CN114782803A - Method for monitoring transmission line galloping based on compression sampling and image recognition - Google Patents
Method for monitoring transmission line galloping based on compression sampling and image recognition Download PDFInfo
- Publication number
- CN114782803A CN114782803A CN202210288719.4A CN202210288719A CN114782803A CN 114782803 A CN114782803 A CN 114782803A CN 202210288719 A CN202210288719 A CN 202210288719A CN 114782803 A CN114782803 A CN 114782803A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- galloping
- images
- transmission line
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000005540 biological transmission Effects 0.000 title claims abstract description 28
- 238000005070 sampling Methods 0.000 title claims abstract description 11
- 230000006835 compression Effects 0.000 title claims abstract description 5
- 238000007906 compression Methods 0.000 title claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000003384 imaging method Methods 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 238000011160 research Methods 0.000 abstract description 3
- 238000006073 displacement reaction Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012612 static experiment Methods 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to a method for monitoring transmission line galloping based on compression sampling and image recognition, which comprises the following steps: s1, acquiring image data of the power line by using a camera; s2, acquiring continuous images of the power transmission line and processing the images; s3, designing a target monitoring algorithm; s4, bringing the experimental data into an algorithm for analysis, and verifying the feasibility of the algorithm; the monitoring method and the algorithm principle are verified, and the monitoring effect is good; the reference significance is provided for the research of the power transmission line galloping monitoring method.
Description
Technical Field
The invention relates to a method for monitoring transmission line galloping based on compressive sampling and image recognition, and belongs to the field of target recognition and detection in a new generation of information technology.
Background
The image processing galloping monitoring method mainly comprises the steps of obtaining video image information by installing a camera on a power transmission line site, sending the video image information to a data processing center through a series of technical means, and analyzing images by the data processing center to obtain related information. The image processing galloping monitoring method has a large measurement range, and can intuitively realize comprehensive measurement of information such as galloping dynamic track, amplitude, frequency, order and the like of the power transmission conductor based on an image processing technology; in addition, the non-contact measurement method cannot generate electromagnetic interference or external force interference on the power transmission line.
However, the traditional dancing video monitoring system based on the image processing technology collects the dancing video and then sends the dancing video to a remote data processing terminal for processing, and the traditional dancing video monitoring system based on the image processing technology has the following main disadvantages:
1) the data volume is large: video surveillance for long periods of time can produce huge amounts of image data.
2) A deficiency in motion monitoring algorithms; the digital image data volume is large, a certain time is needed for data transmission and reception, and the processing speed of the PC end is limited, so that the low-efficiency algorithm cannot timely monitor dangers.
Therefore, the single-pixel camera is applied to the engineering field of monitoring the galloping state of the power transmission line, a novel target detection algorithm design is innovatively provided, the defect of a single motion monitoring algorithm is overcome, and the accuracy of target detection is greatly improved.
Disclosure of Invention
The invention provides a method for monitoring power transmission line galloping based on compression sampling and image recognition, which solves the problems of large data volume and insufficient motion monitoring algorithm and provides a new thought for subsequent power transmission line galloping monitoring research.
In order to solve the problems, the invention provides a method for monitoring power transmission line galloping based on compressive sampling and image recognition, which comprises the following steps of:
s1, acquiring image data of the power transmission line by using a camera;
s2, acquiring continuous images of the power transmission line and processing the images;
s3, designing a target monitoring algorithm;
s4, bringing the experimental data into an algorithm, analyzing and verifying the feasibility of the algorithm;
1. the method for acquiring the image data of the power transmission line by using the camera specifically comprises the following steps: and (3) completing the design of a waving monitoring target point, simulating the building of a power transmission line model, selecting a camera and completing the acquisition of image data.
2. The method for acquiring the continuous images of the power transmission line and processing the images specifically comprises the following steps: dividing the image data image by taking a frame as a unit, and processing the image by adopting a corrosion and expansion method.
3. The design target monitoring algorithm is specifically characterized in that the principle of the interframe difference method is as follows: if a moving object exists in the continuous images, the gray values of the pixel points in the moving area in the two adjacent frames are different, and the pixel values of the adjacent frames are almost indistinguishable if the moving object does not exist in the area. The method has the advantages of simple algorithm, good stability and insensitivity to light ray change.
4. Two adjacent frames of images are respectively set as a Kth frame, a (K +1) th frame, and x and y represent coordinate positions of pixel points in the images, so that the two frames of images can use fk(x,y),fk+1And (x, y) represents. The threshold value of the difference operation is set to be T, and the difference image is represented by G (x, y), and the following steps are included:
in the formula, M (x, y) represents a background picture pixel point set, N (x, y) represents a pixel point set of a previous frame, and T0Is the initial value of the difference.
5. And substituting experimental data into an algorithm, and carrying out error analysis, wherein the feasibility of the algorithm is verified as follows: and setting the position of the galloping monitoring point when the galloping monitoring point is static as a reference point. And changing the aerial horizontal position and the aerial vertical position of the galloping target monitoring point, multiplying the obtained pixel coordinate position by an imaging scale to obtain the galloping amplitude condition, and finally carrying out galloping error analysis.
The method is advanced and scientific, and has the following beneficial effects: the monitoring method and the algorithm principle provided by the invention are verified, so that the monitoring effect is better; the reference significance is provided for the research of the power transmission line galloping monitoring method.
Drawings
FIG. 1 is a diagram of a galloping monitoring scenario;
FIG. 2 is a schematic illustration of a static experiment;
FIG. 3-1 is a graph of dancing displacement (daytime);
FIG. 3-2 is a graph of dancing displacement (cloudy day);
3-3 are graphs of dancing displacement (evening);
fig. 3-4 are graphs of the displacement of the dance (at night).
Detailed Description
The present invention is further illustrated by the following examples.
considering the aspects of imaging quality, resolution, data output type and the like, an OV5640 module produced by the American OMNIVISION company is selected; the resolution ratio supported by the CMOS image sensor is 30-500 ten thousand, the imaging quality is good, the output image is stable, and the imaging material uses complementary metal oxide semiconductors, and belongs to CMOS type digital image cameras. The weight of the galloping monitoring target point is about 150g, the length is 8.36cm, and the radius is 7.51 cm.
As shown in fig. 1, in order to restore the real line dancing scene as much as possible, experiments are performed on the sky terraces of an office building, and the sky background, the illumination intensity and the wind speed level are closer to the real scene than the experiments performed indoors or on the flat ground.
the erosion operation is an AND operation on a 3 × 3 matrix, and the erosion can filter out image details smaller than the minimum template (3 × 3) in the image. From the display effect, the noise in the binary image is reduced after the corrosion, but a part of the image details are lost. The "dilation" operation is an or operation on a 3 × 3 matrix, which can be used to repair images with lost detail. And the 'on operation' is selected to remove salt and pepper noise. The 'open operation' refers to that the image data is firstly 'corroded' and then 'expanded', salt and pepper noise can be well inhibited, the edge information of the image is enhanced, and the accuracy of target detection is enhanced.
the threshold value of the frame difference method is reduced to 2, noise points generated by light field brightness changes can be filtered, and therefore when the galloping target point is static, the identification frame can be drawn. In order to improve the display effect, the four boundaries of the rectangular frame are respectively enlarged by 10 pixel points, so that the rectangular frame can be seen to be obviously larger than the target object in the display process. When the scale is calculated, 20 pixel values in the x and y directions need to be removed. The target point average pixel size was obtained by calculating 100 sets of data: 20.8 × 19.3 pixels, and the actual size of the dancing object point is 7.51 × 7.51cm, resulting in an imaging scale of about 0.36 × 0.39 cm/Pixel.
after obtaining the imaging scale, a static experiment is performed:
1) keeping the vertical distance between the camera and the monitoring point of the dancing object constant, and keeping the threshold value of the motion recognition constant.
2) The range of motion of the dancing target point is limited. The position of the galloping monitoring point when the galloping monitoring point is static is set as a reference point. And changing the aerial horizontal position and the aerial vertical position of the monitoring point of the waving target, and moving by 50cm each time. A total of 8 moves. The schematic diagram is shown in fig. 2.
3) And when each observation point is static, the dancing target point performs target identification, and the upper computer records the coordinate data of each position.
4) And calculating the position offset of the galloping monitoring target point according to the obtained imaging scale and the rectangular frame coordinates, and recording the position offset. Assuming that the horizontal direction is X and the vertical direction is Y, the obtained displacement data is shown in table 1.
According to the coordinate offset obtained by the static experiment, the comprehensive calculation precision of the transverse displacement is about 91.8 percent, and the comprehensive calculation precision of the longitudinal displacement is about 92.6 percent. The displacement errors in the X direction and the Y direction are all below 10%, and precision guarantee is provided for displacement calculation of a galloping simulation experiment. According to the obtained pixel coordinate position, the obtained waving amplitude value is multiplied by an imaging scale, the obtained waving amplitude value situation is shown in fig. 3, the displacement curve of the whole waving can be seen, but under different illumination conditions, the waving displacement monitoring effect is different. The effect in the daytime is optimal, the recognition rate begins to decrease along with the decrease of the brightness of the view field, and the obtained error points are the most when galloping monitoring is carried out at night. Wherein the recognition rates at different times are shown in table 1: as can be seen from table 1, the power transmission line galloping monitoring method provided by the application can realize galloping monitoring. Under the environment with better brightness, the recognition rate exceeds 90 percent; in the night environment with poor light, the recognition rate is about 70 percent.
TABLE 1 static Experimental displacement data sheet
Claims (5)
1. A method for monitoring transmission line galloping based on compression sampling and image recognition is characterized by comprising the following steps:
s1, acquiring image data of the power line by using a camera;
s2, acquiring continuous images of the power transmission line and processing the images;
s3, designing a target monitoring algorithm;
and S4, substituting the experimental data into an algorithm, analyzing and verifying the feasibility of the algorithm.
2. The method for monitoring power line galloping based on compressive sampling and image recognition as claimed in claim 1, wherein in step S1:
the method for acquiring the image data of the power transmission line by using the camera specifically comprises the following steps: and (4) completing the design of a waving monitoring target point, simulating the construction of a power transmission line model, selecting a camera and completing the acquisition of image data.
3. The method for monitoring power line galloping based on compressive sampling and image recognition as claimed in claim 1, wherein in step S2:
the method for acquiring the continuous images of the power transmission line and processing the images specifically comprises the following steps: dividing the image data image by taking a frame as a unit, and processing the image by adopting a corrosion and expansion method.
4. The method for monitoring power line galloping based on compressive sampling and image recognition as claimed in claim 1, wherein in step S3: the design target monitoring algorithm specifically comprises the following steps:
the principle of the interframe difference method is as follows: if a moving object exists in the continuous images, the gray values of the pixel points in the motion region in two adjacent frames are different, and the pixel values of the adjacent frames are almost indistinguishable if no moving object region exists;
subtracting the pixel gray values of two adjacent frames of images of the video stream, and then judging a threshold value to extract a moving part in the images;
two adjacent frames of images are respectively set as the Kth frame, (K +1) th frame, and x and y represent the coordinate positions of pixel points in the images, so that the two frames of images can use fk(x,y),fk+1(x, y) represents; the threshold value of the difference operation is set to be T, and the difference image is represented by G (x, y), and the following steps are included:
in the formula, M (x, y) represents a background picture pixel point set, (x, y) represents a pixel point set of a previous frame, and T0Is the initial value of the difference.
5. The method for monitoring power line galloping based on compressive sampling and image recognition as claimed in claim 1, wherein in step S4:
the experimental data is brought into the algorithm for error analysis, and the feasibility of the verification algorithm is specifically as follows: setting the position of the galloping monitoring point when the galloping monitoring point is static as a reference point; and changing the aerial horizontal position and the aerial vertical position of the galloping target monitoring point, multiplying the obtained pixel coordinate position by an imaging scale to obtain the galloping amplitude condition, and finally carrying out galloping error analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288719.4A CN114782803A (en) | 2022-03-22 | 2022-03-22 | Method for monitoring transmission line galloping based on compression sampling and image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210288719.4A CN114782803A (en) | 2022-03-22 | 2022-03-22 | Method for monitoring transmission line galloping based on compression sampling and image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114782803A true CN114782803A (en) | 2022-07-22 |
Family
ID=82425681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210288719.4A Pending CN114782803A (en) | 2022-03-22 | 2022-03-22 | Method for monitoring transmission line galloping based on compression sampling and image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114782803A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116046076A (en) * | 2023-03-09 | 2023-05-02 | 合肥工业大学 | Online detection system for power transmission line galloping based on machine vision technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977304A (en) * | 2010-10-26 | 2011-02-16 | 西安理工大学 | Power transmission line remote monitoring system and method based on DSP (Digital Signal Processor) video 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 |
| CN110610485A (en) * | 2019-08-26 | 2019-12-24 | 北京许继电气有限公司 | Ultra-high voltage transmission line channel hidden danger early warning method based on SSIM algorithm |
| CN113096063A (en) * | 2021-02-08 | 2021-07-09 | 智洋创新科技股份有限公司 | Transmission conductor galloping detection method based on short video |
-
2022
- 2022-03-22 CN CN202210288719.4A patent/CN114782803A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977304A (en) * | 2010-10-26 | 2011-02-16 | 西安理工大学 | Power transmission line remote monitoring system and method based on DSP (Digital Signal Processor) video 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 |
| CN110610485A (en) * | 2019-08-26 | 2019-12-24 | 北京许继电气有限公司 | Ultra-high voltage transmission line channel hidden danger early warning method based on SSIM algorithm |
| CN113096063A (en) * | 2021-02-08 | 2021-07-09 | 智洋创新科技股份有限公司 | Transmission conductor galloping detection method based on short video |
Non-Patent Citations (3)
| Title |
|---|
| 梁彦霞 等著: "《新编通信技术概论》", 华中科技大学出版社 * |
| 温喆 等著: "《基于物联网的四网融合技术研究及其应用》", 30 April 2016, 吉林人民出版社 * |
| 熊欣著: "《人脸识别技术与应用》", 31 August 2018, 黄河水利出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116046076A (en) * | 2023-03-09 | 2023-05-02 | 合肥工业大学 | Online detection system for power transmission line galloping based on machine vision technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8698913B2 (en) | Color correction device, color correction method, dynamic camera color correction device, and video search device using the same | |
| CN109872483B (en) | Intrusion alert photoelectric monitoring system and method | |
| CN106875437B (en) | RGBD three-dimensional reconstruction-oriented key frame extraction method | |
| WO2017045326A1 (en) | Photographing processing method for unmanned aerial vehicle | |
| CN103778645B (en) | Circular target real-time tracking method based on images | |
| CN113052876B (en) | Video relay tracking method and system based on deep learning | |
| CN104079800A (en) | Shaking preventing method for video image in video surveillance | |
| CN111914695B (en) | Tidal bore monitoring method based on machine vision | |
| CN104794737A (en) | Depth-information-aided particle filter tracking method | |
| CN102256061A (en) | Two-dimensional and three-dimensional hybrid video stabilizing method | |
| CN103035001A (en) | Foundation automatic cloud detection method based on superpixel division | |
| CN110634138A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| WO2023236886A1 (en) | Cloud occlusion prediction method based on dense optical flow method | |
| CN110555377A (en) | pedestrian detection and tracking method based on fisheye camera overlook shooting | |
| CN114979489A (en) | Gyroscope-based heavy equipment production scene video monitoring and image stabilizing method and system | |
| CN114782803A (en) | Method for monitoring transmission line galloping based on compression sampling and image recognition | |
| CN114973028A (en) | Aerial video image real-time change detection method and system | |
| CN102324043B (en) | Image matching method based on DCT (Discrete Cosine Transformation) through feature description operator and optimization space quantization | |
| CN101605269B (en) | Method and device for tracking dense depth images | |
| CN113936060A (en) | Crane load swing angle measurement method under complex background | |
| CN115984768A (en) | Multi-target pedestrian real-time detection positioning method based on fixed monocular camera | |
| CN116152471A (en) | Factory safety production supervision method and system based on video stream and electronic equipment | |
| CN115100245A (en) | High-altitude parabola-based tracing system and tracing method thereof | |
| CN116539001A (en) | Marine wind power tower verticality detection method and system based on unmanned aerial vehicle | |
| CN115880643A (en) | Social distance monitoring method and device based on target detection algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220722 |