CN109448011B - Wind-proof early warning method for photovoltaic power generation device - Google Patents
Wind-proof early warning method for photovoltaic power generation device Download PDFInfo
- Publication number
- CN109448011B CN109448011B CN201811227253.7A CN201811227253A CN109448011B CN 109448011 B CN109448011 B CN 109448011B CN 201811227253 A CN201811227253 A CN 201811227253A CN 109448011 B CN109448011 B CN 109448011B
- Authority
- CN
- China
- Prior art keywords
- power generation
- photovoltaic power
- generation device
- center
- mark
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a windproof early warning method for a photovoltaic power generation device, which realizes remote monitoring and early warning of the swing condition of the photovoltaic power generation device, and comprises the steps of image acquisition, image preprocessing, self-adaptive threshold value transformation, contour extraction and position identification of the photovoltaic power generation device, and finally judging whether the swing of the photovoltaic power generation device exceeds a warning value or not and whether the photovoltaic power generation device can topple over or not. The method can better analyze and early warn the swing condition of the photovoltaic power generation device, has high stability, high operation speed and high prediction precision, and can completely replace manpower to monitor the wind resistance of the photovoltaic panel support in the photovoltaic power station.
Description
Technical Field
The invention belongs to the field of solar power generation, and particularly relates to a wind-proof early warning method for a photovoltaic power generation device.
Background
Solar energy is used as a renewable energy source, and has the advantages of sustainability, cleanness, environmental protection and the like, so the solar energy is widely popularized and applied. Photovoltaic power generation is one of the main application forms for developing and utilizing solar energy resources, and is in an important strategic position in a long-term energy strategy due to the great advantages of no limitation of regional resource distribution, short construction period, high energy quality and the like. At present, many countries and regions actively develop photovoltaic industry and utilize solar energy resources to deal with climate change and environmental problems.
The solar photovoltaic power generation device is a power generation device which is exposed to outdoor sunlight to generate electric energy, and severe environments such as rainstorm, hailstone, strong wind and the like can cause loads to the photovoltaic power generation device, wherein the wind loads are system loads with the largest acting force in a large photovoltaic power station. How to effectively detect the influence of wind load to take necessary windproof measures, thereby avoid the too big destruction to photovoltaic power plant mounting system of wind load, guarantee photovoltaic power plant's normal operating is the problem that present photovoltaic power generation industry is urgently needed to solve.
The large-scale solar photovoltaic power station is mostly built in desert areas with sufficient illumination, the influence of wind and sand on the power station is more serious due to geographical reasons, a photovoltaic power station support system is not examined by the wind and sand all the time, and the situation that the photovoltaic power station collapses or components fall off when encountering strong wind is common. Therefore, how to accurately early warn and take measures in time becomes an important problem of wind load safety of the solar photovoltaic panel, and the development of a system for real-time monitoring, intelligent early warning and timely protection of wind load safety of the solar photovoltaic panel bracket is of great significance.
At present, the position of a photovoltaic power generation device is changed in advance according to weather forecast, and damage of wind load to the photovoltaic power generation device is reduced by manual patrol. The influence of wind load on a photovoltaic power generation device is reduced by using a wind-proof dust suppression net or a wind-proof wall in a domestic large photovoltaic power station, the method has a certain effect on wind prevention, but extremely high construction cost and maintenance cost are required, and a dangerous case cannot be found in the first time due to the fact that an early warning system is not provided.
Disclosure of Invention
The invention provides a wind-proof early warning method for a photovoltaic power generation device, which can realize automatic early warning.
A wind-proof early warning method for a photovoltaic power generation device comprises the following steps:
(1) acquiring an image of the photovoltaic power generation device;
(2) preprocessing an image of the photovoltaic power generation device;
(3) carrying out binarization processing on the preprocessed photovoltaic power generation device image;
(4) performing median filtering and edge detection on the obtained binary image to obtain the center of the mark of the photovoltaic power generation device;
(5) taking the center position of the photovoltaic power generation device mark in a windless state as a zero point, and solving the offset condition of the center of the photovoltaic power generation device mark;
(6) and judging whether the deviation state exceeds a set threshold value, and warning when the deviation state exceeds the set threshold value.
According to the windproof early warning method for the photovoltaic power generation device, the camera is used for obtaining the image of the photovoltaic power generation device, and the target area in the image is accurately positioned according to the special shape and color characteristics of the image. The swing amplitude of the photovoltaic power generation device is monitored in real time, early warning information is sent out once early warning conditions are triggered, and the whole system has the advantages of being fast in response time, high in prediction accuracy and the like.
The method can acquire the images of the photovoltaic power generation device and directly download the images from the existing cloud platform (or cloud end), namely, the preset camera acquires the images of the photovoltaic power generation device in real time, then the images of the photovoltaic power generation device are uploaded to the existing cloud platform, and finally the images of the photovoltaic power generation device are directly downloaded from the cloud platform.
In the step (2), the pretreatment comprises: and performing gray processing after the region of interest is extracted, or performing region of interest extraction after the gray processing. In the technical scheme, the sequence of the steps of the region-of-interest extraction and the graying processing is not strictly required, and certainly, in order to improve the processing efficiency, the region-of-interest extraction can be performed firstly, and then the extracted image is subjected to graying processing.
In the step (2), the region of interest extraction method generally comprises: and removing useless image information according to the set size, and reserving the image containing the photovoltaic power generation device mark. The size of the image size can be derived from a number of previous realizations.
Preferably, the image is processed by adopting an adaptive threshold value binarization method in the step (3) because the fixed threshold value binarization processing effect is poor aiming at the gray value change of the image caused by light change under the conditions of day and night and different weather. Specifically, in step (3), when adaptive threshold binarization is performed, the threshold value T of each pixel is setijAll within n x n range centered by this pixelAnd calculating the pixel value, and performing binarization processing according to the threshold corresponding to each pixel point.
In the invention, the photovoltaic power generation device mark can be a pattern, a figure or a structure arranged on the photovoltaic power generation device. The center may be the center or the centroid of the pattern; the center may also be the center of the end face of the structure or the center or centroid of the plane of projection, etc. The pattern or figure can be added by the person of the invention, and can also be the pattern or figure carried by the photovoltaic power generation device. The structure may be a structure separately provided on the photovoltaic power generation device in the present invention, or may be a structure of the photovoltaic power generation device itself. The graph or the pattern can be preferably a symmetrical graph or a symmetrical pattern, and a symmetrical graph or a symmetrical pattern structure is adopted, so that the subsequent image processing operation is facilitated, and the identification efficiency and the identification precision are improved.
As a further preference, the shape of the pattern or figure is rectangular, circular, oval, triangular, etc.; or the shape of the pattern or figure is approximately rectangular, circular, oval, triangular, etc. The structure has rectangular, circular, oval, triangular or approximately rectangular, circular, oval, triangular end faces or projection surfaces or cross sections and the like.
Preferably, the photovoltaic power generation device comprises a photovoltaic panel and a bracket for fixing the photovoltaic panel, the photovoltaic power generation device is marked as a shaft end face (a shaft end face of a rotating shaft) connecting the photovoltaic panel and the bracket, and the step (1) of obtaining the image of the photovoltaic power generation device in the axial direction of the shaft; namely, the optical axis of the camera can be arranged on the axis of the shaft, so that the camera can acquire images aiming at the marks of the photovoltaic power generation device; in the step (4), the center of the mark of the photovoltaic power generation device is the circle center of the end face of the shaft.
In practical operation, the rotating shaft (axial end face) of the circular photovoltaic panel on the photovoltaic power generation device can be painted with a specific color, and the image area is defined as a mark image of the photovoltaic power generation device. And performing median filtering and edge detection processing on each frame of binary image to accurately position the position of the mark.
In the step (5), the distance between the center of the mark and the zero point or the angle between the connecting line between the center of the mark and the zero point and the horizontal plane is used as the judgment basis of the deviation condition. Both of them can be used as the judgment basis, or one of them can be used as the judgment basis. Preferably, the distance between the center of the mark and the zero point is used as a basis for determining the offset state.
And (5) simultaneously calculating the included angle between the connecting line between the center of the circle of the mark and the zero point and the horizontal position, and displaying in the step (6).
The method takes the circle center position of the mark image in a static windless state as a zero point, and represents the real-time position of the photovoltaic power generation device by calculating the circle center coordinate, so as to obtain the swing offset size and direction of the photovoltaic power generation device.
And (6) when judging:
if the deviation condition of the photovoltaic power generation device does not exceed the warning value lambda or the time for exceeding the warning value lambda is insufficient in one detection period T
No alarm is given;
if in a detection period T, there is
And if the deviation condition of the photovoltaic power generation device is higher than the warning value lambda, judging that the photovoltaic power generation device is in a dangerous state at the moment, and giving an alarm.
And (5) continuously repeating the steps (1) to (5) to process the images frame by frame, and judging whether to give out an alarm or not according to the offset of the photovoltaic power generation device in each time period.
When the system is in a dangerous state, the invention still detects the deviation condition of the photovoltaic power generation device, and the system cancels the dangerous state alarm only when the deviation condition lasting for three detection periods is lower than the alarm value lambda.
The windproof early warning method for the photovoltaic power generation device realizes remote monitoring and early warning of the swing condition of the photovoltaic power generation device, comprises the steps of obtaining images of the photovoltaic power generation device, preprocessing the images, transforming self-adaptive thresholds, extracting outlines and identifying positions, and finally judges whether the swing of the photovoltaic power generation device exceeds a warning value or not and whether the photovoltaic power generation device can topple over or not.
The windproof early warning system for the photovoltaic power generation device disclosed by the invention realizes the identification, analysis and early warning of the photovoltaic power generation device sign aiming at the conditions that the photovoltaic power generation station has severe environment, the photovoltaic power generation device frequently swings and the day and night illumination changes are large, so that whether the photovoltaic power generation device is damaged by wind load or not is judged. The method has the advantages of high stability, high reaction speed, accurate early warning and the like, can greatly reduce the loss of the photovoltaic power generation device, and replaces manual inspection.
Drawings
Fig. 1 is a schematic flow diagram of a wind-proof early warning system of a photovoltaic power generation device according to the present invention.
Detailed Description
In order to more specifically describe the present invention, the following detailed description is provided for the technical solution of the present invention with reference to the accompanying drawings and the specific embodiments.
As shown in fig. 1, a wind-proof early warning system of a photovoltaic power generation device includes the following steps:
(1) device image acquisition
The early warning system acquires data through the cloud platform and acquires images of the photovoltaic power generation device shot by the front-end network camera in real time. The camera collects images of the photovoltaic power generation device in real time and transmits the images to the cloud platform.
(2) Image graying
And carrying out image preprocessing on each frame of image, extracting an interested region and carrying out image graying. According to the set size, the region of interest containing the photovoltaic power generation device mark is selected from the image, and useless image information is removed, so that the processing time is reduced in the subsequent operation, and the precision is improved. And (3) carrying out gray processing on the region of interest according to the formula (1).
f(i,j)＝0.3R(i,j)+0.59G(i,j)+0.11B(i,j) (1)
Wherein f (i, j) represents a gray image corresponding to the photovoltaic power generation device image, R (i, j), G (i, j) and B (i, j) represent three channels of the image, and (i, j) represents pixel point coordinates on the image.
(3) Adaptive threshold binarization
Threshold value T of each pixel when adaptive threshold value is binarizedijAll being different, the threshold value TijAll pixel values in the range of n × n with the pixel as the center are calculated, and binarization processing is performed according to the threshold value corresponding to each pixel point, wherein the specific calculation processes are shown in formulas (2) and (3).
Wherein g (i, j) represents an image of the photovoltaic power generation device image after adaptive threshold binarization processing, and TijThe threshold value of the pixel point is calculated by taking f (i, j) as the center, n is an odd number larger than 1, omega is a constant, the smaller the value of omega is, the more sensitive the change of the pixel value is, the more the edge information is, and the detection precision and the detection efficiency can be comprehensively considered for determination.
(4) Precise positioning of marker images
The photovoltaic power generation device generally comprises a photovoltaic panel and a bracket for fixing the photovoltaic panel, wherein the photovoltaic panel is hinged with the bracket through a rotating shaft; in the embodiment, the end face of the rotating shaft of the circular photovoltaic panel on the photovoltaic power generation device is coated with a specific color, the image area is defined as the mark of the photovoltaic power generation device, and the image of the circular end face is the mark image.
When setting up, can set up the camera of this embodiment on the center pin of above-mentioned rotation axis, the camera just is to the rotation axis terminal surface to gather the image of circular terminal surface.
After median filtering and edge detection processing are carried out on each frame of binary image, the circle center of a fitting circle of the edge profile is calculated by a least square fitting circle method, the circle center is used as the center of a mark of the photovoltaic power generation device, and the fitting circle formula is as follows:
di 2＝(Xi-x)2+(Yi-y)2 (4)
δi＝di 2-R2＝(Xi-A)2+(Yi-B)2-R2＝Xi 2+Yi 2+aXi+bYi+c (5)
wherein, firstly, suppose (X, y) is the coordinate of the center of the fitting circle, R is the radius of the fitting circle, (X)i,Yi) As coordinates of pixels on the edge profile, δiThe difference between the square of the distance from the center of the circle to a pixel point on the edge contour and the square of the radius is shown, and when the parameters a, b and c make the value of Q (a, b and c) be the minimum value, (x and y) are the real coordinates of the center of the fitting circle.
(5) Calculating the magnitude and direction of the offset
And taking the circle center position of the photovoltaic power generation device mark in a windless state as a zero point. Calculating the distance between the center coordinates and the zero point of each frame of image mark as the offset size, and calculating the included angle between the connecting line between the center of the mark and the zero point and the horizontal position as the offset direction, wherein the specific calculation mode is shown in formulas (7) and (8).
D is the offset distance of the mark circle center of the photovoltaic power generation device relative to the zero point, (x)k,yk) Marking the coordinates of the center of a circle for the current frame, (x)0,y0) Is the zero point coordinate.
θkThe included angle between the current frame offset direction and the horizontal direction is shown.
(6) Abnormal situation assessment
If the swing amplitude of the photovoltaic power generation device does not exceed the warning value lambda or the time for exceeding the warning value lambda is insufficient in one detection period T
No alarm is given.
If in a detection period T, there is
And when the swing amplitude of the photovoltaic power generation device is higher than the warning value lambda, judging that the photovoltaic power generation device is in a dangerous state at the moment, and sending an alarm.
t is the time when the swing amplitude of the photovoltaic power generation device in each period exceeds the warning value lambda, and can be a continuous time period or the sum of a plurality of dispersed time periods;
when the system is in a dangerous state, the system still detects the swing amplitude of the photovoltaic power generation device, and only when the swing amplitude lasting for three detection periods is lower than the warning value lambda, the system cancels the dangerous state.
The wobble amplitude can be determined by the offset magnitude or the offset direction, and the object of the present invention can be achieved. In this embodiment, the offset is used as a criterion for judgment.
Finally, it should be noted that: although the present invention has been described in detail by way of examples, it should be understood that various changes, substitutions, and alterations can be made without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. The wind-proof early warning method for the photovoltaic power generation device is characterized by comprising the following steps of:
(1) acquiring an image of the photovoltaic power generation device;
(2) preprocessing an image of the photovoltaic power generation device;
(3) carrying out binarization processing on the preprocessed photovoltaic power generation device image;
(4) performing median filtering and edge detection on the obtained binary image, calculating the circle center of a fitting circle of the edge profile by a least square fitting circle method, and solving the center of the mark of the photovoltaic power generation device;
(5) taking the center position of the photovoltaic power generation device mark in a windless state as a zero point, and solving the offset condition of the center of the photovoltaic power generation device mark;
(6) judging whether the deviation state exceeds a set threshold value or not, and carrying out early warning when the deviation state exceeds the set threshold value;
step (3) of performing binarization processing, determining a threshold value T for each pixelijCalculating all pixel values in the range of n x n with the pixel as the center, and then carrying out binarization processing according to the threshold value corresponding to each pixel point;
when the system is in a dangerous state, the offset condition of the photovoltaic power generation device is still detected, and only when the offset condition lasting for three detection periods is lower than a warning value lambda, the system cancels the dangerous state alarm;
the center of the photovoltaic power generation device mark is any pattern, graph or structure arranged on the photovoltaic power generation device;
in the step (5), the distance between the center of the mark and the zero point or the angle between the connecting line between the center of the mark and the zero point and the horizontal plane is used as the judgment basis of the deviation condition;
and (6) when judging:
if the deviation condition of the photovoltaic power generation device does not exceed the warning value lambda or the time for exceeding the warning value lambda is insufficient in one detection period T
No alarm is given;
if in a detection period T, there is
And if the deviation condition of the photovoltaic power generation device is higher than the warning value lambda, judging that the photovoltaic power generation device is in a dangerous state at the moment, and giving an alarm.
2. The wind-proof early warning method for the photovoltaic power generation device according to claim 1, wherein the preprocessing comprises: and performing gray processing after the region of interest is extracted, or performing region of interest extraction after the gray processing.
3. The wind-proof early warning method for the photovoltaic power generation device according to claim 1, wherein the pattern or the figure is rectangular, circular, elliptical, triangular, approximately rectangular, approximately circular, approximately elliptical or approximately triangular; the structure has a rectangular, circular, oval, triangular, approximately rectangular, approximately circular, approximately oval, approximately triangular end face or cross section.
4. The wind-proof early warning method for the photovoltaic power generation device according to claim 1, wherein the photovoltaic power generation device comprises a photovoltaic panel and a bracket for fixing the photovoltaic panel, the photovoltaic power generation device is marked as an end face of a shaft connecting the photovoltaic panel and the bracket, and the step (1) of obtaining the image of the photovoltaic power generation device in the axial direction of the shaft; in the step (4), the center of the mark of the photovoltaic power generation device is the circle center of the end face of the shaft.
5. The wind-proof early warning method for the photovoltaic power generation device according to claim 1, wherein in the step (5), an included angle between a connecting line between the center of the mark circle and the zero point and the horizontal position is simultaneously obtained and displayed in the step (6).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811227253.7A CN109448011B (en) | 2018-10-22 | 2018-10-22 | Wind-proof early warning method for photovoltaic power generation device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811227253.7A CN109448011B (en) | 2018-10-22 | 2018-10-22 | Wind-proof early warning method for photovoltaic power generation device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109448011A CN109448011A (en) | 2019-03-08 |
| CN109448011B true CN109448011B (en) | 2021-01-15 |
Family
ID=65547799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811227253.7A Active CN109448011B (en) | 2018-10-22 | 2018-10-22 | Wind-proof early warning method for photovoltaic power generation device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109448011B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657735A (en) * | 2013-11-21 | 2015-05-27 | 比亚迪股份有限公司 | Lane line detection method and system, as well as lane departure early warning method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2546641B (en) * | 2011-05-13 | 2017-12-27 | Snell Advanced Media Ltd | Video processing method and apparatus for use with a sequence of stereoscopic images |
| CN106780540B (en) * | 2016-12-08 | 2019-12-10 | 浙江科技学院 | photovoltaic power generation-oriented ground cloud picture cloud layer tracking and early warning method |
| CN107220645B (en) * | 2017-05-24 | 2021-02-26 | 河北省计量监督检测研究院 | Water meter identification method based on dynamic image processing |
| CN107742307A (en) * | 2017-10-25 | 2018-02-27 | 哈尔滨理工大学 | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method |
| CN108152670A (en) * | 2017-12-12 | 2018-06-12 | 广东电网有限责任公司清远供电局 | A kind of overhead transmission line condition monitoring system and method |
-
2018
- 2018-10-22 CN CN201811227253.7A patent/CN109448011B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657735A (en) * | 2013-11-21 | 2015-05-27 | 比亚迪股份有限公司 | Lane line detection method and system, as well as lane departure early warning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109448011A (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113744270B (en) | Unmanned aerial vehicle visual detection and identification method for crane complex steel structure surface defects | |
| CN101625723B (en) | Rapid image-recognizing method of power line profile | |
| CN102842211B (en) | Monitoring and early warning system and monitoring and early warning method for prevention of external force of transmission line based on image recognition | |
| CN106680285B (en) | Method for recognizing insulator contamination state based on infrared image assisted visible light image | |
| US9881212B2 (en) | Infrared image based early detection of oil spills in water | |
| CN103442209A (en) | Video monitoring method of electric transmission line | |
| CN102831393A (en) | Rapid image recognizing method of power tower pole outline | |
| CN110865418B (en) | Sewage illegal discharge monitoring method and device and computer readable storage medium | |
| KR101461184B1 (en) | Wether condition data extraction system using cctv image | |
| CN114240868A (en) | Unmanned aerial vehicle-based inspection analysis system and method | |
| US11605158B2 (en) | System and method for early identification and monitoring of defects in transportation infrastructure | |
| Ahmad et al. | A novel method for vegetation encroachment monitoring of transmission lines using a single 2D camera | |
| CN104077872A (en) | Anti-external force monitoring early warning method of electric transmission line based on image recognition | |
| CN110276787B (en) | Conductor galloping monitoring method based on marker image detection | |
| CN116939532B (en) | 5G-based communication tower remote monitoring system | |
| CN112802004B (en) | Portable intelligent video detection device for health of power transmission line and pole tower | |
| CN115620239B (en) | Point cloud and video combined power transmission line online monitoring method and system | |
| CN112329584A (en) | Method, system and equipment for automatically identifying foreign matters in power grid based on machine vision | |
| CN110718068A (en) | Road monitoring camera installation angle estimation method | |
| CN113963314A (en) | Rainfall monitoring method and device, computer equipment and storage medium | |
| CN109448011B (en) | Wind-proof early warning method for photovoltaic power generation device | |
| CN111307267A (en) | Conductor galloping monitoring method based on concentric circle detection | |
| CN112183467A (en) | Photovoltaic robot subsidence jamming detection method and system based on artificial intelligence | |
| CN109584217B (en) | Automatic judging method for monitoring camera lens pollution | |
| CN105512608A (en) | Method and system for determining man-made geomorphic feature change |
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 |