CN112489018B - Intelligent line inspection method and line inspection method for power line - Google Patents
Intelligent line inspection method and line inspection method for power line Download PDFInfo
- Publication number
- CN112489018B CN112489018B CN202011372560.1A CN202011372560A CN112489018B CN 112489018 B CN112489018 B CN 112489018B CN 202011372560 A CN202011372560 A CN 202011372560A CN 112489018 B CN112489018 B CN 112489018B
- Authority
- CN
- China
- Prior art keywords
- power line
- image
- detected
- area
- abnormal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000007689 inspection Methods 0.000 title claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 60
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000011426 transformation method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims 1
- 238000000605 extraction Methods 0.000 abstract description 9
- 230000000694 effects Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent line patrol method and system for a power line, wherein the method comprises the following steps: making a line inspection path of the unmanned aerial vehicle photographing device, and acquiring a power line channel image by using the unmanned aerial vehicle photographing device; preprocessing the acquired power line channel image, and obtaining an image to be detected; acquiring the position of a power line in an image to be detected; detecting an abnormal region in the power line position of the image to be detected, and marking the abnormal region in the image to be detected to generate an intermediate result image; and marking an abnormal region at a corresponding position in the power line channel image, and outputting the marked power line channel image. The embodiment of the invention improves the speed of image acquisition of the power line channel by utilizing the unmanned aerial vehicle photographing device. According to the embodiment of the invention, the abnormal situation of the power line can be rapidly identified through pretreatment, power line edge extraction and abnormal region identification, so that the aim of reducing manual participation is fulfilled.
Description
Technical Field
The invention belongs to the field of power transmission, and particularly relates to an intelligent power line inspection method and system.
Background
Along with the rapid development of economy, the demand for electric power energy is more and more vigorous, and the electric power transmission system is more and more huge and has wider coverage. The transmission line is an important component of the power transmission system, and is easy to cause disconnection accidents and foreign matter adhesion accidents due to human damage, natural disasters, natural aging and the like.
Traditional transmission line's inspection is mainly accomplished by the manual work, and manual work inspection adopts the mode of climbing power line shaft tower, has very big potential safety hazard. The manual inspection is limited by the geographic environment and the physical ability of the human body, so that the inspection efficiency is low, the real-time performance is poor, and the current power inspection requirement is difficult to meet. In addition, the manual power line inspection mode is often observed through naked eyes, whether the line is faulty or not is judged through experience, faults are easy to cause, and accuracy is low. In addition, the inspection is also started by aid of unmanned aerial vehicle equipment, but the inspection is still performed by means of video monitoring and manual inspection, and the safety of personnel is improved, but the efficiency of fault detection is still low because the image is still judged directly by manpower.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide an intelligent power line inspection method and system based on image processing. The intelligent line inspection method comprises the following steps:
step S1, making a line patrol path of an unmanned aerial vehicle photographing device according to the trend of a power line, and acquiring a power line channel image by using the unmanned aerial vehicle photographing device;
S2, preprocessing the acquired power line channel image, and obtaining an image to be detected;
step S3, extracting the edge of the power line of the image to be detected to obtain the position of the power line in the image to be detected;
Step S4, detecting a high-brightness area or a low-brightness area in the power line position of the image to be detected, marking the high-brightness area or the low-brightness area as an abnormal area, and marking the abnormal area in the image to be detected to generate an intermediate result image;
And S5, marking the abnormal region at a corresponding position in the power line channel image according to the intermediate result image, and outputting the marked power line channel image.
Further, in the step S2, preprocessing the acquired power line channel image includes the following steps: graying, optical correction, image denoising.
Wherein, the step S3 includes:
Step S31, detecting the edge of the power line in the image to be detected by using a Ratio operator;
Step S32, a random Hough transformation method of gradient direction information is utilized to process the power line channel image of the detected power line edge.
Further, the step S4 includes:
Step S41, carrying out region segmentation on the power line position in the image to be detected, and obtaining N segmented areas to be detected;
step S42, counting the number of pixel points of each gray level in each segmented to-be-detected area, and generating N pieces of statistical result data according to a one-to-one correspondence;
Step S43, calculating the overall gray average value of N segmented regions to be detected by using the N statistical result data;
And S44, comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected area with the difference value larger than a preset abnormal threshold value as an abnormal area.
Further, the step of marking the abnormal area at the corresponding position in the power line channel image specifically comprises the following steps: and filling the pixel points marked as the abnormal areas in the power line channel image with red, green or blue.
Further, in step S1, a line patrol path of the unmanned aerial vehicle photographing device is formulated according to the trend of the power line, and is implemented through a GPS navigation system or a beidou navigation system.
An intelligent power line patrol system, comprising:
The unmanned aerial vehicle photographing device is used for collecting power line channel images according to a preset line patrol path, wherein the line patrol path is formulated according to the trend of the power line;
the image preprocessing unit is used for preprocessing the acquired power line channel image and obtaining an image to be detected;
the power line position acquisition unit is used for extracting the power line edge of the image to be detected so as to acquire the power line position of the power line in the image to be detected;
An intermediate result image generating unit configured to detect a high-luminance area or a low-luminance area in a power line position of the image to be detected, mark the high-luminance area or the low-luminance area as an abnormal area, and mark the abnormal area in the image to be detected to generate an intermediate result image;
And the marked image output unit marks the abnormal region at a corresponding position in the power line channel image according to the intermediate result image and outputs the marked power line channel image.
Further, the image preprocessing unit performs preprocessing on the acquired power line channel image, and specifically includes: graying, optical correction, image denoising.
Further, the power line position acquisition unit includes:
A power line edge detection subunit, which detects a power line edge in the image to be detected by using a Ratio operator;
And the power line position acquisition subunit is used for processing the power line channel image of the detected power line edge by using a random Hough conversion method of the gradient direction information so as to acquire the power line position of the power line in the image to be detected.
Further, the intermediate result image generation unit includes:
The to-be-detected region generation subunit is used for carrying out region segmentation on the power line position in the to-be-detected image and obtaining N segmented to-be-detected regions;
the gray level pixel point statistics subunit is used for counting the number of pixel points of each gray level in each segmented to-be-detected area and generating N statistical result data according to a one-to-one correspondence;
the gray average value calculation subunit is used for calculating the overall gray average value of the N segmented regions to be detected by utilizing the N statistical result data;
And the abnormal region marking subunit is used for comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected region with the difference value larger than a preset abnormal threshold value as an abnormal region.
The embodiment of the invention has the following beneficial effects: according to the embodiment of the invention, through the steps of preprocessing, power line edge extraction, abnormal region identification and the like, the situations of damage, foreign matter attachment and the like in the power line can be rapidly and accurately identified, the visual output of the detection result can be further carried out, the whole process utilizes an unmanned aerial vehicle photographing device, and an automatic navigation cruising mode is combined, so that the accuracy of operation can be effectively improved, errors caused by manual acquisition are avoided, the aim of reducing the manual participation degree is achieved, and an indicating effect can be provided for manual re-detection.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an intelligent power line inspection method according to a first embodiment of the invention;
Detailed Description
The following description of embodiments refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced.
Referring to fig. 1, an embodiment of the invention provides an intelligent power line inspection method, which includes steps S1-S5.
Step S1, a line patrol path of the unmanned aerial vehicle photographing device is formulated according to the trend of the power line, and the unmanned aerial vehicle photographing device is used for collecting the power line channel image.
Specifically, the most commonly used mode is to manually operate the unmanned aerial vehicle photographing device to perform video photographing by utilizing the unmanned aerial vehicle photographing device, but when photographing the power line, if the manual operation is adopted to photograph, although manpower can be saved to a certain extent compared with the mode of manually directly checking on site, the manual operation is difficult to keep stable operation of the unmanned aerial vehicle photographing device, the conditions of shaking, abrupt change of height or direction and the like easily occur, and further the acquired power line channel image is blurred or too small, so that the follow-up power line contour extraction is difficult to directly use. By adopting the navigation system, the cruising path of the unmanned aerial vehicle photographing device can be strictly formulated according to the actual trend of the power line, and finally the unmanned aerial vehicle photographing device can acquire the power line channel image at a fixed speed and a proper relative height along the cruising path as far as possible, so that the image quality of the power line channel is ensured.
Specifically, the line patrol path of the unmanned aerial vehicle photographing device is formulated according to the trend of the power line and is realized through a GPS navigation system or a Beidou navigation system, so that the cruising path can be effectively ensured not to deviate or the deviation probability can be reduced.
And S2, preprocessing the acquired power line channel image, and obtaining an image to be detected.
Specifically, the power line channel image is usually a color image after being collected, if the color image is directly utilized for processing, the data volume of operation is too large due to too many features, so that operations such as graying processing are needed to be performed on the power line channel image, the converted image is an image to be detected, and the image to be detected is used for operation during actual operation, so that the algorithm is simplified. In some embodiments, in order to further reduce the data processing amount, frame extraction processing is performed on the acquired power line channel image to reduce the number of pictures to be processed, and the frame extraction number should not be too large so as not to cause the power line channel image to be missing.
Preprocessing the acquired power line channel image may include the steps of: graying, optical correction, image denoising. Because there may be a problem of shake or the like during the shooting process, preliminary processing is required to be performed on the image through steps of optical correction, image denoising or the like, so as to ensure the overall display effect of the power line channel image. The graying processing can reduce the information amount in the picture, thereby reducing the difficulty of subsequent data processing.
And S3, extracting the edge of the power line of the image to be detected to obtain the position of the power line in the image to be detected.
Specifically, there are many ways to extract the edge information of the power line by using the image to be detected, and in some embodiments, the edge extraction is performed by using the Ratio operator, and other existing technologies may also be used. After the extraction of the power line edge information is completed, the power line position is marked in the image to be detected, so that the subsequent abnormal region can be identified for use.
Further, step S3 may include step S31 to step S32.
Step S31, detecting the edge of the power line in the image to be detected by using a Ratio operator;
Step S32, a random Hough transformation method of gradient direction information is utilized to process the power line channel image of the detected power line edge.
The Ratio operator can be used to detect the edge of the power line in the image to be detected. The detected edge information may be affected by a number of factors, such as: the effects of shooting height inconsistencies, the effects of power line bending, and the effects of power line and power tower positions. At this time, a random Hough transformation method using gradient direction information is needed to perform further processing to obtain a final power line position
And S4, detecting a high-brightness area or a low-brightness area in the power line position of the image to be detected, marking the high-brightness area or the low-brightness area as an abnormal area, and marking the abnormal area in the image to be detected to generate an intermediate result image.
Specifically, a brief description is given of the principle of abnormal region identification, where the power line is usually a fixed color (e.g., black), and the surface is usually smooth, if a white object is attached thereto, for example: the gray level of the bird feces will be inconsistent with the gray level of the electric power lines in other areas, and the gray level will be lower, so that we can determine whether foreign matters or breakage are attached to the electric power lines. In a specific area, it is a common technique to identify a high-luminance area and a low-luminance area, which are both understood as being abnormal, and after the abnormality occurs, the abnormal area needs to be marked in the image to be detected to generate an intermediate result image. The high luminance area and the low luminance area are divided with different criteria, and the adjustment is usually achieved by setting different thresholds. In actual engineering, before formally performing fault detection, engineering personnel can adjust the threshold value so as to achieve the optimal judging effect.
In some embodiments, step S4 includes step S41-step S44.
Step S41, carrying out region segmentation on the power line position in the image to be detected, and obtaining N segmented areas to be detected;
Step S42, counting the number of pixel points of each gray level in each segmented to-be-detected area, and generating N pieces of statistical result data according to a one-to-one correspondence;
step S43, calculating the overall gray average value of N segmented regions to be detected by using N pieces of statistical result data;
and S44, comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected area with the difference value larger than the preset abnormal threshold value as an abnormal area.
There are many methods for extracting high luminance points and low luminance points from a picture. A simpler method is used here on the basis of the image to be detected. After the power line position is acquired, the region can be subjected to independent data processing in the image to be detected, and information of other regions in the image to be detected is not considered any more. The method comprises the steps of firstly carrying out regional segmentation on the power line position in an image to be detected to obtain N segmented areas to be detected, wherein regional separation can be directly carried out along the power line, and the number of pixel points in each segmented area to be detected is ensured to be consistent as much as possible. Because the image to be detected is already a gray image, the number of pixels of each gray level in each segmented area to be detected can be counted, then the average gray value of the area of each segmented area to be detected can be calculated, the average gray value of the area to be detected can be small for the segmented area to be detected with higher brightness, and the average gray value of the area to be detected can be large for the segmented area to be detected with lower brightness. And (3) calculating the area average gray values of all the segmented areas to be detected, further calculating the overall gray average value of all the segmented areas to be detected (namely the whole power line), and comparing the area average gray values of all the segmented areas to be detected with the overall gray average value, and judging as abnormal and marking as an abnormal area once the abnormal threshold value is exceeded. In some embodiments, the anomaly threshold value is set to two to distinguish between a high luminance region and a low luminance region, respectively.
And S5, marking an abnormal region at a corresponding position in the power line channel image according to the intermediate result image, and outputting the marked power line channel image.
Specifically, the abnormal region is just marked in the intermediate result image, so that an engineer can intuitively see the abnormal region, the abnormal region marked in the intermediate result image can be directly corresponding to the power line channel image and marked in the same way, and finally the power line channel image marked with the abnormal region is output for the engineer to check.
The method comprises the following steps of: and filling pixels marked as abnormal areas in the power line channel image with red, green or blue. In order to visually check the abnormal region, the abnormal region may be marked, and the mark may be a wire frame or other special mark. Here, a manner of directly filling the pixel points with larger discrimination is adopted, and by this manner, the abnormal region can be more vividly known.
According to the intelligent power line inspection method provided by the embodiment of the invention, through the steps of preprocessing, power line edge extraction, abnormal region identification and the like, the situations of damage, foreign matter attachment and the like in the power line can be rapidly and accurately identified, the detection result can be visually output, the whole process utilizes an unmanned aerial vehicle photographing device and combines an automatic navigation cruising mode, the operation accuracy can be effectively improved, errors caused by manual acquisition are avoided, the aim of reducing the manual participation degree is achieved, and an indicating effect can be provided for manual re-inspection.
Corresponding to the first embodiment of the present invention, the second embodiment of the present invention also provides an intelligent power line patrol system, which is characterized in that the intelligent power line patrol system includes:
The unmanned aerial vehicle photographing device is used for collecting power line channel images according to a preset line patrol path, wherein the line patrol path is formulated according to the trend of the power line;
the image preprocessing unit is used for preprocessing the acquired power line channel image and obtaining an image to be detected;
the power line position acquisition unit is used for extracting the power line edge of the image to be detected so as to acquire the power line position of the power line in the image to be detected;
An intermediate result image generating unit configured to detect a high-luminance area or a low-luminance area in a power line position of the image to be detected, mark the high-luminance area or the low-luminance area as an abnormal area, and mark the abnormal area in the image to be detected to generate an intermediate result image;
And the marked image output unit marks the abnormal region at a corresponding position in the power line channel image according to the intermediate result image and outputs the marked power line channel image.
Further, the image preprocessing unit performs preprocessing on the acquired power line channel image, and specifically includes: graying, optical correction, image denoising.
Further, the power line position acquisition unit includes:
A power line edge detection subunit, which detects a power line edge in the image to be detected by using a Ratio operator;
And the power line position acquisition subunit is used for processing the power line channel image of the detected power line edge by using a random Hough conversion method of the gradient direction information so as to acquire the power line position of the power line in the image to be detected.
Further, the intermediate result image generation unit includes:
The to-be-detected region generation subunit is used for carrying out region segmentation on the power line position in the to-be-detected image and obtaining N segmented to-be-detected regions;
the gray level pixel point statistics subunit is used for counting the number of pixel points of each gray level in each segmented to-be-detected area and generating N statistical result data according to a one-to-one correspondence;
the gray average value calculation subunit is used for calculating the overall gray average value of the N segmented regions to be detected by utilizing the N statistical result data;
And the abnormal region marking subunit is used for comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected region with the difference value larger than a preset abnormal threshold value as an abnormal region.
Regarding the working principle and process of the intelligent power line inspection system in this embodiment, reference is made to the description of the first embodiment of the present invention, and no further description is given here.
As can be seen from the above description, compared with the prior art, the invention has the following beneficial effects: according to the embodiment of the invention, through the steps of preprocessing, power line edge extraction, abnormal region identification and the like, the situations of damage, foreign matter attachment and the like in the power line can be rapidly and accurately identified, the visual output of the detection result can be further carried out, the whole process utilizes an unmanned aerial vehicle photographing device, and an automatic navigation cruising mode is combined, so that the accuracy of operation can be effectively improved, errors caused by manual acquisition are avoided, the aim of reducing the manual participation degree is achieved, and an indicating effect can be provided for manual re-detection.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (8)
1. The intelligent power line inspection method is characterized by comprising the following steps of:
step S1, making a line patrol path of an unmanned aerial vehicle photographing device according to the trend of a power line, and acquiring a power line channel image by using the unmanned aerial vehicle photographing device;
S2, preprocessing the acquired power line channel image, and obtaining an image to be detected;
step S3, extracting the edge of the power line of the image to be detected to obtain the position of the power line in the image to be detected;
Step S4, detecting a high-brightness area or a low-brightness area in the power line position of the image to be detected, marking the high-brightness area or the low-brightness area as an abnormal area, and marking the abnormal area in the image to be detected to generate an intermediate result image;
step S5, marking the abnormal region at the corresponding position in the power line channel image according to the intermediate result image, and outputting the marked power line channel image;
the step S4 includes:
Step S41, carrying out region segmentation on the power line position in the image to be detected, and obtaining N segmented areas to be detected;
step S42, counting the number of pixel points of each gray level in each segmented to-be-detected area, and generating N pieces of statistical result data according to a one-to-one correspondence;
Step S43, calculating the overall gray average value of N segmented regions to be detected by using the N statistical result data;
And S44, comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected area with the difference value larger than a preset abnormal threshold value as an abnormal area.
2. The intelligent power line patrol method according to claim 1, wherein in step S2, the collected power line channel image is preprocessed, and the steps of: graying, optical correction, image denoising.
3. The intelligent power line patrol method according to claim 1, wherein said step S3 comprises:
Step S31, detecting the edge of the power line in the image to be detected by using a Ratio operator;
And step S32, processing the power line channel image with the detected power line edge by using a random Hough transformation method of the gradient direction information so as to acquire the power line position of the power line in the image to be detected.
4. The intelligent power line inspection method according to claim 1, wherein the abnormal area is marked at a corresponding position in the power line channel image, specifically comprising the following steps: and filling the pixel points marked as the abnormal areas in the power line channel image with red, green or blue.
5. The intelligent line patrol method according to claim 1, wherein in step S1, the line patrol path of the unmanned aerial vehicle photographing device is formulated according to the trend of the power line and is implemented by a GPS navigation system or a beidou navigation system.
6. An intelligent power line inspection system, comprising:
The unmanned aerial vehicle photographing device is used for collecting power line channel images according to a preset line patrol path, wherein the line patrol path is formulated according to the trend of the power line;
the image preprocessing unit is used for preprocessing the acquired power line channel image and obtaining an image to be detected;
the power line position acquisition unit is used for extracting the power line edge of the image to be detected so as to acquire the power line position of the power line in the image to be detected;
An intermediate result image generating unit configured to detect a high-luminance area or a low-luminance area in a power line position of the image to be detected, mark the high-luminance area or the low-luminance area as an abnormal area, and mark the abnormal area in the image to be detected to generate an intermediate result image;
A marker image output unit for marking the abnormal region at a corresponding position in the power line channel image according to the intermediate result image, and outputting the marked power line channel image;
The intermediate result image generation unit includes:
The to-be-detected region generation subunit is used for carrying out region segmentation on the power line position in the to-be-detected image and obtaining N segmented to-be-detected regions;
the gray level pixel point statistics subunit is used for counting the number of pixel points of each gray level in each segmented to-be-detected area and generating N statistical result data according to a one-to-one correspondence;
the gray average value calculation subunit is used for calculating the overall gray average value of the N segmented regions to be detected by utilizing the N statistical result data;
And the abnormal region marking subunit is used for comparing the N statistical results with the overall gray average value one by one, and marking the segmented to-be-detected region with the difference value larger than a preset abnormal threshold value as an abnormal region.
7. The intelligent power line patrol system according to claim 6, wherein the image preprocessing unit preprocesses the acquired power line channel image, specifically comprising: graying, optical correction, image denoising.
8. The intelligent power line patrol system of claim 6, wherein the power line position acquisition unit comprises:
A power line edge detection subunit, which detects a power line edge in the image to be detected by using a Ratio operator;
And the power line position acquisition subunit is used for processing the power line channel image of the detected power line edge by using a random Hough conversion method of the gradient direction information so as to acquire the power line position of the power line in the image to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011372560.1A CN112489018B (en) | 2020-11-30 | 2020-11-30 | Intelligent line inspection method and line inspection method for power line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011372560.1A CN112489018B (en) | 2020-11-30 | 2020-11-30 | Intelligent line inspection method and line inspection method for power line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489018A CN112489018A (en) | 2021-03-12 |
| CN112489018B true CN112489018B (en) | 2024-05-28 |
Family
ID=74937535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011372560.1A Active CN112489018B (en) | 2020-11-30 | 2020-11-30 | Intelligent line inspection method and line inspection method for power line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489018B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343841B (en) * | 2021-06-03 | 2024-06-14 | 国网北京市电力公司 | Method and device for determining abnormal condition of power tunnel |
| CN115586792B (en) * | 2022-09-30 | 2023-06-27 | 三峡大学 | Unmanned aerial vehicle power inspection system and method based on iron tower parameters |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10117415A (en) * | 1996-10-09 | 1998-05-06 | Mitsubishi Electric Corp | Automatic inspection device for overhead line |
| CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
| CN108334844A (en) * | 2018-02-06 | 2018-07-27 | 贵州电网有限责任公司 | A kind of automatic tracking method along the line of polling transmission line |
| CN109300118A (en) * | 2018-09-11 | 2019-02-01 | 东北大学 | A kind of high-voltage electric power circuit unmanned plane method for inspecting based on RGB image |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN111626104A (en) * | 2020-04-13 | 2020-09-04 | 国网上海市电力公司 | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery |
-
2020
- 2020-11-30 CN CN202011372560.1A patent/CN112489018B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10117415A (en) * | 1996-10-09 | 1998-05-06 | Mitsubishi Electric Corp | Automatic inspection device for overhead line |
| CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
| CN108334844A (en) * | 2018-02-06 | 2018-07-27 | 贵州电网有限责任公司 | A kind of automatic tracking method along the line of polling transmission line |
| CN109300118A (en) * | 2018-09-11 | 2019-02-01 | 东北大学 | A kind of high-voltage electric power circuit unmanned plane method for inspecting based on RGB image |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN111626104A (en) * | 2020-04-13 | 2020-09-04 | 国网上海市电力公司 | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489018A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108107051B (en) | Lithium battery defect detection system and method based on machine vision | |
| CN112489018B (en) | Intelligent line inspection method and line inspection method for power line | |
| US9811746B2 (en) | Method and system for detecting traffic lights | |
| CN117635565B (en) | Semiconductor surface defect detection system based on image recognition | |
| CN106296612A (en) | Hierarchical monitoring video sharpening system and method for image quality evaluation and weather condition guidance | |
| CN103702111B (en) | A kind of method detecting camera video color cast | |
| CN104483326A (en) | High-voltage wire insulator defect detection method and high-voltage wire insulator defect detection system based on deep belief network | |
| CN111080598A (en) | Bolt and nut missing detection method for coupler yoke key safety crane | |
| CN102169585A (en) | Method and device for detecting image color cast | |
| CN110493574B (en) | Security monitoring visualization system based on streaming media and AI technology | |
| CN105718964B (en) | A kind of visible detection method of power transmission line damper | |
| CN110046584B (en) | Road crack detection device and detection method based on unmanned aerial vehicle inspection | |
| CN108665417A (en) | A kind of license plate image deblurring method, apparatus and system | |
| CN105787470A (en) | Method for detecting power transmission line tower in image based on polymerization multichannel characteristic | |
| US11398054B2 (en) | Apparatus and method for detecting fog on road | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN112801947A (en) | Visual detection method for dead pixel of LED display terminal | |
| CN115620239B (en) | Point cloud and video combined power transmission line online monitoring method and system | |
| CN115936672A (en) | Smart power grid online safety operation and maintenance management method and system | |
| CN112634179B (en) | Camera shake prevention power transformation equipment image change detection method and system | |
| CN105469413A (en) | Normalized ringing weighting based no-reference comprehensive quality assessment method for fuzzy restored image | |
| CN112489017A (en) | Intelligent identification method and system for power equipment faults | |
| CN117351036A (en) | CRH5 motor train unit gearbox body crack edge detection method | |
| CN116749817A (en) | Remote control method and system for charging pile | |
| CN113822200B (en) | Automatic identification method and device for traction substation auxiliary monitoring multi-view gear switch |
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 |