CN108416354A - Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity - Google Patents
Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity Download PDFInfo
- Publication number
- CN108416354A CN108416354A CN201810194411.7A CN201810194411A CN108416354A CN 108416354 A CN108416354 A CN 108416354A CN 201810194411 A CN201810194411 A CN 201810194411A CN 108416354 A CN108416354 A CN 108416354A
- Authority
- CN
- China
- Prior art keywords
- shaft tower
- image
- electricity
- transmission line
- carried out
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06V10/30—Noise filtering
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of shaft tower serial number extracting methods based on helicopter routing inspection transmission line of electricity, including the acquisition of helicopter photographic device to include the image of shaft tower number；Enhancing processing is carried out to image；Enhanced image is split；Denoising is carried out to the image after segmentation；Shaft tower number extraction is carried out to the image after denoising.Shaft tower serial number extracting method proposed by the present invention based on helicopter routing inspection transmission line of electricity, target point enhancing can be carried out to collected figure, and carry out target point segmentation and Denoising disposal, Objective extraction accurately is carried out to the shaft tower number image of transmission line of electricity acquisition, is realized to there are failure shaft towers effectively to be positioned in transmission line of electricity.
Description
Technical field
The present invention relates to a kind of shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity, belong to power grid security with
Protection field.
Background technology
In field of power, helicopter routing inspection transmission line of electricity is a very important job, and is had become defeated
The important means of electric line periodic maintenance.Currently, helicopter routing inspection transmission line of electricity is acquired using visible light or infrared mode
Transmission line of electricity image or video are all to carry out failure using manual identified pattern there is no handling the image in video
Positioning, if failure point image or video are not clear enough, manual identified pattern is difficult to be positioned to fault point.
Invention content
The shaft tower number based on helicopter routing inspection transmission line of electricity that in order to solve the above technical problem, the present invention provides a kind of
Extracting method.
In order to achieve the above object, the technical solution adopted in the present invention is：
Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity, including,
The acquisition of helicopter photographic device includes the image of shaft tower number；
Enhancing processing is carried out to image；
Enhanced image is split；
Denoising is carried out to the image after segmentation；
Shaft tower number extraction is carried out to the image after denoising.
The principle of image enhancement is that the information of prominent shaft tower numbering area inhibits other garbages.
Enhanced image is split using threshold division method.
The gray threshold in gradation of image value range is calculated, by the gray value of each pixel in image and gray threshold phase
Compare, corresponding pixel is divided into two classes according to the result of the comparison, a kind of and gray value that gray value is more than gray threshold is small
In the another kind of of gray threshold, the pixel that gray value is equal to gray threshold can be included into one of this two class.
It is calculated using expansion and etch state student movement and denoising is carried out to the image after segmentation.
Shaft tower number extraction process is,
Shaft tower number target point edge detection is carried out to the image after denoising；
Range statistics are carried out to shaft tower number object edge point quantity；
Binary conversion treatment is carried out to image；
Shaft tower number is identified.
Using improved canny edge detection operators method, shaft tower number target point edge is carried out to the image after denoising
Detection.
Shaft tower number is identified by the character recognition method of neural network.
The advantageous effect that the present invention is reached：The shaft tower based on helicopter routing inspection transmission line of electricity that patent of the present invention proposes is compiled
Number extracting method can carry out target point enhancing to collected figure, and carry out target point segmentation and Denoising disposal, accurately
Objective extraction is carried out to the shaft tower number image of transmission line of electricity acquisition, is realized to there are failure shaft towers to carry out effectively in transmission line of electricity
Positioning.
Description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is enhanced image；
Fig. 3 is the image after segmentation；
Fig. 4 is the image after denoising；
Fig. 5 is the image of canny operators detection；
Fig. 6 is the quantity statistics of line direction marginal point；
Fig. 7 is the quantity statistics of column direction marginal point；
Fig. 8 is the figure after binary conversion treatment.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, the shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity, includes the following steps：
Step 1, the acquisition of helicopter photographic device includes the image of shaft tower number.
Step 2, enhancing processing is carried out to image.
Image enhancement selectively protrudes useful information, i.e. shaft tower not using eyefidelity as principle by handling
The information of numbering area inhibits other garbages, to improve the utilization rate of image, is analyzed convenient for people or computer, enhancing
Image afterwards is as shown in Figure 2.
Step 3, enhanced image is split using threshold division method, divide the image into several are specific,
Region with unique properties simultaneously extracts shaft tower number target.
It is highly relevant that image, which is in the gray value between adjacent pixel inside target and background, but is in target and the back of the body
The pixel of scape intersection both sides has prodigious difference on gray value, can calculate figure to this image threshold application partitioning algorithm
As the gray threshold in gray scale value range, the gray value of each pixel in image is compared with gray threshold, according to comparing
Result corresponding pixel is divided into two classes, gray value is more than one kind of gray threshold and gray value is less than the another of gray threshold
One kind, the pixel that gray value is equal to gray threshold can be included into one of this two class.
Two class pixels after segmentation generally adhere to two different zones of image separately, therefore have achieved the purpose that region segmentation,
Image is as shown in Figure 3 after segmentation.
Step 4, it is calculated using expansion and etch state student movement and denoising is carried out to the image after segmentation.
Since image enhancement and image segmentation produce noise, simultaneously because the influence of shaft tower number background so that shaft tower
Equal device ends and target point are in same cut zone, need to carry out denoising to image.
Denoising disposal：Image is corroded first, then expansion be as a result, can make the profile of image become smooth,
It disconnects narrow interruption and eliminates thin protrusion；Secondly, image is expanded, then corrosion is as a result, make up narrow
Interruption and long thin wide gap, eliminate small hole, and fill up the fracture in contour line.Dry processing is carried out to Fig. 3, removes noise
Image afterwards is as shown in Figure 4.
Step 5, shaft tower number extraction is carried out to the image after denoising.
Detailed process is：Using improved canny edge detection operators method, shaft tower number is carried out to the image after denoising
Target point edge detection, range statistics are carried out to shaft tower number object edge point quantity, are carried out binary conversion treatment to image, are used
Shaft tower number is identified in the character identification system of neural network, realizes the Objective extraction numbered to shaft tower.
Edge detection is carried out to Fig. 4 using improved canny edge detection operators, as shown in Figure 5.Due to canny operators
It detects obtained marginal point distribution to concentrate, the column direction that can be expert to the marginal point in Fig. 5 respectively carries out quantity statistics, statistics knot
Fruit is as shown in Figures 6 and 7.According to statistics as a result, the quantity statistics of shaft tower numbered edges point centainly than non-shaft tower number image district
The quantity statistics in domain are more, and after above-mentioned image preprocessing, the quantity of marginal point of target region is much larger than rest part,
Therefore, the average value of the desirable entire image marginal point of the quantity statistics of line direction and column direction is as critical value.If certain a line
Marginal point sum be more than critical value, then may be defined as capable boundary, it is similar that row are similarly compared, find out the side of row
Boundary.1 is arranged to the pixel value in continuous marginal point, other regions are arranged to 0, i.e., carry out binary conversion treatment to Fig. 5, such as scheme
Shown in 8, finally shaft tower number is identified using the character identification system based on neural network.
Patent of the present invention elaborates the Objective extraction side of shaft tower number using the visible images that shaft tower is numbered as object
Greyscale transformation, grey level enhancement, image segmentation, morphology denoising has been respectively adopted, at the shaft tower number image in method
Reason.This method can effectively number shaft tower and carry out Objective extraction, and technical support is provided to the fault location of transmission line of electricity.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (8)
1. the shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity, it is characterised in that：Including,
The acquisition of helicopter photographic device includes the image of shaft tower number；
Enhancing processing is carried out to image；
Enhanced image is split；
Denoising is carried out to the image after segmentation；
Shaft tower number extraction is carried out to the image after denoising.
2. the shaft tower serial number extracting method according to claim 1 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
The principle of image enhancement is that the information of prominent shaft tower numbering area inhibits other garbages.
3. the shaft tower serial number extracting method according to claim 1 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
Enhanced image is split using threshold division method.
4. the shaft tower serial number extracting method according to claim 3 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
The gray threshold in gradation of image value range is calculated, the gray value of each pixel in image is compared with gray threshold, root
Corresponding pixel is divided into two classes according to result of the comparison, gray value is more than one kind of gray threshold and gray value is less than gray scale threshold
What is be worth is another kind of, and the pixel that gray value is equal to gray threshold can be included into one of this two class.
5. the shaft tower serial number extracting method according to claim 1 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
It is calculated using expansion and etch state student movement and denoising is carried out to the image after segmentation.
6. the shaft tower serial number extracting method according to claim 1 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
Shaft tower number extraction process is,
Shaft tower number target point edge detection is carried out to the image after denoising；
Range statistics are carried out to shaft tower number object edge point quantity；
Binary conversion treatment is carried out to image；
Shaft tower number is identified.
7. the shaft tower serial number extracting method according to claim 6 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
Using improved canny edge detection operators method, shaft tower number target point edge detection is carried out to the image after denoising.
8. the shaft tower serial number extracting method according to claim 6 based on helicopter routing inspection transmission line of electricity, it is characterised in that：
Shaft tower number is identified by the character recognition method of neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810194411.7A CN108416354A (en) | 2018-03-09 | 2018-03-09 | Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810194411.7A CN108416354A (en) | 2018-03-09 | 2018-03-09 | Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108416354A true CN108416354A (en) | 2018-08-17 |
Family
ID=63130830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810194411.7A Pending CN108416354A (en) | 2018-03-09 | 2018-03-09 | Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416354A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110502571A (en) * | 2019-08-29 | 2019-11-26 | 智洋创新科技股份有限公司 | A kind of recognition methods of the high-incidence line segment of electric transmission line channel visual alerts |
| CN111242799A (en) * | 2019-12-10 | 2020-06-05 | 国网通用航空有限公司 | High-voltage line tower center coordinate extraction numbering method and medium based on airborne LiDAR point cloud |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7742650B2 (en) * | 2003-11-12 | 2010-06-22 | British Telecommunications Plc | Object detection in images |
| CN104298993A (en) * | 2014-01-09 | 2015-01-21 | 郑州金惠计算机系统工程有限公司 | Pole number positioning and identification method suitable for railway line in complex scene |
| CN106295655A (en) * | 2016-08-03 | 2017-01-04 | 国网山东省电力公司电力科学研究院 | A kind of transmission line part extraction method patrolling and examining image for unmanned plane |
| CN107358795A (en) * | 2017-07-17 | 2017-11-17 | 陈剑桃 | A kind of effective Vehicle License Plate Recognition System |
-
2018
- 2018-03-09 CN CN201810194411.7A patent/CN108416354A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7742650B2 (en) * | 2003-11-12 | 2010-06-22 | British Telecommunications Plc | Object detection in images |
| CN104298993A (en) * | 2014-01-09 | 2015-01-21 | 郑州金惠计算机系统工程有限公司 | Pole number positioning and identification method suitable for railway line in complex scene |
| CN106295655A (en) * | 2016-08-03 | 2017-01-04 | 国网山东省电力公司电力科学研究院 | A kind of transmission line part extraction method patrolling and examining image for unmanned plane |
| CN107358795A (en) * | 2017-07-17 | 2017-11-17 | 陈剑桃 | A kind of effective Vehicle License Plate Recognition System |
Non-Patent Citations (2)
| Title |
|---|
| 田小林等: "《光学相干层析图像处理及应用》", 31 January 2015, 北京理工大学出版社 * |
| 赵婕: "《图像特征提取与语义分析》", 31 July 2015, 重庆大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110502571A (en) * | 2019-08-29 | 2019-11-26 | 智洋创新科技股份有限公司 | A kind of recognition methods of the high-incidence line segment of electric transmission line channel visual alerts |
| CN110502571B (en) * | 2019-08-29 | 2020-05-08 | 智洋创新科技股份有限公司 | Method for identifying visible alarm high-power-generation line segment of power transmission line channel |
| CN111242799A (en) * | 2019-12-10 | 2020-06-05 | 国网通用航空有限公司 | High-voltage line tower center coordinate extraction numbering method and medium based on airborne LiDAR point cloud |
| CN111242799B (en) * | 2019-12-10 | 2024-01-16 | 国网电力空间技术有限公司 | High-voltage line tower center coordinate extraction numbering method and medium based on airborne LiDAR point cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111079747B (en) | Railway wagon bogie side frame fracture fault image identification method | |
| CN109146860B (en) | Full-automatic mechanical equipment installation leakage detection method and device | |
| CN107679495B (en) | Detection method for movable engineering vehicles around power transmission line | |
| CN105631880A (en) | Lane line segmentation method and apparatus | |
| CN103940824A (en) | Air electric transmission line insulator detecting method | |
| CN105374015A (en) | Binary method for low-quality document image based on local contract and estimation of stroke width | |
| CN111967394B (en) | Forest fire smoke root node detection method based on dynamic and static grid fusion strategy | |
| CN101739549B (en) | Face detection method and system | |
| CN103886589A (en) | Goal-oriented automatic high-precision edge extraction method | |
| CN103400120B (en) | Video analysis-based bank self-service area push behavior detection method | |
| Lin et al. | Image segmentation using the k-means algorithm for texture features | |
| CN102831472A (en) | People counting method based on video flowing image processing | |
| CN108416354A (en) | Shaft tower serial number extracting method based on helicopter routing inspection transmission line of electricity | |
| CN109359554A (en) | A kind of forest fire recognition methods based on more composograph processing techniques | |
| CN108799011B (en) | Device and method for monitoring blades of wind turbine generator | |
| CN109389566A (en) | Subway height adjusting valve fastening nut defective mode detection method based on boundary characteristic | |
| CN107886096A (en) | A kind of insulator of transmission line of electricity comes off defect inspection method | |
| CN112115878B (en) | Forest fire smoke root node detection method based on smoke area density | |
| Rasooli et al. | Farsi license plate detection based on element analysis and characters recognition | |
| CN112508913A (en) | Cable section edge detection method based on image detection | |
| CN112115875A (en) | Forest fire smoke root detection method based on dynamic and static combination area stacking strategy | |
| CN105427316B (en) | Insulator single-deck face extracting method in a kind of transmission line of electricity visible images | |
| Shi et al. | Image enhancement for degraded binary document images | |
| CN113487563A (en) | Photovoltaic module subfissure self-adaptive detection method based on EL image | |
| CN108564024A (en) | Switch identification method applied to power station environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180817 |