CN111523563A - Image comparison method for hydropower station equipment - Google Patents
Image comparison method for hydropower station equipment Download PDFInfo
- Publication number
- CN111523563A CN111523563A CN202010201918.8A CN202010201918A CN111523563A CN 111523563 A CN111523563 A CN 111523563A CN 202010201918 A CN202010201918 A CN 202010201918A CN 111523563 A CN111523563 A CN 111523563A
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- real
- template
- comparison
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 54
- 238000007689 inspection Methods 0.000 abstract description 21
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- 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
Abstract
The invention discloses an image comparison method for hydropower station equipment, which comprises the following steps: shooting a picture of equipment needing to be identified in a power station, and taking the picture as a template image; establishing a template coordinate matrix for pixel points on the template image; shooting a real-time image at the same visual angle position of the shooting template image; establishing a real-time coordinate matrix for pixel points on a real-time image; comparing and matching the template coordinate matrix with the real-time coordinate matrix and establishing a comparison matrix according to a comparison result; and judging the correlation of the images according to the result of the comparison matrix so as to judge the running condition of the equipment. According to the invention, the coordinate matrix formed by the pixel points in the template image and the real-time image is compared, matched and calculated to form the coordinate comparison matrix, and the calculation result of the comparison matrix is used as the operation condition of the judgment equipment, so that a good theoretical basis is provided for the intelligent robot routing inspection of the power station equipment.
Description
Technical Field
The invention relates to the technical field of visual identification, in particular to an image comparison method for hydropower station equipment.
Background
The image comparison and identification is an important means for distinguishing two different objects or different characteristics of the same object by people, and due to the fact that the human nervous system is developed, intelligent calculation and identification have inherent advantages, different images or different similar images can be easily and automatically identified, however, for image identification of a machine, an artificial intelligent algorithm needs to be implanted, identification equipment can judge according to an implanted program, the images can be accurately and respectively located in different positions, and therefore instructions of the next step are guided. In order to realize the intelligent robot inspection of equipment in a power station and reduce the situations of insufficient inspection such as missing inspection, defect inspection and the like caused by manual inspection, an effective inspection identification method needs to be set for the robot inspection of the equipment in the power station, and whether the equipment normally operates in the operation process can be usually displayed from an image of the appearance, such as the color of an indicator light, the on-off state of a switch and the like, the judgment can be carried out through visual identification, the feasibility is provided for the inspection of the robot, and the intelligent identification of the image needs to be realized, so that technical personnel in the field need to design an algorithm for image identification.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the image comparison method for the hydropower station equipment is provided, so that the robot intelligent inspection of the equipment in the hydropower station is realized, the situations of insufficient inspection such as missing inspection, defect inspection and the like caused by manual inspection are reduced, and meanwhile, the labor intensity of inspection personnel of the hydropower station is also reduced.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
an image comparison method for hydropower station equipment comprises the following steps:
s1: shooting a picture of equipment needing to be identified in a power station, and taking the picture as a template image;
s2: establishing a template coordinate matrix for pixel points on the template image;
s3: the real-time image is captured at the same view angle position as the template image in the capturing step S1;
s4: establishing a real-time coordinate matrix for pixel points on a real-time image;
s5: comparing and matching the template coordinate matrix in the step S2 with the real-time coordinate matrix in the step S4, and establishing a comparison matrix according to a comparison result; the comparison matrix is as follows:
wherein T ' (x ', y ') -T (x ', y ') -1/(w · h) · ∑x”,y”T(x”,y”)
I'(x+x',y+y')＝I(x+x',y+y')-1/(w·h)·∑x”,y”I(x+x”,y+y”)
Wherein T (x, y) is a template image matrix, and T' (x, y) is a relative value of the template matrix to a mean value thereof; i (x, y) is a real-time image matrix, I ' (x + x ', y + y ') is a relative value of the real-time image matrix relative to the mean value of the real-time image matrix, w is the width of an image, h is the height of the image, and (x, y) represents the coordinate of a certain pixel point of the image;
s6: and judging the operation condition of the power station equipment according to the result of the comparison matrix.
Further, the matching algorithm in step S5 is a standard correlation matching in OpenCV, that is, method — CV _ TM _ CCORR _ norm.
Further, in step S5, when performing the matching algorithm, the template image matrix and the real-time image matrix are both calculated by using the relative value of the mean value, and the specific matching relationship is as follows: 1 indicates a perfect match, -1 indicates a bad match, and 0 indicates no correlation.
Compared with the prior art, the invention has the following beneficial effects:
the invention sets the pixel points in the image into the coordinate matrix, sets the normal equipment image into a template image, shoots the real-time running condition of the equipment into a real-time image through the shooting device, compares the template image with the coordinate matrix formed by the pixel points in the real-time image to perform matching calculation to form a coordinate comparison matrix, and takes the calculation result of the comparison matrix as the running condition of the judgment equipment, thereby providing a good theoretical basis for the intelligent inspection of the robot of the power station equipment, providing effective guarantee for the intelligent inspection of the robot of the power station, reducing the situations of inspection missing, defect inspection and the like caused by the personnel of the power station, and simultaneously reducing the labor intensity of the personnel of the inspection of the power station.
Detailed Description
The present invention is further illustrated by the following examples, which include, but are not limited to, the following examples.
An image comparison method for hydropower station equipment comprises the following steps:
s1: shooting a picture of equipment needing to be identified in a power station, and taking the picture as a template image; the appearance image of the power station equipment can reflect the color of an operating state indicator lamp when the equipment normally operates, the on-off position of an equipment switch, different numbers displayed by a nixie tube, an oil level indicator, various meters and the like.
S2: establishing a template coordinate matrix for pixel points on the template image; each image is composed of a plurality of pixel points, different image information is formed by the plurality of pixel points which are combined together, one image information is split into the plurality of pixel points to serve as comparison units, and the accuracy of image comparison is improved.
S3: the real-time image is captured at the same view angle position as the template image in the capturing step S1; when the template image is shot, the same point of the robot inspection position is selected for shooting so that the obtained image has comparability with the view finding direction of the template image when the real-time image is shot.
S4: establishing a real-time coordinate matrix for pixel points on a real-time image;
s5: comparing and matching the template coordinate matrix in the step S2 with the real-time coordinate matrix in the step S4, and establishing a comparison matrix according to a comparison result; when the comparison matching is performed, the standard correlation matching in OpenCV, that is, method — TM _ CCORR _ normal is used, and the comparison matching uses the relative value of the template coordinate matrix and the mean value of the real-time coordinate matrix, and the specific comparison formula is as follows:
wherein T ' (x ', y ') -T (x ', y ') -1/(w · h) · ∑x”,y”T(x”,y”)
I'(x+x',y+y')＝I(x+x',y+y')-1/(w·h)·∑x”,y”I(x+x”,y+y”)
Wherein T (x, y) is a template image matrix, and T' (x, y) is a relative value of the template matrix to a mean value thereof; i (x, y) is a real-time image matrix, I ' (x + x ', y + y ') is a relative value of the real-time image matrix relative to the mean value of the real-time image matrix, w is the width of an image, h is the height of the image, and (x, y) represents the coordinate of a certain pixel point of the image;
s6: and judging the operation condition of the power station equipment according to the result of the comparison matrix, wherein the specific matching relationship is as follows: 1 indicates a perfect match, -1 indicates a bad match, and 0 indicates no correlation.
The above-mentioned embodiment is only one of the preferred embodiments of the present invention, and should not be used to limit the scope of the present invention, but all the insubstantial modifications or changes made within the spirit and scope of the main design of the present invention, which still solve the technical problems consistent with the present invention, should be included in the scope of the present invention.
Claims (3)
1. An image comparison method for hydropower station equipment, characterized by: the method comprises the following steps:
s1: shooting a picture of equipment needing to be identified in a power station, and taking the picture as a template image;
s2: establishing a template coordinate matrix for pixel points on the template image;
s3: the real-time image is captured at the same view angle position as the template image in the capturing step S1;
s4: establishing a real-time coordinate matrix for pixel points on a real-time image;
s5: comparing and matching the template coordinate matrix in the step S2 with the real-time coordinate matrix in the step S4, and establishing a comparison matrix according to a comparison result; the comparison matrix is as follows:
wherein T ' (x ', y ') -T (x ', y ') -1/(w · h) · ∑x”,y”T(x”,y”)
I'(x+x',y+y')＝I(x+x',y+y')-1/(w·h)·∑x”,y”I(x+x”,y+y”)
Wherein T (x, y) is a template image matrix, and T' (x, y) is a relative value of the template matrix to a mean value thereof; i (x, y) is a real-time image matrix, I ' (x + x ', y + y ') is a relative value of the real-time image matrix relative to the mean value of the real-time image matrix, w is the width of an image, h is the height of the image, and (x, y) represents the coordinate of a certain pixel point of the image;
s6: and judging the operation condition of the power station equipment according to the result of the comparison matrix.
2. An image comparison method for a hydroelectric power plant according to claim 1, wherein: the matching algorithm in step S5 is a standard correlation matching in OpenCV, that is, method — CV _ TM _ CCORR _ normal.
3. An image comparison method for a hydroelectric power plant according to claim 2, wherein: in step S5, when performing the matching algorithm, the template image matrix and the real-time image matrix are both calculated by using the relative value of the mean value, and the specific matching relationship is as follows: 1 indicates a perfect match, -1 indicates a bad match, and 0 indicates no correlation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201918.8A CN111523563A (en) | 2020-03-20 | 2020-03-20 | Image comparison method for hydropower station equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201918.8A CN111523563A (en) | 2020-03-20 | 2020-03-20 | Image comparison method for hydropower station equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111523563A true CN111523563A (en) | 2020-08-11 |
Family
ID=71901172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010201918.8A Pending CN111523563A (en) | 2020-03-20 | 2020-03-20 | Image comparison method for hydropower station equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523563A (en) |
Citations (7)
| 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 |
| CN102915545A (en) * | 2012-09-20 | 2013-02-06 | 华东师范大学 | OpenCV(open source computer vision library)-based video target tracking algorithm |
| CN104809732A (en) * | 2015-05-07 | 2015-07-29 | 山东鲁能智能技术有限公司 | Electrical equipment appearance abnormity detection method based on image comparison |
| CN107831387A (en) * | 2017-11-03 | 2018-03-23 | 国网江苏省电力公司经济技术研究院 | A kind of electric power station equipment operation condition intelligent monitoring method |
| CN109034535A (en) * | 2018-06-21 | 2018-12-18 | 中国化学工程第六建设有限公司 | Construction site wisdom monitoring method, system and computer readable storage medium |
| CN110648307A (en) * | 2019-07-24 | 2020-01-03 | 国网浙江省电力有限公司湖州供电公司 | Method for checking state of transformer substation pressure plate by using image comparison technology |
| CN111415432A (en) * | 2020-03-20 | 2020-07-14 | 四川华能宝兴河水电有限责任公司 | Intelligent inspection method for hydropower station |
-
2020
- 2020-03-20 CN CN202010201918.8A patent/CN111523563A/en active Pending
Patent Citations (7)
| 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 |
| CN102915545A (en) * | 2012-09-20 | 2013-02-06 | 华东师范大学 | OpenCV(open source computer vision library)-based video target tracking algorithm |
| CN104809732A (en) * | 2015-05-07 | 2015-07-29 | 山东鲁能智能技术有限公司 | Electrical equipment appearance abnormity detection method based on image comparison |
| CN107831387A (en) * | 2017-11-03 | 2018-03-23 | 国网江苏省电力公司经济技术研究院 | A kind of electric power station equipment operation condition intelligent monitoring method |
| CN109034535A (en) * | 2018-06-21 | 2018-12-18 | 中国化学工程第六建设有限公司 | Construction site wisdom monitoring method, system and computer readable storage medium |
| CN110648307A (en) * | 2019-07-24 | 2020-01-03 | 国网浙江省电力有限公司湖州供电公司 | Method for checking state of transformer substation pressure plate by using image comparison technology |
| CN111415432A (en) * | 2020-03-20 | 2020-07-14 | 四川华能宝兴河水电有限责任公司 | Intelligent inspection method for hydropower station |
Non-Patent Citations (1)
| Title |
|---|
| 刘国成: "《人群异常行为数字图像处理与分析》", 30 November 2019, 成都：西南交通大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
| CN104361314B (en) | Based on infrared and transformer localization method and device of visual image fusion | |
| CN101620676B (en) | Fast image recognition method of insulator contour | |
| CN106952280B (en) | A kind of spray gun paint amount uniformity detection method based on computer vision | |
| CN113903081A (en) | Visual identification artificial intelligence alarm method and device for images of hydraulic power plant | |
| CN107610128A (en) | The method for inspecting and device of a kind of oil level indicator | |
| CN107478340A (en) | A kind of converter valve monitoring method and system | |
| CN109687382B (en) | Relay protection pressing plate switching state identification method based on color template matching | |
| CN107749055A (en) | A kind of fault detection method, system and the device of LED traffic guidances screen | |
| CN107103617A (en) | The recognition methods of safety cap wearing state and system based on optical flow method | |
| WO2022028554A1 (en) | Active camera relocalization method having robustness to illumination | |
| CN107595388A (en) | A kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point | |
| CN108830861A (en) | A kind of hybrid optical motion capture method and system | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN107576269A (en) | A kind of transmission line forest fire localization method | |
| CN108734715A (en) | A kind of contact net rigid wire recognition methods of adaptive learning and device | |
| CN106681508A (en) | System for remote robot control based on gestures and implementation method for same | |
| CN105825204A (en) | Method for identifying power equipment meter at night through intelligent camera | |
| CN101561316B (en) | On-line test visual data processing system based on region of interest (ROI) | |
| TWI733616B (en) | Reconition system of human body posture, reconition method of human body posture, and non-transitory computer readable storage medium | |
| CN111523563A (en) | Image comparison method for hydropower station equipment | |
| CN112489018A (en) | Intelligent power line inspection method and inspection line | |
| CN111985436A (en) | Workshop ground mark line identification fitting method based on LSD | |
| CN108074264A (en) | A kind of classification multi-vision visual localization method, system and device | |
| CN111860378A (en) | Market fire-fighting equipment inspection method based on gun-ball linkage and video event perception |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200811 |
|
| RJ01 | Rejection of invention patent application after publication |