CN107063462A - A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method - Google Patents
A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method Download PDFInfo
- Publication number
- CN107063462A CN107063462A CN201611244580.4A CN201611244580A CN107063462A CN 107063462 A CN107063462 A CN 107063462A CN 201611244580 A CN201611244580 A CN 201611244580A CN 107063462 A CN107063462 A CN 107063462A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- value
- optimal adaptation
- particle
- abnormal area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 37
- 230000005611 electricity Effects 0.000 title claims abstract description 34
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000002245 particle Substances 0.000 claims description 30
- 230000006978 adaptation Effects 0.000 claims description 26
- 238000001757 thermogravimetry curve Methods 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000001931 thermography Methods 0.000 abstract description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010429 evolutionary process Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
Abstract
The present invention relates to a kind of transmission line of electricity Infrared Thermography Technology field, especially a kind of transmission line of electricity infrared thermal imagery abnormal area extracting method, the present invention provides a kind of transmission line of electricity infrared thermal imagery abnormal area extracting method, using PSO CV models, abnormal area extraction is carried out to transmission line of electricity infrared thermal imagery abnormal area, noise can effectively be suppressed, and improve the definition of infrared thermal imagery, be conducive to Electrical Engineer to detect the hot stall of transmission line of electricity.
Description
Technical field
The present invention relates to a kind of transmission line of electricity Infrared Thermography Technology field, especially a kind of transmission line of electricity infrared thermal imagery is abnormal
Method for extracting region.
Background technology
The overwhelming majority of transmission line malfunction be all due to it is heating up cause, because infrared imagery technique can be by object
The infra-red radiation itself sent is presented in the form of thermal map picture, passes through the change feelings of Infrared Thermogram analytical equipment temperature
Condition, in order to judge equipment various potential safety hazards that may be present.
Infrared imagery technique can rapidly be diagnosed to be all kinds of outside overheating defects of transmission line of electricity, such as various conductive components
Connection or combine it is bad caused by overheating fault, therefore the intelligent checking system based on infrared imagery technique also obtained extensively
Using.
In power transmission line intelligent detecting system, Infrared Thermogram abnormal area extractive technique is its intelligence software module
Important technology is constituted, and is also the key link that intelligent checking system is realized, the quality directly shadow of image abnormity extracted region result
Ring the whether smooth of successive image analysis identification.So far, substantial amounts of abnormal area extraction has been proposed in domestic and foreign scholars
Method, but still none of these methods can be generally applicable to the Infrared Thermogram processing of transmission line of electricity.
The shooting distance of transmission line of electricity infrared image farther out, causes Infrared Thermogram to have low resolution, and chaff interference is more
The features such as, its abnormal area extraction difficulty is larger, and good abnormal area extracts result and can carried for follow-up equipment automatic identification
For convenience, it can not only so mitigate the input of human and material resources, while artificial interference caused by subjective factors is effectively eliminated,
Operating efficiency and quality are improved, the normal operation of power system has been ensured, therefore no matter technically or economically, research
The infrared image abnormal area of transformer, which is extracted, all has good development prospect and important practical value.
Traditional infrared image abnormity method for extracting region has the following disadvantages：First, this model can not be extracted by average
Intensity level is identical, the image that two pieces of different abnormal areas of the variance of intensity are constituted, because it is that the overall situation of image is averaged
Intensity level as distinguishable region sole criterion；Second, it is uneven that this model can not extract intensity distribution in abnormal area
Image, if any the image of strong noise, for this image, it is easily trapped into local minimum；3rd, although this model has one
Fixed resistance noise immune, but still robustly can not extract the image for having strong noise by abnormal area.
The content of the invention
In order to overcome the shortcomings of background technology, the present invention provides a kind of transmission line of electricity infrared thermal imagery abnormal area extraction side
Method, using PSO-CV models, carries out abnormal area extraction to transmission line of electricity infrared thermal imagery abnormal area, can effectively suppress to make an uproar
Sound, and the definition of infrared thermal imagery is improved, be conducive to Electrical Engineer to detect the hot stall of transmission line of electricity.
The transmission line of electricity infrared thermal imagery abnormal area extracting method of the present invention, comprises the following steps：
Step one：Input the transmission line of electricity Infrared Thermogram of collection in worksite；
Step 2：Corresponding PSO-CV models are calculated, the following steps are specifically included：
1st, the scope curve local average gray value of abnormal area is calculated；
2nd, level set function of future generation is calculated：Specifically include following steps：
(1) level set function weight coefficient to be optimized is inputted, particle swarm optimization algorithm is used as
Input parameter；
(2) initial population is constituted, and by initialization of population, randomly generates the initial velocity of each particle；
(3) fitness value of each particle in initial population is calculated, to extract the average gray value in region and remaining area
Ratio is fitness value；Update the optimal adaptation angle value and global optimal adaptation angle value of each particle；
(4) position coordinates and speed of particle are recalculated；
(5) judge whether to meet end condition：Good fitness value enough is produced, that is, extracts putting down for region and remaining area
Whether equal gray value ratio is more than 1000 or reaches a default maximum algebraically；It is to meet end condition, into (6) step,
It is no, then reenter (4) step；
(6) weight coefficient for the level set function that output is optimized；
(7) level set function is updated；
3rd, judge whether to meet convergence end condition：By iterative search, whether judgment curves local average gray value ratio
Convergence end condition is reached, is, into step 3；It is no, reenter above-mentioned 1st stepping and enter a new circulation；
Step 3：Export the abnormal area of the transmission line of electricity infrared thermal imagery extracted.
It is used as preferred scheme：
In the step 2, optimal adaptation angle value and global optimal adaptation angle value renewal detailed process are：To each particle,
The optimal adaptation angle value that current fitness value is lived through with the present age is compared, if being better than the latter, with current fitness value
As optimal adaptation angle value, i.e., the desired positions lived through using current location as particle, otherwise, optimal adaptation angle value is not
Become；The fitness value of the population desired positions obtained during this is circulated is compared with global optimal adaptation angle value, if being better than the latter,
The size of global optimal adaptation angle value is then recorded again, and otherwise global optimal adaptation angle value is constant.
In the step 2, convergence end condition is：Curve local average gray value ratio >=500, or reach greatest iteration
Number of times.
Transmission line of electricity infrared thermal imagery abnormal area extracting method of the present invention, is realized, Neng Gougen using PSO-CV models
According to transmission line of electricity infrared thermal imagery own characteristic, the weight of each several part is constantly adjusted, and then driving curve develops, and can extract exception
Field strength image pockety, improves the extraction accuracy of model.
Brief description of the drawings
Fig. 1 is flow chart of the invention.
Certain the original transmission line of electricity Infrared Thermogram inputted in Fig. 2 embodiment of the present invention.
Transmission line of electricity Infrared Thermogram in Fig. 3 embodiment of the present invention in iterative process.
Fig. 4 is the transmission line of electricity infrared thermal imagery abnormal area figure that finally extracts in the embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those skilled in the art are not having
There is the every other embodiment made and obtained under the premise of creative work, belong to the scope of protection of the invention.
The transmission line of electricity infrared thermal imagery abnormal area extracting method of the embodiment of the present invention, comprises the following steps：
Step one：Input certain the original power transmission line inputted in the transmission line of electricity Infrared Thermogram of collection in worksite, the present embodiment
Road Infrared Thermogram is as shown in Figure 1.
Step 2：Corresponding PSO-CV models are calculated, the following steps are specifically included：
1st, the scope curve local average gray value of abnormal area is calculated.
Certain original transmission line of electricity Infrared Thermogram of input is assumed to be to be made up of two homogeneous regions (target and background)
, therefore can be approached by bianry image.Specifically, it is to realize that abnormal area is extracted by minimization energy functional,
It is expressed as with Level Set Method：
Wherein, I (x, y) is to treat the image that abnormal area is extracted；μ,λ1,λ2It is weight coefficient, and μ >=0, λ1、λ2＞ 0；c1
And c2Average gray value of the image in region out (C) and in (C) is respectively defined as, wherein out (C) and in (C) are represented respectively
The outwardly and inwardly region of curve, C is evolution curve；φ is level set function；Ω is transmission line of electricity infrared thermal imagery region；H
(φ) is Heaviside functions, that is, works as φ<When 0, H (φ)=0；Work as φ>When 0, H (φ)=1；As φ=0, H (φ)=
0.5；δ (φ) is Dirac functions, i.e., in the point in addition to φ=0, functional value δ (φ) is equal to zero, and it is entirely being defined
Integration on domain is equal to 1.
Using variation principle and steepest descent method, corresponding EVOLUTION EQUATION is obtained, is shown below：
In addition, average gray value c1And c2With formula is expressed as below：
c1And c2It is the arithmetic average of image gray value in out (C) and in (C), i.e. curve local average gray scale respectively
Value.
2nd, level set function of future generation is calculated.
Substantially step is：By above-mentioned weight coefficient μ, λ1,λ2By particle group optimizing, it can obtain next by iteration
For level set functionThe present embodiment sets maximum iterations to be Tmax_cvFor 250 generations.Detailed process is as follows：
(1) level set function weight coefficient to be optimized is inputted
By weight coefficient μ, λ1, λ2Input, is used as the input parameter of particle swarm optimization algorithm.
(2) initialization of population
Initialization, sets aceleration pulse C1And C2, the present embodiment aceleration pulse C1And C2It is respectively set to 0.3 and 0.7.Most
Big iterations is Tmax_pso, the present embodiment maximum iteration Tmax_pso500 are set to, current iteration number of times is represented with t,
The present embodiment sets t=1, in the space S of definitionnIn randomly generate m particle x1, x2..., xm, it is 3, i.e. x to set m1=μ, x2
=λ1, x3=λ2, composition initial population x (t)；Randomly generate each particle initial velocityConstitute speed displacement matrix v
(t)。
(3) calculate the fitness value of each particle in initial population, update each particle contemporary optimal adaptation angle value and
Global optimal adaptation angle value
Calculate each individual fitness value in colony.Particle cluster algorithm typically not need other in search evolutionary process
External information, only evaluates the quality of individual or solution with valuation functions value, and is used as the foundation of later particle group operation.Assess letter
Numerical value is also known as fitness value (fitnessvalue), the average gray value ratio of the invention to extract region and remaining area
For fitness value.
To each particle, contemporary optimal adaptation angle value PiRepresent, global optimal adaptation angle value PgRepresent, will currently fit
The optimal adaptation angle value for answering angle value to be lived through with the present age is compared, if being better than the latter, P is used as using current fitness valuei, i.e.,
The desired positions lived through using current location as particle, otherwise, PiIt is constant.The best position of population obtained during this is circulated
The fitness value and P putgCompare, if being better than the latter, P is recorded againgSize, otherwise PgIt is constant.
(4) position coordinates and speed of more new particle
Recalculate speed and the position of each particle respectively using equation (5) and (6).
vi(t+1)=ω vi(t)+C1r1(pi(t)-xi(t))+C2r2(pg(t)-xi(t)) (5)
xi(t+1)=xi(t)+vi(t+1) (6)
Wherein i=1,2,3 ... m, t=1,2 ... Tmax_psoRepresent the current iterations of particle, r1,r2It is to be uniformly distributed
Random number in interval [0,1], primarily to allowing particle to fly to particle desired positions itself with equiprobable acceleration
With the global best position of particle, parameter ω is referred to as inertia weight, to play balance ability of searching optimum and local search ability
Effect, the present embodiment is set to 0.5.
(5) judge whether to meet end condition
Global optimal adaptation angle value good enough is produced, that is, extracts region and the average gray value ratio of remaining area is more than
1000 or reach a default maximum algebraically Tmax_pso, i.e. 500 generations, at this moment, end condition is met, into (6) step, otherwise weighed
It is new to enter (4) step.
(6) weight coefficient of the level set function of output optimization
Searched for by n1 generations, obtained optimization weight coefficient is μ (n1), λ1(n1), λ2(n1)。
(7) renewal of level set function
The renewal of Level Set Method is expressed as：
3rd, judge whether to reach convergence end condition
Searched for by n2 generations, curve local average gray value ratio, i.e. c2(n2)/c1>=500, or n2 reaches maximum (n2)
Iterations, Tmax_cv=250 generations, then convergence end condition is reached, otherwise, reenter above-mentioned 1st stepping and enter one and new follow
Ring, is as shown in Figure 3 the transmission line of electricity Infrared Thermogram in iterative process in the present embodiment.
Step 3：The abnormal area of the transmission line of electricity infrared thermal imagery extracted is exported, as shown in Figure 4.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Ability
The those of ordinary skill in domain should be understood：It can still modify to the technical scheme described in above-described embodiment, or
Equivalent substitution is carried out to which part technical characteristic；And these modifications or replacement, take off the essence of appropriate technical solution
From the spirit and scope of various embodiments of the present invention technical scheme.
Claims (3)
1. a kind of transmission line of electricity infrared thermal imagery abnormal area extracting method, it is characterised in that：Comprise the following steps：
Step one：Input the transmission line of electricity Infrared Thermogram of collection in worksite；
Step 2：Corresponding PSO-CV models are calculated, the following steps are specifically included：
1) the scope curve local average gray value of abnormal area, is calculated；
2) level set function of future generation, is calculated：Specifically include following steps：
（1）Input level set function weight coefficient to be optimized, is used as the input parameter of particle swarm optimization algorithm；
（2）Initial population is constituted, and by initialization of population, randomly generates the initial velocity of each particle；
（3）The fitness value of each particle in initial population is calculated, to extract the average gray value ratio in region and remaining area
For fitness value；Update the optimal adaptation angle value and global optimal adaptation angle value of each particle；
（4）Recalculate the position coordinates and speed of particle；
（5）Judge whether to meet end condition：Fitness value good enough is produced, that is, extracts the average ash of region and remaining area
Whether angle value ratio is more than 1000 or reaches a default maximum algebraically；It is to meet end condition, into（6）Step, it is no, then
Reenter（4）Step；
（6）Export the weight coefficient of the level set function optimized；
（7）Level set function is updated；
3), judge whether to meet convergence end condition：By iterative search, whether judgment curves local average gray value than reaches
End condition is restrained, is, into step 3；It is no, reenter above-mentioned 1st stepping and enter a new circulation；
Step 3：Export the abnormal area of the transmission line of electricity infrared thermal imagery extracted.
2. a kind of transmission line of electricity infrared thermal imagery abnormal area extracting method as claimed in claim 1, it is characterised in that：The step
Optimal adaptation angle value and global optimal adaptation angle value renewal detailed process are in rapid two：To each particle, by current fitness value
The optimal adaptation angle value lived through with the present age is compared, if being better than the latter, optimal adaptation degree is used as using current fitness value
Value, i.e., the desired positions lived through using current location as particle, otherwise, optimal adaptation angle value are constant；During this is circulated
The fitness value of obtained population desired positions is compared with global optimal adaptation angle value, if being better than the latter, records global again
The size of optimal adaptation angle value, otherwise global optimal adaptation angle value is constant.
3. a kind of transmission line of electricity infrared thermal imagery abnormal area extracting method as claimed in claim 1, it is characterised in that：The step
End condition is restrained in rapid two is：Curve local average gray value ratio >=500, or reach maximum iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244580.4A CN107063462B (en) | 2016-12-29 | 2016-12-29 | A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244580.4A CN107063462B (en) | 2016-12-29 | 2016-12-29 | A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107063462A true CN107063462A (en) | 2017-08-18 |
| CN107063462B CN107063462B (en) | 2019-11-26 |
Family
ID=59624548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611244580.4A Active CN107063462B (en) | 2016-12-29 | 2016-12-29 | A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107063462B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110715736A (en) * | 2019-07-19 | 2020-01-21 | 广东电网有限责任公司 | Cable terminal abnormal heating defect grading method |
| CN114240913A (en) * | 2021-12-21 | 2022-03-25 | 歌尔股份有限公司 | Semiconductor abnormality analysis method, semiconductor abnormality analysis device, terminal device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195591B1 (en) * | 2004-08-14 | 2012-06-05 | Hrl Laboratories, Llc | Cognitive signal processing system |
| CN103678649A (en) * | 2013-12-20 | 2014-03-26 | 上海电机学院 | Traffic path searching system and method based on cloud self-adaptation particle swarm optimization |
| CN104809722A (en) * | 2015-04-13 | 2015-07-29 | 国家电网公司 | Electrical device fault diagnosis method based on infrared thermography |
| CN105844637A (en) * | 2016-03-23 | 2016-08-10 | 西安电子科技大学 | Method for detecting SAR image changes based on non-local CV model |
-
2016
- 2016-12-29 CN CN201611244580.4A patent/CN107063462B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195591B1 (en) * | 2004-08-14 | 2012-06-05 | Hrl Laboratories, Llc | Cognitive signal processing system |
| CN103678649A (en) * | 2013-12-20 | 2014-03-26 | 上海电机学院 | Traffic path searching system and method based on cloud self-adaptation particle swarm optimization |
| CN104809722A (en) * | 2015-04-13 | 2015-07-29 | 国家电网公司 | Electrical device fault diagnosis method based on infrared thermography |
| CN105844637A (en) * | 2016-03-23 | 2016-08-10 | 西安电子科技大学 | Method for detecting SAR image changes based on non-local CV model |
Non-Patent Citations (1)
| Title |
|---|
| JIANGMING KAN等: "《Level set method in standing tree image segmentation based on particle swarm optimization》", 《PROC.SPIE6786，MIPPR2007，AUTOMATIC TARGET RECOGNITION AND IMAGE ANALYSIS，AND MULTISPECTRAL IMAGE ACQUISITION》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110715736A (en) * | 2019-07-19 | 2020-01-21 | 广东电网有限责任公司 | Cable terminal abnormal heating defect grading method |
| CN110715736B (en) * | 2019-07-19 | 2020-12-29 | 广东电网有限责任公司 | Cable terminal abnormal heating defect grading method |
| CN114240913A (en) * | 2021-12-21 | 2022-03-25 | 歌尔股份有限公司 | Semiconductor abnormality analysis method, semiconductor abnormality analysis device, terminal device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107063462B (en) | 2019-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11581130B2 (en) | Internal thermal fault diagnosis method of oil-immersed transformer based on deep convolutional neural network and image segmentation | |
| CN107292882B (en) | One kind being based on the adaptive electrical equipment malfunction detection method of Meanshift | |
| CN104809722B (en) | A kind of fault diagnosis method based on infrared thermal imagery | |
| CN104601109B (en) | A kind of photovoltaic hot spot effect detection method of electrograph model | |
| CN107655159A (en) | A kind of air conditioner energy saving control method and system based on crowd density sensor model | |
| CN107767374A (en) | A kind of GIS disc insulators inner conductor hot-spot intelligent diagnosing method | |
| CN107168292B (en) | Submarine navigation device circuit failure diagnosis method based on ELM algorithm | |
| CN107103609B (en) | Niblack power equipment Infrared Image Segmentation based on particle group optimizing | |
| CN107063462A (en) | A kind of transmission line of electricity infrared thermal imagery abnormal area extracting method | |
| CN105978487B (en) | Photovoltaic module method for diagnosing faults based on internal equivalent parameters | |
| CN114972312A (en) | Improved insulator defect detection method based on YOLOv4-Tiny | |
| CN107153889A (en) | Water quality sampling cruise ship path planning optimal method | |
| CN113919661A (en) | Multi-microgrid energy coordination control method based on carbon ecology | |
| CN116720854A (en) | Equipment coordination control method and system based on intelligent patrol | |
| Tiancheng et al. | Infrared image segmentation method of current transformer based on DeepLabv3+ network | |
| CN110378407A (en) | Power equipment image-recognizing method and device based on parametric texture and neural network | |
| Hu et al. | A detecting algorithm for occlusion on the surface of photovoltaic modules based on improved YOLOv5 | |
| CN116046796A (en) | Photovoltaic module hot spot detection method and system based on unmanned aerial vehicle | |
| Jiang et al. | Transmission line modeling based on 3D laser scanning point cloud | |
| CN107016410A (en) | Power information acquisition system method for diagnosing faults and trouble-shooter | |
| Wang et al. | Substation Equipment Defect Detection based on Temporal-spatial Similarity Calculation | |
| CN113160236A (en) | Image identification method for shadow shielding of photovoltaic cell | |
| KR102549809B1 (en) | Fire detection system and method based on vision | |
| CN110417350A (en) | A kind of method for diagnosing faults of photovoltaic array | |
| CN114237226B (en) | Navigation escaping method under complex environment area coverage of group robot |
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 |