CN112115985A - Multi-information cascade clustering power transmission line detection method - Google Patents
Multi-information cascade clustering power transmission line detection method Download PDFInfo
- Publication number
- CN112115985A CN112115985A CN202010893883.9A CN202010893883A CN112115985A CN 112115985 A CN112115985 A CN 112115985A CN 202010893883 A CN202010893883 A CN 202010893883A CN 112115985 A CN112115985 A CN 112115985A
- Authority
- CN
- China
- Prior art keywords
- image
- power transmission
- transmission line
- straight lines
- information
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 230000001186 cumulative effect Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a multi-information cascade clustering power transmission line detection method, which comprises the following steps: (1) acquiring a power line image, and performing gray level transformation on the image; (2) carrying out image preprocessing on the image after gray level transformation by using an edge enhancement algorithm; (3) performing cumulative probability Hough transform on the enhanced image, and extracting candidate straight lines in the image; (4) performing cascade clustering analysis on the linear information according to the length, the angle and the position information of the linear; (5) calculating the distance between all straight lines according to a straight line distance formula, and removing repeated straight lines; (6) and predicting the trend of the power transmission line by the finally obtained straight line according to the angle position information obtained by calculation, and marking the power transmission line by using a rectangular frame. The method can effectively eliminate the interference line which is caused by the complex background and is not matched with the characteristics of the power transmission line, and finally obtains all straight lines corresponding to the edge of the power transmission line, and has higher accuracy rate and stronger robustness, and better performance under the complex background.
Description
Technical Field
The invention belongs to the field of digital image processing, and particularly relates to a multi-information cascade clustering power transmission line detection method.
Background
The transmission line is generally assumed to be in a field with a complex and variable environment, and is exposed to the outdoor environment for a long time, so that the transmission line is fully tested in severe weather such as high temperature, heavy snow and the like, and further the transmission efficiency is reduced. In order to ensure that power transmission can be stably carried out, regular inspection of the power transmission line is particularly necessary. The traditional manual inspection mode has low efficiency, high cost and large danger coefficient; compared with the prior art, the unmanned aerial vehicle inspection system has the advantages of being high in maneuverability, free of terrain limitation, convenient to operate and the like. Patrol and examine transmission line through using unmanned aerial vehicle and can improve and patrol and examine efficiency, reduce cost avoids the risk.
In electric power patrols and examines, unmanned aerial vehicle often carries on weight lighter, can obtain the camera of abundant environmental information. And acquiring aerial images through a camera, detecting the power transmission line, and preparing for further analyzing the power transmission line fault subsequently. Therefore, it is important to accurately detect the relative position of the power transmission line in the aerial image.
The application number CN201710532067.3 discloses a method for detecting power transmission lines based on aerial images, which mainly uses a Hessian matrix to enhance the aerial images, then blocks the images according to the distribution characteristics of the power transmission lines in the aerial images, applies a Hough line detection algorithm to the power transmission line areas in the aerial images, and finally screens wrong power transmission lines according to line spacing and the slope of the power transmission lines. The method can accurately detect the power transmission line with parallel characteristics in the image. In practical cases, however, the power lines are likely to have no parallel features in the image due to camera view, which affects the robustness of the method.
The power transmission line detection method based on CBS straight line segment detection with the application number of CN201910492848.3 mainly comprises the steps of segmenting an aerial image of an unmanned aerial vehicle by using a direction controllable filter, further detecting the straight line segment of the segmented image by using a CBS straight line detection method, and finally linking the detected straight line segment according to the lattice tower principle. The method does not carry out condition constraint on the power transmission line aerial image, reduces the complexity of the algorithm, but cannot carry out power transmission line detection under a complex background.
The method for detecting the power transmission line under the complex background based on the image processing is disclosed in application number CN201910566009.1, edge detection is mainly carried out on an aerial image by using a Canny operator, then a region growing method is adopted to remove small connected regions, then probability Hough transformation is used for carrying out straight line detection, and finally correct straight line segments are screened. According to the method, the influence of a complex background on the algorithm is reduced by adopting connected region analysis, but the double-edge characteristics of the Canny operator influence the final mark of the transmission line and increase the algorithm complexity.
Therefore, although many studies are made in the field of power line detection at home and abroad, most methods cannot accurately detect a power line while coping with complex background interference.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a multi-information cascade clustering power transmission line detection method which has the advantages that interference lines which are caused by a complex background and are not matched with the characteristics of a power transmission line can be effectively eliminated, all straight lines corresponding to the edge of the power transmission line are finally obtained, the method has higher accuracy and stronger robustness, and better performance is realized under the complex background.
The technical scheme is as follows: the invention discloses a multi-information cascade clustering power transmission line detection method, which comprises the following steps:
(1) acquiring a power line image, and performing gray level transformation on the image;
(2) carrying out image preprocessing on the image after gray level transformation by using an edge enhancement algorithm;
(3) performing cumulative probability Hough transform on the enhanced image, and extracting candidate straight lines in the image;
(4) performing cascade clustering analysis on the linear information according to the length, the angle and the position information of the linear;
(5) calculating the distance between all straight lines according to a straight line distance formula, and removing repeated straight lines;
(6) and predicting the trend of the power transmission line by the finally obtained straight line according to the angle position information obtained by calculation, and marking the power transmission line by using a rectangular frame.
In the step (1), the acquiring of the power line image and the gray level conversion of the image are specifically as follows: the camera is installed at the top of the head of the unmanned aerial vehicle, the unmanned aerial vehicle captures images through the camera in the flying process, and the captured images are transmitted to the processor for graying operation.
In the step (2), an edge enhancement algorithm based on a Hessian matrix is used for the image after the gray level transformation, and edge features belonging to strong edges in the image are extracted, so that the edge of the power transmission line is enhanced.
The calculation formula of the Hessian matrix is as follows:
where f is a function f of the image with respect to coordinates (x, y)xx，fxy，fyx，fyyRespectively representing the second partial derivatives of the function f to x, y and the mixture thereof; the Hessian matrix eigenvalue and eigenvector reflect the intensity and direction of the image gray scale curvature change.
In the step (3), performing cumulative probability hough transform on the enhanced image to extract candidate straight lines in the image specifically includes the following steps:
(3.1) in a specified range, mapping the edge pixel point information subjected to image enhancement to a Hough space;
(3.2) voting is carried out on each edge pixel point mapped to the Hough space;
and (3.3) accumulating a part of suspected points in the plane in the range, wherein the set of points exceeding the set threshold represents a straight line.
In the step (4), the cascade clustering analysis of the linear information specifically includes the following steps:
(4.1) carrying out secondary classification on the length, the angle and the position information of the straight line by using a clustering algorithm;
(4.2) marking the positive class in the straight line according to the ticket number of the straight line in the step (3);
and (4.3) carrying out hard cascade analysis on the result, carrying out intersection operation on the obtained positive classes, and marking the straight lines as power transmission lines when all the straight lines are divided into the positive classes in the 3 types of information.
In the step (5), the distance between all the straight lines is calculated according to a straight line distance formula, and repeated straight lines are removed, and the method specifically comprises the following steps:
(5.1) loading a power line image and linear parameters;
(5.2) estimating the distance from the first straight line to other straight lines;
(5.3) screening all straight lines with the distances smaller than a threshold value, selecting the longest straight line, reserving the longest straight line, and deleting other straight lines;
(5.4) estimating the distance between the second straight line and other straight lines;
(5.5) repeating the step (5.3) and the step (5.4) until the last straight line is calculated.
The distance estimation formula is:
wherein A, B, C is a parameter of a linear general formula in a two-dimensional rectangular coordinate system, wherein (x)i,yi) Is any point of one straight line, n is the number of the points,
to estimate the resulting distance. By setting the threshold value D when
The duplicate detection problem is considered to exist.
Has the advantages that: compared with the prior art, the invention has the following beneficial effects: (1) the influence of a complex background on the detection effect of the power transmission line is effectively reduced by fusing multiple features of the power transmission line in the aerial photography image; (2) the constraint of the algorithm on the power transmission line characteristics in the aerial images is reduced, and the robustness of the algorithm is enhanced; (3) the adopted algorithm has less constraint on aerial images, has stronger robustness and accuracy, is better suitable for practical conditions and is beneficial to engineering realization.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is an original drawing of an aerial photography power line according to the present invention;
FIG. 3 is a diagram of the image enhancement effect of the aerial image based on Hessian matrix according to the present invention;
FIG. 4 is a diagram illustrating the effect of cumulative probability Hough transform line detection in the present invention;
FIG. 5 is a diagram of the results of a multi-information cascade clustering analysis in the present invention;
FIG. 6 is a graph showing the clustering effect of linear length information and linear spatial position information, respectively, in the present invention;
FIG. 7 is a diagram illustrating the effect of cascading clustering linear length, angle and position information in the present invention;
FIG. 8 is a diagram showing the detection results of the power transmission line according to the present invention;
fig. 9 is a diagram illustrating the power line detection effect in other scenarios according to the present invention.
Detailed Description
The invention is described in further detail below with reference to specific embodiments and the attached drawings.
In consideration of the problem that a large number of pseudo straight lines can be encountered when the power transmission line detection is carried out under a complex background, the method carries out cascade clustering analysis on the straight lines by combining the length, the angle and the position information of the power transmission line in the aerial image, and improves the robustness and the accuracy of a power transmission line detection algorithm.
As shown in fig. 1, the method for detecting a multi-information cascade clustering power transmission line of the present invention includes the following steps:
(1) acquiring a power line image, and performing gray level transformation on the image; specifically, a camera is installed on the top of the nose of the unmanned aerial vehicle, the unmanned aerial vehicle captures images through the camera during the flight process, the captured images are transmitted to a processor for graying operation, the obtained original image is shown in figure 2,
(2) in order to facilitate the edge detection of the power transmission line in the image, the aerial image needs to be preprocessed. Since the RGB image includes a large number of redundant color features, it is necessary to perform a graying process on the input image, thereby reducing the data amount of the entire image. The straight line obtained after the image is grayed is not obvious, so the edge of the power line of the image needs to be enhanced. The straight line information corresponding to the power transmission line belongs to the strong edge in the image, and the characteristic belonging to the strong edge is extracted by adopting an image enhancement algorithm based on a Hessian matrix. The two-dimensional Hessian matrix is represented as:
where f is a function f of the image with respect to coordinates (x, y)xx，fxy，fyx，fyyRespectively representing the second partial derivatives of the function f to x, y and the mixture thereof; the Hessian matrix eigenvalue and eigenvector reflect the intensity and direction of the image gray scale curvature change. By calculating the Hessian matrix, the linear structure is enhanced according to the anisotropy of the linear structure in the image, as shown in fig. 3.
(3) Performing cumulative probability Hough transform on the enhanced image, and extracting candidate straight lines in the image, wherein the method specifically comprises the following steps:
(3.1) in a specified range, mapping the edge pixel point information subjected to image enhancement to a Hough space;
(3.2) voting is carried out on each edge pixel point mapped to the Hough space;
(3.3) a part of suspected points in the plane in the accumulation range and a set of points exceeding a set threshold represent a straight line, so that the calculation amount is reduced, and the calculation time is shortened.
(4) Performing cascade clustering analysis on the linear information according to the length, the angle and the position information of the linear; as shown in fig. 4, according to the principle of cumulative hough transform, when the peak of the intersection of line segments in hough space reaches a threshold, the system automatically determines the edge as a straight line. But which do not belong to the edges of the transmission line, will generate spurious peaks. These false peaks may result from dense foliage, or the edges of the house trunk in the background. Performing cascade clustering analysis on the linear information, and specifically comprising the following steps:
(4.1) carrying out secondary classification on the length, the angle and the position information of the straight line by using a clustering algorithm;
(4.2) marking the positive class in the straight line according to the ticket number of the straight line in the step (3);
and (4.3) carrying out hard cascade analysis on the result, carrying out intersection operation on the obtained positive classes, and marking the straight lines as power transmission lines when all the straight lines are divided into the positive classes in the 3 types of information.
The length information and the spatial position information of the straight line in the image are respectively subjected to clustering analysis, and as shown in fig. 6, negative classes cannot be effectively screened. Therefore, after all the information is subjected to cascade clustering analysis, the result shown in fig. 5 is obtained, and the black dots in the graph are positive classes judged by the algorithm. The analysis result is displayed on the original image, and the effect of fig. 7 can be obtained. It can be seen that the power line in the figure is detected as a best effort while there is no disturbing line present, but contains the effect of duplicate detection.
(5) Calculating the distance between all straight lines according to a straight line distance formula, and removing repeated straight lines; the method specifically comprises the following steps:
(5.1) loading a power line image and linear parameters;
(5.2) estimating the distance from the first straight line to other straight lines; the distance estimation formula is:
wherein A, B, C is a parameter of a linear general formula in a two-dimensional rectangular coordinate system, wherein (x)i,yi) Is any point of one straight line, n is the number of the points,
to estimate the resulting distance. By setting the threshold value D when
The duplicate detection problem is considered to exist.
(5.3) screening all straight lines with the distances smaller than a threshold value, selecting the longest straight line, reserving the longest straight line, and deleting other straight lines;
(5.4) estimating the distance between the second straight line and other straight lines;
(5.5) repeating the step (5.3) and the step (5.4) until the last straight line is calculated;
(6) and predicting the trend of the transmission line by using the finally obtained straight line according to the calculated angle position information, and marking the transmission line by using a rectangular frame, wherein the result is shown in figure 8, and all the transmission lines are successfully marked.
The method enhances the strong edge characteristics belonging to the edge of the power transmission line through the Hessian matrix, detects straight lines through cumulative probability Hough transformation, and then enhances the robustness of the algorithm through the length, angle and position information cascade clustering analysis of the straight lines in the image. And finally, obtaining a result graph with higher accuracy through repeated line segment screening work. To demonstrate the applicability of the present invention, method validation was performed in other contexts, as shown in fig. 9.
Claims (8)
1. A multi-information cascade clustering power transmission line detection method is characterized by comprising the following steps:
(1) acquiring a power line image, and performing gray level transformation on the image;
(2) carrying out image preprocessing on the image after gray level transformation by using an edge enhancement algorithm;
(3) performing cumulative probability Hough transform on the enhanced image, and extracting candidate straight lines in the image;
(4) performing cascade clustering analysis on the linear information according to the length, the angle and the position information of the linear;
(5) calculating the distance between all straight lines according to a straight line distance formula, and removing repeated straight lines;
(6) and predicting the trend of the power transmission line by the finally obtained straight line according to the angle position information obtained by calculation, and marking the power transmission line by using a rectangular frame.
2. The method for detecting a multi-information cascade clustering power transmission line according to claim 1, wherein in the step (1), the obtaining of the power transmission line image and the gray level transformation of the image are specifically as follows: the camera is installed at the top of the head of the unmanned aerial vehicle, the unmanned aerial vehicle captures images through the camera in the flying process, and the captured images are transmitted to the processor for graying operation.
3. The method for detecting the multi-information cascade clustering power transmission line according to claim 1, wherein in the step (2), edge features which belong to strong edges in the image are extracted by using an edge enhancement algorithm based on a hessian matrix for the image after gray level transformation, so that the power transmission line edges are enhanced.
4. The method for detecting the multi-information cascade clustering power transmission line according to claim 3, wherein the hessian matrix is calculated by the following formula:
where f is a function f of the image with respect to coordinates (x, y)xx，fxy，fyx，fyyRespectively representing the second partial derivatives of the function f to x, y and the mixture thereof; the Hessian matrix eigenvalue and eigenvector reflect the intensity and direction of the image gray scale curvature change.
5. The method for detecting the multi-information cascade clustering power transmission line according to claim 1, wherein in the step (3), the step of performing cumulative probability Hough transform on the enhanced image to extract the candidate straight lines in the image specifically comprises the following steps:
(3.1) in a specified range, mapping the edge pixel point information subjected to image enhancement to a Hough space;
(3.2) voting is carried out on each edge pixel point mapped to the Hough space;
and (3.3) accumulating a part of suspected points in the plane in the range, wherein the set of points exceeding the set threshold represents a straight line.
6. The method for detecting the multi-information cascade clustering power transmission line according to claim 1, wherein in the step (4), the cascade clustering analysis of the straight line information specifically comprises the following steps:
(4.1) carrying out secondary classification on the length, the angle and the position information of the straight line by using a clustering algorithm;
(4.2) marking the positive class in the straight line according to the ticket number of the straight line in the step (3);
and (4.3) carrying out hard cascade analysis on the result, carrying out intersection operation on the obtained positive classes, and marking the straight lines as power transmission lines when all the straight lines are divided into the positive classes in the 3 types of information.
7. The method for detecting multi-information cascade clustering power transmission lines according to claim 1, wherein in the step (5), the distances between all the straight lines are calculated according to a straight line distance formula, and repeated straight lines are removed, and the method specifically comprises the following steps:
(5.1) loading a power line image and linear parameters;
(5.2) estimating the distance from the first straight line to other straight lines;
(5.3) screening all straight lines with the distances smaller than a threshold value, selecting the longest straight line, reserving the longest straight line, and deleting other straight lines;
(5.4) estimating the distance between the second straight line and other straight lines;
(5.5) repeating the step (5.3) and the step (5.4) until the last straight line is calculated.
8. The method according to claim 7, wherein the distance estimation formula is:
wherein A, B, C is a parameter of a linear general formula in a two-dimensional rectangular coordinate system, wherein (x)i,yi) Is any point of one straight line, n is the number of the points,
to estimate the resulting distance. By setting the threshold value D when
The duplicate detection problem is considered to exist.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893883.9A CN112115985A (en) | 2020-08-31 | 2020-08-31 | Multi-information cascade clustering power transmission line detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893883.9A CN112115985A (en) | 2020-08-31 | 2020-08-31 | Multi-information cascade clustering power transmission line detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112115985A true CN112115985A (en) | 2020-12-22 |
Family
ID=73804973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010893883.9A Pending CN112115985A (en) | 2020-08-31 | 2020-08-31 | Multi-information cascade clustering power transmission line detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115985A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407924A (en) * | 2016-09-10 | 2017-02-15 | 上海大学 | Binocular road identifying and detecting method based on pavement characteristics |
| CN107341470A (en) * | 2017-07-03 | 2017-11-10 | 国网浙江省电力公司信息通信分公司 | A kind of transmission of electricity line detecting method based on Aerial Images |
| CN110298845A (en) * | 2019-06-17 | 2019-10-01 | 中国计量大学 | It transmits electricity under a kind of complex background based on image procossing line detecting method |
-
2020
- 2020-08-31 CN CN202010893883.9A patent/CN112115985A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407924A (en) * | 2016-09-10 | 2017-02-15 | 上海大学 | Binocular road identifying and detecting method based on pavement characteristics |
| CN107341470A (en) * | 2017-07-03 | 2017-11-10 | 国网浙江省电力公司信息通信分公司 | A kind of transmission of electricity line detecting method based on Aerial Images |
| CN110298845A (en) * | 2019-06-17 | 2019-10-01 | 中国计量大学 | It transmits electricity under a kind of complex background based on image procossing line detecting method |
Non-Patent Citations (2)
| Title |
|---|
| 张志扬 等: "基于深度学习的信息级联预测方法综述", 《计算机科学》, 7 July 2020 (2020-07-07), pages 141 - 153 * |
| 张志扬 等: "基于深度学习的信息级联预测方法综述", 计算机科学, 7 July 2020 (2020-07-07), pages 141 - 153 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN108388896B (en) | License plate identification method based on dynamic time sequence convolution neural network | |
| CN109657632B (en) | Lane line detection and identification method | |
| CN110197231B (en) | Bird condition detection equipment and identification method based on visible light and infrared light image fusion | |
| CN111681197B (en) | Remote sensing image unsupervised change detection method based on Siamese network structure | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| Akarsu et al. | A fast and adaptive road defect detection approach using computer vision with real time implementation | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN110263635B (en) | Marker detection and identification method based on structural forest and PCANet | |
| CN109635733B (en) | Parking lot and vehicle target detection method based on visual saliency and queue correction | |
| CN110660065B (en) | Infrared fault detection and identification algorithm | |
| CN110222661B (en) | Feature extraction method for moving target identification and tracking | |
| CN109360179B (en) | Image fusion method and device and readable storage medium | |
| CN107992856B (en) | High-resolution remote sensing building shadow detection method under urban scene | |
| CN112308872B (en) | Image edge detection method based on multi-scale Gabor first derivative | |
| CN110245600B (en) | Unmanned aerial vehicle road detection method for self-adaptive initial quick stroke width | |
| CN110070545B (en) | Method for automatically extracting urban built-up area by urban texture feature density | |
| CN110110618B (en) | SAR target detection method based on PCA and global contrast | |
| CN106886988B (en) | Linear target detection method and system based on unmanned aerial vehicle remote sensing | |
| CN111915583A (en) | Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene | |
| CN115841633A (en) | Power tower and power line associated correction power tower and power line detection method | |
| CN110276747B (en) | Insulator fault detection and fault rating method based on image analysis | |
| CN111310771A (en) | Road image extraction method, device and equipment of remote sensing image and storage medium | |
| CN112396582B (en) | Mask RCNN-based equalizing ring skew detection method | |
| CN111340833B (en) | Power transmission line extraction method for least square interference-free random Hough transformation |
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 |