CN106355580B - Method and device for detecting toppling of tower - Google Patents
Method and device for detecting toppling of tower Download PDFInfo
- Publication number
- CN106355580B CN106355580B CN201610841315.8A CN201610841315A CN106355580B CN 106355580 B CN106355580 B CN 106355580B CN 201610841315 A CN201610841315 A CN 201610841315A CN 106355580 B CN106355580 B CN 106355580B
- Authority
- CN
- China
- Prior art keywords
- group
- power lines
- tower
- detected
- toppling
- 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
- 238000000605 extraction Methods 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000011426 transformation method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Electric Cable Installation (AREA)
Abstract
The embodiment of the invention discloses a method and a device for detecting tower toppling. In the embodiment of the invention, firstly, an unmanned aerial vehicle aerial image of a tower to be detected is obtained, a first group of power lines positioned on a first side of the tower to be detected and a second group of power lines positioned on a second side of the tower to be detected are extracted from the unmanned aerial vehicle aerial image, and whether the tower to be detected is in an inclined state is detected according to the extraction results of the first group of power lines and the second group of power lines; in the embodiment of the invention, the aerial image of the unmanned aerial vehicle is conveniently acquired, so that the unmanned aerial vehicle can quickly respond to sudden natural disasters, and the required labor cost and equipment cost are low when the unmanned aerial vehicle inspects towers in a certain area; moreover, the extraction result of the power line can directly reflect the toppling condition of the tower to be detected, so that the accuracy of detecting whether the tower to be detected is in the toppling state or not according to the extraction result of the power line is higher.
Description
Technical Field
The invention relates to the field of remote sensing data application of unmanned aerial vehicles, in particular to a method and a device for detecting tower dumping.
Background
With the progress of science and technology, the dependence of social production and life on electric power is stronger and stronger, and power transmission lines are distributed all over the world. The transmission line tower is used as large equipment widely applied to the transmission line and has important significance for detecting whether the transmission line tower is inclined or not.
In consideration of the life and property safety of people and the safe operation of the transmission line, the existing transmission line is generally constructed in an area with few personnel and relatively inconvenient traffic, so that the inspection and the maintenance of the transmission line tower are relatively inconvenient. In addition, in case of an emergency, such as a natural disaster like a typhoon or an earthquake, the damaged area is large, the affected area of the transmission line is large, and the damaged condition of the transmission line and the tower needs to be rapidly grasped. Therefore, in the prior art, when detecting whether the tower is toppled or not, a method of installing a detection device on the tower is generally adopted, for example, an inclination angle detection device is installed, and when the tower is toppled, the detection device sends a signal to a command center. However, since the detection device needs to be installed on the tower and needs to be maintained regularly or irregularly after a large number of installations, the labor cost and the equipment cost are high, and when emergency such as typhoon occurs, the communication link of the detection device is easily affected, resulting in false alarm, and thus inaccurate detection results.
In summary, there is a need for an effective method for detecting tower toppling, which is used to detect whether a tower is toppled or not accurately on the basis of reducing cost.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting tower toppling, which are used for accurately detecting whether a tower is in a toppling state or not on the basis of reducing cost.
The method for detecting the tower toppling provided by the embodiment of the invention comprises the following steps:
acquiring an unmanned aerial vehicle aerial image of a tower to be detected;
extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected from the aerial image of the unmanned aerial vehicle;
and detecting whether the tower to be detected is in an toppling state or not according to the extraction results of the first group of power lines and the second group of power lines.
Preferably, detecting whether the tower to be detected is in an inclined state according to the extraction results of the first group of power lines and the second group of power lines includes:
and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
Preferably, when the following conditions are judged to exist according to the extraction results of the first group of power lines and the second group of power lines, the tower to be detected is determined to be in a non-toppling state:
if the first group of power lines and the second group of power lines are extracted and are both straight lines, determining that the tower to be detected is in a non-toppling state; or,
if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state; or,
and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state.
Preferably, when the following conditions are judged to exist according to the extraction results of the first group of power lines and the second group of power lines, the tower to be detected is determined to be in the toppling state:
if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines, determining that the tower to be detected is in an toppling state; or,
if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an toppling state; or,
and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
Preferably, extracting, from the aerial image of the unmanned aerial vehicle, a first group of power lines located on a first side of the tower to be detected and a second group of power lines located on a second side of the tower to be detected, includes:
carrying out image preprocessing on the aerial image of the unmanned aerial vehicle;
based on the preprocessed unmanned aerial vehicle aerial image, adopting a Ratio operator to carry out edge detection;
detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by a Hough transformation method;
and judging and screening the linear information detected by Hough transformation according to the characteristics of the power lines, and extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected.
The embodiment of the invention provides a tower toppling detection device, which comprises:
the acquisition module is used for acquiring an unmanned aerial vehicle aerial image of the tower to be detected;
the extraction module is used for extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected from the unmanned aerial vehicle aerial image;
and the detection module is used for detecting whether the tower to be detected is in an toppling state or not according to the extraction results of the first group of power lines and the second group of power lines.
Preferably, the detection module is specifically configured to:
and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
Preferably, the detection module is specifically configured to determine that the tower to be detected is in a non-toppling state when the following conditions are determined to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and are both straight lines, determining that the tower to be detected is in a non-toppling state; or,
if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state; or,
and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state.
Preferably, the detection module is specifically configured to determine that the tower to be detected is in the toppling state when the following conditions are determined to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines, determining that the tower to be detected is in an toppling state; or,
if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an toppling state; or,
and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
Preferably, the extraction module is specifically configured to:
carrying out image preprocessing on the aerial image of the unmanned aerial vehicle;
based on the preprocessed unmanned aerial vehicle aerial image, adopting a Ratio operator to carry out edge detection;
detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by a Hough transformation method;
and judging and screening the linear information detected by Hough transformation according to the characteristics of the power lines, and extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected.
In the embodiment of the invention, firstly, an unmanned aerial vehicle aerial image of a tower to be detected is obtained, a first group of power lines located on a first side of the tower to be detected and a second group of power lines located on a second side of the tower to be detected are extracted from the unmanned aerial vehicle aerial image, and whether the tower to be detected is in a toppling state is detected according to extraction results of the first group of power lines and the second group of power lines; in the embodiment of the invention, whether the tower to be detected is in the toppling state is detected based on the aerial image of the unmanned aerial vehicle, and the aerial image of the unmanned aerial vehicle is relatively convenient to obtain, so that the aerial image of the unmanned aerial vehicle can quickly respond to sudden natural disasters, and the required labor cost and equipment cost are relatively low when the aerial image of the unmanned aerial vehicle is used for polling the tower in a certain area; moreover, the extraction result of the power line can directly reflect the toppling condition of the tower to be detected, so that the accuracy of detecting whether the tower to be detected is in the toppling state or not according to the extraction result of the power line is higher.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart corresponding to a tower toppling detection method provided in an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a method for extracting a power line according to an embodiment of the present invention;
fig. 3a and 3b are schematic diagrams of power lines under normal operation of a tower;
fig. 4 is a schematic diagram of a power line with a tower in a dumping state;
fig. 5 is a schematic structural diagram of a tower toppling detection device according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The embodiment of the invention provides a method and a device for detecting tower toppling, which are used for accurately detecting whether a tower is in a toppling state or not on the basis of reducing cost.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Based on the importance of detecting the toppling condition of the power transmission line tower and the defects of the existing detection method, the inventor of the application researches the toppling condition of the tower and provides a method for detecting the toppling condition of the tower based on the extraction result of the power line in the aerial image of the unmanned aerial vehicle, so that a new thought and a new method are provided for detecting the toppling condition of the tower.
Fig. 1 is a schematic flow chart corresponding to a tower toppling detection method provided in an embodiment of the present invention, and as shown in fig. 1, the method includes:
101, acquiring an unmanned aerial vehicle aerial image of a tower to be detected;
102, extracting a first group of power lines positioned on a first side of the tower to be detected and a second group of power lines positioned on a second side of the tower to be detected from the aerial image of the unmanned aerial vehicle;
103, detecting whether the tower to be detected is in an inclined state or not according to the extraction results of the first group of power lines and the second group of power lines.
In the embodiment of the invention, whether the tower to be detected is in the toppling state is detected based on the aerial image of the unmanned aerial vehicle, and the aerial image of the unmanned aerial vehicle is relatively convenient to obtain, so that the aerial image of the unmanned aerial vehicle can quickly respond to sudden natural disasters, and the required labor cost and equipment cost are relatively low when the aerial image of the unmanned aerial vehicle is used for polling the tower in a certain area; moreover, the extraction result of the power line can directly reflect the toppling condition of the tower to be detected, so that the accuracy of detecting whether the tower to be detected is in the toppling state or not according to the extraction result of the power line is higher.
Specifically, in step 102, there may be multiple methods for extracting, from the aerial image of the unmanned aerial vehicle, a first group of power lines located on the first side of the tower to be detected and a second group of power lines located on the second side of the tower to be detected, and an extraction method provided in an embodiment of the present invention is: firstly, all line segments of the whole image are detected by using a straight line detection method, then the angle and position information of each line segment are compared and analyzed with the similarity (distance difference) and the colinearity (angle difference), and whether the line segments belong to the same wire or not is judged. If the power lines belong to the same wire, the power lines are combined to obtain a complete power line, and then the power lines which do not meet the semantic rule of the power lines are removed by combining the semantic knowledge (which can be the power line characteristics) of the power lines. The method may be implemented based on Ratio operators and Hough transforms.
As shown in fig. 2, a schematic flow chart corresponding to the method for extracting a power line provided in the embodiment of the present invention specifically includes:
Particularly, because the content of the unmanned aerial vehicle aerial image is comparatively complicated, the accuracy of identification can be improved by preprocessing according to the characteristics of the image, wherein the preprocessing that can be carried out comprises filtering and binaryzation. The image can be denoised by median filtering, the median filtering can filter out high-frequency noise, loss of image edge details can be avoided, and the edge of the image is well protected. Then, binarization processing is performed on the image so as to highlight the edges of the image.
And step 202, based on the preprocessed unmanned aerial vehicle aerial image, adopting a Ratio operator to carry out edge detection.
Specifically, the Ratio operator mainly comprises three parameters, the first parameter is the size of the template, the size of the template is selected to be 5 × 5 through experiments in order to suppress noise and consider the size of a calculation quantity template, the second parameter is the number of detected straight line directions, the power transmission line is generally in an approximately horizontal state in the unmanned aerial vehicle line patrol process, the Ratio operator in the horizontal direction can be used for detecting linear edges all the time, and the third parameter is a threshold value, and the average value of the linear edge image can be selected to be 3 times in order to enable the threshold value to be adaptive to the image.
And step 203, detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by adopting a Hough transformation method.
And 204, judging and screening the linear information detected by Hough transformation according to the characteristics of the power lines, and extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected.
Specifically, after linear edges are detected, cumulative probability Hough transformation is carried out to obtain a series of line segments, then line segment connection is carried out, the line segments on the same straight line are connected to be the maximum length, then the line segments with the angles ranging from-PI/4 to PI/4 are selected, the longest line segment M is obtained, and all the line segments approximately parallel to M can be determined as power lines.
According to the practical situation, when the tower does not topple over, the power line in the aerial image of the unmanned aerial vehicle is represented as a straight line, as shown in fig. 3a and 3b, the power line is a schematic diagram of the power line under normal operation of the tower. If the tower falls, the power line falls off and relaxes, so that the power line cannot be represented as a straight line in an aerial image of the unmanned aerial vehicle, as shown in fig. 4, the power line is a schematic diagram of the power line with the tower in a falling state; or, the tower topples over and still can lead to the power line to bury in ground objects such as weeds woods, and can't draw out from unmanned aerial vehicle aerial image. Therefore, in step 103, detecting whether the tower to be detected is in an inclined state according to the extraction results of the first group of power lines and the second group of power lines may include: and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
Specifically, in the embodiment of the present invention, when it is determined that the following three conditions exist according to the extraction results of the first group of power lines and the second group of power lines, it may be determined that the tower to be detected is in a non-toppling state:
the first condition is as follows: and if the first group of power lines and the second group of power lines are extracted and both the first group of power lines and the second group of power lines are straight lines (as shown in fig. 3a and 3 b), determining that the tower to be detected is in a non-toppling state.
Case two: and if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state. For example, the first group of power lines is shown as a straight line, and the second group of power lines is shown as a curve, which is usually caused by that the adjacent tower located at the second side of the tower to be detected is in an inclined state or the power lines are broken, so that the second group of power lines is shown as a curve, and therefore, the tower to be detected can be preliminarily determined to be in a non-inclined state, and the adjacent tower located at the second side of the tower to be detected can be further detected, so that the accuracy of the result can be confirmed.
Case three: and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state. For example, only the first group of power lines are extracted, the first group of power lines are straight lines, and the second group of power lines are not extracted, which is usually caused by that the adjacent tower located at the second side of the tower to be detected is in an inclined state or the power lines are broken, so that the second group of power lines are buried in ground objects such as a weed forest and cannot be extracted, and therefore, the tower to be detected can be preliminarily determined to be in a non-inclined state, and the adjacent tower located at the second side of the tower to be detected can be further detected, so that the accuracy of the result can be confirmed.
Specifically, in the embodiment of the present invention, when it is determined that the following three conditions exist according to the extraction results of the first group of power lines and the second group of power lines, it may be determined that the tower to be detected is in an inclined state:
the first condition is as follows: and if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines (as shown in fig. 4), determining that the tower to be detected is in an inclined state.
Case two: and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an inclined state.
Case three: and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
In the embodiment of the invention, firstly, an unmanned aerial vehicle aerial image of a tower to be detected is obtained, a first group of power lines located on a first side of the tower to be detected and a second group of power lines located on a second side of the tower to be detected are extracted from the unmanned aerial vehicle aerial image, and whether the tower to be detected is in a toppling state is detected according to extraction results of the first group of power lines and the second group of power lines; in the embodiment of the invention, whether the tower to be detected is in the toppling state is detected based on the aerial image of the unmanned aerial vehicle, and the aerial image of the unmanned aerial vehicle is relatively convenient to obtain, so that the aerial image of the unmanned aerial vehicle can quickly respond to sudden natural disasters, and the required labor cost and equipment cost are relatively low when the aerial image of the unmanned aerial vehicle is used for polling the tower in a certain area; moreover, the extraction result of the power line can directly reflect the toppling condition of the tower to be detected, so that the accuracy of detecting whether the tower to be detected is in the toppling state or not according to the extraction result of the power line is higher.
Aiming at the method flow, the embodiment of the invention also provides a tower toppling detection device, and the specific content of the device can be implemented by referring to the method.
Fig. 5 is a schematic structural diagram of a tower toppling detection device according to an embodiment of the present invention, and as shown in fig. 5, the tower toppling detection device includes:
the acquiring module 501 is used for acquiring an unmanned aerial vehicle aerial image of a tower to be detected;
an extracting module 502, configured to extract, from the unmanned aerial vehicle aerial image, a first group of power lines located on a first side of the tower to be detected and a second group of power lines located on a second side of the tower to be detected;
the detection module 503 is configured to detect whether the tower to be detected is in an inclined state according to the extraction results of the first group of power lines and the second group of power lines.
Preferably, the detecting module 503 is specifically configured to:
and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
Preferably, the detection module 503 is specifically configured to determine that the tower to be detected is in a non-toppling state when the following conditions are determined to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and are both straight lines, determining that the tower to be detected is in a non-toppling state; or,
if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state; or,
and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state.
Preferably, the detection module 503 is specifically configured to determine that the tower to be detected is in the toppling state when the following conditions are determined to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines, determining that the tower to be detected is in an toppling state; or,
if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an toppling state; or,
and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
Preferably, the extracting module 502 is specifically configured to:
carrying out image preprocessing on the aerial image of the unmanned aerial vehicle;
based on the preprocessed unmanned aerial vehicle aerial image, adopting a Ratio operator to carry out edge detection;
detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by a Hough transformation method;
and judging and screening the linear information detected by Hough transformation according to the characteristics of the power lines, and extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected.
From the above, it can be seen that: in the embodiment of the invention, firstly, an unmanned aerial vehicle aerial image of a tower to be detected is obtained, a first group of power lines located on a first side of the tower to be detected and a second group of power lines located on a second side of the tower to be detected are extracted from the unmanned aerial vehicle aerial image, and whether the tower to be detected is in a toppling state is detected according to extraction results of the first group of power lines and the second group of power lines; in the embodiment of the invention, whether the tower to be detected is in the toppling state is detected based on the aerial image of the unmanned aerial vehicle, and the aerial image of the unmanned aerial vehicle is relatively convenient to obtain, so that the aerial image of the unmanned aerial vehicle can quickly respond to sudden natural disasters, and the required labor cost and equipment cost are relatively low when the aerial image of the unmanned aerial vehicle is used for polling the tower in a certain area; moreover, the extraction result of the power line can directly reflect the toppling condition of the tower to be detected, so that the accuracy of detecting whether the tower to be detected is in the toppling state or not according to the extraction result of the power line is higher.
It should be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (6)
1. A tower toppling detection method is characterized by comprising the following steps: acquiring an unmanned aerial vehicle aerial image of a tower to be detected;
extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected from the aerial image of the unmanned aerial vehicle;
detecting whether the tower to be detected is in an toppling state or not according to the extraction results of the first group of power lines and the second group of power lines;
the tower to be detected is detected, and the method comprises the following steps:
carrying out image preprocessing on the aerial image of the unmanned aerial vehicle;
the method comprises the steps of carrying out edge detection on an unmanned aerial vehicle aerial image based on preprocessing by adopting a Ratio operator, wherein the Ratio operator mainly comprises three parameters, the first parameter is the size of a template, the size of the template is selected to be 5 × 5 through experiments in order to suppress noise and in consideration of the size of a calculated template, the second parameter is the number in the direction of a detected straight line, a power transmission line is in an approximately horizontal state in the process of unmanned aerial vehicle line patrol, the Ratio operator in the horizontal direction is adopted to carry out linear edge detection, the third parameter is a threshold value, and a linear edge image mean value which is 3 times is selected in order to enable the threshold value to be adaptive to the image;
detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by a Hough transformation method;
according to the characteristics of the power lines, linear information detected by Hough transformation is distinguished and screened, and a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected are extracted;
the specific method comprises the following steps: carrying out cumulative probability Hough transformation after detecting the linear edge to obtain a series of line segments, then carrying out line segment connection, connecting the line segments on the same straight line to be the maximum length, then selecting the line segment with the angle between-PI/4 and PI/4, and solving the longest line segment M, wherein all the line segments approximately parallel to M can be determined as power lines;
and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
2. The method according to claim 1, wherein the tower to be detected is determined to be in a non-toppling state when the following conditions are judged to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and are both straight lines, determining that the tower to be detected is in a non-toppling state;
or,
if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state;
or,
and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state.
3. The method according to claim 1, wherein the tower to be detected is determined to be in the toppling state when the following conditions are judged to exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines, determining that the tower to be detected is in an toppling state;
or,
if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an toppling state;
or,
and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
4. A tower toppling detection device is characterized by comprising:
the acquisition module is used for acquiring an unmanned aerial vehicle aerial image of the tower to be detected;
the extraction module is used for extracting a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected from the unmanned aerial vehicle aerial image;
the detection module is used for detecting whether the tower to be detected is in an toppling state or not according to the extraction results of the first group of power lines and the second group of power lines;
the extraction module is specifically configured to: carrying out image preprocessing on the aerial image of the unmanned aerial vehicle;
the method comprises the steps of carrying out edge detection on an unmanned aerial vehicle aerial image based on preprocessing by adopting a Ratio operator, wherein the Ratio operator mainly comprises three parameters, the first parameter is the size of a template, the size of the template is selected to be 5 × 5 through experiments in order to suppress noise and in consideration of the size of a calculated template, the second parameter is the number in the direction of a detected straight line, a power transmission line is in an approximately horizontal state in the process of unmanned aerial vehicle line patrol, the Ratio operator in the horizontal direction is adopted to carry out linear edge detection, the third parameter is a threshold value, and a linear edge image mean value which is 3 times is selected in order to enable the threshold value to be adaptive to the image;
detecting the linear information of the preprocessed unmanned aerial vehicle aerial image by a Hough transformation method;
according to the characteristics of the power lines, linear information detected by Hough transformation is distinguished and screened, and a first group of power lines positioned on the first side of the tower to be detected and a second group of power lines positioned on the second side of the tower to be detected are extracted;
carrying out cumulative probability Hough transformation after detecting the linear edge to obtain a series of line segments, then carrying out line segment connection, connecting the line segments on the same straight line to be the maximum length, then selecting the line segment with the angle between-PI/4 and PI/4, and solving the longest line segment M, wherein all the line segments approximately parallel to M can be determined as power lines;
and determining to extract at least one group of power lines in the first group of power lines and the second group of power lines according to the extraction results of the first group of power lines and the second group of power lines, and determining that the tower to be detected is in a non-toppling state if one group of power lines is straight, or determining that the tower to be detected is in a toppling state if not.
5. The device according to claim 4, wherein the detection module is specifically configured to determine that the tower to be detected is in a non-toppling state when it is determined that the following conditions exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and are both straight lines, determining that the tower to be detected is in a non-toppling state;
or,
if the first group of power lines and the second group of power lines are extracted, one group of power lines are represented as straight lines, and the other group of power lines are not represented as straight lines, determining that the tower to be detected is in a non-toppling state;
or,
and if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines is straight, determining that the tower to be detected is in a non-toppling state.
6. The device according to claim 5, wherein the detection module is specifically configured to determine that the tower to be detected is in the toppling state when it is determined that the following conditions exist according to the extraction results of the first group of power lines and the second group of power lines:
if the first group of power lines and the second group of power lines are extracted and neither the first group of power lines nor the second group of power lines are represented as straight lines, determining that the tower to be detected is in an toppling state;
or,
if only one group of power lines in the first group of power lines and the second group of power lines are extracted and the extracted group of power lines do not represent a straight line, determining that the tower to be detected is in an toppling state;
or,
and if the first group of power lines and the second group of power lines are not extracted, determining that the tower to be detected is in the toppling state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610841315.8A CN106355580B (en) | 2016-09-22 | 2016-09-22 | Method and device for detecting toppling of tower |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610841315.8A CN106355580B (en) | 2016-09-22 | 2016-09-22 | Method and device for detecting toppling of tower |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106355580A CN106355580A (en) | 2017-01-25 |
| CN106355580B true CN106355580B (en) | 2020-07-14 |
Family
ID=57858768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610841315.8A Active CN106355580B (en) | 2016-09-22 | 2016-09-22 | Method and device for detecting toppling of tower |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106355580B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107221006A (en) * | 2017-05-11 | 2017-09-29 | 南京邮电大学 | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform |
| CN107833206B (en) * | 2017-10-24 | 2021-07-06 | 武汉大学 | Accurate power line extraction method under complex background |
| CN107917695B (en) * | 2017-11-16 | 2021-07-27 | 南京工业大学 | House inclination monitoring method based on image recognition technology |
| CN108985143B (en) * | 2018-05-10 | 2022-03-29 | 国电南瑞科技股份有限公司 | Method for identifying iron tower structure of overhead transmission line based on unmanned aerial vehicle image |
| CN109657677A (en) * | 2018-12-14 | 2019-04-19 | 广东电网有限责任公司 | A kind of detection method of electric power line pole tower, device, equipment and storage medium |
| CN110889827A (en) * | 2019-11-06 | 2020-03-17 | 国网山西省电力公司吕梁供电公司 | Transmission line tower online identification and inclination detection method based on vision |
| CN112541455B (en) * | 2020-12-21 | 2023-07-07 | 国网河南省电力公司电力科学研究院 | Machine vision-based prediction method for reverse breaking accidents of distribution network concrete electric pole |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101666636A (en) * | 2008-09-04 | 2010-03-10 | 华东电力试验研究院有限公司 | Method for monitoring wire icing thickness of iced circuit and straight line tower stress |
| CN101950357A (en) * | 2010-09-21 | 2011-01-19 | 上海大学 | Method for identifying towers, drainage threads and wires of high-voltage line based on position relations |
| CN103761722A (en) * | 2014-01-16 | 2014-04-30 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8655939B2 (en) * | 2007-01-05 | 2014-02-18 | Digital Doors, Inc. | Electromagnetic pulse (EMP) hardened information infrastructure with extractor, cloud dispersal, secure storage, content analysis and classification and method therefor |
| JP6209141B2 (en) * | 2014-09-04 | 2017-10-04 | 公益財団法人鉄道総合技術研究所 | Obstacle detection apparatus and method |
-
2016
- 2016-09-22 CN CN201610841315.8A patent/CN106355580B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101666636A (en) * | 2008-09-04 | 2010-03-10 | 华东电力试验研究院有限公司 | Method for monitoring wire icing thickness of iced circuit and straight line tower stress |
| CN101950357A (en) * | 2010-09-21 | 2011-01-19 | 上海大学 | Method for identifying towers, drainage threads and wires of high-voltage line based on position relations |
| CN103761722A (en) * | 2014-01-16 | 2014-04-30 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106355580A (en) | 2017-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106355580B (en) | Method and device for detecting toppling of tower | |
| US8504431B2 (en) | Method and system for monitoring forestry products | |
| CN110160583A (en) | A kind of heritage monitor device, historical relic ambient condition monitoring system and storage box | |
| US20230005176A1 (en) | Throwing position acquisition method and apparatus, computer device and storage medium | |
| CN103106766A (en) | Forest fire identification method and forest fire identification system | |
| CN103065413A (en) | Method and device of acquiring fire class information | |
| CN110084169A (en) | A kind of architecture against regulations object recognition methods based on K-Means cluster and profile topological constraints | |
| CN104599427A (en) | Intelligent image type fire alarming system for highway tunnel | |
| EP4102401A1 (en) | Traffic anomaly detection method and apparatus, device, storage medium, and program product | |
| CN102708643A (en) | Invasion detection method and system | |
| CN109460787A (en) | IDS Framework method for building up, device and data processing equipment | |
| CN113076899B (en) | High-voltage transmission line foreign matter detection method based on target tracking algorithm | |
| CN113484858A (en) | Intrusion detection method and system | |
| CN112381041A (en) | Tree identification method and device for power transmission line and terminal equipment | |
| CN117314157A (en) | Safety evaluation method, device, medium and equipment for mine slope stability | |
| CN107632306A (en) | A kind of wire obstacle safe distance detection method for considering trees lodging | |
| CN112906441A (en) | Image recognition system and method for communication industry survey and maintenance | |
| CN104574729A (en) | Alarming method, device and system | |
| CN113920339A (en) | Crane false alarm method in power transmission line channel hidden danger based on deep learning | |
| CN112016641A (en) | Method and device for alarming line short circuit fault caused by foreign matter | |
| CN105991969A (en) | Detector of floating suspension objects on high tension transmission line, and method of using and installing the detector | |
| CN111951505A (en) | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system | |
| CN111461655A (en) | Personnel management system | |
| CN115134159B (en) | Safety alarm analysis optimization method | |
| CN113177431B (en) | Method and system for preventing lifting of collection card based on machine vision and deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210315 Address after: 650217 No. 105 Yunda West Road, Kunming Economic and Technological Development Zone, Yunnan Province Patentee after: ELECTRIC POWER RESEARCH INSTITUTE, YUNNAN POWER GRID Co.,Ltd. Address before: 650217 No. 105 Yunda West Road, Kunming Economic and Technological Development Zone, Yunnan Province Patentee before: ELECTRIC POWER RESEARCH INSTITUTE, YUNNAN POWER GRID Co.,Ltd. Patentee before: TIANJIN ZHONG WEI AEROSPACE DATA SYSTEM TECHNOLOGY Co.,Ltd. Patentee before: China South Power Grid International Co.,Ltd. |
|
| TR01 | Transfer of patent right |