CN105426825B - A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification - Google Patents
A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification Download PDFInfo
- Publication number
- CN105426825B CN105426825B CN201510754209.1A CN201510754209A CN105426825B CN 105426825 B CN105426825 B CN 105426825B CN 201510754209 A CN201510754209 A CN 201510754209A CN 105426825 B CN105426825 B CN 105426825B
- Authority
- CN
- China
- Prior art keywords
- image
- substation
- shaft tower
- power grid
- gray
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000010586 diagram Methods 0.000 title claims abstract description 30
- 238000013461 design Methods 0.000 claims abstract description 35
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 230000002787 reinforcement Effects 0.000 claims abstract description 4
- 238000005260 corrosion Methods 0.000 claims description 12
- 230000007797 corrosion Effects 0.000 claims description 12
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 239000003518 caustics Substances 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000006740 morphological transformation Effects 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 239000000463 material Substances 0.000 abstract description 3
- 230000009466 transformation Effects 0.000 description 3
- 235000015170 shellfish Nutrition 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
Abstract
The invention discloses it is a kind of based on Aerial Images identification power grid geographical wiring diagram method for drafting, choose substation, shaft tower characteristic value, be fitted and make template;The interception image frame from video of taking photo by plane;Gradation conversion is carried out to image;Carry out histogram equalization reinforcement;Obtain binaryzation design sketch;Obtain denoising effect figure;Obtain containing only the foreground picture of marginal information;Obtain doubtful substation, shaft tower graph outline;The edge contour information of extraction is matched with the feature templates of substation, shaft tower, successful match marks;The connection of the key point of substation or shaft tower is plotted in power grid geographical wiring diagram;Artificial nucleus are to power grid geographical wiring diagram;Invention has the advantages of high efficiency, and position is accurate, and error rate is low, the problem of using manpower and material resources sparingly, realizes computer automatic drafting, substantially increases the efficiency and accuracy of the drafting of power grid geographical wiring diagram.
Description
Technical field:
The present invention relates to power grid geographical wiring diagram method for drafting more particularly to a kind of power grid based on Aerial Images identification
Manage wiring drawing drawing method.
Background technology:
For traditional power grid geographical wiring diagram by experienced Electric Power Network Planning personnel hand drawn, this method efficiency is low
Under, a large amount of manpower and materials are expended, and position is inaccurate, and mistake easily occur.
Invention content:
A kind of flexible and convenient, high efficiency, standard are provided it is an object of the invention to overcome the shortcomings of above-mentioned prior art
Really the power grid geographical wiring diagram method for drafting based on Aerial Images identification.
The purpose of the present invention can be reached by following measure:A kind of power grid geography wiring based on Aerial Images identification
Drawing drawing method is as follows:
Step 1: according to national grid modular design handbook design scheme selection substation, the characteristic value of shaft tower, then make
The characteristic value of substation, shaft tower is fitted with " least square method ";Characteristic value is then made into template;
Step 2: being shot to the required region for drawing power grid geographical wiring diagram using satellite or unmanned plane, obtain
It takes photo by plane video, then the interception image frame from video of taking photo by plane;
Step 3: carrying out gradation conversion to image;Detailed process is as follows:
R, G and B triple channel image are converted into single channel gray-scale map, i.e. Three-channel data is converted to gradation data, conversion
Formula is as follows:
(1)
Wherein, R is the red channel in image, and G is the green channel in image, and B is the blue channel in image;
Step 4: the figure to gradation conversion carries out histogram equalization reinforcement, the marginal information in image is made to reinforce;Specifically
Process is as follows:
If variable γ is pixel grayscale in gray-scale map;Gray-scale map is by formula(1)It is converted to by rgb space,
Gray level in imageThe probability of appearance
In formula,For sum of all pixels in gray level image,It is that gray level isNumber of pixels,It is grey in gray-scale map
The sum of grade is spent, it willWithRelationship show in rectangular coordinate system, obtained figure is exactly histogram;
The iterated integral distribution function of gray-scale map exports image gray levelsForFunction
(2)
Using formula(2), it is by gray level in input gray level figureEach pixel-map to output gradation of image grade
ForRespective pixel obtain output image, obtain histogram equalization design sketch;
Step 5: histogram equalization design sketch is obtained binaryzation design sketch by adaptive threshold fuzziness;Specific mistake
Journey is as follows:
Histogram equalization is determined according to the pixel Distribution value of the neighborhood block of histogram equalization design sketch gray-level pixels
Change the binary-state threshold on design sketch gray-level pixels position;
Step 6: binaryzation design sketch to be carried out to the denoising of morphological transformation, denoising effect figure is obtained;Detailed process
It is as follows:
(1)The point on binaryzation design sketch is subjected to convolution with core using caustic solution, and convolution results are put into and two
On the point in the identical new image of point coordinates on value design sketch, to calculate the minimum value of core region pixel;And it obtains
Image after one corrosion;Wherein, core is that the centre of 3 × 3 pixels carries the solid disk of reference point;
(2)Expansion is the inverse operations of corrosion, i.e., core calculates the pixel in the region of kernel covering with after the image convolution after corrosion
The maximum value of point, and this maximum value is assigned to the point in new image identical with the point coordinates on the image after corrosion
On, the image finally obtained is design sketch after denoising;
Step 7: by denoising effect figure by Canny edge detections, the foreground picture for containing only marginal information is obtained, specifically
Process is as follows:
(1)With Gaussian filter smoothed image;
WhereinFor the abscissa and ordinate of denoising effect figure,For variance
(2)Amplitude and the direction of gradient are calculated with the finite difference of single order local derviation;
(3)Non-maxima suppression is carried out to gradient magnitude;
(4)Edge is detected and connected with dual threashold value-based algorithm;
Step 8: by the foreground picture for containing only marginal information progress contours extract obtain substation, shaft tower characteristic value wheel
Wide number, and each profile is saved in the form of profile tree, draw out each profile of foreground picture one by one according to profile tree,
Obtain doubtful substation, shaft tower graph outline, detailed process is as follows:
In OpenCV(Open Source Computer Vision Library)In extraction objective contour function be
FindCoutours, can identify the profile of foreground picture, wherein the input picture of findCoutours be a width bianry image i.e.
The foreground picture of marginal information, findCoutours output be marginal information foreground picture in each connected region profile point
Set;The set of profile point includes the number information put on profile number and each profile, and can be according to the set of profile point
Draw out doubtful substation, shaft tower graph outline;
Step 9: the edge contour information of extraction is matched with the feature templates of substation, shaft tower, successful match
Shaft tower is marked using mapping software with a point on the diagram, and the substation of successful match uses mapping software by substation
Four angles mark;Detailed process is as follows:
(1)Acquisition extract doubtful substation, shaft tower graph outline characteristic value;
(2)Sample is created using the graph outline characteristic value of doubtful substation, shaft tower, utilizes sample training decision tree, shellfish
Four kinds of Ye Si, support vector machines and k nearest neighbor sorter models, when at least there are three graders to doubtful power transformation in four kinds of graders
It stands, when result that the graph outline of shaft tower is differentiated is consistent, then the result differentiated is substation or shaft tower;
Step 10: using the connecting line graphic element representation in G language specification by substation or the key point of shaft tower
Connection is plotted in power grid geographical wiring diagram;It is as follows:
It is identified as the figure of 220kV substations, its four angle connections are marked using blue lines, are identified as 110kV changes
Its four angle connections are marked using red lines, are identified as the figure of 35kV substations, use yellow line by the figure in power station
Its four angle connections are marked;It is identified as the figure of 220kV shaft towers, it is connected one by one using blue line segment and is described;It is identified as
It is connected using red line segment and is described, is identified as the figure of 35kV shaft towers, use yellow line by the figure of 110kV shaft towers one by one
Section connects it one by one to be described;
Step 11: artificial nucleus are as follows power grid geographical wiring diagram:
The drawn power grid geographical wiring diagram of manual examination and verification G language corrects the substation's shape and line for deviateing physical location
It moves towards on road.
The present invention can generate following good effect compared with the prior art:The present invention is painted for present situation power grid geographical wiring diagram
Method inefficiency processed, position are inaccurate, and error rate is high, the problem of expending a large amount of manpower and materials, realize computer automatic drafting,
Substantially increase the efficiency and accuracy of the drafting of power grid geographical wiring diagram.
Description of the drawings:
Fig. 1 is the flow chart of the present invention;
Fig. 2 is the interception image frame figure from video of taking photo by plane of the present invention;
Fig. 3 is the gradation conversion figure of the present invention;
Fig. 4 is the Equalization Histogram of the present invention;
Fig. 5 is the binaryzation design sketch of the present invention;
Fig. 6 is the denoising effect figure of the present invention;
Fig. 7 is the edge detection design sketch of the present invention;
Fig. 8 is that the G language of the present invention draws power grid geographical wiring diagram;
Fig. 9 is the power grid geographical wiring diagram after the artificial correction of the present invention.
Specific implementation mode:
The following further describes the specific embodiments of the present invention with reference to the drawings, embodiments of the present invention include but
It is not limited to the following example.
Embodiment:A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification(Referring to Fig. 1-Fig. 9), tool
Steps are as follows for body:
Step 1: according to national grid modular design handbook design scheme selection substation, the characteristic value of shaft tower, then make
The characteristic value of substation, shaft tower is fitted with " least square method ".Such as pass through cat head shaft tower, gate tower, wineglass tower, dry word
Turriforms, insulator chain length, the conducting wire information such as type tower, Crimea tower, upper font tower, single column tower, stretched wire type tower identify
Shaft tower and voltage class;By the color of substation, shape, size, floor plan, lightning rod, transformer identify power transformation
It stands and voltage class.Characteristic value is then made into template.
Step 2: being shot to the required region for drawing power grid geographical wiring diagram using satellite or unmanned plane, obtain
It takes photo by plane video, then the interception image frame from video of taking photo by plane;
Step 3: carrying out gradation conversion to image;Detailed process is as follows:
R, G and B triple channel image are converted into single channel gray-scale map, i.e. Three-channel data is converted to gradation data, conversion
Formula is as follows:
(1)
Wherein, R is the red channel in image, and G is the green channel in image, and B is the blue channel in image;
Step 4: the figure to gradation conversion carries out histogram equalization reinforcement, the marginal information in image is made to reinforce;Specifically
Process is as follows:
If variable γ is pixel grayscale in gray-scale map;Gray-scale map is by formula(1)It is converted to by rgb space,
Gray level in imageThe probability of appearance
In formula,For sum of all pixels in gray level image,It is that gray level isNumber of pixels,For gray scale in gray-scale map
The sum of grade, willWithRelationship show in rectangular coordinate system, obtained figure is exactly histogram;
The iterated integral distribution function of gray-scale map exports image gray levelsForFunction
(2)
Using formula(2), it is by gray level in input gray level figureEach pixel-map to output gradation of image grade
ForRespective pixel obtain output image, obtain histogram equalization design sketch;
Step 5: histogram equalization design sketch is obtained binaryzation design sketch by adaptive threshold fuzziness;Specific mistake
Journey is as follows:
Histogram equalization is determined according to the pixel Distribution value of the neighborhood block of histogram equalization design sketch gray-level pixels
Change the binary-state threshold on design sketch gray-level pixels position;
Step 6: binaryzation design sketch to be carried out to the denoising of morphological transformation, denoising effect figure is obtained;Detailed process
It is as follows:
(1)The point on binaryzation design sketch is subjected to convolution with core using caustic solution, and convolution results are put into and two
On the point in the identical new image of point coordinates on value design sketch, to calculate the minimum value of core region pixel;And it obtains
Image after one corrosion;Wherein, core is that the centre of 3 × 3 pixels carries the solid disk of reference point;
(2)Expansion is the inverse operations of corrosion, i.e., core calculates the pixel in the region of kernel covering with after the image convolution after corrosion
The maximum value of point, and this maximum value is assigned to the point in new image identical with the point coordinates on the image after corrosion
On, the image finally obtained is design sketch after denoising;
Step 7: by denoising effect figure by Canny edge detections, the foreground picture for containing only marginal information is obtained, specifically
Process is as follows:
(1)With Gaussian filter smoothed image;
WhereinFor the abscissa and ordinate of denoising effect figure,For variance
(2)Amplitude and the direction of gradient are calculated with the finite difference of single order local derviation;
(3)Non-maxima suppression is carried out to gradient magnitude;
(4)Edge is detected and connected with dual threashold value-based algorithm;
Step 8: by the foreground picture for containing only marginal information progress contours extract obtain substation, shaft tower characteristic value wheel
Wide number, and each profile is saved in the form of profile tree, draw out each profile of foreground picture one by one according to profile tree,
Obtain doubtful substation, shaft tower graph outline, detailed process is as follows:
In OpenCV(Open Source Computer Vision Library)In extraction objective contour function be
FindCoutours, can identify the profile of foreground picture, wherein the input picture of findCoutours be a width bianry image i.e.
The foreground picture of marginal information, findCoutours output be marginal information foreground picture in each connected region profile point
Set;The set of profile point includes the number information put on profile number and each profile, and can be according to the set of profile point
Draw out doubtful substation, shaft tower graph outline.
Step 9: the edge contour information of extraction is matched with the feature templates of substation, shaft tower, successful match
Shaft tower is marked using mapping software with a point on the diagram, and the substation of successful match uses mapping software by substation
Four angles mark.Detailed process is as follows:
(1)Acquisition extract doubtful substation, shaft tower graph outline characteristic value;
(2)Sample is created using the graph outline characteristic value of doubtful substation, shaft tower, utilizes sample training decision tree, shellfish
Four kinds of Ye Si, support vector machines and k nearest neighbor sorter models, when at least there are three graders to doubtful power transformation in four kinds of graders
It stands, when result that the graph outline of shaft tower is differentiated is consistent, then the result differentiated is substation or shaft tower.
Step 10: using the connecting line graphic element representation in G language specification by substation or the key point of shaft tower
Connection is plotted in power grid geographical wiring diagram.It is as follows:
It is identified as the figure of 220kV substations, its four angle connections are marked using blue lines, are identified as 110kV changes
Its four angle connections are marked using red lines, are identified as the figure of 35kV substations, use yellow line by the figure in power station
Its four angle connections are marked;It is identified as the figure of 220kV shaft towers, it is connected one by one using blue line segment and is described;It is identified as
It is connected using red line segment and is described, is identified as the figure of 35kV shaft towers, use yellow line by the figure of 110kV shaft towers one by one
Section connects it one by one to be described.
Step 11: artificial nucleus are as follows power grid geographical wiring diagram:
The drawn power grid geographical wiring diagram of manual examination and verification G language corrects the substation's shape and line for deviateing physical location
It moves towards on road.
Claims (1)
1. a kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification, is as follows:
Step 1: according to national grid modular design handbook design scheme selection substation, the characteristic value of shaft tower, then use
" least square method " is fitted the characteristic value of substation, shaft tower;Characteristic value is then made into template;
Step 2: being shot to the required region for drawing power grid geographical wiring diagram using satellite or unmanned plane, taken photo by plane
Video, then the interception image frame from video of taking photo by plane;
Step 3: carrying out gradation conversion to image;Detailed process is as follows:
R, G and B triple channel image are converted into single channel gray-scale map, i.e. Three-channel data is converted to gradation data, conversion formula
It is as follows:
(1)
Wherein, R is the red channel in image, and G is the green channel in image, and B is the blue channel in image;
Step 4: the figure to gradation conversion carries out histogram equalization reinforcement, the marginal information in image is made to reinforce;Detailed process
It is as follows:
If variable γ is pixel grayscale in gray-scale map;Gray-scale map is by formula(1)It is converted to by rgb space,
Gray level in imageThe probability of appearance
In formula,For sum of all pixels in gray level image,It is that gray level isNumber of pixels,For in gray-scale map gray level it is total
Number, willWithRelationship show in rectangular coordinate system, obtained figure is exactly histogram;
The iterated integral distribution function of gray-scale map exports image gray levelsForFunction
(2)
Using formula(2), it is by gray level in input gray level figureEach pixel-map to output gradation of image grade be
Respective pixel obtain output image, obtain histogram equalization design sketch;
Step 5: histogram equalization design sketch is obtained binaryzation design sketch by adaptive threshold fuzziness;Detailed process is such as
Under:
Determine that histogram equalization is imitated according to the pixel Distribution value of the neighborhood block of histogram equalization design sketch gray-level pixels
Binary-state threshold on fruit figure gray-level pixels position;
Step 6: binaryzation design sketch to be carried out to the denoising of morphological transformation, denoising effect figure is obtained;Detailed process is such as
Under:
(1)Point and the core on binaryzation design sketch are subjected to convolution using caustic solution, and convolution results are put into and binaryzation
On the point in the identical new image of point coordinates on design sketch, to calculate the minimum value of core region pixel;And obtain one
Image after corrosion;Wherein, core is that the centre of 3 × 3 pixels carries the solid disk of reference point;
(2)Expansion is the inverse operations of corrosion, i.e., core calculates the pixel in the region of kernel covering with after the image convolution after corrosion
Maximum value, and this maximum value is assigned on the point in new image identical with the point coordinates on the image after corrosion, most
The image obtained afterwards is design sketch after denoising;
Step 7: by denoising effect figure by Canny edge detections, the foreground picture for containing only marginal information, detailed process are obtained
It is as follows:
(1)With Gaussian filter smoothed image;
WhereinFor the abscissa and ordinate of denoising effect figure,For variance
(2)Amplitude and the direction of gradient are calculated with the finite difference of single order local derviation;
(3)Non-maxima suppression is carried out to gradient magnitude;
(4)Edge is detected and connected with dual threashold value-based algorithm;
Step 8: by the foreground picture that contains only marginal information progress contours extract obtain substation, shaft tower characteristic value profile
Number, and each profile is saved in the form of profile tree, according to profile tree draw out one by one each profile of foreground picture to get
To doubtful substation, the graph outline of shaft tower, detailed process is as follows:
In OpenCV(Open Source Computer Vision Library)In extraction objective contour function be
FindCoutours, can identify the profile of foreground picture, wherein the input picture of findCoutours be a width bianry image i.e.
The foreground picture of marginal information, findCoutours output be marginal information foreground picture in each connected region profile point
Set;The set of profile point includes the number information put on profile number and each profile, and can be according to the set of profile point
Draw out doubtful substation, shaft tower graph outline;
Step 9: the edge contour information of extraction is matched with the feature templates of substation, shaft tower, the shaft tower of successful match
It is marked on the diagram with a point using mapping software, the substation of successful match uses mapping software by four of substation
Angle marks;Detailed process is as follows:
(1)Acquisition extract doubtful substation, shaft tower graph outline characteristic value;
(2)Using doubtful substation, shaft tower graph outline characteristic value create sample, using sample training decision tree, Bayes,
Four kinds of sorter models of support vector machines and k nearest neighbor, when at least there are three graders to doubtful substation, bar in four kinds of graders
When the result that the graph outline of tower is differentiated is consistent, then the result differentiated is substation or shaft tower;
Step 10: the key point of substation or shaft tower is connected using the connecting line graphic element representation in G language specification
It is plotted in power grid geographical wiring diagram;It is as follows:
It is identified as the figure of 220kV substations, its four angle connections are marked using blue lines, are identified as 110kV substations
Figure, its four angles connection is marked using red lines, is identified as the figure of 35kV substations, using yellow line by its
Four angle connections mark;It is identified as the figure of 220kV shaft towers, it is connected one by one using blue line segment and is described;It is identified as 110kV
It is connected using red line segment and is described, is identified as the figure of 35kV shaft towers by the figure of shaft tower one by one, using yellow line segment by its
Connection describes one by one;
Step 11: artificial nucleus are as follows power grid geographical wiring diagram:
The drawn power grid geographical wiring diagram of manual examination and verification G language, corrects the substation's shape for deviateing physical location and circuit is walked
To.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510754209.1A CN105426825B (en) | 2015-11-09 | 2015-11-09 | A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510754209.1A CN105426825B (en) | 2015-11-09 | 2015-11-09 | A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105426825A CN105426825A (en) | 2016-03-23 |
CN105426825B true CN105426825B (en) | 2018-10-16 |
Family
ID=55505025
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510754209.1A Expired - Fee Related CN105426825B (en) | 2015-11-09 | 2015-11-09 | A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105426825B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108230257A (en) * | 2017-11-15 | 2018-06-29 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic equipment and storage medium |
CN108615253B (en) * | 2018-04-12 | 2022-09-13 | 广东数相智能科技有限公司 | Image generation method, device and computer readable storage medium |
CN108829130A (en) * | 2018-06-11 | 2018-11-16 | 重庆大学 | A kind of unmanned plane patrol flight control system and method |
CN110334651B (en) * | 2019-07-05 | 2023-06-23 | 云南电网有限责任公司电力科学研究院 | Substation coordinate verification method based on transfer learning |
CN111950523A (en) * | 2020-08-28 | 2020-11-17 | 珠海大横琴科技发展有限公司 | Ship detection optimization method and device based on aerial photography, electronic equipment and medium |
CN114430462B (en) * | 2022-04-07 | 2022-07-05 | 北京御航智能科技有限公司 | Unmanned aerial vehicle autonomous photographing parameter adjusting method, device, equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102496030B (en) * | 2011-12-12 | 2013-06-26 | 杭州市电力局 | Identification method and identification device for dangerous targets in power monitoring system |
CN102831393A (en) * | 2012-07-19 | 2012-12-19 | 安徽工业大学 | Rapid image recognizing method of power tower pole outline |
CN102930120B (en) * | 2012-11-20 | 2015-01-21 | 华北电力大学 | Method for automatically drawing power grid and geography wiring diagram based on G language |
US9129355B1 (en) * | 2014-10-09 | 2015-09-08 | State Farm Mutual Automobile Insurance Company | Method and system for assessing damage to infrastructure |
-
2015
- 2015-11-09 CN CN201510754209.1A patent/CN105426825B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN105426825A (en) | 2016-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105426825B (en) | A kind of power grid geographical wiring diagram method for drafting based on Aerial Images identification | |
CN103049763B (en) | Context-constraint-based target identification method | |
CN107871119B (en) | Target detection method based on target space knowledge and two-stage prediction learning | |
CN103400151B (en) | The optical remote sensing image of integration and GIS autoregistration and Clean water withdraw method | |
CN107784661B (en) | Transformer substation equipment infrared image classification and identification method based on region growing method | |
CN108596055B (en) | Airport target detection method of high-resolution remote sensing image under complex background | |
CN110263717B (en) | Method for determining land utilization category of street view image | |
CN103186904B (en) | Picture contour extraction method and device | |
CN106909902B (en) | Remote sensing target detection method based on improved hierarchical significant model | |
CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
CN103727930B (en) | A kind of laser range finder based on edge matching and camera relative pose scaling method | |
CN104881841B (en) | High-tension electricity pylon image split-joint method of taking photo by plane based on edge feature and point feature | |
CN104050446B (en) | Meter pointer image identification method based on pointer width character | |
CN104778721A (en) | Distance measuring method of significant target in binocular image | |
CN105160686B (en) | A kind of low latitude various visual angles Remote Sensing Images Matching Method based on improvement SIFT operators | |
CN107808386A (en) | A kind of sea horizon detection method based on image, semantic segmentation | |
CN105574527A (en) | Quick object detection method based on local feature learning | |
CN102346015A (en) | Method for measuring icing thickness of insulator of power transmission line based on video difference analysis | |
CN105894503A (en) | Method for restoring Kinect plant color and depth detection images | |
CN103984963B (en) | Method for classifying high-resolution remote sensing image scenes | |
CN104598885A (en) | Method for detecting and locating text sign in street view image | |
CN104573685A (en) | Natural scene text detecting method based on extraction of linear structures | |
CN108230376A (en) | Remote sensing image processing method, device and electronic equipment | |
CN102184404B (en) | Method and device for acquiring palm region in palm image | |
CN111160328A (en) | Automatic traffic marking extraction method based on semantic segmentation technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181016 Termination date: 20191109 |