CN104751145B - The SAR image electric power line detecting method that local Hough transformation optimizes with morphology - Google Patents
The SAR image electric power line detecting method that local Hough transformation optimizes with morphology Download PDFInfo
- Publication number
- CN104751145B CN104751145B CN201510168893.5A CN201510168893A CN104751145B CN 104751145 B CN104751145 B CN 104751145B CN 201510168893 A CN201510168893 A CN 201510168893A CN 104751145 B CN104751145 B CN 104751145B
- Authority
- CN
- China
- Prior art keywords
- marginal
- pixel
- hough transformation
- line segment
- bianry image
- 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.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to SAR image power line detection technique field, the SAR image electric power line detecting method that more particularly to local Hough transformation optimizes with morphology, it is concretely comprised the following steps：Rim detection is carried out using Edison operators to SAR original images, the bianry image for including marginal information is obtained；Multiple marginal belts are marked off in the bianry image comprising marginal information；In the bianry image for marking off multiple marginal belts, straight-line detection is carried out using the Hough transformation method based on polar coordinate transform space to each marginal belt, Hough transformation testing result is drawn；In each marginal belt of Hough transformation testing result, choose length most long line segment, if the minimum distance of remaining any line segment and length most long line segment is less than setpoint distance threshold value, and the angle of correspondence line segment and length most long line segment is less than setting angle threshold value, then correspondence line segment is cast out, otherwise, correspondence line segment is retained；Finally draw SAR image power line testing result.
Description
Technical field
The invention belongs to SAR image power line detection technique field, more particularly to local Hough transformation optimizes with morphology
SAR image electric power line detecting method.
Background technology
Power line is one of important threat key element under low-latitude flying environment, seriously threatens the flight safety of aircraft,
So how using the dangerous electric power line target of microwave radar quick detection, ensureing aircraft low-latitude flying safety, being particularly significant
Problem in science.
Synthetic aperture radar (Synthetic Aperture Radar, SAR) be a kind of round-the-clock, round-the-clock, effect away from
From remote high-resolution microwave remotely sensed image radar, it is one of important means of low latitude environment sensing, utilizes obtained SAR to scheme
As carrying out power line detection, environmental threat key element detection in low latitude is had important practical significance and wide application prospect.But
Electric power line target is smaller, reflected intensity is weak, only when radar line of sight is vertical with power line or the two small drift angle of left and right deviation occurs
Just had during Bragg resonance (Bragger) effect compared with strong scattering, and electric power line target is easy to and the atural object line such as road, ridge
Section mixes, and causes SAR image power line to detect that erroneous judgement causes false alarm rate high.
The content of the invention
The problem of it is an object of the invention to for required solution, propose the SAR that local Hough transformation optimizes with morphology
Image electric power line detecting method, improves SAR image power line detectability, can be applied to microwave radar under the environment of low latitude
Stationary obstruction is detected and positioned, and improves the detectability that key element is threatened in the environment of aircraft low latitude.
To realize above-mentioned technical purpose, the present invention, which is adopted the following technical scheme that, to be achieved.
The SAR image electric power line detecting method that local Hough transformation optimizes with morphology comprises the following steps：
Step 1, SAR original images are obtained, rim detection is carried out using Edison operators to SAR original images, wrapped
Bianry image containing marginal information；In the bianry image comprising marginal information, white pixel part represents marginal information, black
Color pixel part represents non-edge information；
Step 2, multiple marginal belts are marked off in the above-mentioned bianry image comprising marginal information；
Step 3, in the bianry image for marking off multiple marginal belts, empty based on polar coordinate transform is used to each marginal belt
Between Hough transformation method carry out straight-line detection, draw Hough transformation testing result；Hough transformation testing result is comprising at least
One bianry image by white pixel line segment, the white pixel line segment refers to the line segment being made up of white pixel point；
Step 4, in each marginal belt of Hough transformation testing result, length most long line segment is chosen, if remaining is appointed
The minimum distance of one line segment and length most long line segment is less than setpoint distance threshold value, and correspondence line segment and length most long line segment
Angle be less than setting angle threshold value, then by correspondence line segment cast out, otherwise, by correspondence line segment retain；It is final to draw SAR image electricity
Line of force testing result.
Beneficial effects of the present invention are：1) present invention proposes the local Hough transformation straight-line detection side divided based on marginal belt
Method.This method improves processing real-time while the global Hough transformation of effective reduction pseudo- peak.2) in order to suppress local Hough
After conversion joint distance and angle are proposed in image in the overlapping interference detected with bifurcated line segment to following needs line, the present invention
The morphology optimization method of threshold value, has filtered out overlapping and bifurcated line segment, improves the reliability of power line detection.
Brief description of the drawings
The flow chart for the SAR image electric power line detecting method that Fig. 1 optimizes for the local Hough transformation of the present invention with morphology；
Fig. 2 is SAR original images pending during measured data is tested；
Fig. 3 is that measured data tests the binary map for using Edison operators obtain after rim detection according to the present invention
Picture；
Fig. 4 is that measured data tests the bianry image containing marginal belt after the filtering process drawn according to the present invention；
Fig. 5 is to carry out result schematic diagram after global Hough transformation lines detection during measured data is tested to Fig. 3；
Fig. 6 is the binary map for the local Hough transformation processing for carrying out step 4 during measured data is tested according to the present invention to Fig. 3
Picture；
Fig. 7 be during measured data is tested according to the step 4 of the present invention give up in each marginal belt with the maximum line segment of length away from
From the bianry image after the less repetition of close and angle or bifurcated line segment；
Fig. 8 is for Fig. 7 to filter out the SAR image power line after length short segment according to the present invention in measured data experiment
Testing result schematic diagram.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings：
Reference picture 1, is the stream of the local Hough transformation and the SAR image electric power line detecting method of morphology optimization of the present invention
Cheng Tu.The SAR image electric power line detecting method that the local Hough transformation optimizes with morphology comprises the following steps：
Step 1, SAR original images are obtained, rim detection is carried out using Edison operators to SAR original images, wrapped
Bianry image containing marginal information；In the above-mentioned bianry image comprising marginal information, white pixel part represents marginal information, black
Color pixel part represents non-edge information, and marginal information refers mainly to the marginal information of power line, ridge, house, road etc..
Step 2, multiple marginal belts are marked off in the above-mentioned bianry image comprising marginal information, each marginal belt is exactly one
The continuous line segment of bar, broken line or curve.
Its specific sub-step is：
(2.1) flag bit flag, each pixel are assigned by each pixel of the above-mentioned bianry image comprising marginal information
The flag bit flag of point initial value is 0.K=1 is made, 2 ..., K, K represent picture in the above-mentioned bianry image comprising marginal information
The number of vegetarian refreshments；Sub-step (2.2) is skipped to as k=1.
(2.2) if k-th of pixel of the above-mentioned bianry image comprising marginal information be white pixel point (according to gray value
Judge, the pixel that gray value is 255 is white pixel point) and its flag bit flag value is 0, then includes edge letter by above-mentioned
K-th of pixel of the bianry image of breath skips to sub-step (2.3) as marginal belt pixel；If above-mentioned include marginal information
K-th of pixel of bianry image (judged according to gray value, the pixel that gray value is 0 is black picture for black pixel point
Vegetarian refreshments) or the above-mentioned bianry image comprising marginal information k-th of pixel flag bit flag value be 1, then skip to sub-step
Suddenly (2.5).
(2.3) record the coordinate (line number and columns i.e. in bianry image) of each marginal belt pixel and indicated
Position flag value is updated to 1, skips to sub-step (2.4).
(2.4) white pixel that search sign position flag value is 0 in 8 connection neighborhoods of each marginal belt pixel
Point, if searched, using each pixel searched as the marginal belt pixel after renewal, is back to sub-step
(2.3), if do not searched, sub-step (2.5) is skipped to.
8 connection neighborhoods of pixel are made explanations below, 8 connection fields of pixel refer to：By the adjacent pixel in top
The adjacent pixel in the adjacent pixel upper left side in the adjacent pixel in the adjacent pixel in point, lower section, left, right, lower-left
The set of the pixel of the adjacent pixel composition in the adjacent pixel in Fang Xianglin pixel, upper right side, lower right.Obviously work as
When pixel is not edge pixel point, 8 connection fields of pixel include 8 pixels；When pixel is located at one side of image
But when not being the pixel of image corner, 8 connection fields of pixel include 5 pixels；When pixel is image corner
During pixel, 8 connection fields of pixel include 3 pixels.
(2.5) if k<K, then make k value from increasing 1, be back to sub-step (2.2)；If k=K, illustrate to include side above-mentioned
The process that multiple marginal belts are marked off in the bianry image of edge information terminates.
The process of step 2 can be regarded as is searched one by one in the above-mentioned bianry image comprising marginal information to pixel
The process of rope, the order of search can be manually set.After step 2, own in the above-mentioned bianry image comprising marginal information
Adjacent edge pixel point is divided each different marginal belt.
Step 3, pixel number threshold filter and local Hough transformation method is utilized to carry out straight-line detection.
In the bianry image for marking off multiple marginal belts, pixel number is less than to the edge of setting pixel number threshold value
Band casts out (black pixel point after each pixel of corresponding marginal belt is updated), obtain after filtering process containing marginal belt
Bianry image；In the bianry image containing marginal belt after above-mentioned filtering process, each marginal belt is used and become based on polar coordinates
The Hough transformation method for changing space carries out straight-line detection, draws Hough transformation testing result；Hough transformation testing result be comprising
The bianry image of at least one line segment being made up of white pixel point.
Preferably, in step 3, pixel number threshold value is set as 30.
Specifically, straight-line detection problem in image space is changed into parameter by Hough transformation method by spatial alternation
The test problems put in space, the cumulative statistics carried out in parameter space completes detection work.Chosen not according to parameter field
Together, the parameter space in parameter space conversion and polar coordinate system in rectangular coordinate system converts two kinds, the present invention is used and is based on
The Hough transformation method in polar coordinate transform space.Its transformation relation is as follows：If every on straight line L in image space, straight line
When a bit (x, y) all meets below equation, parameter space H is r- θ spaces,
R=x cos θ+y sin θs (1)
R is distance of the origin to straight line L, and θ is that straight line L crosses the vertical line of origin and the angle of x-axis positive direction.
The process bag of straight-line detection is carried out using the Hough transformation method based on polar coordinate transform space to each marginal belt
Include following sub-step：
(3.1) i=1 is made, 2 ..., M, M are represented in pending bianry image (bianry image after above-mentioned filtering process)
The number of marginal belt；As i=1, sub-step (3.2) is skipped to；
(3.2) Hough transformation based on polar coordinate transform space is carried out to i-th marginal belt, by i-th of marginal belt according to
Formula (1) is transformed in parameter space, obtains relevant parameter space matrix H, and its row correspond to θ, and row correspond to r, its numerical value pair
Answer the accumulated value for crossing this straight line number.
(3.3) peakvalue's checking is carried out to parameter space matrix H, retains 5 maximum elements of numerical value in matrix H, record it
Corresponding ranks number, if element number is less than 5 in parameter space matrix H, retain whole elements of matrix H.
(3.4) the element contravariant retained in matrix H is changed in bianry image, draws the corresponding line segment of each element, protected
Deposit the image coordinate of each pixel on line segment.
(3.5) if i<M, then make i value from increasing 1, be back to sub-step (3.2)；If i=M, terminate Hough transformation mistake
Journey.
In the present invention, the Hough transformation process in step 3 is carried out for each marginal belt, rather than for whole two
It is worth what image was carried out, therefore, the Hough transformation in step 3 is referred to as local Hough transformation.
Step 4, the morphology of joint distance and angle threshold value optimizes.
In each marginal belt of Hough transformation testing result, length most long line segment is chosen, if remaining any line segment
It is less than setpoint distance threshold value with the minimum distance of length most long line segment, and the angle of correspondence line segment and length most long line segment
Less than setting angle threshold value, then correspondence line segment is cast out and (each pixel of correspondence line segment is updated into black pixel point), it is no
Then, correspondence line segment is retained.And folder close with length max line segment distance is given up in aiming at for step 4 in each marginal belt
The less repetition in angle or bifurcated line segment.
Preferably, in step 4, setpoint distance threshold value is the total length of 40 pixels, and set angle threshold value is 20 degree.
Preferably, in the bianry image that step 4 is drawn, if any line segment is less than setting length threshold, by the line
Section is cast out and (each pixel of correspondence line segment is updated into black pixel point), and otherwise, correspondence line segment is retained；Finally draw
SAR image power line testing result.Further, total length of the length threshold as 110 pixels is set.
The effect of the present invention is further illustrated by the experiment of following measured data：
Reference picture 2, is SAR original images pending during measured data is tested；Reference picture 3, be measured data experiment by
The bianry image for using Edison operators obtain after rim detection according to the present invention；Reference picture 4, be measured data experiment according to
The bianry image containing marginal belt after the filtering process that the present invention is drawn.Comparison diagram 3 and Fig. 4 can be found that mixed and disorderly thin in Fig. 4
Small edge is significantly reduced than Fig. 3, it is known that after the step 3 by the present invention, has successfully been filtered out and has been upset the mixed and disorderly thin of power line detection
Small edge.
Reference picture 5, is to carry out result schematic diagram after global Hough transformation lines detection during measured data is tested to Fig. 3；Ginseng
It is the bianry image for the local Hough transformation processing for carrying out step 4 during measured data is tested according to the present invention to Fig. 3 according to Fig. 6.It is right
It can be seen that than Fig. 5 and Fig. 6 and power line included in both extraction results, and global Hough transformation is due on same straight line
The a plurality of line segment of separation causes have longer straight-line segment in lines detection result in the pseudo- peak of accumulation generation by mistake, reduces power line inspection
Survey performance；Though the local Hough transformation in the present invention includes many short segments, it can be suppressed by subsequent treatment,
The detectability of power line is improved while the missing inspection for avoiding power line.
Reference picture 7, be measured data experiment according to the present invention step 4 give up in each marginal belt with length max line
Segment distance is close and the less repetition of angle or bifurcated line segment after bianry image.Compared with Fig. 6, the atural object of image shown in Fig. 7
Profile it is overlapping less, overlapping edges are less.
Reference picture 8, is for Fig. 7 to filter out the SAR image after length short segment according to the present invention in measured data experiment
Power line testing result schematic diagram.As can be seen from Figure 8, the figure has filtered out the shorter edge straight line such as ridge, house, road, successfully carries
Take out the power line in SAR image.
In summary, the present invention is realized reliably detects to the power line in actual measurement SAR image.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (7)
1. the SAR image electric power line detecting method that local Hough transformation optimizes with morphology, it is characterised in that including following step
Suddenly：
Step 1, SAR original images are obtained, rim detection is carried out using Edison operators to SAR original images, obtains and includes side
The bianry image of edge information；In the bianry image comprising marginal information, white pixel part represents marginal information, black picture
Plain part represents non-edge information；
Step 2, multiple marginal belts are marked off in the above-mentioned bianry image comprising marginal information；
Wherein, the specific sub-step of the step 2 is：
(2.1) flag bit flag is assigned by each pixel of the bianry image comprising marginal information, each pixel
Flag bit flag initial value is 0；K=1 is made, 2 ..., K, K represent pixel in the above-mentioned bianry image comprising marginal information
Number；Sub-step (2.2) is skipped to as k=1；
(2.2) if k-th of pixel of the bianry image comprising marginal information is white pixel point and its flag bit flag
Value be 0, then k-th of pixel of the bianry image comprising marginal information is skipped into sub-step as marginal belt pixel
Suddenly (2.3)；If k-th of pixel of the bianry image comprising marginal information is black pixel point or described comprising edge letter
The flag bit flag of k-th of pixel of the bianry image of breath value is 1, then skips to sub-step (2.5)；
(2.3) the flag bit flag of each marginal belt pixel value is updated to 1, skips to sub-step (2.4)；
(2.4) the white pixel point that search sign position flag value is 0 in 8 connection neighborhoods of each marginal belt pixel, such as
Fruit searches, then using each pixel searched as the marginal belt pixel after renewal, is back to sub-step (2.3), such as
Fruit does not search, then skips to sub-step (2.5)；
(2.5) if k ＜ K, make k value from increasing 1, be back to sub-step (2.2)；If k=K, multiple marginal belts are marked off, are drawn
The multiple marginal belts separated refer to：The image-region that all pixels point for being 1 by flag bit flag value is constituted；
Step 3, in the bianry image for marking off multiple marginal belts, each marginal belt is used based on polar coordinate transform space
Hough transformation method carries out straight-line detection, draws Hough transformation testing result；Hough transformation testing result is to include at least one
By the bianry image of white pixel line segment, the white pixel line segment refers to the line segment being made up of white pixel point；
Step 4, in each marginal belt of Hough transformation testing result, length most long line segment is chosen, if remaining any line
The minimum distance of section and length most long line segment is less than setpoint distance threshold value, and the folder of correspondence line segment and length most long line segment
Angle is less than setting angle threshold value, then casts out correspondence line segment, otherwise, and correspondence line segment is retained；Finally draw SAR image power line
Testing result.
2. the SAR image electric power line detecting method that part Hough transformation as claimed in claim 1 optimizes with morphology, its feature
It is, in step 3, in the bianry image for marking off multiple marginal belts, pixel number is less than setting pixel number threshold
The marginal belt of value is cast out, and obtains the bianry image containing marginal belt after filtering process；Contain marginal belt after above-mentioned filtering process
Bianry image in, to each marginal belt using based on polar coordinate transform space Hough transformation method carry out straight-line detection, obtain
Go out Hough transformation testing result.
3. the SAR image electric power line detecting method that part Hough transformation as claimed in claim 2 optimizes with morphology, its feature
It is, in step 3, the pixel number threshold value that sets is 30.
4. the SAR image electric power line detecting method that part Hough transformation as claimed in claim 1 optimizes with morphology, its feature
It is, in step 3, straight-line detection is carried out using the Hough transformation method based on polar coordinate transform space to each marginal belt
Process includes following sub-step：
(3.1) i=1 is made, 2 ..., M, M represent the number of marginal belt in pending bianry image；As i=1, sub-step is skipped to
Suddenly (3.2)；
(3.2) Hough transformation based on polar coordinate transform space is carried out to i-th of marginal belt, i-th of marginal belt is transformed into pole
In coordinate parameters space, relevant parameter space matrix H is obtained, its row correspond to polar angle, and row correspond to polar diameter, and its numerical value correspond to
Cross the accumulated value of this straight line number；
(3.3) peakvalue's checking is carried out to parameter space matrix H, retains 5 maximum elements of numerical value in matrix H, if parameter space
Element number then retains whole elements of matrix H less than 5 in matrix H；
(3.4) the element contravariant retained in matrix H is changed in bianry image, draws the corresponding line segment of each element, preserve line
The image coordinate of each pixel in section；
(3.5) if i ＜ M, make i value from increasing 1, be back to sub-step (3.2)；If i=M, terminate Hough transformation process.
5. the SAR image electric power line detecting method that part Hough transformation as claimed in claim 1 optimizes with morphology, its feature
It is,, should if any line segment is less than setting length threshold in the bianry image that step 4 is drawn after step 4
Line segment is cast out, otherwise, and correspondence line segment is retained；Finally draw SAR image power line testing result.
6. the SAR image electric power line detecting method that part Hough transformation as claimed in claim 5 optimizes with morphology, its feature
It is, the total length for setting length threshold as 110 pixels.
7. the SAR image power line detection side that the local Hough transformation as described in any one of claim 1 to 6 optimizes with morphology
Method, it is characterised in that in step 4, the setpoint distance threshold value is the total length of 40 pixels, the setting angle threshold value
For 20 degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510168893.5A CN104751145B (en) | 2015-04-10 | 2015-04-10 | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510168893.5A CN104751145B (en) | 2015-04-10 | 2015-04-10 | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104751145A CN104751145A (en) | 2015-07-01 |
| CN104751145B true CN104751145B (en) | 2017-10-13 |
Family
ID=53590802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510168893.5A Active CN104751145B (en) | 2015-04-10 | 2015-04-10 | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104751145B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108132675A (en) * | 2017-11-23 | 2018-06-08 | 东南大学 | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426277B (en) * | 2017-08-30 | 2022-11-08 | 广州极飞科技股份有限公司 | Method and device for planning movement track |
| CN111045431B (en) * | 2019-12-31 | 2022-05-27 | 芜湖哈特机器人产业技术研究院有限公司 | Ribbon-based mobile robot navigation method and system |
| CN111695548B (en) * | 2020-07-20 | 2022-12-13 | 内蒙古工业大学 | High-voltage line detection method based on millimeter wave radar |
| CN112001906B (en) * | 2020-08-24 | 2024-02-02 | 徐工汉云技术股份有限公司 | Steel plate weld image detection method combined with non-maximum suppression |
| CN112541405A (en) * | 2020-11-27 | 2021-03-23 | 陕西海泰电子有限责任公司 | Automatic identification method of nonlinear double-frequency graph |
| CN112752093B (en) * | 2020-12-25 | 2022-08-16 | 浙江大华技术股份有限公司 | Video fringe detection method and device, storage medium and electronic device |
| CN113807325B (en) * | 2021-11-17 | 2022-02-22 | 南京三叶虫创新科技有限公司 | Line type identification method and system based on image processing |
| CN114663713B (en) * | 2022-05-20 | 2022-08-30 | 海门市博洋铸造有限公司 | Metal wire drawing production control method and system based on Hough transform |
| CN115237159B (en) * | 2022-09-21 | 2023-09-15 | 国网江苏省电力有限公司苏州供电分公司 | Wire inspection method adopting unmanned aerial vehicle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255259A (en) * | 2011-03-29 | 2011-11-23 | 山东鲁能智能技术有限公司 | Transmission line tour inspection device suitable for unmanned aerial vehicle |
| CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
| CN103810462A (en) * | 2012-11-14 | 2014-05-21 | 中国科学院沈阳自动化研究所 | High voltage transmission line detection method based on linear targets |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7457445B2 (en) * | 2004-03-01 | 2008-11-25 | Siemens Medical Solutions Usa, Inc. | Using corner pixels as seeds for detection of convex objects |
-
2015
- 2015-04-10 CN CN201510168893.5A patent/CN104751145B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255259A (en) * | 2011-03-29 | 2011-11-23 | 山东鲁能智能技术有限公司 | Transmission line tour inspection device suitable for unmanned aerial vehicle |
| CN103810462A (en) * | 2012-11-14 | 2014-05-21 | 中国科学院沈阳自动化研究所 | High voltage transmission line detection method based on linear targets |
| CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
Non-Patent Citations (2)
| Title |
|---|
| 基于多种遥感数据的电力线走廊特征物提取方法研究;穆超;《中国博士学位论文全文数据库 基础科学辑》;20130915(第9期);参见正文第14，27页 * |
| 霍夫域极化相干性的雷达影像电力线检测;邓少平 等;《测绘科学》;20150228;第40卷(第2期);参见第66-71页 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108132675A (en) * | 2017-11-23 | 2018-06-08 | 东南大学 | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory |
| CN108132675B (en) * | 2017-11-23 | 2020-02-21 | 东南大学 | Autonomous path cruising and intelligent obstacle avoidance method for factory inspection unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104751145A (en) | 2015-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751145B (en) | The SAR image electric power line detecting method that local Hough transformation optimizes with morphology | |
| CN102509089B (en) | Method for recognizing zebra crossing and measuring zebra crossing distance based on line-by-line scanning | |
| CN104183133B (en) | A kind of method gathered and transmit road traffic flow state information | |
| CN103984961A (en) | Image detection method for detecting foreign matter at bottom of vehicle | |
| CN104535356A (en) | Method and system for monitoring rope arrangement faults of drum steel wire rope on basis of machine vision | |
| CN102930280A (en) | Method for identifying overhead high-voltage wire automatically from infrared image | |
| CN104132942B (en) | The detection of a kind of body eutrophication based on unmanned plane and processing method | |
| CN103559703A (en) | Crane barrier monitoring and prewarning method and system based on binocular vision | |
| CN103148881A (en) | Method and device for automatically reading pointer instrument by video frequency | |
| CN106951898B (en) | Vehicle candidate area recommendation method and system and electronic equipment | |
| CN102831773A (en) | RFID-based traffic violation lane-changing detection system | |
| CN107103654A (en) | A kind of Cargo Inspection safety detection controlling and management and method | |
| CN107097794B (en) | System and method for detecting lane line of road | |
| CN103049739A (en) | Tree detection method for use in intelligent monitoring of power transmission line | |
| CN104240239A (en) | Method for detecting local road segment hazy weather based on road image | |
| CN111176271B (en) | Intelligent ship collision avoidance auxiliary decision-making system based on shore radar and implementation method thereof | |
| US20210150694A1 (en) | Vehicle-based measurement of signal object integrity | |
| CN114248819B (en) | Railway intrusion foreign matter unmanned aerial vehicle detection method, device and system based on deep learning | |
| CN103020627B (en) | A kind of extracting method of special vehicle gauge pointer | |
| CN207473847U (en) | Night intersection pedestrian's street crossing safety signal system | |
| CN113658427A (en) | Road condition monitoring method, system and equipment based on vision and radar | |
| CN112597926A (en) | Method, device and storage medium for identifying airplane target based on FOD image | |
| CN113903180B (en) | Method and system for detecting vehicle overspeed on expressway | |
| CN105243360A (en) | Ship object self-organizing cluster method based on distance search | |
| CN205827663U (en) | A kind of rfid interrogator with laser scanning and camera function |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200724 Address after: 116085 412, floor 4, block a, comprehensive office building, No. 3, Kehai street, high tech Industrial Park, Dalian City, Liaoning Province Patentee after: Dalian Haifu Technology Co.,Ltd. Address before: Xi'an City, Shaanxi province Taibai Road 710071 No. 2 Patentee before: XIDIAN University |
|
| TR01 | Transfer of patent right |