CN106570863A - Power transmission line detection method and device - Google Patents
Power transmission line detection method and device Download PDFInfo
- Publication number
- CN106570863A CN106570863A CN201610949803.0A CN201610949803A CN106570863A CN 106570863 A CN106570863 A CN 106570863A CN 201610949803 A CN201610949803 A CN 201610949803A CN 106570863 A CN106570863 A CN 106570863A
- Authority
- CN
- China
- Prior art keywords
- difference image
- adjacent
- transmission line
- image
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 78
- 238000001514 detection method Methods 0.000 title claims abstract description 67
- 238000003708 edge detection Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000007689 inspection Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 11
- 230000005611 electricity Effects 0.000 claims description 51
- 238000001914 filtration Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 10
- 238000012360 testing method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000001960 triggered effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000010189 synthetic method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
Abstract
The embodiment of the invention relates to the electric power inspection technical field, and discloses a power transmission line detection method and device; the method comprises the following steps: carrying out frame difference operation between two adjacent frame images of a collected visible light video sequence so as to obtain a difference image, and binarizing same to obtain a binary difference image; using a preset threshold edge detection algorithm to carry out edge detection for the binary difference image so as to obtain an edge binary difference image; carrying out Hough conversion so as to detect linear sections; carrying out cycle iterations and screening merging for detected linear sections according to the transmission line parallel characteristics until the obtained target linear section number is smaller than a preset value, and marking and displaying same; calculating the central position of a target zone, and sending the central position to a hang cabin so as to adjust the posture of the hang cabin. The method and device can effectively improve the power transmission line detection efficiency and accuracy, thus reducing work load of inspection personnel.
Description
Technical field
The present invention relates to electric inspection process technical field, and in particular to a kind of detection method and device of transmission line of electricity.
Background technology
Electric inspection process always concerns the major issue of national economy, and the major way that current power is patrolled and examined has:Manually
Patrol and examine and helicopter routing inspection, wherein, manual inspection is easily affected by the subjective factorss of weather conditions and patrol officer, time-consuming to take
Power, patrol and examine that efficiency is low and dangerous height;Helicopter routing inspection is by means of aeroplane photography and the fast development of e measurement technology, its side of having
Just, efficiently, reliably and by geographical environment many merits such as do not limited, in consideration of it, " based on helicopter routing inspection, manual inspection be
It is auxiliary " it is developing direction that China's high pressure, extra high voltage network are patrolled and examined.However, with power transmission line pass through geographical environment increasingly
Also there is further development and the needs for being lifted, the master of detection with the identification of current transmission line of electricity in complexity, the mode of electric inspection process
The technological difficulties are wanted to be:The extraction of transmission line of electricity, from the monitoring of motion tracking and real-time performance.
In actual applications, because the shaft tower of transmission line of electricity has the situation that height rises and falls because physical features changes, and transmit electricity
Circuit itself has certain radian, during helicopter routing inspection, need manually control ride over testing equipment head or
Person's gondola, so that transmission line of electricity is in angular field of view all the time, this not only brings the workload of high load capacity to patrol officer,
Further reduces the detection efficiency and Detection accuracy for transmission line of electricity.
The content of the invention
The embodiment of the invention discloses the detection method and device of a kind of transmission line of electricity, can effectively improve for power transmission line
The detection efficiency and Detection accuracy on road, and reduce the workload of patrol officer.
Embodiment of the present invention first aspect discloses a kind of detection method of transmission line of electricity, and methods described includes:
The adjacent two field pictures of the visible light video sequence to collecting carry out inter-frame difference computing, obtain difference image,
And binaryzation is carried out to the difference image, obtain two-value difference image;
Rim detection is carried out to the two-value difference image using predetermined threshold value edge detection algorithm, the value difference of edge two is obtained
Partial image, and Hough transform is carried out to the edge two-value difference image, with detection of straight lines section;
Iteration is circulated to the straightway for detecting according to the parallel nature of power transmission line and screening merges, until
The quantity of the target line section for arriving is less than preset value, and the target described in labelling in the second two field picture of the adjacent two field pictures
Straightway to recognize transmission line of electricity in power transmission line, and show and be marked with the visible light video sequence of the target line section;
The center of target area is calculated, and the center is fed back to into gondola, to adjust the appearance of the gondola
State, wherein, the target area is by the edge area defined of the target line section and second two field picture.
As a kind of optional embodiment, in embodiment of the present invention first aspect, the described pair of visible ray for collecting
The adjacent two field pictures of video sequence carry out inter-frame difference computing, obtain difference image, including:
The two field picture of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image,
And next two field picture of the current frame image and the current frame image is defined as into the one of the visible light video sequence
The adjacent two field pictures of group;
By Gaussian filter to adjacent two field pictures per group described in next two field picture carry out smothing filtering, and with this
Current frame image in adjacent two field pictures carries out inter-frame difference computing, obtains the difference image of the adjacent two field pictures.
As a kind of optional embodiment, in embodiment of the present invention first aspect, the two-value difference image D (x,
Y) it is expressed as:
As a kind of optional embodiment, in embodiment of the present invention first aspect, the predetermined threshold value rim detection
Algorithm is Canny edge detection algorithms.
Embodiment of the present invention second aspect discloses a kind of detection means of transmission line of electricity, and described device includes calculus of differences
Module, binarization block, edge detection module, Hough transform module, straightway processing module, mark module, display module,
Computing module and feedback module, wherein:
The calculus of differences module, for carrying out frame-to-frame differences to the adjacent two field pictures of the visible light video sequence for collecting
Partite transport is calculated, and obtains difference image;
The binarization block, for carrying out binaryzation to the difference image, obtains two-value difference image;
The edge detection module, for carrying out side to the two-value difference image using predetermined threshold value edge detection algorithm
Edge detection, obtains edge two-value difference image;
The Hough transform module, for carrying out Hough transform to the edge two-value difference image, with detection of straight lines
Section;
The straightway processing module, follows for the parallel nature according to power transmission line to the straightway for detecting
Ring iterative and screening merge, until the quantity of the target line section for obtaining is less than preset value;
The mark module, for the target line section described in labelling in the second two field picture of the adjacent two field pictures with
Power transmission line in identification transmission line of electricity;
The display module, for showing the visible light video sequence for being marked with the target line section;
The computing module, for calculating the center of target area, wherein, the target area is by the target
The edge area defined of straightway and second two field picture;
The feedback module, for the center to be fed back to into gondola, to adjust the attitude of the gondola.
Used as a kind of optional embodiment, in embodiment of the present invention second aspect, the calculus of differences module is to adopting
The adjacent two field pictures of the visible light video sequence for collecting carry out inter-frame difference computing, and the concrete mode for obtaining difference image is:
The frame of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image, and will
Next two field picture of the current frame image and the current frame image is defined as one group of phase of the visible light video sequence
Adjacent two field pictures;
By Gaussian filter to adjacent two field pictures per group described in next two field picture carry out smothing filtering, and with this
Current frame image in adjacent two field pictures carries out calculus of differences, obtains the difference image of the adjacent two field pictures.
As a kind of optional embodiment, in embodiment of the present invention second aspect, the two-value difference image D (x,
Y) it is expressed as:
As a kind of optional embodiment, in embodiment of the present invention second aspect, the predetermined threshold value rim detection
Algorithm is Canny edge detection algorithms.
Compared with prior art, the embodiment of the present invention has the advantages that:
In the embodiment of the present invention, the adjacent two field pictures of the visible light video sequence to collecting carry out frame-to-frame differences partite transport
Calculate, obtain difference image, and binaryzation is carried out to difference image obtaining two-value difference image, calculated using predetermined threshold value rim detection
Method carries out rim detection to two-value difference image and obtains edge two-value difference image, and edge two-value difference image is carried out
Hough transform, with detection of straight lines section, iteration and screening is circulated according to the parallel nature of power transmission line to the straightway for detecting
Merge until the quantity of the target line section for obtaining is less than preset value, and the labelling mesh in the second two field picture of adjacent two field pictures
Power transmission line during straightway is marked to recognize transmission line of electricity, and the visible light video sequence for being marked with target line section is shown, meter
The center of target area is calculated, and center is fed back to into gondola, to adjust the attitude of gondola, wherein, target area is
By target line section and the edge area defined of the second two field picture.It can be seen that, implementing the embodiment of the present invention can pass through interframe
The mode of calculus of differences obtains the profile of transmission line of electricity, effectively reduces algorithm complex and operand, and time delay is less, and in real time
Better performances, improve the detection efficiency of transmission line of electricity;Using Hough transform detection of straight lines section and according to the parallel of transmission line of electricity
Characteristic is circulated iteration to the straightway for detecting and screening merges, until number of straight segments is less than preset value and labelling shows
Show, effectively inhibit the interference of background noise and clutter in video image, testing result more accurate and effective to improve defeated
The Detection accuracy of electric line;It is right to be realized by way of calculating center and being fed back to gondola to adjust its attitude
The real-time tracking detection of transmission line of electricity, reduces the workload of patrol officer, effectively raises the detection effect of transmission line of electricity
Rate.
Description of the drawings
Technical scheme in order to be illustrated more clearly that the embodiment of the present invention, below by to be used needed for embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, can be attached to obtain others according to these accompanying drawings
Figure.
Fig. 1 is a kind of schematic flow sheet of the detection method of transmission line of electricity disclosed in the embodiment of the present invention;
Fig. 2 is the schematic flow sheet of the detection method of another kind of transmission line of electricity disclosed in the embodiment of the present invention;
Fig. 3 is a kind of structural representation of the detection means of transmission line of electricity disclosed in the embodiment of the present invention;
Fig. 4 is a kind of result schematic diagram of helicopter routing inspection tracking result disclosed in the embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example is applied, the scope of protection of the invention is belonged to.
The embodiment of the invention discloses the detection method and device of a kind of transmission line of electricity, it is possible to increase for transmission line of electricity
Detection efficiency and Detection accuracy, and reduce the workload of patrol officer.It is described in detail individually below.
Embodiment one
Fig. 1 is referred to, Fig. 1 is a kind of schematic flow sheet of the detection method of transmission line of electricity disclosed in the embodiment of the present invention.
Wherein, the method described by Fig. 1 goes in the testing equipment of transmission line of electricity.As shown in figure 1, the detection of the transmission line of electricity
Method can include following operation:
101st, the adjacent two field pictures of the visible light video sequence to collecting carry out inter-frame difference computing, obtain difference diagram
Picture, and binaryzation is carried out to the difference image, obtain two-value difference image.
In the embodiment of the present invention, the noise in image mostly typically is Gaussian noise, and to adjacent two field pictures interframe is being carried out
Before calculus of differences, first image can be filtered using Gaussian filter, to suppress background clutter and effect of noise, its
In, Gaussian filter is a kind of linear low-pass filters, and it is mainly used in eliminating Gaussian noise, to reach the mesh of smoothed image
, and gaussian filtering is exactly that average process is weighted to entire image, concrete operations are:With the mould that size is n × n
Plate travels through each pixel (also known as convolution or mask) in image, and substitutes mould with the weighted average gray value of pixel in neighborhood
The value of plate central pixel point.It should be noted that the embodiment of the present invention only need to be entered to the second two field picture in adjacent two field pictures
Row gaussian filtering.
Optionally, the adjacent two field pictures of the visible light video sequence to collecting carry out inter-frame difference computing, poor
Partial image can include:
The two field picture of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image,
And next two field picture of the current frame image and the current frame image is defined as into one group adjacent two of visible light video sequence
Two field picture;
By Gaussian filter to next two field picture (in also known as adjacent two field pictures in per group of adjacent two field pictures
Two two field pictures) current frame image (in also known as adjacent two field pictures that carry out in smothing filtering, and two field pictures adjacent with this
One two field picture) inter-frame difference computing is carried out, obtain the difference image of the adjacent two field pictures.
In the embodiment of the present invention, Gauss filter in the current frame image two field pictures adjacent with this in adjacent two field pictures
Next two field picture after ripple carries out inter-frame difference computing and obtains after difference image, then the difference image to obtaining carries out binaryzation and obtains
To two-value difference image, so as to the profile of subsequent extracted target transmission line of electricity, wherein, two-value difference image D (x, y) can be with table
It is shown as:
Wherein, fk(x, y) is the current frame image in adjacent two field pictures, and it is specifically by pixel in the current frame image
The matrix that the pixel value of point is constituted, fk+1(x, y) is that the next two field picture after gaussian filtering is carried out in the adjacent two field pictures,
Its matrix being specifically made up of the pixel value for carrying out pixel in the next two field picture after gaussian filtering, T is the two-value
The threshold value of difference image, " | | " absolute value is represented, x is the row that the pixel in image is located, and y is that the pixel in image is located
Row, and k is 15 integral multiple.
Wherein, inter-frame difference computing realizes that simply fast operation is stronger to the adaptive ability of dynamic environment, to week
The change of light in collarette border is not very sensitive, visible light video sequence is processed using inter-frame difference computing, pole
The big time for shortening computing, effectively raise the real-time of algorithm.
102nd, rim detection is carried out to above-mentioned two-value difference image using predetermined threshold value edge detection algorithm, obtains edge two
Value difference partial image, and Hough transform is carried out to the edge two-value difference image, with detection of straight lines section.
In the embodiment of the present invention, the predetermined threshold value edge detection algorithm need to meet three below principle:1st, maximum output
Signal to noise ratio (ratio of normal signal and noise signal), and non-edge point is judged as that marginal point and marginal point are judged to non-edge point
Probability will be low;2nd, accurate positioning performance, the greatly possible marginal point for ensureing to detect is positioned in actual edge
The heart;3rd, single edges response, i.e., farthest suppress false edge response, and for the only unique response in single edge.Always
For, the basis for selecting of the predetermined threshold value edge detection algorithm is while edge is extracted, can either to improve to target side
The sensitivity of edge, can farthest suppress noise again.
Preferably, the predetermined threshold value edge detection algorithm can be Canny edge detection algorithms, wherein, derived by Canny
The first derivative being shaped like in Gaussian function of the optimal edge detector for going out, therefore, the optimal edge detector can lead to
Cross Gaussian function to approach well.Canny edge detection algorithms (also known as Canny operators) be actually first with Gaussian function with it is upper
Stating two-value difference image carries out convolution, and gradient is then sought again, i.e., first carry out smothing filtering to two-value difference image and eliminate noise
Affect, then the image after denoising is sharpened again, to obtain edge details.Wherein, two-dimensional Gaussian function can be represented
For:
Wherein, σ is the standard deviation of the two-dimensional Gaussian function, and exp is the exponential function with natural constant e as bottom, x for this two
The abscissa of dimension Gaussian function, y is the vertical coordinate of the two-dimensional Gaussian function, and when above-mentioned two-value difference image is f1When (x, y),
The computing formula of Canny edge detection algorithms can be expressed as:
Wherein,The gradient of G (x, y) is sought in expression, that is, seek the first derivative of G (x, y), and " * " represents convolution fortune
Calculate, and above-mentioned two-value difference image f1The edge strength of (x, y) can be expressed as:
Wherein,Expression finds a functionModulus value,Letter is sought in expression
Number G (x, y) * f1(x, y) single order local derviation in the x direction,Expression finds a function G (x, y) * f1(x, y) single order in y-direction
Local derviation, and edge direction θ can be expressed as:
According to the definition of Canny, marginal point centered on the maximum of the neighborhood on its gradient direction, and meet following bar
The pixel of part is considered as the marginal point of above-mentioned two-value difference image:1st, the edge strength of the pixel is more than along the pixel
The edge strength of two neighbor pixels of gradient direction;2 is poor with the direction of adjacent two pixel on the pixel gradient direction
Less than certain direction threshold value;3rd, the edge strength maximum in 3 × 3 neighborhoods centered on the pixel is less than certain intensity threshold
Value.Wherein, condition 1 is referred to as non-maxima suppression, and condition 2 belongs to characteristic synthetic method, when a pixel meets condition 1 simultaneously
During with condition 2, two neighbor pixels on its gradient direction just can be excluded from the marginal point of candidate, the Shi Jiang areas of condition 3
The threshold binary image that domain maximum of gradients is constituted is matched with marginal point, can eliminate the marginal point of many falsenesses.It can be seen that,
The rim detection noise suppressed Performance comparision of Canny edge detection algorithms is good, and the edge for detecting is more clear obvious.
In the embodiment of the present invention, Hough transformation (Hough Transform) is a kind of special extractive technique, is mainly used in straight
Line detects that it is the mapping relations from a kind of image space to parameter space, by edge feature information complicated in image space
The cluster test problems being mapped as in parameter space, this causes Hough transform to have clear aggregating characteristic, very strong anti-interference
Ability and the advantages of be easily achieved parallel processing, and its maximum advantage is strong interference immunity, even if there is little disturbing on curve
Dynamic, gap even dotted line, after Hough transform, remains to form obvious peak dot in parameter space.That is, Hough transform
Principle can explain that in image space, all linear equations for crossing point (x, y) all meet by point-line duality:
Y=px+q; (1-6)
Wherein, p is the slope of the linear equation, and q is the intercept of the linear equation, if setting up a parameter space to p and q
PQ, then point (p, q) represent a point in parameter space PQ, i.e., in straight line in image space correspondence parameter space
One point, above-mentioned linear equation can be rewritten into:
Q=-px+y; (1-7)
Straight line in formula (1-7) representation parameter space PQ, and a point (x, y) in correspondence image space.Image
Point (x is crossed in spacei, yi) general linear equation can be write as yi=pxi+ q, it is also possible to write as q=-px according to formula (1-7)i+yi,
Point (x can be obtained in the same mannerj, yj) linear equation be yj=pxj+ q and q=-pxj+yj, it is assumed that this two straight lines are in parameter
Point (p ', q ') is intersected in the PQ of space, then the point is represented and cross simultaneously in image space point (xi, yi) and point (xj, yj) one
Straight line.
It follows that the line that point correspondence conllinear in image space intersects in parameter space, conversely, in parameter space
In intersect at all straight lines of same point and have conllinear point to correspond to therewith in image space, here it is the antithesis of point-line
Property.
In the embodiment of the present invention, Hough transform is carried out with the concrete of detection of straight lines section to above-mentioned edge two-value difference image
Detecting step is as follows:
1st, the possibility span of parameter p in parameter space and q is quantified, and it is tired according to quantized result construction one
Plus array A (pmin:pmax,qmin:qmax), and the cumulative array is initialized as into 0;
2nd, the given pixel point in above-mentioned edge two-value difference image is taken all over all probable values, and by formula (1-7) by p
Q is calculated, according to the value of p and q cumulative A, i.e. A (p, q)=A (p, q)+1;
3rd, the p and q corresponding to the maximum in cumulative rear A, made by formula (1-6) in image space is straight
Line, the maximum in A represents the number of the set point on this straight line, and the point for meeting linear equation is all conllinear.
In the embodiment of the present invention, Hough transform is accurate about the apriority of figure knowing as a kind of operator of overall importance
Boundary curve is then obtained down, and discontinuous pixel can be coupled together, with very strong robustness and anti-interference energy
Power.
103rd, iteration is circulated to the above-mentioned straightway for detecting according to the parallel nature of power transmission line and screening merges, directly
Quantity to the target line section for obtaining is less than preset value, and labelling mesh in the second two field picture of above-mentioned adjacent two field pictures
Power transmission line during straightway is marked to recognize transmission line of electricity, and show the visible light video sequence for being marked with the target line section.
In the embodiment of the present invention, specifically, after above-mentioned straightway is detected, iteration is circulated to above-mentioned straightway
Operation is less than the first preset value (such as 20) up to the quantity of the straightway for obtaining, then again by the quantity less than the first preset value
The same or like straightway of intercept and slope is merged in straightway, obtains mesh of the quantity less than the second preset value (such as 4)
Mark straightway, and the target line section is marked in the second two field picture of above-mentioned adjacent two field pictures, with above-mentioned adjacent two
The power transmission line represented by target line section is positioned in second two field picture of two field picture.
For example, the video interception of the visible light video sequence for being marked with target line section of display can be such as Fig. 4 institutes
Show, Fig. 4 is a kind of result schematic diagram of helicopter routing inspection tracking result disclosed in the embodiment of the present invention.As shown in figure 4, regarding per opening
The center of the edge area defined of equal mark two parallel power transmission line and power transmission line and video interception in frequency sectional drawing
Position.
104th, the center of target area is calculated, and the center is fed back to into gondola, to adjust the attitude of gondola,
The target area is by the edge area defined of above-mentioned target line section and above-mentioned second two field picture.
In the embodiment of the present invention, above-mentioned target line section and the edge area defined of above-mentioned second two field picture are calculated
, while improving degree of accuracy by optimized algorithm, by error control in allowed band, there is the position letter of power transmission line center
After breath, the positional information is fed back to into gondola to control its elevation-depression angle and level angle, realize to power transmission line it is real-time with
Track.
It should be noted that the detection method of transmission line of electricity disclosed in the embodiment of the present invention can be in Visual
After test is realized under Studio2010 development environments, field programmable gate array (FPGA, Field- are integrated into
Programmable Gate Array) in hardware realizing, effectively enhance the Stability and dependability of transmission line faultlocating.
In the embodiment of the present invention, for example, distinguished by the detection method of transmission line of electricity disclosed in the embodiment of the present invention
Newly facing Lincang 220KV the rich black I loop lines of line and 500KV carries out helicopter routing inspection, and when patrolling and examining, helicopter is two
Distance during bar flight line away from power transmission line is 40-50m, and the structure of power transmission line is quadripartion structure, then for two lines
Road carries out the data of patrolling and examining of helicopter routing inspection test can respectively as shown in Table 1 and Table 2, and table 1 newly faces line and patrols and examines number for 220KV
According to, table 2 is that the rich ink I loop lines of 500KV patrol and examine data, wherein:
The 220KV of table 1 newly faces line and patrols and examines data
The rich ink I lines of the 500KV of table 2 patrol and examine data
It can be seen that, implementing the detection method of the transmission line of electricity described by Fig. 1 can be obtained by way of inter-frame difference computing
The profile of transmission line of electricity, effectively reduces algorithm complex and operand, and time delay is less, and real-time performance is preferably, improves defeated
The detection efficiency of electric line;It is using Hough transform detection of straight lines section and straight to what is detected according to the parallel nature of transmission line of electricity
Line segment is circulated iteration and screening merges, until number of straight segments is less than preset value and labelling shows, effectively inhibits and regards
The interference of background noise and clutter in frequency image, testing result more accurate and effective, the detection that improve transmission line of electricity is accurate
Rate;Calculate center and realize by way of being fed back to gondola to adjust its attitude to transmission line of electricity it is real-time with
Track detection, reduces the workload of patrol officer, effectively raises the detection efficiency of transmission line of electricity.
Embodiment two
Fig. 2 is referred to, Fig. 2 is that the flow process of the detection method of another kind of transmission line of electricity disclosed in the embodiment of the present invention is illustrated
Figure.As shown in Fig. 2 the detection method of the transmission line of electricity can include following operation:
201st, the real time imaging of transmission line of electricity to be detected is gathered by photographic head, visible light video sequence is obtained.
Whether the frame number for the 202nd, judging the current frame image in above-mentioned visible light video sequence is 15 integral multiple.
In the embodiment of the present invention, when the judged result of step 202 is to be, execution step 203 is triggered;When step 202
When judged result is no, directly displays and export the current frame image.
203rd, next two field picture of above-mentioned current frame image and above-mentioned current frame image is cached.
204th, call the above-mentioned next two field picture of thread process function pair to carry out smothing filtering, and enter with above-mentioned current frame image
Row inter-frame difference computing, obtains difference image.
205th, binaryzation is carried out to above-mentioned difference image, obtains two-value difference image, and by Canny edge detection algorithms
Rim detection is carried out to the two-value difference image, edge two-value difference image is obtained.
206th, Hough transform is carried out to above-mentioned edge two-value difference image, with detection of straight lines section.
Whether the quantity for the 207th, judging the straightway for detecting is 0.
In the embodiment of the present invention, when the judged result of step 207 is to be, the above-mentioned current frame image of output is directly displayed;
When the judged result of step 207 is no, execution step 208 is triggered.
208th, judge the quantity of the straightway for detecting whether more than 500.
In the embodiment of the present invention, when the judged result of step 208 is to be, the above-mentioned current frame image of output is directly displayed;
When the judged result of step 208 is no, execution step 209 is triggered.
209th, judge the quantity of the straightway for detecting whether less than 75.
In the embodiment of the present invention, when the judged result of step 209 is no, execution step 210 is triggered;When step 209
When judged result is to be, execution step 211 is triggered.
210th, iteration threshold is updated, and the above-mentioned straightway for detecting is circulated repeatedly according to the iteration threshold after renewal
Generation, until obtaining straightway of the quantity less than 20.
211st, combined screening straightway, until straightway of the quantity less than 4 is obtained, and in above-mentioned next two field picture acceptance of the bid note
Straightway of the quantity less than 4.
212nd, number of computations less than 4 straightway surround region with the edge of above-mentioned next two field picture centre coordinate simultaneously
Labelling.
213rd, above-mentioned zone centre coordinate is fed back to into gondola, to trigger gondola adjust automatically its attitude.
214th, display output is labeled with the visible light video sequence of straightway of the quantity less than 4.
It can be seen that, the detection method of the transmission line of electricity described by enforcement Fig. 2 can effectively improve the detection for transmission line of electricity
Efficiency and Detection accuracy, and reduce the workload of patrol officer.
Embodiment three
Fig. 3 is referred to, Fig. 3 is a kind of structural representation of the detection means of transmission line of electricity disclosed in the embodiment of the present invention.
As shown in figure 3, the detection means of the transmission line of electricity can include calculus of differences module 301, binarization block 302, rim detection
Module 303, Hough transform module 304, straightway processing module 305, mark module 306, display module 307, computing module
308 and feedback module 309, wherein:
Calculus of differences module 301 is used for the adjacent two field pictures of the visible light video sequence to collecting carries out inter-frame difference
Computing, obtains difference image.
Binarization block 302 is used to carry out binaryzation to above-mentioned difference image, obtains two-value difference image.
Edge detection module 303 is used to carry out edge to above-mentioned two-value difference image using predetermined threshold value edge detection algorithm
Detection, obtains edge two-value difference image.
Hough transform module 304 is used to carry out Hough transform to above-mentioned edge two-value difference image, with detection of straight lines section.
Straightway processing module 305 is used to be circulated iteration to the straightway for detecting according to the parallel nature of power transmission line
And screening merges, until the quantity of the target line section for obtaining is less than preset value.
It is defeated to recognize that mark module 306 is used for the labelling target line section in the second two field picture of above-mentioned adjacent two field pictures
Power transmission line in electric line;
Display module 307 is used to show the visible light video sequence for being marked with target line section.
Computing module 308 is used to calculate the center of target area, wherein, the target area is by above-mentioned target line
Section and the edge area defined of above-mentioned second two field picture.
Feedback module 309 is used to for above-mentioned center to feed back to gondola, to adjust the attitude of gondola.
Wherein, the adjacent two field pictures of the visible light video sequence that calculus of differences module 301 pairs is collected carry out frame-to-frame differences
Partite transport is calculated, and the concrete mode for obtaining difference image is:
The frame of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image, and will
Next two field picture of the current frame image and the current frame image is defined as one group of adjacent two frames figure of visible light video sequence
Picture;
Smothing filtering is carried out to the next two field picture in per group of adjacent two field pictures by Gaussian filter, and it is adjacent with this
Current frame image in two field pictures carries out calculus of differences, obtains the difference image of the adjacent two field pictures.
Wherein, above-mentioned two-value difference image D (x, y) can be expressed as:
Wherein, above-mentioned predetermined threshold value edge detection algorithm is Canny edge detection algorithms.
It can be seen that, the detection means 300 of the transmission line of electricity described by implementing Fig. 3 can improve the detection effect for transmission line of electricity
Rate and Detection accuracy, and reduce the workload of patrol officer.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
Completed with instructing the hardware of correlation by program, the program can be stored in a computer-readable recording medium, storage
Medium include read only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), read-only optical disc (Compact
Disc Read-Only Memory, CD-ROM) or other disk storages, disk memory, magnetic tape storage or can
For carrying or computer-readable any other medium of data storage.
The detection method and device of a kind of transmission line of electricity disclosed in the embodiment of the present invention are described in detail above, this
Apply specific case in text to be set forth the principle and embodiment of the present invention, the explanation of above example is only intended to
Help understands the method for the present invention and its core concept;Simultaneously for one of ordinary skill in the art, according to the think of of the present invention
Think, will change in specific embodiments and applications, in sum, it is right that this specification content should not be construed as
The restriction of the present invention.
Claims (8)
1. a kind of detection method of transmission line of electricity, it is characterised in that methods described includes:
The adjacent two field pictures of the visible light video sequence to collecting carry out inter-frame difference computing, obtain difference image, and right
The difference image carries out binaryzation, obtains two-value difference image;
Rim detection is carried out to the two-value difference image using predetermined threshold value edge detection algorithm, edge two-value difference diagram is obtained
Picture, and Hough transform is carried out to the edge two-value difference image, with detection of straight lines section;
Iteration is circulated to the straightway for detecting according to the parallel nature of power transmission line and screening merges, until obtain
The quantity of target line section is less than preset value, and the target line described in labelling in the second two field picture of the adjacent two field pictures
Section to recognize transmission line of electricity in power transmission line, and show and be marked with the visible light video sequence of the target line section;
The center of target area is calculated, and the center is fed back to into gondola, to adjust the attitude of the gondola, its
In, the target area is by the edge area defined of the target line section and second two field picture.
2. method according to claim 1, it is characterised in that adjacent the two of the described pair of visible light video sequence for collecting
Two field picture carries out inter-frame difference computing, obtains difference image, including:
The two field picture of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image, and will
Next two field picture of the current frame image and the current frame image is defined as one group of phase of the visible light video sequence
Adjacent two field pictures;
By Gaussian filter to adjacent two field pictures per group described in next two field picture carry out smothing filtering, it is and adjacent with this
Current frame image in two field pictures carries out inter-frame difference computing, obtains the difference image of the adjacent two field pictures.
3. method according to claim 2, it is characterised in that two-value difference image D (x, y) is expressed as:
Wherein, fk(x, y) is the current frame image in the adjacent two field pictures, fk+1(x, y) is to enter in the adjacent two field pictures
Next two field picture after row smothing filtering, T is the threshold value of the two-value difference image.
4. the method according to any one of claim 1-3, it is characterised in that the predetermined threshold value edge detection algorithm is
Canny edge detection algorithms.
5. a kind of detection means of transmission line of electricity, it is characterised in that described device include calculus of differences module, binarization block,
Edge detection module, Hough transform module, straightway processing module, mark module, display module, computing module and feedback
Module, wherein:
The calculus of differences module, for carrying out frame-to-frame differences partite transport to the adjacent two field pictures of the visible light video sequence for collecting
Calculate, obtain difference image;
The binarization block, for carrying out binaryzation to the difference image, obtains two-value difference image;
The edge detection module, for carrying out edge inspection to the two-value difference image using predetermined threshold value edge detection algorithm
Survey, obtain edge two-value difference image;
The Hough transform module, for carrying out Hough transform to the edge two-value difference image, with detection of straight lines section;
The straightway processing module, is circulated repeatedly for the parallel nature according to power transmission line to the straightway for detecting
Generation and screening merge, until the quantity of the target line section for obtaining is less than preset value;
The mark module, for the target line section described in labelling in the second two field picture of the adjacent two field pictures recognizing
Power transmission line in transmission line of electricity;
The display module, for showing the visible light video sequence for being marked with the target line section;
The computing module, for calculating the center of target area, wherein, the target area is by the target line
Section and the edge area defined of second two field picture;
The feedback module, for the center to be fed back to into gondola, to adjust the attitude of the gondola.
6. device according to claim 5, it is characterised in that the calculus of differences module is to the visible light video that collects
The adjacent two field pictures of sequence carry out inter-frame difference computing, and the concrete mode for obtaining difference image is:
The frame of the integral multiple that frame number in the visible light video sequence for collecting is 15 is extracted as current frame image, and will be described
Next two field picture of current frame image and the current frame image is defined as a group adjacent two of the visible light video sequence
Two field picture;
By Gaussian filter to adjacent two field pictures per group described in next two field picture carry out smothing filtering, it is and adjacent with this
Current frame image in two field pictures carries out calculus of differences, obtains the difference image of the adjacent two field pictures.
7. device according to claim 6, it is characterised in that two-value difference image D (x, y) is expressed as:
Wherein, fk(x, y) is the current frame image in the adjacent two field pictures, fk+1(x, y) is to enter in the adjacent two field pictures
Next two field picture after row smothing filtering, T is the threshold value of the two-value difference image.
8. the device according to any one of claim 5-7, it is characterised in that the predetermined threshold value edge detection algorithm is
Canny edge detection algorithms.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610949803.0A CN106570863A (en) | 2016-10-25 | 2016-10-25 | Power transmission line detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610949803.0A CN106570863A (en) | 2016-10-25 | 2016-10-25 | Power transmission line detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106570863A true CN106570863A (en) | 2017-04-19 |
Family
ID=58535064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610949803.0A Pending CN106570863A (en) | 2016-10-25 | 2016-10-25 | Power transmission line detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106570863A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194333A (en) * | 2017-05-10 | 2017-09-22 | 深圳增强现实技术有限公司 | The detection method and device of transmission line of electricity |
CN107657614A (en) * | 2017-10-31 | 2018-02-02 | 成都意町工业产品设计有限公司 | A kind of rail for high voltage transmission line damage testing hands over detection means |
CN107742292A (en) * | 2017-10-31 | 2018-02-27 | 成都意町工业产品设计有限公司 | A kind of foreign matter cruising inspection system on ultra-high-tension power transmission line |
CN107741431A (en) * | 2017-10-31 | 2018-02-27 | 成都意町工业产品设计有限公司 | A kind of breakage detection system of ultra-high-tension power transmission line |
CN107766801A (en) * | 2017-09-28 | 2018-03-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of insulator recognition methods and device based on infrared heat point tracking |
CN107945193A (en) * | 2017-10-31 | 2018-04-20 | 成都意町工业产品设计有限公司 | A kind of detecting system for being used to detect high-voltage line breakage |
CN108322693A (en) * | 2018-03-01 | 2018-07-24 | 上海创视通软件技术有限公司 | A kind of method and system of the ends MCU control third party's terminal secondary flow |
CN108961276A (en) * | 2018-04-04 | 2018-12-07 | 山东鲁能智能技术有限公司 | The distribution line inspection automatic data collection method and system of view-based access control model servo |
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 |
CN109828681A (en) * | 2017-11-20 | 2019-05-31 | 深圳市Tcl高新技术开发有限公司 | Laser pen light stream trace tracking method, projection device and computer readable storage medium |
CN110134148A (en) * | 2019-05-24 | 2019-08-16 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of transmission line of electricity helicopter make an inspection tour in tracking along transmission line of electricity |
CN110415249A (en) * | 2019-06-06 | 2019-11-05 | 国网浙江省电力有限公司杭州供电公司 | Transmission of electricity line detecting method based on CBS line segment detection |
CN111445450A (en) * | 2020-03-19 | 2020-07-24 | 广州市维安科技股份有限公司 | Power transmission line state detection method based on video image analysis |
CN112233137A (en) * | 2020-11-19 | 2021-01-15 | 成都寰蓉光电科技有限公司 | High-performance weighted standard deviation background modeling method |
CN112364874A (en) * | 2020-09-15 | 2021-02-12 | 广东电网有限责任公司 | Extraction method of power transmission line |
CN114387248A (en) * | 2022-01-12 | 2022-04-22 | 苏州天准科技股份有限公司 | Silicon material melting degree monitoring method, storage medium, terminal and crystal pulling equipment |
CN115237159A (en) * | 2022-09-21 | 2022-10-25 | 南通荣茂电子科技有限公司 | Electric wire inspection method adopting unmanned aerial vehicle |
CN116046076A (en) * | 2023-03-09 | 2023-05-02 | 合肥工业大学 | Online detection system for power transmission line galloping based on machine vision technology |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
CN103063166A (en) * | 2013-01-05 | 2013-04-24 | 山西省电力公司大同供电分公司 | Detection method and device for wind deflection angle of suspension type composite insulator chain |
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 |
CN105931259A (en) * | 2016-06-21 | 2016-09-07 | 国网重庆市电力公司电力科学研究院 | High voltage transmission line extraction method based on morphology processing and device |
-
2016
- 2016-10-25 CN CN201610949803.0A patent/CN106570863A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
CN103063166A (en) * | 2013-01-05 | 2013-04-24 | 山西省电力公司大同供电分公司 | Detection method and device for wind deflection angle of suspension type composite insulator chain |
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 |
CN105931259A (en) * | 2016-06-21 | 2016-09-07 | 国网重庆市电力公司电力科学研究院 | High voltage transmission line extraction method based on morphology processing and device |
Non-Patent Citations (3)
Title |
---|
仝卫国等: "图像处理技术在直升机巡检输电线路中的应用综述", 《电网技术》 * |
宋峥峥: "架空电力线路巡检的空中视频监测系统综述", 《中国电力教育》 * |
李高磊: "基于机器视觉的无人机电力巡线技术研究", 《安徽理工大学硕士学位论文数据库》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194333A (en) * | 2017-05-10 | 2017-09-22 | 深圳增强现实技术有限公司 | The detection method and device of transmission line of electricity |
CN107766801A (en) * | 2017-09-28 | 2018-03-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of insulator recognition methods and device based on infrared heat point tracking |
CN107766801B (en) * | 2017-09-28 | 2021-02-05 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Insulator identification method and device based on infrared hotspot tracking |
CN107657614A (en) * | 2017-10-31 | 2018-02-02 | 成都意町工业产品设计有限公司 | A kind of rail for high voltage transmission line damage testing hands over detection means |
CN107742292A (en) * | 2017-10-31 | 2018-02-27 | 成都意町工业产品设计有限公司 | A kind of foreign matter cruising inspection system on ultra-high-tension power transmission line |
CN107741431A (en) * | 2017-10-31 | 2018-02-27 | 成都意町工业产品设计有限公司 | A kind of breakage detection system of ultra-high-tension power transmission line |
CN107945193A (en) * | 2017-10-31 | 2018-04-20 | 成都意町工业产品设计有限公司 | A kind of detecting system for being used to detect high-voltage line breakage |
CN109828681A (en) * | 2017-11-20 | 2019-05-31 | 深圳市Tcl高新技术开发有限公司 | Laser pen light stream trace tracking method, projection device and computer readable storage medium |
CN108322693A (en) * | 2018-03-01 | 2018-07-24 | 上海创视通软件技术有限公司 | A kind of method and system of the ends MCU control third party's terminal secondary flow |
CN108322693B (en) * | 2018-03-01 | 2021-03-02 | 上海创视通软件技术有限公司 | Method and system for controlling auxiliary stream of third-party terminal by MCU (microprogrammed control Unit) terminal |
CN108961276B (en) * | 2018-04-04 | 2020-09-25 | 国网智能科技股份有限公司 | Distribution line inspection data automatic acquisition method and system based on visual servo |
CN108961276A (en) * | 2018-04-04 | 2018-12-07 | 山东鲁能智能技术有限公司 | The distribution line inspection automatic data collection method and system of view-based access control model servo |
CN109325935B (en) * | 2018-07-24 | 2022-02-22 | 国网浙江省电力有限公司杭州供电公司 | Power transmission line detection method based on unmanned aerial vehicle image |
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 |
CN110134148A (en) * | 2019-05-24 | 2019-08-16 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | A kind of transmission line of electricity helicopter make an inspection tour in tracking along transmission line of electricity |
CN110415249A (en) * | 2019-06-06 | 2019-11-05 | 国网浙江省电力有限公司杭州供电公司 | Transmission of electricity line detecting method based on CBS line segment detection |
CN111445450A (en) * | 2020-03-19 | 2020-07-24 | 广州市维安科技股份有限公司 | Power transmission line state detection method based on video image analysis |
CN112364874A (en) * | 2020-09-15 | 2021-02-12 | 广东电网有限责任公司 | Extraction method of power transmission line |
CN112233137A (en) * | 2020-11-19 | 2021-01-15 | 成都寰蓉光电科技有限公司 | High-performance weighted standard deviation background modeling method |
CN114387248A (en) * | 2022-01-12 | 2022-04-22 | 苏州天准科技股份有限公司 | Silicon material melting degree monitoring method, storage medium, terminal and crystal pulling equipment |
CN114387248B (en) * | 2022-01-12 | 2022-11-25 | 苏州天准科技股份有限公司 | Silicon material melting degree monitoring method, storage medium, terminal and crystal pulling equipment |
CN115237159A (en) * | 2022-09-21 | 2022-10-25 | 南通荣茂电子科技有限公司 | Electric wire inspection method adopting unmanned aerial vehicle |
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 |
CN116046076A (en) * | 2023-03-09 | 2023-05-02 | 合肥工业大学 | Online detection system for power transmission line galloping based on machine vision technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106570863A (en) | Power transmission line detection method and device | |
Kalfarisi et al. | Crack detection and segmentation using deep learning with 3D reality mesh model for quantitative assessment and integrated visualization | |
Peng et al. | A UAV-based machine vision method for bridge crack recognition and width quantification through hybrid feature learning | |
CN106910203B (en) | The quick determination method of moving target in a kind of video surveillance | |
CN102252623B (en) | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis | |
CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
WO2018028103A1 (en) | Unmanned aerial vehicle power line inspection method based on characteristics of human vision | |
CN109087510A (en) | traffic monitoring method and device | |
CN109738910A (en) | A kind of curb detection method based on three-dimensional laser radar | |
CN106530281B (en) | Unmanned plane image fuzzy Judgment method and system based on edge feature | |
CN108985169A (en) | Across the door operation detection method in shop based on deep learning target detection and dynamic background modeling | |
CN108564814A (en) | A kind of parking position detection method and device based on image | |
CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
CN107845264A (en) | A kind of volume of traffic acquisition system and method based on video monitoring | |
CN109214439A (en) | A kind of infrared image icing River detection method based on multi-feature fusion | |
CN105426894B (en) | Railway plug pin image detecting method and device | |
CN102930279B (en) | For the image-recognizing method that product quantity detects | |
CN108932273A (en) | Picture screening technique and device | |
CN107264570A (en) | steel rail light band distribution detecting device and method | |
WO2023231262A1 (en) | Hoisting wire rope tension measurement method based on visual vibration frequency identification | |
CN114187511A (en) | Intelligent monitoring method for power transmission panoramic big data | |
CN115841633A (en) | Power tower and power line associated correction power tower and power line detection method | |
CN107729814A (en) | A kind of method and device for detecting lane line | |
CN208271388U (en) | A kind of volume of traffic acquisition system based on video monitoring | |
CN104331708B (en) | A kind of zebra crossing automatic detection analysis method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170419 |