CN115237159A - Electric wire inspection method adopting unmanned aerial vehicle - Google Patents
Electric wire inspection method adopting unmanned aerial vehicle Download PDFInfo
- Publication number
- CN115237159A CN115237159A CN202211146787.3A CN202211146787A CN115237159A CN 115237159 A CN115237159 A CN 115237159A CN 202211146787 A CN202211146787 A CN 202211146787A CN 115237159 A CN115237159 A CN 115237159A
- Authority
- CN
- China
- Prior art keywords
- highlight
- hough space
- aerial vehicle
- unmanned aerial
- electric wire
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000007689 inspection Methods 0.000 title claims abstract description 26
- 230000003595 spectral effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of data processing, in particular to a wire inspection method adopting an unmanned aerial vehicle, which is used for acquiring an image containing a wire; obtaining a Hough space corresponding to the image containing the electric wire according to the image containing the electric wire; according to the acquired corresponding Hough space, a linear ideal value corresponding to the highlight in the Hough space is acquired, the necessity that two highlight points in the Hough space need to judge the intersection of the straight lines is acquired according to the linear ideal value corresponding to the highlight in the Hough space, the final flight angle of the unmanned aerial vehicle is acquired according to the necessity of judging whether the straight lines are intersected, and the angle adjustment of the unmanned aerial vehicle is completed. The scheme of the invention can be used for routing inspection of the electric wire based on obtaining the Hough space, so that missing inspection of the electric wire can be prevented, and routing inspection of the electric wire can be further realized.
Description
Technical Field
The invention relates to the field of data processing, in particular to a wire inspection method adopting an unmanned aerial vehicle.
Background
In the electric wire inspection, the electric wire is missed to be inspected due to the fact that the electric wire is mistakenly dropped and complicated. When the electric wire is missed to be detected, if the electric wire is aged, the electric wire can be short-circuited, light people influence the normal use of a user, and serious people generate fire to cause safety accidents, so that the comprehensive inspection of the electric wire is very necessary.
When adopting unmanned aerial vehicle to carry out the electric wire and patrolling and examining, current unmanned aerial vehicle can only carry out the electric wire image acquisition of fixed direction according to the electric wire orbit, but the electric wire probably appears overlapping and sheltering from, leads to unmanned aerial vehicle when carrying out the electric wire and patrolling and examining, takes place to leak easily and examines, so unmanned aerial vehicle patrols and examines the well needs adjustment shooting angle to prevent when patrolling and examining the electric wire, appear leaking and examine the condition.
Disclosure of Invention
In order to solve the technical problem, the invention aims to provide an electric wire inspection method adopting an unmanned aerial vehicle, and the adopted technical scheme is as follows:
the invention relates to a wire inspection method adopting an unmanned aerial vehicle, which comprises the following steps:
acquiring an image containing electric wires acquired during electric wire inspection of an unmanned aerial vehicle, and acquiring a binary image containing the electric wires acquired during electric wire inspection of the unmanned aerial vehicle;
obtaining a Hough space corresponding to the image containing the electric wire according to the binary image containing the electric wire; obtaining a linear ideal value corresponding to a highlight in the Hough space according to the Hough space;
step three, obtaining the necessity of judging the intersection of straight lines between any two highlight points in the Hough space according to the ideal straight line values corresponding to the highlight points in the Hough space;
step four, obtaining a final flying angle of the unmanned aerial vehicle according to the necessity of judging whether the corresponding straight lines of the two highlights intersect or not, and finishing the angle adjustment of the unmanned aerial vehicle;
the process of acquiring the necessity of the intersection of the straight lines is as follows:
obtaining an angle value and a distance value of any two highlight points in Hough space;
and calculating the necessity of intersection of the corresponding straight lines of any two highlight points according to the ratio, the angle value and the distance value.
Further, the necessity of the intersection of the straight lines is:
wherein ,
indicating the possibility that the current kth highlight is a wire,
indicating the possibility that the current nth highlight is a wire,
respectively an angle value and a distance value between the kth highlight point in the hough space,
respectively an angle value and a distance value between nth high points in the hough space,xand acquiring the length value of the image corresponding to the image resolution for the current addition module.
Further, before obtaining the Hough space corresponding to the electric wire image, the method further comprises the step of segmenting the electric wire image collected when the electric wire of the unmanned aerial vehicle is patrolled and examined to obtain a binary image containing the electric wire.
Further, the process of obtaining the ideal linear value corresponding to the highlight in the hough space is as follows:
counting points with the median value in the Hough space being larger than or equal to a threshold value r as highlight points in the Hough space;
randomly selecting a highlight, and counting the ratio of the number of ideal pixel points of the highlight in the binary image to the value corresponding to the highlight in the current Hough space to serve as the linear ideal value corresponding to the highlight in the Hough space.
Further, before obtaining the Hough space corresponding to the electric wire image, the method further comprises the step of segmenting the electric wire image collected when the electric wire of the unmanned aerial vehicle is patrolled and examined to obtain a binary image containing the electric wire.
Further, according to the necessity of whether the corresponding straight lines of any two highlight points in the current hough space intersect, the process of obtaining the final flight angle of the unmanned aerial vehicle is as follows:
and establishing a completely undirected graph, taking each highlight point in the Hough space as a vertex, and taking the necessity of the intersection calculated between the two highlight points as a connecting line weight between the two vertexes to obtain the graph structure of the completely undirected graph.
Further, performing secondary classification on the obtained completely undirected graph by adopting a spectral clustering algorithm, further solving an average edge weight in two categories, screening the category with a high edge weight, and then calculating an intersection distance value between all highlight points in the category with the high edge weight; and selecting the shortest distance value of the intersection distance values L between all the highlight points in the category of the highlight weight, acquiring the corresponding intersection point position coordinates of the shortest distance value in the binary image, and adjusting the flight angle of the unmanned aerial vehicle according to the intersection point coordinates.
The invention has the beneficial effects that:
according to the scheme, after the image containing the electric wire is collected, the necessity of judging intersection between two highlight points can be obtained by obtaining the highlight point characteristics of the contained electric wire image in the Hough space, the calculated amount is reduced, the time delay is reduced when the steering is needed, extra redundant unmanned aerial vehicle adjusting time is provided, and the unmanned aerial vehicle is prevented from colliding with the electric wire; when the necessity of calculating the intersection is obtained, the condition that the final intersection point of the corresponding straight lines of the two highlight points is too far away is also prevented, so that the position of the final intersection point of the two straight lines is stable; and then carry out unmanned the turning to according to the crossing point position, prevent that the electric wire from patrolling and examining and appearing lou examining, and then realize that the electric wire patrols and examines.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart showing steps of a wire inspection method using an unmanned aerial vehicle according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the embodiments, structures, features and effects thereof according to the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Specifically, the method for inspecting the electric wire by using the unmanned aerial vehicle provided by the invention is introduced, as shown in fig. 1, and includes the following steps:
acquiring an image containing electric wires acquired during electric wire inspection of an unmanned aerial vehicle, and acquiring a binary image containing the electric wires acquired during electric wire inspection of the unmanned aerial vehicle;
obtaining a Hough space corresponding to the image containing the electric wire according to the binary image containing the electric wire; obtaining a linear ideal value corresponding to a highlight in the Hough space according to the Hough space;
step three, obtaining the necessity of judging the intersection of straight lines between any two highlight points in the Hough space according to the ideal straight line values corresponding to the highlight points in the Hough space;
and step four, obtaining the final flight angle of the unmanned aerial vehicle according to the necessity of judging whether the corresponding straight lines of the two highlights intersect or not, and finishing the angle adjustment of the unmanned aerial vehicle.
In the embodiment, the image containing the electric wire is acquired through the unmanned aerial vehicle camera module; specifically, because unmanned aerial vehicle is at the flight in-process, can shoot by the camera module and obtain the electric wire image. And acquiring an image containing the electric wire according to the unmanned aerial vehicle acquisition to obtain a binary image corresponding to the electric wire.
In the embodiment, when obtaining the electric wire image, in order to facilitate the analysis of the electric wire, the image needs to be segmented to obtain the image segmentation result with the electric wire, and a binary image of the electric wire image is obtained.
In the shooting process of nobody, the background change is large, the electric wire is thin and has more interference, so that when the electric wire image is subjected to electric wire segmentation, the image segmentation effect by the existing Dajin threshold segmentation method is not good, and the segmented image still has larger noise interference, so that the segmented image needs to be subjected to subsequent analysis.
In this embodiment, the Hough space corresponding to the binary image of the electric wire is obtained by the Hough algorithm on the binary image.
In this embodiment, after the Hough space is obtained, the electric wire in the collected image is searched for through the highlight in the Hough space, but when the unmanned aerial vehicle patrols and examines the electric wire, the background of the shot image is complex, so that the binary image obtained by segmentation has more noise, so that there are highlight formed by more non-electric wires in the Hough space, and the judgment whether the corresponding straight line of the highlight is the electric wire is influenced. Therefore, when the intersection determination is performed on the electric wire, there is a problem that the amount of calculation is too large because there are too many bright points in the hough space.
Therefore, a threshold value r is set, a value with relatively large luminance in the hough space is selected, if the luminance value in the hough space is smaller than the threshold value r, it is considered that a highlight point is generated by noise, and if r or more, it is considered that there is a possibility that an electric wire is generated by the highlight point and the possibility is high.
And obtaining K points with the brightness value larger than or equal to the threshold value r in the Hough space, namely obtaining K highlight points. If the kth highlight in the K highlights is a wire, and the wire is not considered to be suddenly interrupted in the routing inspection process, the imaging result of the wire necessarily penetrates through the whole collected image when the wire is imaged.
Therefore, the ratio of the number of ideal pixels of the k-th highlight point in the binary image corresponding to the straight line to the brightness value of the k-th highlight point in the current hough space is obtained, wherein the current k-th brightness value is a statistical value of the number of pixels of the corresponding straight line forming the straight line in the binary image of the electric wire.
The number of ideal pixel points of the line corresponding to the kth highlight point in the binary image is used for obtaining the corresponding angle value of the kth highlight point in the Hough space
And a distance value
And further by the angle value
And a distance value
Obtaining a corresponding straight line of the kth highlight point by a conversion formula of Hough space, generating a mask image with the same size as the binary image of the electric wire for the straight line, wherein the mask image only contains a mask corresponding to the straight line, and counting the sum of all pixel point values in the mask image
Indicating that the line should have in the ideal continuous case on the binary image
A pixel point, and the brightness value of the current kth highlight is
Representing the actual situation with only the binary image of the wire
And (5) each pixel point.
When in use
And
the smaller the difference is, the closer the line corresponding to the kth highlight is to the ideal line, and since the electric wire is present in the image throughout the entire image, the smaller the difference is
And
the smaller the difference is, the more likely the straight line corresponding to the kth highlight point isIs a straight line, which has a greater probability of belonging to the electric wire when performing intersection calculation of the electric wire.
When judging whether two straight lines intersect or not, the angle values of the two straight lines in the Hough space are known
And a distance value
And obtaining the slope of the corresponding straight line of the kth highlight point and the distance value between the corresponding straight line of the kth highlight point and the coordinate origin of the binary image through the existing Hough formula and slope formula.
So if the angle value between two highlight points is known
And a distance value
Through the existing Hough inverse operation formula and trigonometric function formula, the intersection point coordinate between the corresponding straight lines of the two highlight points can be calculated, and the distance value L between the intersection position of the two straight lines and the origin point in the binary image is obtained through the intersection point coordinate and the origin point coordinate in the image.
However, the calculation amount is too large because there are many highlight points in the hough space. And part of the data may be nearly parallel, resulting in the finding of the distance value L approaching infinity.
Therefore, a completely undirected graph is established, each highlight point in the Hough space is taken as a vertex, and the necessity of calculating intersection between two highlight points is taken as a connecting line weight between the two vertexes. Therefore, by establishing the graph structure, partial highlight points can be conveniently screened out, and the phenomenon that the distance value L is very large when the calculation of L is carried out is prevented.
The necessity of calculating the intersection between the kth highlight point and any other highlight point (such as the nth highlight point) is as follows:
wherein ,
indicating the current probability that the kth highlight point is a wire, if the probability that the kth highlight point is a wire is higher, the necessity of calculating the intersection of the kth highlight point should be higher,
the larger the value of (b), the closer to 1, so the minimum value between the kth highlight point and the nth highlight point is taken for the calculation between the kth highlight point and the nth highlight point
And (4) calculating.
Since the equation is complicated and time-consuming to solve and the phenomenon of near infinite distance may occur, the angle value between two highlight points in the Hough space is passed
And a distance value
And removing partial highlight points to reduce the calculation amount.
If two straight lines intersect, there is necessarily a difference in angle value, but when the angle difference is small, the two straight lines will approach to be parallel, the necessity of performing intersection calculation is low, and the possibility that the flying angle of the camera needs to be adjusted is low. Namely, it is
The smaller the value of (c), the more parallel the two curves approach, and the less necessary the intersection calculation is. It needs to be inversely related mapped so that
The smaller the ex (-. Mu.)
I) the larger the intersection calculation is, the necessity of intersection calculation
The larger.
If the angle difference is large, the probability of intersection is greater and the angle of flight of the camera needs to be adjusted more. But if the distance value corresponding to two highlight points
If the distance between the two straight lines is too large, the necessity is reduced if the two straight lines are considered to be relatively long from the image, because the distance between the two straight lines corresponding to the region range represented on the binary image is too long even if the intersection position is calculated, the calculation result has no meaning. So according to the distance value corresponding to the two highlight points
And the image length x difference, representing the approximate location of the intersection by prediction. Wherein x is the length value of the image corresponding to the resolution of the acquired image of the current addition module, and is the forward-looking direction of the unmanned aerial vehicle. I.e. if
If the value is greater than 0, it is simply assumed that L is not included in the image even if calculated, and it is meaningless to indicate that the calculation is performed, so that the value is not included in the image
Making a 0-1 function sgn, i.e. sgn
To represent
Sgn greater than 0
Is 1, when
Sgn at 0 or less
Is 0.
Therefore, it is not only easy to use
The larger the value of (a) is, the higher the calculation necessity of calculating the intersection between the current kth highlight point and the nth highlight point is, the more the adjustment of the flying angle of the camera is required.
And then carrying out secondary classification on the obtained completely undirected graph by adopting a spectral clustering algorithm, further solving an average side weight in the two categories, screening the category with the high side weight, and then calculating the intersection distance value L between all the high-light points in the category with the high side weight. But the situation that the intersection point is not on the binary image can be obtained, and the judgment of the flight angle of the unmanned aerial vehicle is not influenced.
And selecting the shortest distance value of the intersection distance values L between all the highlight points in the category of the highlight weight, acquiring the corresponding intersection point position coordinates of the shortest distance value in the binary image, and adjusting the flight angle of the unmanned aerial vehicle according to the intersection point coordinates. Wherein if need adjust, then unmanned aerial vehicle flight angle is for flying the shooting to left or right slope.
Wherein in the slope shooting process, according to the crossing point position of real-time computation, adjust unmanned aerial vehicle inclination angle value to left or right, if abscissa and x undersize in the crossing point position coordinate distance, then it is close to unmanned to explain the crossing point distance of electric wire, need bigger slope, constantly slope through unmanned aerial vehicle flight angle promptly for the difference of abscissa and x in the crossing point position coordinate distance is not less than a distance threshold value scope, guarantees when gathering image detection, and the crossing electric wire does not influence the result of patrolling and examining.
The distance threshold range is xr =50, and the implementer can adjust the distance according to the specific implementation requirements. When the distance threshold range is determined to be xr, calibration between a camera coordinate system and a world coordinate system is needed to be carried out so as to enable the distance range in reality to be converted into an xr value in an image, wherein the left-right tilting speed is a fixed value, and when tilting is needed, the unmanned aerial vehicle does not advance for ensuring safety until the intersection point is controlled in a certain range, or the intersection point does not exist in the image.
Wherein the relation between the inclination value of unmanned aerial vehicle flight angle and the nodical position can be experimented by the implementer and then the relation table between the inclination value of unmanned aerial vehicle flight angle and the nodical position is obtained, and then after obtaining the nodical position at every turn, the inclination of unmanned aerial vehicle flight angle is accomplished through the look-up relation table. It should be noted that, in the implementation, the relationship table between the inclination value of the flight angle of the drone and the intersection position is inconsistent between different devices.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present application, and they should be construed as being included in the present application.
Claims (6)
1. The utility model provides an adopt unmanned aerial vehicle's electric wire inspection method which characterized in that includes following step:
acquiring an image containing electric wires acquired during electric wire inspection of an unmanned aerial vehicle, and acquiring a binary image containing the electric wires acquired during electric wire inspection of the unmanned aerial vehicle;
obtaining a Hough space corresponding to the image containing the electric wire according to the binary image containing the electric wire; obtaining a linear ideal value corresponding to a highlight in the Hough space according to the Hough space;
thirdly, obtaining the necessity of judging the intersection of straight lines between any two highlight points in the current Hough space according to the ideal values of the straight lines corresponding to the highlight points in the Hough space;
step four, obtaining a final flight angle of the unmanned aerial vehicle according to the necessity of judging whether the two highlight corresponding straight lines intersect, and finishing the angle adjustment of the unmanned aerial vehicle;
the process of acquiring the necessity of the intersection of the straight lines is as follows:
obtaining an angle value and a distance value of any two highlight points in a Hough space;
and calculating the necessity of intersection of corresponding straight lines of any two highlight points according to the ratio, the angle value and the distance value.
2. The electric wire inspection method using the unmanned aerial vehicle according to claim 1,
the necessity of the intersection of the straight lines is:
wherein ,
indicating the possibility that the current kth highlight is a wire,
indicating the possibility that the current nth highlight is a wire,
respectively an angle value and a distance value between the kth highlight point in the hough space,
respectively an angle value and a distance value between nth high points in the hough space,xand acquiring the length value of the image corresponding to the image resolution for the current addition module.
3. The wire inspection method according to claim 1, wherein before obtaining the hough space corresponding to the wire image, the method further comprises segmenting the wire image collected during wire inspection of the unmanned aerial vehicle to obtain a binary image containing the wire.
4. The wire inspection method by the unmanned aerial vehicle according to claim 1, wherein the process of obtaining the ideal linear value corresponding to the highlight in the Hough space comprises:
counting points with the median value in the Hough space being larger than or equal to a threshold value r as highlight points in the Hough space;
randomly selecting a highlight, and counting the ratio of the number of ideal pixel points of the highlight in the binary image to the value corresponding to the highlight in the current Hough space to serve as the linear ideal value corresponding to the highlight in the Hough space.
5. The electric wire inspection method adopting the unmanned aerial vehicle according to claim 1, wherein the process of obtaining the final flight angle of the unmanned aerial vehicle according to the necessity of whether the corresponding straight lines of any two highlight points in the current Hough space intersect is as follows:
and establishing a completely undirected graph, taking each highlight point in the Hough space as a vertex, and taking the necessity of the intersection calculated between the two highlight points as a connecting line weight between the two vertexes to obtain the graph structure of the completely undirected graph.
6. The electric wire inspection method adopting the unmanned aerial vehicle according to claim 5, characterized in that the obtained completely undirected graph is classified twice by adopting a spectral clustering algorithm, further an average edge weight value in the two categories is obtained, the category with the high edge weight value is screened out, and then an intersection distance value between all high-bright points in the category with the high edge weight value is calculated; and selecting the shortest distance value of the intersection distance values between all the highlight points in the category of the highlight weight, acquiring the corresponding intersection point position coordinates of the shortest distance value in the binary image, and adjusting the flight angle of the unmanned aerial vehicle according to the intersection point coordinates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146787.3A CN115237159B (en) | 2022-09-21 | 2022-09-21 | Wire inspection method adopting unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146787.3A CN115237159B (en) | 2022-09-21 | 2022-09-21 | Wire inspection method adopting unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115237159A true CN115237159A (en) | 2022-10-25 |
| CN115237159B CN115237159B (en) | 2023-09-15 |
Family
ID=83680802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211146787.3A Active CN115237159B (en) | 2022-09-21 | 2022-09-21 | Wire inspection method adopting unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115237159B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751145A (en) * | 2015-04-10 | 2015-07-01 | 西安电子科技大学 | Local Hough transform and morphological optimization SAR (synthetic aperture radar) image power line detection method |
| CN106570863A (en) * | 2016-10-25 | 2017-04-19 | 南方电网科学研究院有限责任公司 | Power transmission line detection method and device |
| CN109325935A (en) * | 2018-07-24 | 2019-02-12 | 国网浙江省电力有限公司杭州供电公司 | A kind of transmission line faultlocating method based on unmanned plane image |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN110782524A (en) * | 2019-10-25 | 2020-02-11 | 重庆邮电大学 | Indoor three-dimensional reconstruction method based on panoramic image |
| CN113435801A (en) * | 2021-08-27 | 2021-09-24 | 海门裕隆光电科技有限公司 | Method, device and equipment for evaluating potential safety hazard of power transmission line based on artificial intelligence |
| CN114943366A (en) * | 2022-04-11 | 2022-08-26 | 中国人民解放军海军航空大学 | Aircraft equipment transfer scheduling method and device considering taking and delivering coordination |
-
2022
- 2022-09-21 CN CN202211146787.3A patent/CN115237159B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751145A (en) * | 2015-04-10 | 2015-07-01 | 西安电子科技大学 | Local Hough transform and morphological optimization SAR (synthetic aperture radar) image power line detection method |
| CN106570863A (en) * | 2016-10-25 | 2017-04-19 | 南方电网科学研究院有限责任公司 | Power transmission line detection method and device |
| CN109325935A (en) * | 2018-07-24 | 2019-02-12 | 国网浙江省电力有限公司杭州供电公司 | A kind of transmission line faultlocating method based on unmanned plane image |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN110782524A (en) * | 2019-10-25 | 2020-02-11 | 重庆邮电大学 | Indoor three-dimensional reconstruction method based on panoramic image |
| CN113435801A (en) * | 2021-08-27 | 2021-09-24 | 海门裕隆光电科技有限公司 | Method, device and equipment for evaluating potential safety hazard of power transmission line based on artificial intelligence |
| CN114943366A (en) * | 2022-04-11 | 2022-08-26 | 中国人民解放军海军航空大学 | Aircraft equipment transfer scheduling method and device considering taking and delivering coordination |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115237159B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108985186B (en) | Improved YOLOv 2-based method for detecting pedestrians in unmanned driving | |
| TWI677826B (en) | License plate recognition system and method | |
| CN110570454B (en) | Method and device for detecting foreign matter invasion | |
| CN109636771B (en) | Flight target detection method and system based on image processing | |
| CN111160407B (en) | Deep learning target detection method and system | |
| CN109919026B (en) | Surface unmanned ship local path planning method | |
| CN109993804A (en) | A kind of road scene defogging method generating confrontation network based on condition | |
| CN107248174A (en) | A kind of method for tracking target based on TLD algorithms | |
| CN112731436B (en) | Multi-mode data fusion travelable region detection method based on point cloud up-sampling | |
| CN115631116B (en) | Aircraft power inspection system based on binocular vision | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN104796582A (en) | Video image denoising and enhancing method and device based on random ejection retinex | |
| CN106407951A (en) | Monocular vision-based nighttime front vehicle detection method | |
| CN116486287A (en) | Target detection method and system based on environment self-adaptive robot vision system | |
| Wang et al. | Ship detection in foggy remote sensing image via scene classification R-CNN | |
| CN111738071A (en) | Inverse perspective transformation method based on movement change of monocular camera | |
| Alami et al. | Local fog detection based on saturation and RGB-correlation | |
| CN108520255B (en) | Infrared weak and small target detection method and device | |
| CN109871903B (en) | Target detection method based on end-to-end deep network and counterstudy | |
| CN115237159A (en) | Electric wire inspection method adopting unmanned aerial vehicle | |
| CN116129329A (en) | Early-stage tiny flame detection method based on deep-space deconvolution and Kalman filtering | |
| Bolten et al. | Evaluation of Deep Learning based 3D-Point-Cloud Processing Techniques for Semantic Segmentation of Neuromorphic Vision Sensor Event-streams. | |
| CN115272284A (en) | Power transmission line defect identification method based on image quality evaluation | |
| CN112102412B (en) | Method and system for detecting visual anchor point in unmanned aerial vehicle landing process | |
| CN111008555B (en) | Unmanned aerial vehicle image small and weak target enhancement extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230821 Address after: No. 555, labor Road, Suzhou City, Jiangsu Province Applicant after: STATE GRID JIANGSU ELECTRIC POWER Co.,Ltd. SUZHOU BRANCH Address before: No. 366, Zhonghua East Road, Sanchang street, Haimen District, Nantong City, Jiangsu Province, 226000 Applicant before: Nantong Rongmao Electronic Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |