CN117314022A - Method and device for analyzing hidden danger of power transmission line - Google Patents
Method and device for analyzing hidden danger of power transmission line Download PDFInfo
- Publication number
- CN117314022A CN117314022A CN202311606266.6A CN202311606266A CN117314022A CN 117314022 A CN117314022 A CN 117314022A CN 202311606266 A CN202311606266 A CN 202311606266A CN 117314022 A CN117314022 A CN 117314022A
- Authority
- CN
- China
- Prior art keywords
- target
- power grid
- transmission line
- power transmission
- targets
- 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.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000010586 diagram Methods 0.000 claims abstract description 29
- 238000001514 detection method Methods 0.000 claims description 51
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010276 construction Methods 0.000 description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 6
- 239000000779 smoke Substances 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 3
- 229910052742 iron Inorganic materials 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000003517 fume Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a method and a device for analyzing hidden danger of a power transmission line, comprising the steps of obtaining a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; judging a scene environment corresponding to the power transmission line graph according to the power grid target; obtaining a target alarm region according to all the power grid targets; judging the type of the non-power grid target to obtain a target hazard level; judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level. By analyzing the scene characteristics, the power grid targets and the characteristics of the non-power grid targets, the false alarm rate of the target alarms is reduced, the identification effect of the target alarms in the specific scene is improved, and the problem of missing alarms is avoided.
Description
Technical Field
The invention relates to the technical field of power failure analysis, in particular to a method and a device for analyzing hidden danger of a power transmission line.
Background
Some targets with potential safety hazards often appear in the power transmission line, and how to accurately judge the targets with potential safety hazards is an important means for ensuring the safety of the power transmission line. Meanwhile, the judging method for hidden danger targets is also very important, if all targets in the area are alarmed, the alarming quantity is large, and the pressure of staff screening is increased.
At present, a conventional judging method generally uses a wire and a projection area as an alarm area, and judges whether to report an alarm by judging the intersection ratio of a target and the alarm area. The method reduces the number of alarm pictures in a certain proportion, but still has high false alarm rate. Meanwhile, detection effects on construction site scenes or other unconventional line scenes are poor, and a large number of missing reports exist.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the method and the device for analyzing the potential safety hazards of the power transmission lines are provided, and the judgment precision of potential safety hazard targets in different power transmission line scenes is improved.
In order to solve the technical problems, the invention adopts the following technical scheme:
a hidden danger analysis method for a power transmission line comprises the following steps:
acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram;
judging a scene environment corresponding to the power transmission line graph according to the power grid target;
obtaining a target alarm region according to all the power grid targets;
judging the type of the non-power grid target to obtain a target hazard level;
judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level.
The invention has the beneficial effects that: the method comprises the steps of identifying all power grid targets and non-power grid targets in a power transmission line graph, analyzing scene characteristics of the power transmission line based on the power grid targets, calculating to obtain corresponding target alarm areas, obtaining hazard levels of the non-power grid targets in a power transmission scene based on the analysis of the non-power grid targets, judging the identified non-power grid targets based on scene environments, target alarm areas and target hazard levels corresponding to the power transmission line graph, analyzing scene characteristics, power grid targets and characteristics of the non-power grid targets, reducing false alarm rate of target alarms, improving identification effect of the target alarms in specific scenes, and avoiding missing alarm problems.
Drawings
Fig. 1 is a step flowchart of a method for analyzing hidden danger of a power transmission line in an embodiment of the present invention;
fig. 2 is a schematic diagram of a scenario of a line alarm region in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a first example scenario in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a second example scenario in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a third example scenario in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a fourth example scenario in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a fifth example scenario in a method for analyzing hidden danger of a power transmission line according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a hidden danger analysis device for a power transmission line in an embodiment of the present invention.
Detailed Description
In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings.
Referring to fig. 1, a method for analyzing hidden danger of a power transmission line includes:
acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram;
judging a scene environment corresponding to the power transmission line graph according to the power grid target;
obtaining a target alarm region according to all the power grid targets;
judging the type of the non-power grid target to obtain a target hazard level;
judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level.
From the above description, the beneficial effects of the invention are as follows: the method comprises the steps of identifying all power grid targets and non-power grid targets in a power transmission line graph, analyzing scene characteristics of the power transmission line based on the power grid targets, calculating to obtain corresponding target alarm areas, obtaining hazard levels of the non-power grid targets in a power transmission scene based on the analysis of the non-power grid targets, judging the identified non-power grid targets based on scene environments, target alarm areas and target hazard levels corresponding to the power transmission line graph, analyzing scene characteristics, power grid targets and characteristics of the non-power grid targets, reducing false alarm rate of target alarms, improving identification effect of the target alarms in specific scenes, and avoiding missing alarm problems.
Further, the grid targets include towers and wires;
the judging the scene environment corresponding to the power transmission line graph according to the power grid target comprises the following steps:
judging whether the tower is associated with the wire or not, if so, determining that the scene environment is a line scene; if not, determining the scene environment as a non-line scene;
the judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the non-power grid target characteristics comprises the following steps:
if the scene environment is the non-line scene and comprises the non-power grid target, the non-power grid target is a hidden danger target.
According to the description, the scene environment is divided into the line scene and the non-line scene based on the relation between the towers and the wires in the transmission line graph, so that the alarm judgment can be carried out on the non-power grid targets existing in the line scene and the non-line scene in a targeted manner, and the judgment precision of the non-power grid targets in different scene environments is improved.
Further, the determining whether there is an association between the tower and the wire includes:
obtaining a region with the most dense wire crossing points according to all the wires;
if the towers are located in the area with the most dense intersection points of the wires, the towers are associated with the wires, otherwise, the towers are not associated with the wires.
From the above description, it can be seen that, after the area with the most dense intersection points of the wires is obtained by calculation, whether there is a connection between the tower and the wires is determined according to the positional relationship between the tower and the area with the most dense intersection points of the wires, so that the line scene and the non-line scene can be effectively distinguished.
Further, the obtaining the area with the most dense wire intersections according to all the wires comprises:
and obtaining the area with the most dense wire intersection points through a wire intersection point clustering method or a sliding window method.
From the above description, the area with the denser wire intersection points can be accurately obtained based on the wire intersection point clustering method or the sliding window method, so that the accuracy of judging the association relationship between the tower and the wires is improved.
Further, the obtaining the target alarm region according to all the grid targets includes:
obtaining a tower alarm area according to the position of the tower;
and obtaining a line alarm area according to the area surrounded by the pole tower and the wire.
From the above description, it can be seen that the tower alarm region is obtained based on the position of the tower, and the line alarm region is obtained according to the region surrounded by the tower and the wires, so that on the basis of the scene environment, the non-grid target can be subjected to alarm judgment according to the position relationship between the non-grid target and the tower alarm region and the line alarm region, and the detection effect on the non-grid target is improved.
Further, the obtaining the line alarm area according to the area surrounded by the tower and the wire includes:
obtaining a detection frame according to the position of the tower;
obtaining a detection boundary line according to the position of the wire at the outermost side of the tower;
the detection boundary line comprises a first end point connected with the vertex of the detection frame and a second end point intersected with the first edge of the power transmission line graph;
and obtaining the line alarm region according to the region surrounded by the first endpoint and the second endpoint.
From the above description, it can be seen that, the detection boundary line is obtained based on the positions of the detection frame and the wire corresponding to the tower, and the line alarm region is obtained through the region surrounded by the edge of the power transmission line graph, the detection frame and the detection boundary line, so that the position of the non-grid target is compared based on the generated line alarm region, and the alarm detection of the non-grid target is realized.
Further, the obtaining the line alarm area according to the area surrounded by the tower and the wire further includes:
projecting the detection boundary line to the second edge of the power transmission line graph to obtain a third end point; the second edge is parallel to the first edge;
obtaining a first sub-line alarm area according to an area surrounded by the first endpoint and the second endpoint;
and obtaining a second sub-line alarm area according to the area surrounded by the first end point and the third end point.
As can be seen from the above description, by projecting the detection boundary line to the second edge of the power transmission line graph, and generating the first sub-line alarm region and the second sub-line alarm region, respectively, the wire entity portion is taken as the detection region, and the projected portion of the wire is taken as the detection region, so that the overall detection of the wire along the line region is realized.
Further, the method further comprises the following steps: and expanding or shrinking the target alarm area according to a preset proportion.
From the above description, the range of the target alarm area can be enlarged or reduced according to different detection precision, so as to meet the detection requirements in different scenes.
Further, the target hazard classes include general targets, important targets, and dangerous targets;
the judging of the type of the non-power grid target, the obtaining of the target hazard level comprises the following steps:
marking the non-grid targets as general targets, important targets or dangerous targets according to the types of the non-grid targets;
the judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the non-power grid target characteristics comprises the following steps:
if the scene environment is the line scene and the non-power grid target is the dangerous target, the non-power grid target is a hidden danger target.
According to the description, the non-power grid targets are marked as the general targets, the important targets or the dangerous targets, and the non-power grid targets are judged in an alarm mode by combining the scene environment and the target alarm area, so that the non-power grid targets with different hazard grades can be effectively distinguished, the target alarm precision is improved, and the false alarm rate of the target alarm is reduced.
The invention further provides a hidden danger analysis device for a power transmission line, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the hidden danger analysis method for the power transmission line when executing the computer program.
The method and the device for analyzing the hidden danger of the power transmission line can be applied to the identification of the hidden danger targets in the power transmission line, can aim at the identification of the hidden danger targets in a power transmission scene, a construction site scene, a reservoir scene and the like, and can give an alarm based on the identification result, and the method and the device are described in the following specific embodiments:
example 1
Referring to fig. 1, a method for analyzing hidden danger of a power transmission line includes:
s1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; for a power transmission scene, the camera device is generally installed on a pole tower, and the current line is focused; the power grid targets comprise towers and wires, the towers can be detected and identified through a deep learning target detection algorithm in some embodiments, and the wires can be detected and identified through a straight line detection or a deep learning target segmentation algorithm; the non-grid targets include volcanic, smoke, pile drivers, tower cranes, etc., and in some embodiments the detection of the target categories described above is detected by a deep learning target detection algorithm.
S2, judging a scene environment corresponding to the power transmission line graph according to the power grid target, wherein the scene environment comprises whether a power transmission tower exists, whether a power transmission wire exists or not, and whether the power transmission tower is associated with the power transmission wire or not, namely analyzing scene characteristics of the power transmission line, and specifically:
judging whether the tower is associated with the wire or not, if so, determining that the scene environment is a line scene; if not, determining the scene environment as a non-line scene; that is, only when the tower and the wire exist in the transmission line graph and the tower is associated with the wire, determining the scene environment as a line scene; the non-line scenes comprise construction site scenes, reservoir scenes and the like; the warning area in the non-line scene has certain specificity and is a whole picture; in a line scene, the target itself is often concerned; the association between the tower and the wire means that the wire belongs to the tower, wherein the specific judging method is as follows:
s21, obtaining a region with the most dense wire intersection points according to all the wires, wherein in some embodiments, the region with the most dense wire intersection points can be obtained through a wire intersection point clustering method or a sliding window method; if the tower is positioned in the area with the most dense intersection points of the wires, the tower is associated with the wires, otherwise, the tower is not associated with the wires;
the clustering algorithm adopts a K-means clustering algorithm, and K-means can be used for acquiring a wire intersection point gathering area; the sliding window method is to set a window with a specified size, calculate the number of wire intersection points in the window, then set a sliding step length, slide the window, finally obtain the window with the maximum number of intersection points as a wire intersection point gathering area; according to the physical relationship of the wires in the image, the wire intersection point gathering area and the iron tower are in certain relevance, the two areas are close to each other in the vertical direction (the reason that the wires are not close to each other in the horizontal direction is that the wires are bent when approaching to the vicinity of the iron tower), and therefore the relevance of the iron tower and the wires can be judged by the method.
S3, obtaining a target alarm region according to all the power grid targets; the target alarm area refers to an area with potential safety hazards when a target enters the area, namely, the target alarm area is used for analyzing the characteristics of the target alarm area in the power transmission line, calculating and dividing the target alarm area, and specifically:
s31, obtaining a tower alarm region according to the position of the tower, wherein the tower alarm region comprises a tower body and a peripheral region, and a detection frame in the detection of a deep learning target detection algorithm can be used as the tower alarm region; the peripheral area of the pole tower can be obtained by amplifying according to a certain proportion according to the detection frame;
s32, obtaining a line alarming area according to an area surrounded by the pole tower and the wire, wherein the line alarming area comprises the wire and a peripheral area, and in an optional implementation manner, the line alarming area is obtained through the following steps:
referring to fig. 2, S321, a detection frame is obtained according to the position of the tower, and a lower vertex of the detection frame is taken as an example to describe the detection frame, so as to obtain a lower left point T1 (T1 x, T1 y) of the detection frame and a lower right point T2 (T2 x, T2 y) of the detection frame;
s322, obtaining a detection boundary line according to the position of the wire at the outermost side of the tower, namely obtaining a left detection boundary line L and a right detection boundary line L; the calculation method is described by taking the left detection boundary line L as an example, and specifically includes the following steps:
s3221, creating a BGR image with the same size as the input image, and filling the colors (0, 0); the vertex coordinates are (upper left- > upper right- > lower left- >) respectively: a (ax, ay), B (bx, by), C (cx, cy), and D (dx, dy);
s3222, drawing the detected wires, and filling the colors (255 );
s3223, traversing the input image, and finding a left point set (the first color in each row of the image is a set of (255, 255) points) according to the filling color;
s3224, performing curve fitting on the obtained left point set, and removing isolated points in the left point set to obtain a fitting equation;
s3225, dividing the left point set into a preset number of intervals according to the y value range, if taking 20 intervals as an example, obtaining [ y0,.,. Y19], substituting a fitting equation, and calculating a corresponding x value to obtain a point set S: [ [ x0, y0], [ x19, y19] ]; the purpose of the calculation point set S is to reduce the calculation amount of searching edge points;
s3226, calculating left edge points: LP (xp, yp) is any point in the point set S, and when the absolute value of the slope of T1LP is minimum, LP is the left edge point to obtain L1 (L1 x, L1 y); similarly, right edge points L2 (L2 x, L2 y);
s323, the detection boundary line comprises a first end point connected with the vertex of the detection frame and a second end point intersected with the first edge of the power transmission line graph; the first end points are the T1 (T1 x, T1 y) and T2 (T2 x, T2 y); the second end points are T1L1 connecting lines and intersection points of extension lines and the upper edges of the images, namely a left second end point C11 (C11 x, C11 y) and a right second end point C12 (C12 x, C12 y) are obtained through calculation according to the T1L1 and the images; meanwhile, C11 may be located on the extension line of AB, the calculation method is unchanged, and the part inside the image is taken when the alarm area is at last; c12 is obtained by the same method;
s324, obtaining the line alarm area according to the area surrounded by the first endpoint and the second endpoint; the line alarm area is obtained according to an area surrounded by a left first endpoint T1 (T1 x, T1 y), a right first endpoint T2 (T2 x, T2 y), a left second endpoint C11 (C11 x, C11 y) and a right second endpoint C12 (C12 x, C12 y);
in another alternative embodiment, the method further comprises the steps of:
s325, projecting the detection boundary line to a second edge of the power transmission line graph to obtain a third point; the second edge is parallel to the first edge; let the third end point on the left be C21, then C21 is the mapping point of C11 at the bottom of the image, get C21 (C21 x, C21 y); wherein c21 x=c11x, c21y=image height H; similarly, C22 is the mapping point of C12 at the bottom of the image, and C22 (C22 x, C22 y) is obtained;
s326, a first sub-line alarm area is obtained according to an area surrounded by the first endpoint and the second endpoint; the first sub-line alarm area is obtained according to an area surrounded by a left first endpoint T1 (T1 x, T1 y), a right first endpoint T2 (T2 x, T2 y), a left second endpoint C11 (C11 x, C11 y) and a right second endpoint C12 (C12 x, C12 y);
s327, a second sub-line alarm area is obtained according to an area surrounded by the first end point and the third end point; namely, the second sub-line alarm area is obtained according to an area surrounded by a left first end point T1 (T1 x, T1 y), a right first end point T2 (T2 x, T2 y), a left third end point C21 (C21 x, C21 y) and a right third end point C22 (C22 x, C22 y);
in an optional implementation manner, the target alarm area can be enlarged or reduced according to a preset proportion; such as: expanding the line segments T1T2 and T1T2 by 10%, and obtaining a new left first endpoint T1 'and a new right first endpoint T2' respectively when the centers are unchanged; c11': the line segments C11C12, C21C22 and C21C22 are obtained by expanding 10%, and the centers are unchanged, so that new left second end point C11', right second end point C12', left third end point C21 'and right third end point C22' are respectively obtained; the detectable range is enlarged through a preset proportion; currently set to 10% of the hidden trouble area; if the original tower hidden trouble area is a rectangular area with the width of 100 pixels and the height of 200 pixels, the enlarged area is 110 pixels wide and 220 pixels high, and the center point is unchanged; the larger the expansion ratio, the more sensitive the alarm.
S4, judging the type of the non-power grid target to obtain a target hazard level, namely analyzing the characteristics of the non-power grid target in the power transmission line and dividing the non-power grid target; wherein the non-grid target characteristics include a target hazard level and a target physical characteristic; the target hazard level comprises a general target, an important target and a dangerous target; the physical characteristics of the target are the activity space range of the target; marking the non-grid targets as general targets, important targets or dangerous targets according to the type of the non-grid targets, as follows:
dangerous target: the target may cause significant hazards such as forest fires, smoke, etc.;
important targets: the target vertical space has wide moving range; targets that may cause damage to the poles and wires; such as long arm excavators, tower cranes, pile drivers, etc.;
general goals: the target vertical space has a narrow moving range; may pose a hazard to the mast but is unlikely to pose a threat to the wire, such as bulldozers, forklift trucks, etc.;
s5, judging whether the non-power grid target is a hidden danger target or not according to the scene environment, the target warning area and the target hazard level, wherein the method specifically comprises the following steps of:
(1) In a non-line scene, all non-grid targets are hidden danger targets;
(2) In a line scene, all dangerous targets are hidden danger targets;
(3) In the line scene, the important target is a hidden danger target only when the intersection exists between the important target and the line alarm region or the tower alarm region;
(4) In the line scene, the general target is a hidden danger target only when the intersection exists between the general target and the tower alarm region.
Example two
The present embodiment describes the steps in the first embodiment through an actual detection scenario:
scene one, please refer to fig. 3, is a non-line scene detection:
a1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; namely, an original figure 3 is obtained, and a tower in the picture, such as a rectangle in the figure, is detected by using a Yolov5 target detection algorithm; and detecting the wire in the picture using a fast straight line detection algorithm (FLD), detecting no wire in fig. 3; meanwhile, a YOLOv5 target detection algorithm is used for detecting targets such as construction machinery in the picture, namely, rectangles in fig. 3; wherein, the power grid target and the non-power grid target can be distinguished by detection frames with different colors;
a2, judging a scene environment corresponding to the power transmission line graph according to the power grid target; because no wires are detected in fig. 3, the current scene environment is a non-line scene;
a3, obtaining a target alarm region according to all the power grid targets; namely, a corresponding target alarm area is obtained according to a rectangular frame corresponding to the tower;
a4, judging the type of the non-power grid target to obtain a target hazard level; the non-power grid target is a construction machine, and belongs to an important target;
a5, judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level; the targets in the current picture are hidden danger targets because of non-line scenes; meanwhile, when the scene is a non-line scene and a non-grid target exists, the steps A3 and A4 can be skipped to directly judge.
Scenario two, please refer to fig. 4, is a non-line scenario:
b1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; namely, acquiring an original figure 4, and detecting a tower, a wire and a non-power grid target by adopting the same method as in a first scene; a construction machine as in the rectangular inspection frame of fig. 4;
b2, judging a scene environment corresponding to the power transmission line graph according to the power grid target; although there are towers and wires in fig. 4, they are not associated, so the current scenario is a non-line scenario; for fig. 4, the small poles in the line are not in the identified range, so the current scene is still judged as a non-line scene although there are wires but the wires do not correspond to the towers; for a line scene, interference of transverse wires may exist, but the corresponding relation is determined by a wire intersection gathering area, and a small number of transverse wires cannot influence final association judgment;
because of the non-line scene and the non-grid target, the step B3 is directly executed by skipping the corresponding judging step;
b3, judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level; the targets in the current picture are all hidden danger targets due to the non-line scene.
Scene three, please refer to fig. 5, is a line scene:
c1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; namely, acquiring an original figure 5, and detecting a tower, a wire and a non-power grid target by adopting the same method as in a first scene; towers in rectangular detection boxes as in fig. 5, and non-grid targets-fumes;
c2, judging a scene environment corresponding to the power transmission line graph according to the power grid target; the wires in fig. 5 have corresponding towers, so the wires are associated with towers as a line scene;
c3, obtaining a target alarm region according to all the power grid targets; namely, according to the step in the first embodiment, a corresponding target alarm area is obtained;
c4, judging the type of the non-power grid target to obtain a target hazard level; the non-power grid target is a construction machine, and belongs to an important target; the non-power grid target is smoke, namely judging that the smoke is a dangerous target;
c5, judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level; smoke is a dangerous target that, although not within the target alert zone, is still a potential target.
Scene 4, please refer to fig. 6, is a line scene:
d1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; namely, acquiring an original figure 6, and detecting a tower, a wire and a non-power grid target by adopting the same method as in a first scene; towers, wire borderlines and non-grid target-dumpers in rectangular detection boxes as in fig. 6;
d2, judging a scene environment corresponding to the power transmission line graph according to the power grid target; the wires in fig. 6 have corresponding towers, so the wires are associated with towers as a line scene;
d3, obtaining a target alarm region according to all the power grid targets; namely, according to the step in the first embodiment, a corresponding target alarm area is obtained;
d4, judging the type of the non-power grid target to obtain a target hazard level; the non-power grid target is a construction machine, and belongs to an important target; the non-power grid target is a dump truck, namely the dump truck is judged to be a general target;
d5, judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level; the dump truck is a general target, and although the target is in the line warning area, the target is not in the tower warning area, so the target is a non-hidden danger target.
Scene 5, please refer to fig. 7, is a line scene:
e1, acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; i.e. obtaining the original figure 7, and detecting the tower, the wire and the non-grid targets by adopting the same method as in the first scene; the towers, wire boundary lines, and non-grid target-cranes in the rectangular test frame as in fig. 7;
e2, judging a scene environment corresponding to the power transmission line graph according to the power grid target; the wires in fig. 6 have corresponding towers, so the wires are associated with towers as a line scene;
e3, obtaining a target alarm region according to all the power grid targets; namely, according to the step in the first embodiment, a corresponding target alarm area is obtained;
e4, judging the type of the non-power grid target to obtain a target hazard level; the non-power grid target is a construction machine, and belongs to an important target; the non-power grid target is a crane, namely the crane is judged to be an important target;
e5, judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level; the crane is an important target and the target is within the line warning area, so the target is a hidden danger target.
Example III
Referring to fig. 8, an apparatus for analyzing hidden danger of a power transmission line includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for analyzing hidden danger of a power transmission line according to the first and second embodiments when executing the computer program.
In summary, the method and the device for analyzing hidden danger of the power transmission line provided by the invention comprise the steps of obtaining a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram; judging a scene environment corresponding to the power transmission line graph according to the power grid target; obtaining a target alarm region according to all the power grid targets; judging the type of the non-power grid target to obtain a target hazard level; judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level. The method comprises the steps of identifying all power grid targets and non-power grid targets in a power transmission line graph, analyzing scene characteristics of the power transmission line based on the power grid targets, calculating to obtain corresponding target alarm areas, obtaining hazard levels of the non-power grid targets in a power transmission scene based on the analysis of the non-power grid targets, judging the identified non-power grid targets based on scene environments, target alarm areas and target hazard levels corresponding to the power transmission line graph, analyzing scene characteristics, power grid targets and characteristics of the non-power grid targets, reducing false alarm rate of target alarms, improving identification effect of the target alarms in specific scenes, and avoiding missing alarm problems.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent changes made by the specification and drawings of the present invention, or direct or indirect application in the relevant art, are included in the scope of the present invention.
Claims (10)
1. The utility model provides a transmission line hidden danger analysis method which is characterized in that the method comprises the following steps:
acquiring a power transmission line diagram to be analyzed, and identifying all power grid targets and non-power grid targets in the power transmission line diagram;
judging a scene environment corresponding to the power transmission line graph according to the power grid target;
obtaining a target alarm region according to all the power grid targets;
judging the type of the non-power grid target to obtain a target hazard level;
judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the target hazard level.
2. The method for analyzing hidden danger of a power transmission line according to claim 1, wherein the power grid object comprises a tower and a wire;
the judging the scene environment corresponding to the power transmission line graph according to the power grid target comprises the following steps:
judging whether the tower is associated with the wire or not, if so, determining that the scene environment is a line scene; if not, determining the scene environment as a non-line scene;
the judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the non-power grid target characteristics comprises the following steps:
if the scene environment is the non-line scene and comprises the non-power grid target, the non-power grid target is a hidden danger target.
3. The method of claim 2, wherein determining whether the tower is associated with the wire comprises:
obtaining a region with the most dense wire crossing points according to all the wires;
if the towers are located in the area with the most dense intersection points of the wires, the towers are associated with the wires, otherwise, the towers are not associated with the wires.
4. A method for analyzing hidden danger of a power transmission line according to claim 3, wherein said obtaining a region where intersection points of wires are most dense according to all the wires comprises:
and obtaining the area with the most dense wire intersection points through a wire intersection point clustering method or a sliding window method.
5. The method of claim 2, wherein obtaining the target alert area according to all the grid targets comprises:
obtaining a tower alarm area according to the position of the tower;
and obtaining a line alarm area according to the area surrounded by the pole tower and the wire.
6. The method for analyzing hidden danger of a power transmission line according to claim 5, wherein the obtaining a line alarm area according to an area surrounded by the tower and the wire comprises:
obtaining a detection frame according to the position of the tower;
obtaining a detection boundary line according to the position of the wire at the outermost side of the tower;
the detection boundary line comprises a first end point connected with the vertex of the detection frame and a second end point intersected with the first edge of the power transmission line graph;
and obtaining the line alarm region according to the region surrounded by the first endpoint and the second endpoint.
7. The method for analyzing hidden danger of a power transmission line according to claim 6, wherein the obtaining a line alarm area according to an area surrounded by the tower and the wire further comprises:
projecting the detection boundary line to the second edge of the power transmission line graph to obtain a third end point; the second edge is parallel to the first edge;
obtaining a first sub-line alarm area according to an area surrounded by the first endpoint and the second endpoint;
and obtaining a second sub-line alarm area according to the area surrounded by the first end point and the third end point.
8. The method for analyzing hidden danger of a power transmission line according to claim 2, further comprising:
and expanding or shrinking the target alarm area according to a preset proportion.
9. The method for analyzing hidden danger of a power transmission line according to claim 2, wherein the target hazard level includes a general target, an important target and a dangerous target;
the judging of the type of the non-power grid target, the obtaining of the target hazard level comprises the following steps:
marking the non-grid targets as general targets, important targets or dangerous targets according to the types of the non-grid targets;
the judging whether the non-power grid target is a hidden danger target according to the scene environment, the target warning area and the non-power grid target characteristics comprises the following steps:
if the scene environment is the line scene and the non-power grid target is the dangerous target, the non-power grid target is a hidden danger target.
10. A power transmission line hidden trouble analysis device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor when executing the computer program implements the steps of a power transmission line hidden trouble analysis method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311606266.6A CN117314022B (en) | 2023-11-29 | Method and device for analyzing hidden danger of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311606266.6A CN117314022B (en) | 2023-11-29 | Method and device for analyzing hidden danger of power transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117314022A true CN117314022A (en) | 2023-12-29 |
| CN117314022B CN117314022B (en) | 2024-05-28 |
Family
ID=
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223071A (en) * | 2019-11-20 | 2020-06-02 | 智洋创新科技股份有限公司 | Power transmission line scene semantic understanding method based on deep learning technology |
| CN112766689A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Method and device for dividing maintenance-patrolling route of power transmission line |
| CN114037900A (en) * | 2021-10-09 | 2022-02-11 | 国网江苏省电力有限公司南京供电分公司 | Power transmission line channel visual grading early warning method combined with scene analysis |
| CN115841487A (en) * | 2023-02-20 | 2023-03-24 | 深圳金三立视频科技股份有限公司 | Hidden danger positioning method and terminal along power transmission line |
| US20230095882A1 (en) * | 2020-07-31 | 2023-03-30 | Electric Power Research Institute Of Guangxi Power Grid Co., Ltd. | In-Place Supervision Method and Apparatus Suitable for Overhead Transmission Line Maintenance Operation |
| CN115995043A (en) * | 2023-02-16 | 2023-04-21 | 深圳金三立视频科技股份有限公司 | Transmission line hidden danger target identification method and computer readable storage medium |
| WO2023174020A1 (en) * | 2022-03-18 | 2023-09-21 | 广东电网有限责任公司东莞供电局 | Power transmission line detection method and apparatus, computer device, and storage medium |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223071A (en) * | 2019-11-20 | 2020-06-02 | 智洋创新科技股份有限公司 | Power transmission line scene semantic understanding method based on deep learning technology |
| US20230095882A1 (en) * | 2020-07-31 | 2023-03-30 | Electric Power Research Institute Of Guangxi Power Grid Co., Ltd. | In-Place Supervision Method and Apparatus Suitable for Overhead Transmission Line Maintenance Operation |
| CN112766689A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Method and device for dividing maintenance-patrolling route of power transmission line |
| CN114037900A (en) * | 2021-10-09 | 2022-02-11 | 国网江苏省电力有限公司南京供电分公司 | Power transmission line channel visual grading early warning method combined with scene analysis |
| WO2023174020A1 (en) * | 2022-03-18 | 2023-09-21 | 广东电网有限责任公司东莞供电局 | Power transmission line detection method and apparatus, computer device, and storage medium |
| CN115995043A (en) * | 2023-02-16 | 2023-04-21 | 深圳金三立视频科技股份有限公司 | Transmission line hidden danger target identification method and computer readable storage medium |
| CN115841487A (en) * | 2023-02-20 | 2023-03-24 | 深圳金三立视频科技股份有限公司 | Hidden danger positioning method and terminal along power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232320B (en) | Method and system for detecting danger of workers approaching construction machinery on construction site in real time | |
| CN110136273B (en) | Sample data labeling method and device used in machine learning | |
| CN112102409B (en) | Target detection method, device, equipment and storage medium | |
| CN104933387A (en) | Rapid positioning and identifying method based on two-dimensional code decoding | |
| CN111626277B (en) | Vehicle tracking method and device based on over-station inter-modulation index analysis | |
| US20150117835A1 (en) | Information processing apparatus, control method and program | |
| US9928429B2 (en) | Image processing apparatus and image processing method | |
| CN111626275B (en) | Abnormal parking detection method based on intelligent video analysis | |
| CN112802302B (en) | Electronic fence method and system based on multi-source algorithm | |
| CN104282011A (en) | Method and device for detecting interference stripes in video images | |
| CN112149649B (en) | Road spray detection method, computer equipment and storage medium | |
| CN109001757A (en) | A kind of parking space intelligent detection method based on 2D laser radar | |
| CN110379168A (en) | A kind of vehicular traffic information acquisition method based on Mask R-CNN | |
| CN107491738A (en) | Parking space detection method and system, storage medium and electronic equipment | |
| CN107609555A (en) | Detection method of license plate, model recognizing method and relevant apparatus using it | |
| Chian et al. | Dynamic identification of crane load fall zone: A computer vision approach | |
| CN107154034A (en) | The condition detection method and system of a kind of high ferro contact net lateral conductor location hook | |
| CN104079798B (en) | Image detecting method, device and a kind of video monitoring system | |
| CN117314022B (en) | Method and device for analyzing hidden danger of power transmission line | |
| CN109558765A (en) | The detection method of automobile and lane line, device | |
| CN117314022A (en) | Method and device for analyzing hidden danger of power transmission line | |
| CN108629225A (en) | A kind of vehicle checking method based on several subgraphs and saliency analysis | |
| CN113240682A (en) | Overturn-preventing construction driving map generation method and system for crawler crane | |
| JP3883124B2 (en) | Template matching processing method and processing apparatus in image processing | |
| CN113032272A (en) | Automatic parking system test evaluation method, device, equipment and storage medium |
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 |