CN107392127B - Transmission line of electricity extracting method based on Chebyshev polynomials description - Google Patents
Transmission line of electricity extracting method based on Chebyshev polynomials description Download PDFInfo
- Publication number
- CN107392127B CN107392127B CN201710568713.1A CN201710568713A CN107392127B CN 107392127 B CN107392127 B CN 107392127B CN 201710568713 A CN201710568713 A CN 201710568713A CN 107392127 B CN107392127 B CN 107392127B
- Authority
- CN
- China
- Prior art keywords
- class
- curve
- chebyshev polynomials
- image
- rank
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 37
- 230000005611 electricity Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012217 deletion Methods 0.000 claims 1
- 230000037430 deletion Effects 0.000 claims 1
- 239000000284 extract Substances 0.000 abstract description 13
- 238000000605 extraction Methods 0.000 abstract description 9
- 238000003064 k means clustering Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 240000004808 Saccharomyces cerevisiae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 229910052704 radon Inorganic materials 0.000 description 1
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/469—Contour-based spatial representations, e.g. vector-coding
- G06V10/471—Contour-based spatial representations, e.g. vector-coding using approximation functions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of transmission line of electricity extraction algorithms based on Chebyshev polynomials description, comprising: be pre-processed to input picture, the straight line and curve in image are extracted using random Hough transformation, advantage is described using the curve that Chebyshev polynomials describe son, feature description is carried out to extracted object, and visual dictionary is trained by K-means clustering method, by the comparison of visual dictionary, extract the transmission line of electricity in image.The present invention can effectively improve the precision of the extraction of the transmission line of electricity under complex background.
Description
Technical field
The present invention relates to electric system, pattern-recognition and the classification and detection of classify field, especially specific objective.
Background technique
In the power system, used main power transmission mode since overhead transmission line transmission of electricity is electric power industry development.It relies on
In manually carrying out the mode of inspection and maintenance not only low efficiency, at high cost to transmission line of electricity, but also there is very big safeties
Problem.With the development of intellectual technology, the detecting to transmission line of electricity using computer vision and image processing techniques is being protected
It is had very important effect in terms of the safe operation for hindering electric system.Since image data acquisition is vulnerable to sensor, shooting
The influence of many factors such as environment, shooting angle, image obtained are not simple transmission lines of electricity, mostly containing complexity
Background, the extraction algorithm for studying the transmission line of electricity under complex background have great importance.
In the recent period, researchers are proposed many and are known in visible images using computer vision and image processing techniques
Indescribably take the algorithm of transmission line of electricity.Document (" the Power Lines from Aerial Images such as Li Chaoyang, Yan Guangjian it is automatic
Extract [J], Journal of Image and Graphics, 2007,12 (6): 1041-1047. ") one kind is proposed in complicated nature background condition
Under, the algorithm of 550kV high-voltage power line, this method are automatically extracted from aviation image with Ratio operator and segmentation Radon transformation
The high-voltage power line under complicated nature background can be automatically extracted, but is the image of high-altitude shooting, electric power thread handled by this method
Linearly, the curve-like power line that there is greater curvature with journey can not be extracted；(" such as Li Cailin, Feng Chaohui are intricately for document
Power line extraction method [J] under object background, computer engineering and application, 2016,52 (22): 198-202. ") it is utilizing
Canny operator extraction image border, Hough transform propose a kind of geometry according to power line on the basis of generating broken straightway
The algorithm of the complete power line of characteristic recovery, the algorithm can be to extract complete power line, but the party in unmanned plane image
It is the image of high-altitude shooting handled by method, linear power line can only be extracted, curve-like power line can not be extracted；Document ("
It is few flat, the Aerial Images power line extraction method [J] that the such as Yang Zhong are detected based on feature, applicating technology, 2012,39 (5): 36-
39. ") in analyzing power transmission line unmanned machine cruising inspection system Aerial Images on the basis of power line characteristic, with Ratio operator and
Hough transform proposes a kind of power line extraction algorithm based on feature detection, but is the shadow of unmanned plane shooting handled by this method
Picture can only extract linear power line, can not extract curve-like power line；Document (" Qirong Ma, Darren
S.Goshi,Yi-Chi Shih,Ming-Ting Sun,An Algorithm for Power Line Detection and
Warning Based on a Millimeter-Wave Radar Video[J],IEEE Transactions on Image
Processing, 2011,20 (12): 3534-3543. ") propose it is a kind of based on Hough transform and support vector machines (SVM)
The algorithm is used to detect video image acquired in millimetre-wave radar by transmission line faultlocating algorithm, but this method can not be handled
There are problems that the electric power line drawing in the visible images of complex background；Document (" Wei Song, Xiaorui Hu, Jin Fu,
Qing Zhou,Ting Zhou,Pengju Si,The Method of Hybrid-laser Image Spot Extracts
Based on HSV Space SVD for Power Transmission Line Detection[C],2016IEEE
International Conference on Information and Automation(ICIA),2016,1361-1364”)
Using multiple lasers for positioning, a kind of transmission line faultlocating algorithm based on HSV space singular value decomposition is proposed, is used for
Transmission line faultlocating under complex environment and background condition, but this method can not still handle curve-like electric power line drawing problem.
Existing most of existing power line detection work lays particular emphasis on straight-line detection, can not be applied to have compared with yeast
The detection of rate electric power line image；Meanwhile in complex background extract power line still exist extract electric power thread breakage it is imperfect,
The deficiencies of algorithm is complicated unstable place.
Summary of the invention
The present invention to overcome above-mentioned the deficiencies in the prior art place, provide it is a kind of based on Chebyshev polynomials description son
Transmission line of electricity extraction algorithm to the influence that complex background can be overcome to detect power line, and is able to detect and extracts curve-like
Power line, so as to can accurately extract the transmission line of electricity under complex background.
The technical scheme adopted by present invention for solving the technical problem is that
The present invention is by following step a kind of the characteristics of sub transmission line of electricity extracting method is described based on Chebyshev polynomials
It is rapid to carry out:
Several width electric power line images in step 1, acquisition transmission line of electricity, and carry out median filtering and histogram equalization
Pretreatment, obtains several pretreated electric power line images；Recycle thresholding method to the pretreated power line
Image is handled, and several width bianry images are obtained, and remembers that any one width bianry image is present image；
Step 2 detects the curve in the present image using random Hough transformation, obtains several curves,
Remember that any one curve is C；
Step 3 describes son using Chebyshev polynomials to curve C progress character representation, obtains m rank Chebyshev
Multinomial description, is denoted as TC=(a0,a1,…,am-1,b0,b1,…,bm-1), a0,a1,…,am-1Indicate the cross of the curve C
Coordinate function be unfolded according to Chebyshev polynomials after coefficient, b0,b1,…,bm-1Indicate that the ordinate function of the curve C is pressed
According to the coefficient after Chebyshev polynomials expansion；
Step 4 utilizes the visual dictionary of machine learning method training power line:
K step 4.1, random initializtion central pointIndicate i-th of central point, i=1,
2,…,K；
Step 4.2, the m rank Chebyshev polynomials for calculating the curve C describe sub- TCTo i-th of central pointDistanceTo obtain sample point to K central point distance { d1,d2,…,di,…,dK}；From the distance { d1,
d2,…,di,…,dKIn choose minimum value and by sample point TCIt is referred in class corresponding to minimum value；Thus by all curves
It is referred in corresponding class, and obtains K class；
Step 4.3, the central point for calculating the K classAnd with original K central pointIt is compared, if all the same, thens follow the steps 4.4；Otherwise, by the center for K class being calculated
PointIt is assigned to the K central pointAfter being updated, return step
4.2；
Step 4.4, the central point for calculating the K classIn class where each central point it is flat
Mean value obtains average value vectorIndicate the average value of i-th of class；
Step 4.5 obtains the visual dictionary L of power line using formula (1):
In formula (1), μiFor the matching threshold of i-th of class, matching threshold μiIt is multinomial for m rank Chebyshevs all in i-th of class
The average value of formula description son and i-th of classBetween difference maximum norm；
Step 5 passes through dictionary pattern matching, eliminates non-electrical line of force feature:
Step 5.1 obtains another width electric power line image on transmission line of electricity as test image, and according to step 1 to step
Rapid 3 are handled, and are obtained m rank Chebyshev polynomials description of n curve in the test image, are denoted as { T(1),T(2),…,T(j),…,T(n)}；T(j)Indicate that the m rank Chebyshev polynomials description of j-th strip curve in the test image is sub, 1≤
j≤n；
Step 5.2, initialization j=1；
Step 5.3, initialization i=1；
The m rank Chebyshev polynomials of j-th strip curve are described sub- T by step 5.4(j)With the average value of i-th of classPhase
The matching threshold μ of the mould of the difference obtained after subtracting and i-th of classiIt compares, if difference is less than or equal to matching threshold μi, then it represents that
The m rank Chebyshev polynomials of j-th strip curve describe sub- T(j)Belong to i-th of class, executes step 5.5；Otherwise, indicate that j-th strip is bent
The m rank Chebyshev polynomials of line describe sub- T(j)It is not belonging to i-th of class, executes step 5.6；
Step 5.5, judge whether j > n is true, if so, then indicate that test image has been matched with the visual dictionary L
At p curve corresponding to m rank Chebyshev polynomials description after being matched is as power line；Otherwise, j+1 is assigned
It is worth to after j, return step 5.3；
Step 5.6, judge whether i > K is true, if so, then indicate that the m rank Chebyshev polynomials of j-th strip curve are retouched
State sub- T(j)It is not belonging to any one class, and deletes j-th strip curve from the m rank Chebyshev polynomials of n curve description
M rank Chebyshev polynomials describe sub- T(j)Afterwards, j+1 is assigned to j, executes step 5.3；Otherwise, it after i+1 being assigned to i, returns
Return step 5.4.
Compared with existing technology, the beneficial effects of the present invention are embodied in:
1, the present invention input picture is pre-processed first, using random Hough transformation extract image in straight line and
Curve, describes advantage using the curve that Chebyshev polynomials describe son, carries out feature description to extracted object, and pass through
Visual dictionary is trained in K-means clustering method, by the comparison of visual dictionary, extracts the transmission line of electricity in image, from
And effectively increase the precision of the transmission line faultlocating under complex background.
2, the present invention detects image using random Hough transformation, can efficiently extract straight in extraction image
Line and curve；
3, the present invention is described open curve and straight line using Chebyshev polynomials description, can be to described
Object carries out effective character representation；
4, the present invention trains visual dictionary, model training link using K-means clustering method in machine learning
Simply, while the diversity of sample also improves the adaptability to different scenes, by dictionary pattern matching, to improve power transmission line
The precision of road detection.
Detailed description of the invention
Fig. 1 is algorithm flow chart of the invention.
Specific embodiment
In the present embodiment, as shown in Figure 1, a kind of transmission line of electricity extracting method based on Chebyshev polynomials description,
It is to be pre-processed to input picture, extracts the straight line and curve in image using random Hough transformation, it is more using Chebyshev
The curve of item formula description describes advantage, carries out feature description to extracted object, and pass through K-means clustering method
Visual dictionary is trained, by the comparison of visual dictionary, the transmission line of electricity in image is extracted, specifically carries out as follows:
Several width electric power line images in step 1, acquisition transmission line of electricity, and carry out median filtering and histogram equalization
The problems such as pretreatment, median filtering can overcome edge blurry and noise, it can preferably retain the marginal information of transmission line of electricity；
The contrast for enhancing image using histogram equalization obtains several pretreated electric power line images；Recycle threshold value
Split plot design handles pretreated electric power line image, obtains several width bianry images, remembers that any one width bianry image is
Present image；
Step 2 detects the curve in present image using random Hough transformation, and random Hough transformation is extracting
It is high-efficient using a kind of random method when edge pixel, while to the noise of image more robust, obtain several songs
Line remembers that any one curve is C；
Step 3 describes son using Chebyshev polynomials to curve C progress character representation, and it is multinomial to obtain m rank Chebyshev
Formula description, is denoted as TC=(a0,a1,…,am-1,b0,b1,…,bm-1), a0,a1,…,am-1Indicate the abscissa function of curve C
Coefficient after being unfolded according to Chebyshev polynomials, b0,b1,…,bm-1Indicate that the ordinate function of curve C is more according to Chebyshev
Coefficient after item formula expansion；
There is Chebyshev polynomials description very strong open curve to indicate that ability, Stability and veracity are high, calculate letter
The advantages that single, Chebyshev polynomials are defined as
P0(t)=1, P1(t)=t, Pm(t)=2tPm-1(t)-Pm-2(t), m=2,3 ...
One-dimensional functions f (t) is deployable to be
In practice, in order to realize computability, the m approximations as f (t) before generally taking, i.e.,
The parametric equation of one open curve C can be expressed as Z (t)=(x (t), y (t), t ∈ [0, L]), wherein x (t) and y
(t) curvilinear abscissa and ordinate when length is t are indicated, is the function about length t, L is the total length of curve.X (t) with
Y (t) can regard two one-dimensional functions as, expand into according to Chebyshev polynomials
Wherein coefficient ai(i=0,1 ..., m-1), bi(i=0,1 ..., m-1), the referred to as Chebyshev polynomials of curve C
It describes sub (CPDs) and is denoted as TC=(a0,a1,…,am-1,b0,b1,…,bm-1)。
Step 4 utilizes the visual dictionary of K-means clustering method training power line in machine learning:
K step 4.1, random initializtion central pointIndicate i-th of central point, i=1,
2,…,K；
Step 4.2, the m rank Chebyshev polynomials of calculated curve C describe sub- TCTo i-th of central pointDistanceIndicate vector 2 norms, thus obtain sample point to K central point distance { d1,d2,…,di,…,
dK}；From gained distance { d1,d2,…,di,…,dKIn choose minimum value and by sample point TCIt is referred to class corresponding to minimum value
In；To which all curves is referred in corresponding class, and obtain K class；
Step 4.3, the central point for calculating K class of step 4.2 gainedAnd with original K center
PointIt is compared, if all the same, thens follow the steps 4.4；It otherwise, will be in the K class that be calculated
Heart pointIt is assigned to K central pointAfter being updated, return step 4.2；
Step 4.4, the central point for calculating K classIn class where each central point average value,
Obtain average value vectorIndicate the average value of i-th of class；
Step 4.5 obtains the visual dictionary L of power line using formula (1):
In formula (1), μiFor the matching threshold of i-th of class, matching threshold μiIt is multinomial for m rank Chebyshevs all in i-th of class
The average value of formula description son and i-th of classBetween difference maximum norm；
Step 5 passes through dictionary pattern matching, eliminates non-electrical line of force feature:
Step 5.1 obtains another width electric power line image on transmission line of electricity as test image, and according to step 1 to step
Rapid 3 are handled, and are obtained m rank Chebyshev polynomials description of n curve in test image, are denoted as { T(1),T(2),…,T(j),…,T(n)}；T(j)Indicate that the m rank Chebyshev polynomials of j-th strip curve in test image describe son, 1≤j≤n；
Step 5.2, initialization j=1；
Step 5.3, initialization i=1；
The m rank Chebyshev polynomials of j-th strip curve are described sub- T by step 5.4(j)With the average value of i-th of classPhase
The matching threshold μ of the mould of the difference obtained after subtracting and i-th of classiIt compares, if difference is less than or equal to matching threshold μi, then it represents that
The m rank Chebyshev polynomials of j-th strip curve describe sub- T(j)Belong to i-th of class, executes step 5.5；Otherwise, indicate that j-th strip is bent
The m rank Chebyshev polynomials of line describe sub- T(j)It is not belonging to i-th of class, executes step 5.6；
Step 5.5, judge whether j > n is true, if so, it then indicates that test image matches completion with visual dictionary L, obtains
P curve corresponding to m rank Chebyshev polynomials description after to matching is as power line；Otherwise, j+1 is assigned to j
Afterwards, return step 5.3；
Step 5.6, judge whether i > K is true, if so, then indicate that the m rank Chebyshev polynomials of j-th strip curve are retouched
State sub- T(j)It is not belonging to any one class, and deletes j-th strip curve from the m rank Chebyshev polynomials of n curve description
M rank Chebyshev polynomials describe sub- T(j)Afterwards, j+1 is assigned to j, executes step 5.3；Otherwise, it after i+1 being assigned to i, returns
Return step 5.4.
Pass through the matching of step 5, so that it may which the feature for excluding most of non-transmission lines of electricity leaves the spy of all transmission lines of electricity
Sign, achievees the purpose that transmission line faultlocating.
Claims (1)
1. a kind of transmission line of electricity extracting method based on Chebyshev polynomials description, it is characterized in that carrying out as follows:
Several width electric power line images in step 1, acquisition transmission line of electricity, and carry out the pre- place of median filtering and histogram equalization
Reason, obtains several pretreated electric power line images；Recycle thresholding method to the pretreated electric power line image
It is handled, obtains several width bianry images, remember that any one width bianry image is present image；
Step 2 detects the curve in the present image using random Hough transformation, obtains several curves, and note is appointed
Curve of anticipating is C；
Step 3 describes son using Chebyshev polynomials to curve C progress character representation, and it is multinomial to obtain m rank Chebyshev
Formula description, is denoted as TC=(a0,a1,…,am-1,b0,b1,…,bm-1), a0,a1,…,am-1Indicate the abscissa of the curve C
Function be unfolded according to Chebyshev polynomials after coefficient, b0,b1,…,bm-1Indicate the ordinate function of the curve C according to cutting
Than the coefficient after snow husband's polynomial expansion；
Step 4 utilizes the visual dictionary of machine learning method training power line:
K step 4.1, random initializtion central point Indicate i-th of central point, i=1,2 ...,
K；
Step 4.2, the m rank Chebyshev polynomials for calculating the curve C describe sub- TCTo i-th of central pointDistanceTo obtain sample point to K central point distance { d1,d2,…,di,…,dK}；From the distance { d1,
d2,…,di,…,dKIn choose minimum value and by sample point TCIt is referred in class corresponding to minimum value；Thus by all curves
It is referred in corresponding class, and obtains K class；
Step 4.3, the central point for calculating the K classAnd with original K central pointIt is compared, if all the same, thens follow the steps 4.4；Otherwise, by the center for K class being calculated
PointIt is assigned to the K central pointAfter being updated, return step
4.2；
Step 4.4, the central point for calculating the K classIn class where each central point average value,
Obtain average value vector Indicate the average value of i-th of class；
Step 4.5 obtains the visual dictionary L of power line using formula (1):
In formula (1), μiFor the matching threshold of i-th of class, matching threshold μiIt is retouched for m rank Chebyshev polynomials all in i-th of class
State the average value of son with i-th of classBetween difference maximum norm；
Step 5 passes through dictionary pattern matching, eliminates non-electrical line of force feature:
Step 5.1, obtain transmission line of electricity on another width electric power line image as test image, and according to step 1 to step 3 into
Row processing obtains m rank Chebyshev polynomials description of n curve in the test image, is denoted as { T(1),T(2),…,T(j),…,T(n)}；T(j)Indicate m rank Chebyshev polynomials description of j-th strip curve in the test image, 1≤j≤n；
Step 5.2, initialization j=1；
Step 5.3, initialization i=1；
The m rank Chebyshev polynomials of j-th strip curve are described sub- T by step 5.4(j)With the average value of i-th of classAfter subtracting each other
The matching threshold μ of the mould of the difference arrived and i-th of classiIt compares, if difference is less than or equal to matching threshold μi, then it represents that j-th strip is bent
The m rank Chebyshev polynomials of line describe sub- T(j)Belong to i-th of class, executes step 5.5；Otherwise, the m rank of j-th strip curve is indicated
Chebyshev polynomials describe sub- T(j)It is not belonging to i-th of class, executes step 5.6；
Step 5.5, judge whether j > n is true, if so, it then indicates that test image matches completion with the visual dictionary L, obtains
P curve corresponding to m rank Chebyshev polynomials description after to matching is as power line；Otherwise, j+1 is assigned to j
Afterwards, return step 5.3；
Step 5.6, judge whether i > K is true, if so, then indicate that the m rank Chebyshev polynomials of j-th strip curve describe sub- T(j)It is not belonging to any one class, and the m rank of deletion j-th strip curve is cut from the m rank Chebyshev polynomials of n curve description
Sub- T is described than snow husband's multinomial(j)Afterwards, j+1 is assigned to j, executes step 5.3；Otherwise, after i+1 being assigned to i, return step
5.4。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710568713.1A CN107392127B (en) | 2017-07-13 | 2017-07-13 | Transmission line of electricity extracting method based on Chebyshev polynomials description |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710568713.1A CN107392127B (en) | 2017-07-13 | 2017-07-13 | Transmission line of electricity extracting method based on Chebyshev polynomials description |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107392127A CN107392127A (en) | 2017-11-24 |
| CN107392127B true CN107392127B (en) | 2019-09-10 |
Family
ID=60339587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710568713.1A Active CN107392127B (en) | 2017-07-13 | 2017-07-13 | Transmission line of electricity extracting method based on Chebyshev polynomials description |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107392127B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334844B (en) * | 2018-02-06 | 2022-08-12 | 贵州电网有限责任公司 | Line automatic tracking method for power transmission line inspection |
| CN110148211B (en) * | 2019-05-15 | 2019-11-26 | 贵州电网有限责任公司 | A kind of power line three-dimensional rebuilding method based on point cloud data |
| CN111695548B (en) * | 2020-07-20 | 2022-12-13 | 内蒙古工业大学 | High-voltage line detection method based on millimeter wave radar |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110126314A (en) * | 2010-05-17 | 2011-11-23 | 성균관대학교산학협력단 | Method for extracting 3d line using stereo camera based fuzzy k-means clustering scheme |
| CN104380282A (en) * | 2012-09-04 | 2015-02-25 | Sk普兰尼特有限公司 | Clustering support system and method, and device for supporting same |
| CN104809476A (en) * | 2015-05-12 | 2015-07-29 | 西安电子科技大学 | Multi-target evolutionary fuzzy rule classification method based on decomposition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070242863A1 (en) * | 2006-04-13 | 2007-10-18 | Bernice Eland Hoppel | Methods and Apparatus for Contouring at Least One Vessel |
-
2017
- 2017-07-13 CN CN201710568713.1A patent/CN107392127B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110126314A (en) * | 2010-05-17 | 2011-11-23 | 성균관대학교산학협력단 | Method for extracting 3d line using stereo camera based fuzzy k-means clustering scheme |
| CN104380282A (en) * | 2012-09-04 | 2015-02-25 | Sk普兰尼特有限公司 | Clustering support system and method, and device for supporting same |
| CN104809476A (en) * | 2015-05-12 | 2015-07-29 | 西安电子科技大学 | Multi-target evolutionary fuzzy rule classification method based on decomposition |
Non-Patent Citations (1)
| Title |
|---|
| "Representing and Characterizing Handwritten Mathematical Symbols through Succinct Functional Approximation";B.W.Char;《International Conference on Document Analysis and Recognition (ICDAR 2007)》;20071231;第1-5页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107392127A (en) | 2017-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110189344B (en) | Method for extracting straight line segment in electric power disconnecting link image | |
| CN107257161B (en) | Transformer substation disconnecting link remote control auxiliary checking method and system based on state recognition algorithm | |
| CN102509091B (en) | Airplane tail number recognition method | |
| CN111260629A (en) | Pantograph structure abnormity detection algorithm based on image processing | |
| CN111428748A (en) | Infrared image insulator recognition and detection method based on HOG characteristics and SVM | |
| CN107392127B (en) | Transmission line of electricity extracting method based on Chebyshev polynomials description | |
| Aly et al. | Arabic sign language fingerspelling recognition from depth and intensity images | |
| Bai et al. | Scene text localization using gradient local correlation | |
| CN107833211B (en) | Infrared image-based zero value insulator automatic detection method and device | |
| CN105701835A (en) | Image edge detection method and system facing electric power facilities | |
| Rahim et al. | Hand gesture recognition based on optimal segmentation in human-computer interaction | |
| CN110751619A (en) | Insulator defect detection method | |
| CN107705256B (en) | Forward vehicle-mounted video image enhancement method based on contact network semantics | |
| Rasooli et al. | Farsi license plate detection based on element analysis and characters recognition | |
| CN115272306A (en) | Solar cell panel grid line enhancement method utilizing gradient operation | |
| Yuan et al. | Fast QR code detection based on BING and AdaBoost-SVM | |
| Bai et al. | A fast stroke-based method for text detection in video | |
| CN104751139A (en) | Fast fingerprint recognition method based on feature points of sweat glands and fingerprint images | |
| CN104063682A (en) | Pedestrian detection method based on edge grading and CENTRIST characteristic | |
| Lin et al. | A traffic sign recognition method based on deep visual feature | |
| CN103605993A (en) | Image-to-video face identification method based on distinguish analysis oriented to scenes | |
| Patel et al. | Vision Based Real-time Recognition of Hand Gestures for Indian Sign Language using Histogram of Oriented Gradients Features. | |
| CN108960241A (en) | Insulator based on statistical shape model falls to go here and there detection algorithm | |
| Xia et al. | Insulator recognition based on mathematical morphology and Bayesian segmentation | |
| Wronkowicz | Vision diagnostics of power transmission lines: approach to recognition of insulators |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |