so that the infrared thermography can be obtainedThe outer image matches the visible light image.
It should be noted that the implementation way of the region interception method when the visible light image and the infrared image are completely matched is not unique, and is not specifically limited herein, and those skilled in the art may perform other implementations according to actual situations.
S103: and registering the processed visible light images of the to-be-measured and normal electrical components to obtain an affine transformation matrix.
Specifically, in the embodiment of the invention, a currently popular SURF algorithm is adopted to extract the feature points of the processed visible light images of the electrical component to be detected and normal, and the algorithm has the characteristics of rotation and scale invariance. In addition, any existing feature extraction algorithm can be used for feature extraction, and the embodiment of the invention is not described again.
After the features are extracted, the embodiment of the invention uses Euclidean distance similarity measurement to perform rough matching, and preferably, uses RANSAC algorithm to eliminate mismatching point pairs so as to optimize the matching result. And finally, solving the optimal affine transformation matrix by using a least square method for the correct matching point pairs.
S104: graying the infrared images of the to-be-measured and normal electrical components to obtain grayscale images of the to-be-measured and normal electrical components, and then completing registration of the grayscale images of the to-be-measured and normal electrical components by using the affine transformation matrix of the visible light image.
S105: and carrying out differential comparison analysis on the gray level images of the completely matched electrical components to be detected and normal to obtain a differential comparison result.
Specifically, first, the same and unlimited size ROI (region of interest) is defined in the two grayscale images, and the region contains the complete electrical components; then, carrying out differential operation on the two ROI areas to obtain a differential image; converting a preset temperature difference threshold value into a corresponding gray level threshold value; and finally, comparing the gray value of each pixel point in the differential image with the gray threshold value, setting the gray value of the pixel point with the gray value larger than the gray threshold value as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold value as 0 to form a binary image.
S106: and analyzing the difference comparison result to determine the abnormal condition of the electrical component to be tested.
And (4) calculating the ratio of the total area of the gray scale value of 255 in the binarized image obtained in the step (S105) to the total area of the ROI, if the ratio is larger than a preset area threshold value, judging that the electrical component is abnormal, otherwise, judging that the electrical component is normal.
According to the embodiment of the invention, firstly, infrared and visible light images of a normal electrical component are collected as standard images, and infrared and visible light images of an electrical component to be detected are collected during detection; secondly, correspondingly processing the infrared images and the visible light images of the normal component and the electrical component to be detected so as to realize the complete matching of the visible light images and the infrared images; registering the processed visible light images of the component to be measured and the normal electrical component to obtain an affine transformation matrix; then, carrying out graying processing on the infrared images of the to-be-detected and normal electrical components, and completing registration of two grayscale images by utilizing a visible light image matching matrix of the infrared images; then, carrying out differential comparison analysis on the gray level images of the two completely matched electrical components to be tested and normal to obtain a differential comparison result; and finally, analyzing the difference comparison result to determine the abnormal condition of the electrical component to be tested. The method and the corresponding detection device realize automatic identification of the electric component fault, and overcome the defects of low efficiency, large workload, high requirement on professional skills of detection personnel and the like of the current infrared manual detection method for the electric component fault. In addition, the infrared detection method for the electric component fault provided by the embodiment of the invention completes the registration of the infrared images by using the affine transformation matrix obtained by the visible light image registration, and solves the problems of high error point rate, low matching success rate and the like when the two infrared images are directly registered.
Fig. 4 is a schematic structural diagram of an infrared detection apparatus for electrical component failure according to the above method according to an embodiment of the present invention. The infrared detection device for the electric component fault provided by the embodiment of the invention can realize the flow of the infrared detection method for the electric component fault, and the device comprises the following components:
s201: the image acquisition module is used for acquiring visible light images and infrared images of the electrical component to be detected, and simultaneously acquiring the visible light images and the infrared images of the normal electrical component to be archived as standard images.
S202: the image processing module is used for completing registration of the infrared images of the to-be-detected and normal electrical components by using the affine transformation matrix of the visible light images of the to-be-detected and normal electrical components, and performing differential comparison analysis to obtain a differential comparison result;
wherein, the image processing module is divided into: the device comprises an area intercepting module, a registering module and a difference module.
The area intercepting module is used for correspondingly processing the infrared images and the visible light images of the normal and to-be-detected electrical components so as to realize the complete matching of the visible light images and the infrared images;
the registration module is used for performing feature extraction and registration on the processed visible light images of the to-be-detected and standard electrical components to obtain an affine transformation matrix, and then completing the registration of the infrared images of the to-be-detected and normal electrical components by using the visible light affine transformation;
and the difference module is used for carrying out difference comparison analysis on the gray level images of the two completely matched electrical components to be tested and normal to obtain a difference comparison result.
Specifically, first, the ROI regions of the same and unlimited size are defined in the two grayscale images, and the regions contain the complete electrical components; then, carrying out differential operation on the two ROI areas to obtain a differential image; converting a preset temperature difference threshold value into a corresponding gray level threshold value; and finally, comparing the gray value of each pixel point in the differential image with the gray threshold value, setting the gray value of the pixel point with the gray value larger than the gray threshold value as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold value as 0 to form a binary image.
S203: and the fault alarm module is used for determining the abnormal condition of the electrical component to be detected according to the image difference comparison analysis result, and sending out a warning if the abnormal condition is judged.
S204: and the diagnosis record storage module is used for storing the diagnosis result of the electric component to be detected and storing the coordinates of the abnormal part of the detected abnormal result.
It should be noted that, for convenience of description, the functional modules are only divided and exemplified by the functional modules, in practical applications, a person skilled in the art may divide different functional modules according to actual situations to complete all or part of the functions, and a specific working process of the apparatus may refer to the operation flow of the electrical component fault infrared detection method, which is not described herein again.
According to the device provided by the embodiment of the invention, firstly, infrared and visible light images of a normal electrical component are collected as standard images, and the infrared and visible light images of the electrical component to be detected are collected during detection; then, completely matching the visible light image and the infrared image of the standard and to-be-detected electrical component by respectively using the infrared image and the visible light image of the standard and to-be-detected electrical component through a fixed region interception method, and registering the processed visible light image of the to-be-detected and standard electrical component to obtain an affine transformation matrix; secondly, carrying out graying processing on the infrared images of the to-be-detected and standard electrical components, and completing registration of two grayscale images by utilizing a visible light image matching matrix of the infrared images; and finally, carrying out differential comparison analysis on the gray level images of the two completely matched electrical components to be detected and the standard electrical component to obtain a differential comparison result, and analyzing the differential comparison result to determine the abnormal condition of the electrical component to be detected, thereby realizing automatic identification of the fault of the electrical component, and overcoming the defects of low efficiency, large workload, high requirement on professional skills of detection personnel and the like of the current infrared manual detection method for the fault of the electrical component.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. An infrared detection method for electric component faults is characterized by comprising the following steps:
s101, acquiring infrared and visible light images of a normal electrical component and archiving the images to be used as standard images, and acquiring the infrared and visible light images of an electrical component to be detected during fault detection;
s102, respectively carrying out corresponding processing on the infrared images and the visible light images of the normal and to-be-detected electrical components so as to realize complete matching of the visible light images and the infrared images;
s103, registering the processed visible light images of the to-be-detected and normal electrical components to obtain an affine transformation matrix;
s104, graying the infrared images of the to-be-detected and normal electrical components to obtain grayscale images of the to-be-detected and normal electrical components, and then completing registration of the grayscale images of the to-be-detected and normal electrical components by using the affine transformation matrix of the visible light image;
s105, carrying out differential comparison analysis on the gray level images of the completely matched electrical components to be detected and normal to obtain a differential comparison result;
and S106, analyzing the difference comparison result and determining the abnormal condition of the electrical component to be tested.
2. The method according to claim 1, wherein before the step S101, further comprising the steps of:
s001, collecting an infrared image by using an infrared thermal imager;
s002, collecting a visible light image by using a visible light camera;
s003, the thermal infrared imager and the visible light camera are relatively fixed in position, and the mirror surfaces are relatively parallel or have a certain included angle, so that the thermal infrared imager can synchronously acquire visible light images while acquiring infrared thermal images;
the field angle of the visible light camera is larger than that of the thermal infrared imager, so that the infrared image collected by the thermal infrared imager is a part of the visible light image.
3. The method of claim 2, wherein the angle in step S003 is in a range of: 170 to 180.
4. The method of claim 1, wherein the processing the infrared image and the visible light image of the normal and the electrical component to be tested respectively to achieve a perfect match between the visible light image and the infrared image comprises:
intercepting a visible light region completely matched with an infrared image of an electrical component to be measured from the visible light image of the electrical component to be measured to obtain a first visible light image;
and intercepting a visible light region which is completely matched with the infrared image of the normal electric component from the visible light image of the normal electric component to obtain a second visible light image.
5. The method according to claim 1, wherein the performing a differential comparison analysis on the gray-scale images of the completely matched electrical components to be tested and normal to obtain a differential comparison result comprises:
defining ROI areas with the same and unlimited size in the gray level images of the two, wherein the ROI areas contain complete electric components;
carrying out difference operation on the two ROI areas to obtain a difference image;
converting a preset temperature difference threshold value into a corresponding gray level threshold value;
and comparing the gray value of each pixel point in the differential image with a gray threshold, setting the gray value of the pixel point with the gray value larger than the gray threshold as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold as 0 to form a binary image.
6. The method according to claim 5, wherein analyzing the differential comparison result to determine an abnormal condition of the electrical component to be tested comprises:
and calculating the ratio of the total area of the gray value of 255 in the binary image to the total area of the ROI, if the ratio is larger than a preset area threshold value, judging that the electrical component is abnormal, otherwise, judging that the electrical component is normal.
7. An infrared detection device of electric component failure according to the method of any one of claims 1 to 6, characterized in that it comprises:
the image acquisition module is used for acquiring visible light images and infrared images of the electrical component to be detected and acquiring visible light images and infrared images of the normal electrical component to be archived as standard images;
the image processing module is used for completing registration of the infrared images of the to-be-detected and normal electrical components by using the affine transformation matrix of the visible light images of the to-be-detected and normal electrical components, and performing differential comparison analysis to obtain a differential comparison result;
the fault alarm module is used for determining the abnormal condition of the electrical component to be detected according to the image difference comparison analysis result, and sending out a warning if the abnormal condition is judged;
and the diagnosis record storage module is used for storing the diagnosis result of the electric component to be detected and storing the coordinates of the abnormal part of the detected abnormal result.
8. The apparatus of claim 7, wherein the image acquisition module comprises:
the thermal infrared imager is used for acquiring infrared images;
the visible light camera is used for collecting visible light images;
the infrared thermal imager and the visible light camera are relatively fixed in position, and the mirror surfaces are relatively parallel or have a certain included angle, so that the infrared thermal imager can synchronously acquire visible light images while acquiring infrared thermal images;
the field angle of the visible light camera is larger than that of the thermal infrared imager, so that the infrared image collected by the thermal infrared imager is a part of the visible light image.
9. The apparatus of claim 7, wherein the image processing module comprises:
the area intercepting module is used for intercepting a visible light area which is completely matched with an infrared image of the to-be-detected and normal electrical component from the visible light image to obtain a first visible light image and a second visible light image;
the registration module is used for extracting and registering the characteristics of the first visible light image and the second visible light image to obtain an affine transformation matrix, and then the affine transformation matrix is used for completing the registration of the infrared images of the electric component to be detected and the normal electric component;
the difference module is used for dividing ROI areas which are the same and are not limited in size in the two registered gray level images, the areas comprise complete electrical components, and the two ROI areas are subjected to difference operation to obtain difference images; converting a preset temperature difference threshold value into a corresponding gray level threshold value; and comparing the gray value of each pixel point in the differential image with the gray threshold value, setting the gray value of the pixel point with the gray value larger than the gray threshold value as 255, and setting the gray value of the pixel point with the gray value smaller than or equal to the gray threshold value as 0 to form a binary image.
10. The apparatus of claim 9, wherein the fault alarm module comprises:
and calculating the ratio of the total area of the gray value of 255 in the binary image to the total area of the ROI, if the ratio is larger than a preset area threshold value, judging that the electrical component is abnormal, otherwise, judging that the electrical component is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910619982.5A CN110335271B (en) | 2019-07-10 | 2019-07-10 | Infrared detection method and device for electrical component fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910619982.5A CN110335271B (en) | 2019-07-10 | 2019-07-10 | Infrared detection method and device for electrical component fault |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110335271A CN110335271A (en) | 2019-10-15 |
| CN110335271B true CN110335271B (en) | 2021-05-25 |
Family
ID=68146189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910619982.5A Active CN110335271B (en) | 2019-07-10 | 2019-07-10 | Infrared detection method and device for electrical component fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110335271B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110850723B (en) * | 2019-12-02 | 2023-01-03 | 西安科技大学 | Fault diagnosis and positioning method based on transformer substation inspection robot system |
| CN111156655A (en) * | 2019-12-24 | 2020-05-15 | 珠海格力电器股份有限公司 | Air conditioner main control board fault self-detection method and air conditioner |
| CN111062941B (en) * | 2019-12-31 | 2024-04-19 | 深圳爱克莱特科技股份有限公司 | Point light source fault detection device and method |
| CN111815560B (en) * | 2020-06-09 | 2024-04-05 | 理光软件研究所（北京）有限公司 | Photovoltaic power station fault detection method and device, portable detection equipment and storage medium |
| CN114783141A (en) * | 2022-04-24 | 2022-07-22 | 王江湖 | Fire safety system |
| CN115661016B (en) * | 2022-12-08 | 2023-04-18 | 瑞纳智能设备股份有限公司 | Fault monitoring method and system of heat exchange station and embedded image diagnosis control platform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102305664A (en) * | 2011-05-19 | 2012-01-04 | 中国农业大学 | Thermal imaging temperature measurement and fault location inspection system |
| CN102800097A (en) * | 2012-07-19 | 2012-11-28 | 中国科学院自动化研究所 | Multi-feature multi-level visible light and infrared image high-precision registering method |
| CN105388414A (en) * | 2015-10-23 | 2016-03-09 | 国网山西省电力公司大同供电公司 | Omnidirectional fault automatic identification method of isolation switch |
| US9286718B2 (en) * | 2013-09-27 | 2016-03-15 | Ortery Technologies, Inc. | Method using 3D geometry data for virtual reality image presentation and control in 3D space |
| CN107025648A (en) * | 2017-03-20 | 2017-08-08 | 中国人民解放军空军工程大学 | A kind of board failure infrared image automatic testing method |
| CN107179494A (en) * | 2017-05-27 | 2017-09-19 | 浙江万里学院 | Device fault detection method and system on a kind of general-purpose circuit board plate |
| CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
| CN109859101A (en) * | 2019-01-18 | 2019-06-07 | 黑龙江八一农垦大学 | The recognition methods of corps canopy thermal infrared images and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103487729B (en) * | 2013-09-06 | 2016-04-27 | 广东电网公司电力科学研究院 | Based on the power equipments defect detection method that ultraviolet video and infrared video merge |
| JP6289142B2 (en) * | 2014-02-07 | 2018-03-07 | キヤノン株式会社 | Image processing apparatus, image processing method, program, and storage medium |
| CN106257535B (en) * | 2016-08-11 | 2019-05-21 | 河海大学常州校区 | Electrical equipment based on SURF operator is infrared and visible light image registration method |
-
2019
- 2019-07-10 CN CN201910619982.5A patent/CN110335271B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102305664A (en) * | 2011-05-19 | 2012-01-04 | 中国农业大学 | Thermal imaging temperature measurement and fault location inspection system |
| CN102800097A (en) * | 2012-07-19 | 2012-11-28 | 中国科学院自动化研究所 | Multi-feature multi-level visible light and infrared image high-precision registering method |
| US9286718B2 (en) * | 2013-09-27 | 2016-03-15 | Ortery Technologies, Inc. | Method using 3D geometry data for virtual reality image presentation and control in 3D space |
| CN105388414A (en) * | 2015-10-23 | 2016-03-09 | 国网山西省电力公司大同供电公司 | Omnidirectional fault automatic identification method of isolation switch |
| CN107025648A (en) * | 2017-03-20 | 2017-08-08 | 中国人民解放军空军工程大学 | A kind of board failure infrared image automatic testing method |
| CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
| CN107179494A (en) * | 2017-05-27 | 2017-09-19 | 浙江万里学院 | Device fault detection method and system on a kind of general-purpose circuit board plate |
| CN109859101A (en) * | 2019-01-18 | 2019-06-07 | 黑龙江八一农垦大学 | The recognition methods of corps canopy thermal infrared images and system |
Non-Patent Citations (1)
| Title |
|---|
| 高分辨率热感图像与可见光图像配准方法研究;卢毅 等;《现代测绘》;20180331;第24-26页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110335271A (en) | 2019-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335271B (en) | Infrared detection method and device for electrical component fault | |
| CN107492091B (en) | Label appearance detection method based on machine vision and terminal equipment | |
| CN109300161B (en) | Positioning method and device based on binocular vision | |
| CN111798407B (en) | Electrified equipment fault diagnosis method based on neural network model | |
| CN108230237B (en) | Multispectral image reconstruction method for electrical equipment online detection | |
| CN106056594A (en) | Double-spectrum-based visible light image extraction system and method | |
| CN107092905B (en) | Method for positioning instrument to be identified of power inspection robot | |
| CN108537170A (en) | A kind of power equipment firmware unmanned plane inspection pin missing detection method | |
| CN109698906B (en) | Image-based jitter processing method and device and video monitoring system | |
| CN106846304B (en) | Electrical equipment detection method and device based on infrared detection | |
| CN106705850B (en) | A kind of terminal quality determining method based on image | |
| CN110617772A (en) | Non-contact type line diameter measuring device and method | |
| CN115359239A (en) | Wind power blade defect detection and positioning method and device, storage medium and electronic equipment | |
| CN111627073B (en) | Calibration method, calibration device and storage medium based on man-machine interaction | |
| CN112595936A (en) | Power transmission line composite insulator intelligent detection system based on unmanned aerial vehicle patrols and examines | |
| CN113077416A (en) | Welding spot welding defect detection method and system based on image processing | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| CN104966283A (en) | Imaging layered registering method | |
| CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
| CN113269744A (en) | Infrared intelligent identification method and system applied to defects of power transmission line equipment | |
| CN112541478A (en) | Insulator string stain detection method and system based on binocular camera | |
| CN117314986A (en) | Unmanned aerial vehicle cross-mode power distribution equipment inspection image registration method based on semantic segmentation | |
| CN112489017A (en) | Intelligent identification method and system for power equipment faults | |
| CN110619626B (en) | Image processing apparatus, system, method and device | |
| CN115077722B (en) | Partial discharge and temperature comprehensive monitoring system and method applied to high-voltage cabinet |
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 |