CN103761722A - Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line - Google Patents
Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line Download PDFInfo
- Publication number
- CN103761722A CN103761722A CN201410020480.8A CN201410020480A CN103761722A CN 103761722 A CN103761722 A CN 103761722A CN 201410020480 A CN201410020480 A CN 201410020480A CN 103761722 A CN103761722 A CN 103761722A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- image
- wing unmanned
- unmanned plane
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a fixed wing unmanned aerial vehicle touring image accurately-splicing method for a power transmission line. The accurately-splicing method includes the following steps: (1) conducting data preparation and sample training; (2) conducting feature extraction on the power transmission line based on textural features and straight line features to obtain a power transmission line distributing area and power transmission line extraction data, screening the power transmission line extraction data through the power transmission line distributing area, and obtaining power transmission line extracting results through power transmission line double-edge features; (3) conducting SIFT image registration and fusing based on power transmission line customization on the power transmission line extracting results. According to the fixed wing unmanned aerial vehicle touring image accurately-splicing method, curvelet transformation is adopted for achieving extraction on power transmission line texture information and detection on power transmission line distribution, and the power transmission line double-edge features in high-resolution unmanned aerial vehicle images are further adopted for obtaining the reliable and accurate power transmission line extracting results.
Description
Technical field
The present invention relates to image split-joint method, be specifically related to a kind of method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane.
Background technology
Existing fixed-wing unmanned plane is maked an inspection tour Image Mosaics technology and is mainly used in mapping aspect, and the joining method of employing is numerous, exist subject matter comprise that splicing precision is not high and splicing speed is slow.
Fixed-wing unmanned plane is maked an inspection tour the not application at present of Image Mosaics aspect, domestic also without relevant achievement report, transmission line of electricity fixed-wing unmanned plane is maked an inspection tour to sequence image to be spliced, form complete power transmission line corridor panoramic picture, particularly corridor information of transmission line of electricity can be provided intuitively accurately, fixed-wing unmanned plane during flying height is high, flight generally reaches 300-500m to ground level, and extra high voltage network wire diameter is generally 30mm left and right, realize transmission line of electricity fixed-wing unmanned plane and make an inspection tour the high-precision joining of image, a kind of brand-new joining method need to be proposed.
It is higher to splicing accuracy requirement that fixed-wing unmanned plane is maked an inspection tour image, wire splicing is a gordian technique point wherein, restriction due to prior art, use existing mapping splicing to carry out transmission line of electricity fixed-wing unmanned plane and make an inspection tour Image Mosaics, there will be obvious problem of misalignment, occurred that wire does not dock, wire moves towards factitious phenomenon.
Summary of the invention
For above deficiency, the object of this invention is to provide a kind of method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane.
For realizing above object, the technical scheme that the present invention has taked is:
For transmission line of electricity fixed-wing unmanned plane, make an inspection tour an accurately method for splicing of image, it comprises the following steps:
Step 1, data are prepared and sample training; Described step 1 comprises the following steps:
Step 1.1, the training subimage that is a plurality of formed objects by sample cutting;
Step 1.2, the bent wave conversion of employing based on USFFT algorithm carry out sample characteristics extraction to described training subimage, to obtain training sample;
Step 1.3, by PCA algorithm, calculate the PCA parameter of described training sample, described PCA parameter comprises mean value vector and projection matrix;
The training of step 1.4, RBF neural network;
Step 2, based on textural characteristics and linear feature to power transmission line feature extraction, to obtain power transmission line distributed areas and power transmission line, extract data; By described power transmission line distributed areas, described power transmission line is extracted to data and screen, by the dual edge feature of power transmission line, obtain power transmission line and extract result;
Step 3, SIFT image registration and fusion that described power transmission line extraction result is customized based on power transmission line.
Described step 1.4 comprises the following steps:
To described training subimage in include power transmission line be labeled as 1, what do not comprise power transmission line is labeled as-1;
Set RBF network parameter, nodes and the number of plies;
The form of random weight of take at least repeats neural metwork training ten times as starting point;
The network weight of the RBF neural network after output has been trained.
Described step 2 comprises the following steps:
Step 2.1, utilize textural characteristics to carry out the detection of power transmission line distributed areas;
Step 2.2, by Canny operator, carrying out the detection of image border, is original candidates edge;
Step 2.3, by Probabilistic Hough Transform, power transmission line is carried out to straight-line detection, complete the extraction of power transmission line, and the power transmission line of fracture is connected, preserve linear position information;
Step 2.4, the result that detects according to power transmission line distributed areas are screened Hough straight-line detection, and the straight line in power transmission line distributed areas is chosen as power transmission line original candidates edge;
Step 2.5, according to following rule, carry out the further screening at power transmission line original candidates edge:
A) direction at original candidates edge meets the direction of the power transmission line calculating according to geography information;
B) length at original candidates edge surpasses the threshold value of appointment;
Step 2.6, by the candidate edge through further screening, choose and be parallel to each other and distance is two straight lines of M pixel, getting its average is reference line, described M=power transmission line diameter/image resolution ratio;
If the reference line not satisfying condition M=M-1 carries out standard straight-line retrieval again, until M=0 is single straight line;
The result that step 2.7, output power transmission line extract.
Described step 2.1 is utilized textural characteristics to carry out the detection of power transmission line distributed areas and is comprised the following steps:
Step 2.1.1, Aerial Images is converted into gray level image;
Step 2.1.2, utilize the pattern of moving window to extract the subregion of gray level image;
Step 2.1.3, every sub regions is carried out to power transmission line regional determination;
Step 2.1.4, go through all over all subregions, complete the region that power transmission line distributes and detect, wherein, district's testing result intermediate value be greater than 0 be power transmission line distributed areas.
Described step 2.1.3 comprises the following steps:
Step 2.1.3.1, to subregion, utilize USFFT algorithm to extract bent wave characteristic;
USFFT algorithm key step comprises:
A) f is done to the Fourier transform that 2DFFT obtains f
B) under every pair of yardstick and angle (j, l) to f[n
1, n
2] sample (or interpolation) obtain f[n again
1, n
2-n
1tan θ
l];
C) by f[n
1, n
2-n
1tan θ
l] and window function U
j[n
1, n
2] multiplying each other obtains f
j,l;
D) by f
j,ldoing contrary 2DFFT conversion obtains bent wave system and counts c
d(i, l, k).
Step 2.1.3.2, antithetical phrase extracted region to feature carry out the Feature Dimension Reduction based on principal component analysis;
Step 2.1.3.3, the feature after utilizing RBF neural network that training obtains to dimensionality reduction are differentiated, if judge, comprising power transmission line is 1 by subregion assignment, otherwise assignment is-1;
Described step 3 comprises the following steps:
Step 3.1, the SIFT feature point detection customizing based on power transmission line;
Step 3.2, unique point are described vector and are generated, and utilize SIFT operator extraction SIFT eigenvector, then extract bent wave characteristic and as unique point, describe vector together with SIFT eigenvector;
The coupling of step 3.3, unique point, the coupling of described unique point is usingd unique point and is described Euclidean distance between vector as the similarity criteria of Feature Points Matching, adopt preferential k-d tree to carry out two approximate KNN unique points that first search is searched each unique point, calculate this unique point Euclidean distance of two the approximate KNN unique points corresponding with it respectively, and calculate the ratio of two Euclidean distances, if ratio is less than threshold value, the match is successful, otherwise, again mate;
Step 3.4, Image Mosaics and fusion, realize the splicing between two width or multiple image by image weighting average method.
Described step 3.1 comprises the following steps:
With SIFT feature point detection algorithm, on the power transmission line extracting, select N unique point, in graphical rule space, travel through the point on all power transmission lines, judge the relation of point in itself and neighborhood, if the value of this point is greater than or less than neighborhood institute value a little, this point is candidate feature point;
In image, other regions utilize SIFT feature point detection algorithm to choose equally N unique point, require distant with described candidate feature point and are evenly distributed in image-region as far as possible.
Between described step 1 and step 2, also comprise image pre-service.
Described image pre-service comprises the following steps:
The geometric calibration that utilizes unmanned plane POS information to carry out Aerial Images, to correct distortion, the distortion of making an inspection tour the image that shooting angle and lens distortion cause due to fixed-wing unmanned plane;
By anisotropic filtering, realize in the situation that fully retaining boundary information image is carried out to denoising.
The present invention is mainly that the power transmission line having proposed based on bent wave conversion and dual edge feature extracts the splicing that the SIFT Feature Correspondence Algorithm customizing with wire is realized image, while having avoided power transmission line fixed-wing unmanned plane to make an inspection tour Sequential images mosaic, there is larger error problem, reduce wrong and a phenomenon unmatching, completed the quick high accuracy splicing that transmission line of electricity fixed-wing unmanned plane is maked an inspection tour sequence image.Its utilization has anisotropic bent wave conversion and realizes the extraction to power transmission line textural characteristics, utilize the thinking that moving window and RBF neural network are differentiated that the problem of power transmission line extraction is converted into the power transmission line test problems that comprises subregion, dual edge feature and texture information by power transmission line are realized the Integrated Selection that power transmission line extracts result, finally utilize the SIFT operator of wire weight to determine the unique point of image, and fully utilize SIFT feature and bent wave characteristic comes the coupling of realization character point to guarantee continuity and the integrality of wire in image registration.
The present invention compared with prior art, its beneficial effect is: the present invention utilizes bent wave conversion to realize the detection to the extraction of power transmission line texture information and power transmission line distribution, also utilize the power transmission line dual edge feature in high resolving power unmanned plane image, obtain the more reliable and result of power transmission line extraction accurately.And the assemblage characteristic vector that adopts feature point detection that wire customizes and SIFT proper vector and bent wave characteristic vector guaranteed the integrality of wire in the accuracy of Image Mosaics and stitching image, the problems such as wire fracture fragmentation have been avoided in traditional images splicing.
The present invention can overcome transmission line of electricity fixed-wing unmanned plane and make an inspection tour the problem that larger error appears in Sequential images mosaic, eliminate dislocation and mate phenomenon by mistake, complete transmission line of electricity fixed-wing unmanned plane and make an inspection tour the quick high accuracy splicing of sequence image, complete clear the representing of realizing the whole generaI investigation information of transmission line of electricity.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that power transmission line extracts;
Fig. 2 is the schematic flow sheet of Image Mosaics.
Embodiment
Below in conjunction with the drawings and specific embodiments, content of the present invention is described in further details.
Embodiment
For the fixed-wing unmanned plane of power industry, make an inspection tour image higher to Image Mosaics technical requirement, Major Difficulties is that wire there will be dislocation, the not first-class phenomenon of docking when splicing.The present invention mainly can be divided into 4 parts: data are prepared, and power transmission line extracts, the coupling of image and splicing, image registration and fusion.
The present invention is directed to the deficiency of only utilizing the marginal information of image in traditional power transmission line extractive technique, by thering is anisotropic bent wave conversion, extract the textural characteristics in image, realize the estimation to power transmission line distributed areas.According to the two-wire feature of power transmission line in high-definition picture, realize the further screening of the power transmission line to extracting again, the power transmission line that completes the high robust of high accuracy extracts.
On the basis of extracting at power transmission line, on power transmission line, choose SIFT unique point, in image, SIFT feature point detection is carried out in other regions simultaneously, the SIFT feature that guarantees power transmission line count with image in other unique point numbers basically identical, and in traditional SIFT proper vector, supplement the feature based on bent wave conversion, finally utilize Euclidean distance to determine that the unique point of coupling completes registration and the fusion of image.The flow process that power transmission line extracts please refer to shown in Fig. 1, and the flow process that images match and splicing are merged please refer to shown in Fig. 2.Concrete technical step is as follows:
1. the preparation of data and the training of sample
1) data are prepared: the training subimage that is 100 * 100 by sample cutting
2) calculating PCA(Principal Component Analysis principal component analysis (PCA)), PCA algorithm be a kind of conventional based on variable covariance matrix to information process, the effective ways of compression and extracting.
A) utilize in step 2 1) method introduced carries out sample characteristics extraction
B) computation of mean values vector, the parameters such as projection matrix
3) the RBF(Radial Basis Function radial basis function) training of neural network
A) to subimage in comprise power transmission line and be labeled as 1, what do not comprise power transmission line is labeled as-1
B) set RBF network parameter, nodes and the number of plies
C) take the form of random weight carries out neural metwork training as starting point.(at least repeating ten times)
D) output RBF neural network, training result.
2. image pre-service
Mainly being divided into two steps is first to carry out geometric calibration and figure image intensifying.
1) geometric calibration: the geometric calibration that utilizes unmanned plane POS information to carry out Aerial Images, correct distortion, the distortion of due to fixed-wing unmanned plane, making an inspection tour the image that shooting angle and lens distortion cause.
2) figure image intensifying: realize in the situation that fully retaining boundary information image is carried out to denoising by anisotropic filtering.
3. based on texture information and wire dual edge unique point power transmission line, extract
1) the power transmission line distributed areas based on bent wave conversion are detected:
A) image is converted into gray level image;
B) utilize the subregion of the pattern extraction image of moving window;
C) by bent wave conversion, extract feature;
2) utilize in step 1 2) the PCA parameter that obtains carries out Feature Dimension Reduction;
A) feature after dimensionality reduction is carried out based in step 1 3) in the differentiation of the RBF neural network that obtains, and this region of mark is 1;
B) in repeating step 3 4) c～f step until image go through all over complete;
C) according to the judgement situation of subregion, extract power transmission line distributed areas (mark value >0).
3) based on power transmission line candidate edge extracting
A) image is converted into gray level image;
B) by Canny operator, carrying out the detection of image border, is original candidates edge;
C) by Probabilistic Hough Transform, complete the extraction of power transmission line, and the power transmission line of fracture is connected, preserve linear position information.
4) screening of the power transmission line based on bent wave conversion and power transmission line dual edge feature
A) according to the power transmission line distributed areas that obtain, carry out the preliminary screening at power transmission line candidate edge;
B) through in the candidate edge of preliminary screening, carry out based on direction the screening of the base attributes such as length;
C), by the candidate edge through further screening, choose and be parallel to each other and distance is no more than M(M<5) two straight lines of individual pixel, getting its average is reference line.
D) if the reference line not satisfying condition M=M-1 carry out again standard straight-line retrieval, until M=0 is single straight line.
E) in original candidates edge, utilize probability Hough to carry out potential power transmission line extraction, be strictly parallel to reference line, and parallel distance meets parallel wire separation criteria, continuity requirement reduction.
F) power transmission line that output is extracted.
4. the SIFT image registration and the fusion that based on power transmission line, customize
1) the SIFT feature point detection customizing based on wire
1. the method for choosing with SIFT unique point is selected N unique point on the power transmission line extracting.In graphical rule space, travel through the point on all power transmission lines, judge the relation of point in itself and neighborhood, if the value of this point is greater than or less than neighborhood institute value a little, this point is candidate feature point
2. in image, other regions utilize N unique point of SIFT feature point detection algorithm picks, require with step 1) in the power transmission line unique point selected distant and be evenly distributed as far as possible with image-region in.
2) unique point is described vector generation: utilize SIFT operator extraction 128 dimensional feature vectors, then extract bent wave characteristic and as unique point, describe vector together with SIFT feature.
3) coupling of unique point: the Euclidean distance of usining between descriptor is as the similarity criteria of Feature Points Matching.Adopt preferential k-d tree to carry out two approximate KNN unique points that first search is searched each unique point, as find out unique point p Euclidean distance recently and time near two neighbours' unique point q ' and q "; then calculate p and q ' and p and q " ratio r of Euclidean distance between two group descriptors, if ratio r is less than defined threshold T, be considered as that the match is successful, receiving station is a pair of match point in image sequence to (p, q '), otherwise it fails to match.
4) Image Mosaics and fusion: by image weighting average method, realize the splicing between two width or multiple image.
Above-listed detailed description is for the illustrating of possible embodiments of the present invention, and this embodiment is not in order to limit the scope of the claims of the present invention, and the equivalence that all the present invention of disengaging do is implemented or change, all should be contained in the scope of the claims of this case.
Claims (9)
1. for transmission line of electricity fixed-wing unmanned plane, make an inspection tour an accurately method for splicing of image, it is characterized in that, it comprises the following steps:
Step 1, data are prepared and sample training; Described step 1 comprises the following steps:
Step 1.1, the training subimage that is a plurality of formed objects by sample cutting;
Step 1.2, the bent wave conversion of employing based on USFFT algorithm carry out sample characteristics extraction to described training subimage, to obtain training sample;
Step 1.3, by PCA algorithm, calculate the PCA parameter of described training sample, described PCA parameter comprises mean value vector and projection matrix;
The training of step 1.4, RBF neural network;
Step 2, based on textural characteristics and linear feature to power transmission line feature extraction, to obtain power transmission line distributed areas and power transmission line, extract data; By described power transmission line distributed areas, described power transmission line is extracted to data and screen, by the dual edge feature of power transmission line, obtain power transmission line and extract result;
Step 3, SIFT image registration and fusion that described power transmission line extraction result is customized based on power transmission line.
2. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 1, is characterized in that, described step 1.4 comprises the following steps:
To described training subimage in include power transmission line be labeled as 1, what do not comprise power transmission line is labeled as-1;
Set RBF network parameter, nodes and the number of plies;
The form of random weight of take at least repeats neural metwork training ten times as starting point;
The network weight of the RBF neural network after output has been trained.
3. according to the method for making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane described in claim 1-2 any one, it is characterized in that, described step 2 comprises the following steps:
Step 2.1, utilize textural characteristics to carry out the detection of power transmission line distributed areas;
Step 2.2, by Canny operator, carrying out the detection of image border, is original candidates edge;
Step 2.3, by Probabilistic Hough Transform, power transmission line is carried out to straight-line detection, complete the extraction of power transmission line, and the power transmission line of fracture is connected, preserve linear position information;
Step 2.4, the result that detects according to power transmission line distributed areas are screened Hough straight-line detection, and the straight line in power transmission line distributed areas is chosen as power transmission line original candidates edge;
Step 2.5, according to following rule, carry out the further screening at power transmission line original candidates edge:
A) direction at original candidates edge meets the direction of the power transmission line calculating according to geography information;
B) length at original candidates edge surpasses the threshold value of appointment;
Step 2.6, by the candidate edge through further screening, choose and be parallel to each other and distance is two straight lines of M pixel, getting its average is reference line, described M=power transmission line diameter/image resolution ratio;
If the reference line not satisfying condition M=M-1 carries out standard straight-line retrieval again, until M=0 is single straight line;
The result that step 2.7, output power transmission line extract.
4. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 3, is characterized in that, described step 2.1 is utilized textural characteristics to carry out the detection of power transmission line distributed areas and comprised the following steps:
Step 2.1.1, Aerial Images is converted into gray level image;
Step 2.1.2, utilize the pattern of moving window to extract the subregion of gray level image;
Step 2.1.3, every sub regions is carried out to power transmission line regional determination;
Step 2.1.4, go through all over all subregions, complete the region that power transmission line distributes and detect, wherein, area detection result intermediate value be greater than 0 be power transmission line distributed areas.
5. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 4, is characterized in that, described step 2.1.3 comprises the following steps:
Step 2.1.3.1, to subregion, utilize USFFT algorithm to extract bent wave characteristic;
Step 2.1.3.2, antithetical phrase extracted region to bent wave characteristic carry out the Feature Dimension Reduction based on principal component analysis;
Step 2.1.3.3, the feature after utilizing RBF neural network that training obtains to dimensionality reduction are differentiated, if judge, comprise power transmission line by region corresponding to testing result all assignment be 1, otherwise assignment is-1.
6. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 5, is characterized in that, described step 3 comprises the following steps:
Step 3.1, the SIFT feature point detection customizing based on power transmission line;
Step 3.2, unique point are described vector and are generated, and utilize SIFT operator extraction SIFT eigenvector, then extract bent wave characteristic and as unique point, describe vector together with SIFT eigenvector;
The coupling of step 3.3, unique point, the coupling of described unique point is usingd unique point and is described Euclidean distance between vector as the similarity criteria of Feature Points Matching, adopt preferential k-d tree to carry out two approximate KNN unique points that first search is searched each unique point, calculate this unique point Euclidean distance of two the approximate KNN unique points corresponding with it respectively, and calculate the ratio of two Euclidean distances, if ratio is less than threshold value, the match is successful, otherwise, again mate;
Step 3.4, Image Mosaics and fusion, realize the splicing between two width or multiple image by image weighting average method.
7. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 6, is characterized in that, described step 3.1 comprises the following steps:
With SIFT feature point detection algorithm, on the power transmission line extracting, select N unique point, in graphical rule space, travel through the point on all power transmission lines, judge the relation of point in itself and neighborhood, if the value of this point is greater than or less than neighborhood institute value a little, this point is candidate feature point;
In image, other regions utilize SIFT feature point detection algorithm to choose equally N unique point, require distant with described candidate feature point and are evenly distributed in image-region as far as possible.
8. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 1, is characterized in that, also comprises image pre-service between described step 1 and step 2.
9. method of making an inspection tour the accurate splicing of image for transmission line of electricity fixed-wing unmanned plane according to claim 8, is characterized in that, described image pre-service comprises the following steps:
The geometric calibration that utilizes unmanned plane POS information to carry out Aerial Images, to correct distortion, the distortion of making an inspection tour the image that shooting angle and lens distortion cause due to fixed-wing unmanned plane;
By anisotropic filtering, realize in the situation that fully retaining boundary information image is carried out to denoising.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410020480.8A CN103761722B (en) | 2014-01-16 | 2014-01-16 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410020480.8A CN103761722B (en) | 2014-01-16 | 2014-01-16 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103761722A true CN103761722A (en) | 2014-04-30 |
| CN103761722B CN103761722B (en) | 2015-03-11 |
Family
ID=50528955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410020480.8A Active CN103761722B (en) | 2014-01-16 | 2014-01-16 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103761722B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139374A (en) * | 2015-07-09 | 2015-12-09 | 天津航天中为数据系统科技有限公司 | Power transmission line tracking method and system |
| CN105825207A (en) * | 2016-04-20 | 2016-08-03 | 北京航空航天大学 | Fragmented high-voltage line detection method and device |
| CN106355580A (en) * | 2016-09-22 | 2017-01-25 | 云南电网有限责任公司电力科学研究院 | Detection method and device of tilting pole tower |
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
| CN106932688A (en) * | 2017-04-24 | 2017-07-07 | 国家电网公司 | Power transmission line detector and the power transmission line detecting system based on unmanned plane |
| CN106971453A (en) * | 2017-04-06 | 2017-07-21 | 深圳怡化电脑股份有限公司 | The method and device of bank note fragments mosaicing |
| CN108377033A (en) * | 2018-04-20 | 2018-08-07 | 国网辽宁省电力有限公司沈阳供电公司 | Polling transmission line based on multi-rotor unmanned aerial vehicle compares modification system with line map |
| CN108496188A (en) * | 2017-05-31 | 2018-09-04 | 深圳市大疆创新科技有限公司 | Method, apparatus, computer system and the movable equipment of neural metwork training |
| CN109544608A (en) * | 2018-03-22 | 2019-03-29 | 广东电网有限责任公司清远供电局 | A kind of unmanned plane Image Acquisition feature registration method |
| CN110827335A (en) * | 2019-11-01 | 2020-02-21 | 北京推想科技有限公司 | Mammary gland image registration method and device |
| US10692200B2 (en) | 2018-04-25 | 2020-06-23 | Microsoft Technology Licensing, Llc | Sensor location determination for geographical region |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038691A1 (en) * | 2005-04-07 | 2007-02-15 | Emmanuel Candes | Methods for performing fast discrete curvelet transforms of data |
| CN102722734A (en) * | 2012-05-23 | 2012-10-10 | 南京航空航天大学 | Image target identification method based on curvelet domain bilateral two-dimension principal component analysis |
-
2014
- 2014-01-16 CN CN201410020480.8A patent/CN103761722B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038691A1 (en) * | 2005-04-07 | 2007-02-15 | Emmanuel Candes | Methods for performing fast discrete curvelet transforms of data |
| CN102722734A (en) * | 2012-05-23 | 2012-10-10 | 南京航空航天大学 | Image target identification method based on curvelet domain bilateral two-dimension principal component analysis |
Non-Patent Citations (4)
| Title |
|---|
| 周峰等: "基于PCA+RBF的多光谱卫星遥感影像分类", 《物探化探计算技术》, vol. 30, no. 2, 29 February 2008 (2008-02-29), pages 159 - 1 * |
| 张少平: "输电线路典型目标图像识别技术研究", 《南京航空航天大学硕士学位论文》, 1 December 2012 (2012-12-01) * |
| 肖波: "无人机图像自动拼接问题研究", 《昆明理工大学硕士学位论文》, 8 October 2013 (2013-10-08) * |
| 陈润锋: "无人机航拍图像配准方法的研究", 《辽宁大学硕士学位论文》, 1 May 2013 (2013-05-01) * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139374A (en) * | 2015-07-09 | 2015-12-09 | 天津航天中为数据系统科技有限公司 | Power transmission line tracking method and system |
| CN105825207A (en) * | 2016-04-20 | 2016-08-03 | 北京航空航天大学 | Fragmented high-voltage line detection method and device |
| CN105825207B (en) * | 2016-04-20 | 2019-05-14 | 北京航空航天大学 | The high-voltage line detection method and device of fragmentation |
| CN106355580B (en) * | 2016-09-22 | 2020-07-14 | 云南电网有限责任公司电力科学研究院 | Method and device for detecting toppling of tower |
| CN106355580A (en) * | 2016-09-22 | 2017-01-25 | 云南电网有限责任公司电力科学研究院 | Detection method and device of tilting pole tower |
| CN106595500A (en) * | 2016-11-21 | 2017-04-26 | 云南电网有限责任公司电力科学研究院 | Transmission line ice coating thickness measurement method based on unmanned aerial vehicle binocular vision |
| CN106595500B (en) * | 2016-11-21 | 2019-06-14 | 云南电网有限责任公司电力科学研究院 | Electric power line ice-covering thickness measurement method based on unmanned plane binocular vision |
| CN106971453A (en) * | 2017-04-06 | 2017-07-21 | 深圳怡化电脑股份有限公司 | The method and device of bank note fragments mosaicing |
| CN106932688A (en) * | 2017-04-24 | 2017-07-07 | 国家电网公司 | Power transmission line detector and the power transmission line detecting system based on unmanned plane |
| CN106932688B (en) * | 2017-04-24 | 2023-09-05 | 国家电网公司 | Power transmission line detector and power transmission line detection system based on unmanned aerial vehicle |
| CN108496188A (en) * | 2017-05-31 | 2018-09-04 | 深圳市大疆创新科技有限公司 | Method, apparatus, computer system and the movable equipment of neural metwork training |
| CN109544608A (en) * | 2018-03-22 | 2019-03-29 | 广东电网有限责任公司清远供电局 | A kind of unmanned plane Image Acquisition feature registration method |
| CN109544608B (en) * | 2018-03-22 | 2023-10-24 | 广东电网有限责任公司清远供电局 | Unmanned aerial vehicle image acquisition characteristic registration method |
| CN108377033A (en) * | 2018-04-20 | 2018-08-07 | 国网辽宁省电力有限公司沈阳供电公司 | Polling transmission line based on multi-rotor unmanned aerial vehicle compares modification system with line map |
| US10692200B2 (en) | 2018-04-25 | 2020-06-23 | Microsoft Technology Licensing, Llc | Sensor location determination for geographical region |
| CN110827335A (en) * | 2019-11-01 | 2020-02-21 | 北京推想科技有限公司 | Mammary gland image registration method and device |
| CN110827335B (en) * | 2019-11-01 | 2020-10-16 | 北京推想科技有限公司 | Mammary gland image registration method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103761722B (en) | 2015-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103761722B (en) | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN103679674B (en) | Method and system for splicing images of unmanned aircrafts in real time | |
| CN110245678B (en) | Image matching method based on heterogeneous twin region selection network | |
| Liu et al. | Automated vehicle extraction and speed determination from QuickBird satellite images | |
| CN102865859B (en) | Aviation sequence image position estimating method based on SURF (Speeded Up Robust Features) | |
| CN102708370B (en) | Method and device for extracting multi-view angle image foreground target | |
| CN103426186A (en) | Improved SURF fast matching method | |
| CN103593832A (en) | Method for image mosaic based on feature detection operator of second order difference of Gaussian | |
| US8666170B2 (en) | Computer system and method of matching for images and graphs | |
| CN107480727A (en) | The unmanned plane image fast matching method that a kind of SIFT and ORB are combined | |
| CN101470896A (en) | Automotive target flight mode prediction technique based on video analysis | |
| CN106355197A (en) | Navigation image matching filtering method based on K-means clustering algorithm | |
| CN112991487B (en) | System for multithreading real-time construction of orthophoto semantic map | |
| CN112149547A (en) | Remote sensing image water body identification based on image pyramid guidance and pixel pair matching | |
| CN106548169A (en) | Fuzzy literal Enhancement Method and device based on deep neural network | |
| CN105389774A (en) | Method and device for aligning images | |
| CN105160303A (en) | Fingerprint identification method based on mixed matching | |
| CN112184746A (en) | Transmission line insulator defect analysis method | |
| CN103729631A (en) | Vision-based connector surface feature automatically-identifying method | |
| CN102867192B (en) | A kind of Scene Semantics moving method propagated based on supervision geodesic line | |
| CN104851089A (en) | Static scene foreground segmentation method and device based on three-dimensional light field | |
| CN102663733B (en) | Characteristic points matching method based on characteristic assembly | |
| CN107909018A (en) | A kind of sane multi-modal Remote Sensing Images Matching Method and system | |
| CN111213154A (en) | Lane line detection method, lane line detection equipment, mobile platform and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Maintenance Test Center, Building A4, No. 181, Kexue Avenue, Science City, Luogang District, Guangzhou, Guangdong 510663 Patentee after: China Southern Power Grid Corporation Ultra High Voltage Transmission Company Electric Power Research Institute Patentee after: TIANJIN ZHONG WEI AEROSPACE DATA SYSTEM TECHNOLOGY Co.,Ltd. Address before: Maintenance Test Center, Building A4, No. 181, Kexue Avenue, Science City, Luogang District, Guangzhou, Guangdong 510663 Patentee before: MAINTENANCE & TEST CENTRE, CSG EHV POWER TRANSMISSION Co. Patentee before: TIANJIN ZHONG WEI AEROSPACE DATA SYSTEM TECHNOLOGY Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20140430 Assignee: Yidao Smart (Beijing) Supply Chain Management Co.,Ltd. Assignor: China Southern Power Grid Corporation Ultra High Voltage Transmission Company Electric Power Research Institute Contract record no.: X2023980041958 Denomination of invention: A Method for Accurate Mosaicing of Inspection Images of Fixed Wing Unmanned Aerial Vehicles on Transmission Lines Granted publication date: 20150311 License type: Common License Record date: 20230918 |