CN104794707A - Automatic extraction method of insulator chain infrared imagery disk and steel cap area - Google Patents
Automatic extraction method of insulator chain infrared imagery disk and steel cap area Download PDFInfo
- Publication number
- CN104794707A CN104794707A CN201510161115.3A CN201510161115A CN104794707A CN 104794707 A CN104794707 A CN 104794707A CN 201510161115 A CN201510161115 A CN 201510161115A CN 104794707 A CN104794707 A CN 104794707A
- Authority
- CN
- China
- Prior art keywords
- insulator chain
- insulator
- steel cap
- infrared image
- region
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Disclosed is an automatic extraction method of an insulator chain infrared imagery disk and steel cap area. The automatic extraction method includes preprocessing insulator chain infrared images taken on the site into binary images, extracting characteristic sets reflecting an insulator chain from the binary images by the morphological method, applying Hough transformation to correct angle of the binary images, and finally extracting the disk and steel cap area of insulators by the specific algorithm in area extraction. The automatic extraction method specifically includes steps of (1) image preprocessing; (2) extraction of insulator characteristics; (3) oblique angle correction of the insulator chain and (4) extraction of the insulator chain disk and steel cap area; (5) division results according to the insulator chain original infrared images of the step (1) and position information of the disk and steel cap area of the step (4). The insulator disk and steel cap edges in the binary images can be subjected to morphological processing and statistical analysis to obtain the ideal analysis results and then are divided and extracted to obtain good extraction effect.
Description
Technical field
The present invention relates to the extraction method in a kind of insulator chain infrared image card and steel cap region, belong to high-tension power transmission and transformation equipment operation maintenance service technique field.
Background technology
Porcelain suspended insulator (calling insulator in the following text) is the primary insulation parts in electrical network, plays the effect of mechanical support simultaneously.Find that the performance degradation of insulator is the important leverage of power transmission and transforming equipment safe and stable operation as early as possible in power transmission and transforming equipment operation maintenance service technique field, and be directly connected to the safety and stability of electrical network and the reliability to customer power supply.
Porcelain insulator card or steel cap Temperature Distribution can characterize insulator state, therefore, the information obtaining insulator card and steel cap is most important, in infrared image, the automatic identification extraction of insulator is then basic steps wherein, and prior art still can not realize the automatic extraction of insulator steel cap and card information in insulator chain infrared image.
Summary of the invention
The object of the invention is, according to the defect that existing porcelain insulator card or the information extraction of steel cap exist, the present invention proposes the extraction method that a kind of application image treatment technology realizes insulator steel cap and card region in insulator chain infrared image.
The technical scheme of the extraction method in the present invention's a kind of insulator chain infrared image card and steel cap region is, the insulator chain infrared image of shooting is carried out pre-service and obtains binary map, then use morphological method from binary map, extract the characteristic set of reflection insulator chain, application Hough transform carries out angularity correction to binary map, extracts card and the steel cap region of insulator finally by the special algorithm in extracted region.
The method of the invention comprises the following steps:
(1) Image semantic classification: pre-service is carried out to the original infrared image of insulator chain, comprises infrared image gray processing, denoising and binaryzation; This step is input as the insulator chain infrared image of shooting, and Output rusults is the binary map of insulator chain and background primary segmentation in infrared image;
(2) insulator feature extraction: use morphological method to extract the characteristic set of reflection insulator chain from binary map, the Output rusults of this step is the feature set binary map in the insulator chain region after morphological dilations process;
(3) angle of inclination of insulator chain corrects: after application Hough transform extracts the length of insulator and horizontal tilt angle, carry out angle of inclination correction to the insulator chain in the binary map in insulator chain region, the Output rusults of this step is postrotational insulator chain binary map;
(4) insulator chain steel cap and card extracted region: this step is input as the bianry image after the correction of angle of inclination, and Output rusults is bianry image and the positional information in card and steel cap region;
(5) card exported according to the original infrared image of insulator chain and the step (4) of step (1) and steel cap zone position information obtain segmentation result.
The process of described insulator chain Infrared images pre-processing is:
Step 101: infrared image gray processing;
Step 102: image denoising;
Step 103: image binaryzation.
The described process extracting the characteristic set of reflection insulator chain is:
Step 201: the morphology skeletonizing of bianry image;
Step 202: the right-angled intersection point extracting skeleton diagram;
Step 203: the morphological dilations of bianry image.
Described insulator angle of inclination trimming process is:
Step 301: insulator chain characteristic set Hough transform;
Step 302: insulator backbone length and horizontal tilt angle calculate;
Step 303: insulator chain level correction.
Described insulator chain steel cap and card extracted region process are:
Step 401: morphological dilations, corrosion area filter;
Step 402: angle is counter to be corrected.
Advantage of the present invention and beneficial effect are, the present invention is converted into simple binary morphology and mathematical statistics problem extracted region problem abstract for complexity, namely Morphological scale-space and statistical study are carried out to the edge of insulator card and steel cap in bianry image, obtain optimal analysis result, then carry out algorithm of the present invention segmentation to extract, achieve good extraction effect.The present invention can realize insulator steel cap and card region in insulator chain infrared image automatic, accurately extract, the fault diagnosis for insulator provides the necessary technical support.
The inventive method is applicable to the automatic extraction in insulator chain infrared image card and steel cap region.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of insulator chain infrared image card provided by the invention and steel cap region extraction method;
Fig. 2 is the collection of illustrative plates of each step of the embodiment of the present invention;
Fig. 2 (a) is the infrared image figure containing insulator chain; The infrared image binary map that Fig. 2 (b) is insulator chain; The feature set binary map that Fig. 2 (c) is insulator chain; Fig. 2 (d) is the insulator chain binary map after angularity correction; Fig. 2 (e) is card region binary map; Fig. 2 (f) is the binary map in steel cap region; Fig. 2 (g) is card region segmentation result figure; Fig. 2 (h) is steel cap region segmentation result figure.
Embodiment
Content of the present invention is further illustrated below in conjunction with drawings and Examples.
Embodiment:
Step 1: Image semantic classification.Infrared image Fig. 2 (a) containing insulator chain is input to Image semantic classification program, obtains insulator chain infrared image binary map Fig. 2 (b).
Step 2: insulator feature extraction.Insulator chain infrared image binary map Fig. 2 (b) is input to insulator feature extraction program, obtains feature set binary map Fig. 2 (c) of insulator chain.
Step 3: the angle of inclination of insulator corrects.Feature set binary map Fig. 2 (c) of insulator chain is input to insulator angle of inclination correction program, obtains insulator chain binary map Fig. 2 (d) after angularity correction.
Step 4: insulator chain steel cap and card extracted region.Insulator chain binary map Fig. 2 (d) after angularity correction is input to insulator chain steel cap and card area extraction program, obtains the binary map Fig. 2 (f) in card region binary map Fig. 2 (e) and steel cap region.
Step 5: export card region segmentation result figure Fig. 2 (g), steel cap region segmentation result figure Fig. 2 (h).
Claims (5)
1. the extraction method in an insulator chain infrared image card and steel cap region, it is characterized in that, the insulator chain infrared image of shooting is carried out pre-service and obtains binary map by described method, then use morphological method from binary map, extract the characteristic set of reflection insulator chain, application Hough transform carries out angularity correction to binary map, extracts card and the steel cap region of insulator finally by the special algorithm in extracted region; The step of described method is:
(1) Image semantic classification: pre-service is carried out to the original infrared image of insulator chain, comprises infrared image gray processing, denoising and binaryzation; This step is input as the insulator chain infrared image of shooting, and Output rusults is the binary map of insulator chain and background primary segmentation in infrared image;
(2) insulator feature extraction: use morphological method to extract the characteristic set of reflection insulator chain from binary map, the Output rusults of this step is the feature set binary map in the insulator chain region after morphological dilations process;
(3) angle of inclination of insulator chain corrects: after application Hough transform extracts the length of insulator and horizontal tilt angle, carry out angle of inclination correction to the insulator chain in the binary map in insulator chain region, the Output rusults of this step is postrotational insulator chain binary map;
(4) insulator chain steel cap and card extracted region: this step is input as the bianry image after the correction of angle of inclination, and Output rusults is bianry image and the positional information in card and steel cap region;
(5) card exported according to the original infrared image of insulator chain and the step (4) of step (1) and steel cap zone position information obtain segmentation result.
2. the extraction method in a kind of insulator chain infrared image card according to claim 1 and steel cap region, is characterized in that, the process of described insulator chain Infrared images pre-processing is:
(1) infrared image gray processing;
(2) image denoising;
(3) image binaryzation.
3. the extraction method in a kind of insulator chain infrared image card according to claim 1 and steel cap region, is characterized in that, the described process extracting the characteristic set of reflection insulator chain is:
(1) the morphology skeletonizing of bianry image;
(2) the right-angled intersection point of skeleton diagram is extracted;
(3) morphological dilations of bianry image.
4. the extraction method in a kind of insulator chain infrared image card according to claim 1 and steel cap region, is characterized in that, described insulator chain angle of inclination trimming process is:
(1) insulator chain characteristic set Hough transform;
(2) insulator backbone length and horizontal tilt angle calculate;
(3) insulator chain level correction.
5. the extraction method in a kind of insulator chain infrared image card according to claim 1 and steel cap region, is characterized in that, described insulator chain steel cap and card extracted region process are:
(1) morphological dilations, corrosion area filter;
(2) angle is counter corrects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510161115.3A CN104794707A (en) | 2015-04-08 | 2015-04-08 | Automatic extraction method of insulator chain infrared imagery disk and steel cap area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510161115.3A CN104794707A (en) | 2015-04-08 | 2015-04-08 | Automatic extraction method of insulator chain infrared imagery disk and steel cap area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104794707A true CN104794707A (en) | 2015-07-22 |
Family
ID=53559487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510161115.3A Pending CN104794707A (en) | 2015-04-08 | 2015-04-08 | Automatic extraction method of insulator chain infrared imagery disk and steel cap area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104794707A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261011A (en) * | 2015-09-22 | 2016-01-20 | 武汉大学 | Extraction method for extracting insulator out of complex background figure during routing inspection and aerial photograph process of unmanned plane |
| CN107240141A (en) * | 2017-05-19 | 2017-10-10 | 华南理工大学 | A kind of paper fibre cellulose fiber two-dimensional structure method for reconstructing based on image procossing |
| CN107507194A (en) * | 2017-08-07 | 2017-12-22 | 广东电网有限责任公司珠海供电局 | A kind of insulator chain fault detection method based on infrared image temperature distributing rule and BP neural network |
| CN108332713A (en) * | 2018-01-16 | 2018-07-27 | 安徽慧视金瞳科技有限公司 | A kind of inclined detection method of insulator pin |
| CN108986104A (en) * | 2018-06-04 | 2018-12-11 | 国网浙江省电力有限公司检修分公司 | Insulator image partition method based on range conversion and Based On Method of Labeling Watershed Algorithm |
| CN109146852A (en) * | 2018-07-30 | 2019-01-04 | 国网江苏省电力有限公司电力科学院研究院 | A kind of porcelain insulating substring chapeau de fer disk edge detection method based on infrared image |
| CN110136131A (en) * | 2019-05-24 | 2019-08-16 | 贵州电网有限责任公司 | A kind of zero resistance insulator detection method based on deep learning |
| TWI731502B (en) * | 2019-12-09 | 2021-06-21 | 國立臺灣科技大學 | Intelligent detection method and system for power equipment failures |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001088837A1 (en) * | 2000-05-16 | 2001-11-22 | Fidelica Microsystems, Inc. | Method and apparatus for pressure sensing |
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
-
2015
- 2015-04-08 CN CN201510161115.3A patent/CN104794707A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001088837A1 (en) * | 2000-05-16 | 2001-11-22 | Fidelica Microsystems, Inc. | Method and apparatus for pressure sensing |
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
Non-Patent Citations (2)
| Title |
|---|
| 李唐兵 等: "绝缘子串红外图像中绝缘子盘面和钢帽区域的自动提取方法", 《红外技术》 * |
| 陈芳 等: "绝缘子串红外图像中单个绝缘子盘面的提取方法", 《电网技术》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261011A (en) * | 2015-09-22 | 2016-01-20 | 武汉大学 | Extraction method for extracting insulator out of complex background figure during routing inspection and aerial photograph process of unmanned plane |
| CN105261011B (en) * | 2015-09-22 | 2017-12-15 | 武汉大学 | A kind of unmanned plane inspection is taken photo by plane the extracting method of insulator in complex background image |
| CN107240141A (en) * | 2017-05-19 | 2017-10-10 | 华南理工大学 | A kind of paper fibre cellulose fiber two-dimensional structure method for reconstructing based on image procossing |
| CN107240141B (en) * | 2017-05-19 | 2019-10-18 | 华南理工大学 | A kind of paper fibre cellulose fiber two-dimensional structure method for reconstructing based on image procossing |
| CN107507194A (en) * | 2017-08-07 | 2017-12-22 | 广东电网有限责任公司珠海供电局 | A kind of insulator chain fault detection method based on infrared image temperature distributing rule and BP neural network |
| CN108332713A (en) * | 2018-01-16 | 2018-07-27 | 安徽慧视金瞳科技有限公司 | A kind of inclined detection method of insulator pin |
| CN108986104A (en) * | 2018-06-04 | 2018-12-11 | 国网浙江省电力有限公司检修分公司 | Insulator image partition method based on range conversion and Based On Method of Labeling Watershed Algorithm |
| CN109146852A (en) * | 2018-07-30 | 2019-01-04 | 国网江苏省电力有限公司电力科学院研究院 | A kind of porcelain insulating substring chapeau de fer disk edge detection method based on infrared image |
| CN110136131A (en) * | 2019-05-24 | 2019-08-16 | 贵州电网有限责任公司 | A kind of zero resistance insulator detection method based on deep learning |
| TWI731502B (en) * | 2019-12-09 | 2021-06-21 | 國立臺灣科技大學 | Intelligent detection method and system for power equipment failures |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104794707A (en) | Automatic extraction method of insulator chain infrared imagery disk and steel cap area | |
| US11905926B2 (en) | Method and apparatus for inspecting wind turbine blade, and device and storage medium thereof | |
| CN107257161B (en) | Transformer substation disconnecting link remote control auxiliary checking method and system based on state recognition algorithm | |
| CN204155293U (en) | A kind of demo plant based on recognition of face and verification system | |
| WO2016082618A1 (en) | Power-grid-gis-based meteorological data calling and preprocessing method and system | |
| CN112116540B (en) | Gear identification method and system for knob switch | |
| CN103940824A (en) | Air electric transmission line insulator detecting method | |
| CN104217425B (en) | Superpixel-based electric transmission and transformation equipment infrared fault image segmentation method | |
| CN108009547A (en) | A kind of nameplate recognition methods of substation equipment and device | |
| CN112784853B (en) | Terminal connection state detection method and device | |
| CN105261011A (en) | Extraction method for extracting insulator out of complex background figure during routing inspection and aerial photograph process of unmanned plane | |
| CN106778752A (en) | A kind of character recognition method | |
| CN108921844A (en) | A kind of defects of insulator detection method and device | |
| CN111310899B (en) | Power defect identification method based on symbiotic relation and small sample learning | |
| CN112418089A (en) | Gesture recognition method and device and terminal | |
| CN111830051A (en) | Transformer substation equipment oil leakage detection method and detection system based on deep learning | |
| CN109145879B (en) | Method, equipment and storage medium for identifying printing font | |
| WO2017041552A1 (en) | Texture feature extraction method and apparatus | |
| CN105469097A (en) | Transformer station feature extraction method based on nerve network | |
| CN111767777B (en) | Transformer substation disconnecting switch state analysis method based on image processing algorithm | |
| CN113726824B (en) | Fraud website searching method and system based on image characteristics | |
| CN114061476A (en) | Deflection detection method for insulator of power transmission line | |
| CN114639022A (en) | Switch cabinet on-off state identification method and system based on SUFR template matching | |
| CN113762384B (en) | Defect detection method and device for insulator image | |
| CN110298875A (en) | A kind of method that three-dimensional laser point cloud data obtains tree height automatically |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150722 |