CN115830450A - Method and device for monitoring potential hazard of power transmission line tree obstacle - Google Patents
Method and device for monitoring potential hazard of power transmission line tree obstacle Download PDFInfo
- Publication number
- CN115830450A CN115830450A CN202211534803.6A CN202211534803A CN115830450A CN 115830450 A CN115830450 A CN 115830450A CN 202211534803 A CN202211534803 A CN 202211534803A CN 115830450 A CN115830450 A CN 115830450A
- Authority
- CN
- China
- Prior art keywords
- tree
- point
- point cloud
- power transmission
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a method and a device for monitoring potential tree obstacle hazards of a power transmission line, which are used for monitoring the potential tree obstacle hazards based on a power transmission channel monitoring image and power transmission channel point cloud, and comprise the following steps: dividing trees in the point cloud of the power transmission channel into a plurality of groups through connectivity; mapping each group of trees in the power transmission channel point cloud to the monitoring image; identifying a tree area in the monitored image, and comparing the tree area mapped to the monitored image by the point cloud; and calculating the height of the trees in the image according to the comparison result, and calculating the distance between the trees in the image and the wire of the power transmission line. When the hidden danger of the power transmission line channel is transported and detected, the damage degree of the hidden danger of the tree obstacle can be rapidly judged, the damage of the tree to the conducting wire due to the growth of the tree is avoided, and the technical support is provided for the safety guarantee of the power transmission line.
Description
Technical Field
The invention relates to a method and a device for monitoring potential hazard of a tree obstacle of a power transmission line, and belongs to the technical field of intelligent operation and inspection of the power transmission line.
Background
The power transmission channel has complex and various scenes, wherein trees are near a plurality of power transmission lines, and the trees are too far away from the wires, so that the wires are easy to discharge, and the trees near the power transmission lines are at great risk to the power transmission lines.
When the weather is windy, the wire and the tree can shake, the possibility that the distance between the tree and the wire is further reduced exists, and accidents are more easily caused. The hidden danger of tree obstacle is the problem that transmission line intelligence patrolled and examined key concern, and current commonly used prevention and control means has the manual work to patrol and examine, visual monitoring, unmanned aerial vehicle patrols and examines etc. and these several kinds of modes of patrolling and examining can effectively avoid the harm of hidden danger of tree obstacle, nevertheless also exist simultaneously inadequately, and the mode of patrolling and examining needs consume a large amount of costs of labor, and the degree of accuracy that visual monitoring's mode was judged true distance is relatively poor, and unmanned aerial vehicle patrols and examines the price and costsly, and unable frequent patrolling and examining.
In summary, how to provide a method for monitoring the hidden danger of the tree obstacle of the power transmission line, which is efficient, accurate and low in cost, and reduce the hidden danger of the tree obstacle is one of the problems to be solved urgently by the technical staff in the field at present.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a device for monitoring the damage of the hidden danger of the tree obstacle of the power transmission line, which can judge the damage degree of the hidden danger of the tree obstacle, avoid the damage of the growth of trees to a lead and provide technical support for the safety guarantee of the power transmission line.
The technical scheme adopted for solving the technical problems is as follows:
in a first aspect, the method for monitoring the potential hazards of the tree barriers of the power transmission line provided by the embodiment of the invention is used for monitoring the potential hazards of the tree barriers based on the power transmission channel monitoring image and the power transmission channel point cloud, and comprises the following steps:
dividing trees in the point cloud of the power transmission channel into a plurality of groups through connectivity;
mapping each group of trees in the power transmission channel point cloud to the monitoring image;
identifying a tree area in the monitored image, and comparing the tree area mapped to the monitored image by the point cloud;
and calculating the height of the trees in the image according to the comparison result, and calculating the distance between the trees in the image and the wire of the power transmission line.
As a possible implementation manner of this embodiment, the dividing trees in the point cloud of the power transmission channel into multiple groups through connectivity includes:
a1: setting a segmentation threshold s, target point p 0 Set of tree points T = { p = { (p) 0 }；
a2: adding all points with a distance less than s from the target point into the set T, namely T = { p = { (p) 0 ,p 1 ,p 2 A survey, and removing points added to the set from the point cloud;
a3: setting the target point as the next point of the current target point;
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a divided tree region;
a5: reselecting a target point p in a point cloud 0 Repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: and (5) forming a Tree set Tree by using all sets T with more than 100 points.
As a possible implementation manner of this embodiment, the mapping each group of trees in the power transmission channel point cloud onto the monitoring image includes:
mapping each group of trees in the power transmission channel point cloud to a monitoring image, and recording pixel points and three-dimensional points corresponding to the pixel points, wherein the mapping formula for mapping each group of trees in the power transmission channel point cloud to the monitoring image is as follows:
temp＝(p-T)·R
m＝(M·temp T ) T
m = m ÷ m (0, 2) (homogeneous transformation)
Wherein p is a three-dimensional point, M is a two-dimensional point, R is a point cloud rotation matrix, T is a point cloud translation vector, and M is a camera internal reference matrix.
As a possible implementation manner of this embodiment, the identifying a tree region in the monitored image and comparing the tree region with the tree region mapped on the monitored image by the point cloud includes:
c1: a, mapping the point cloud to a tree region set on the monitored image, and D identifying the tree region set in the monitored image;
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD;
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
As a possible implementation manner of this embodiment, the corresponding pixel points refer to the pixel coordinate systems having the same x coordinate, and the matching error is considered when the y coordinate difference is smaller than 20 and the y coordinate difference is larger than 20.
As a possible implementation manner of this embodiment, the calculating the height of the tree in the image according to the comparison result, and calculating the distance between the tree in the image and the wire of the power transmission line includes:
d1: upper boundary t a In each pixel point is marked as m a (u a ,v a )，m a (u a ,v a ) The corresponding three-dimensional point is denoted as p a (x a ,y a ,z a )，m a (u a ,v a ) The corresponding pixel point is marked as d a (u a ,v d ) If m is a (u a ,v a ) Skipping the pixel point if the corresponding pixel point does not exist;
d2: calculating pixel difference: diff is a unit of a product a ＝(v d -v a )；
d3: according to the camera imaging principle
Calculating diff a Corresponding true height H a Where f is the focal lengthL is the distance of the object plane from the camera plane, H is the pixel height, and H is the true height;
d4: calculating tree three-dimensional point p a (x a ,y a ,z a ) Corresponding three-dimensional coordinate p d (x a ,y a ,z a +H a )；
d5: calculating all conducting wire points and three-dimensional coordinates p d (x a ,y a ,z a +H a ) Finding the nearest wire point and the nearest distance;
d6: upper boundary t a All corresponding wire closest points form a set Near, and all the closest distances form a set Dis;
d7: and selecting the minimum value in the set Dis as the shortest distance between the tree area and the wire.
In a second aspect, the monitoring device for monitoring potential tree obstacle hazards of a power transmission line provided in an embodiment of the present invention is configured to monitor potential tree obstacle hazards based on a power transmission channel surveillance image and power transmission channel point cloud, and the device includes:
the tree grouping module is used for dividing the trees in the point cloud of the power transmission channel into a plurality of groups through connectivity;
the point cloud mapping module is used for mapping each group of trees in the point cloud of the power transmission channel to the monitoring image;
the tree area comparison module is used for identifying a tree area in the monitored image and comparing the tree area with the tree area mapped to the monitored image by the point cloud;
and the distance calculation module is used for calculating the height of the trees in the image according to the comparison result and calculating the distance between the trees in the image and the wire of the power transmission line.
As a possible implementation manner of this embodiment, the specific process of dividing the trees in the point cloud of the power transmission channel into multiple groups by the tree grouping module through connectivity is as follows:
a1: setting a segmentation threshold s, target point p 0 Set of tree points T = { p = { (p) 0 }；
a2: adding all points with a distance less than s from the target point into the set T, namely T = { p = { (p) 0 ,p 1 ,p 2 A survey, and removing points added to the set from the point cloud;
a3: setting the target point as the next point of the current target point;
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a divided tree region;
a5: reselecting a target point p from the point cloud 0 Repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: and (5) forming a Tree set Tree by using all sets T with more than 100 points.
As a possible implementation manner of this embodiment, the point cloud mapping module maps each group of trees in the point cloud of the power transmission channel to the monitored image according to a mapping formula:
temp＝(p-T)·R
m＝(M·temp T ) T
m = m ÷ m (0, 2) (homogeneous transformation)
Wherein p is a three-dimensional point, M is a two-dimensional point, R is a point cloud rotation matrix, T is a point cloud translation vector, and M is a camera internal reference matrix.
As a possible implementation manner of this embodiment, the tree region comparison module identifies a tree region in the monitored image, and a specific process of comparing the tree region with a tree region mapped by the point cloud onto the monitored image is as follows:
c1: a, mapping the point cloud to a tree region set on the monitored image, and D identifying the tree region set in the monitored image;
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD;
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
As a possible implementation manner of this embodiment, the corresponding pixel points refer to the pixel coordinate systems having the same x coordinate, and the matching error is considered when the y coordinate difference is smaller than 20 and the y coordinate difference is larger than 20.
As a possible implementation manner of this embodiment, the specific process of calculating the height of the tree in the image according to the comparison result and calculating the distance between the tree in the image and the power transmission line lead by the distance calculation module is as follows:
d1: upper boundary t a In each pixel point is marked as m a (u a ,v a )，m a (u a ,v a ) The corresponding three-dimensional point is denoted as p a (x a ,y a ,z a )，m a (u a ,v a ) The corresponding pixel point is marked as d a (u a ,v d ) If m is a (u a ,v a ) Skipping the pixel point if the corresponding pixel point does not exist;
d2: calculating pixel difference: diff (diff) a ＝(v d -v a )；
d3: according to the camera imaging principle
Calculating diff a Corresponding true height H a Where f is the focal length, L is the distance of the object plane from the camera plane, H is the pixel height, and H is the true height;
d4: calculating tree three-dimensional point p a (x a ,y a ,z a ) Corresponding three-dimensional coordinate p d (x a ,y a ,z a +H a )；
d5: calculating all conducting wire points and three-dimensional coordinates p d (x a ,y a ,z a +H a ) Finding the nearest wire point and the nearest distance;
d6: upper boundary t a All corresponding wire closest points form a set Near, and all the closest distances form a set Dis;
d7: and selecting the minimum value in the set Dis as the shortest distance between the tree area and the wire.
The technical scheme of the embodiment of the invention has the following beneficial effects:
the method adopts the technologies of tree connected domain division, image and point cloud mapping, area comparison and the like, realizes automatic division of trees in the power transmission line channel, calculates the shortest distance between each tree area and a wire, infers the tree growth condition in the image according to the tree identification result, can perform risk grade division according to the tree distance measurement result, timely finds and processes the potential tree obstacle hazard which may cause harm to the power transmission channel line, enhances the control strength of the power transmission channel, and the operation and inspection personnel can more accurately control the tree height, thereby reducing the accident caused by the potential tree obstacle.
Compared with a manual inspection or visual inspection method, the method disclosed by the invention has the advantages that based on the monitoring image and the three-dimensional point cloud, the precision and the management and control strength of the tree obstacle hidden danger distance measurement are greatly improved, and the inspection is more convenient.
The method can collect the point cloud only once, perform long-term tree obstacle hidden danger ranging through subsequent monitoring images, and update the point cloud once again if the scene changes greatly, so that compared with a mode of unmanned aerial vehicle inspection or point cloud analysis, the method greatly reduces inspection cost.
The method calculates the shortest distance between the tree and the wire, can divide the hidden danger hazard grades according to different distances, and better controls the power transmission line.
When the hidden danger of the power transmission line channel is transported and detected, the damage degree of the hidden danger of the tree obstacle can be rapidly judged, the damage of the tree to the conducting wire due to the growth of the tree is avoided, and the technical support is provided for the safety guarantee of the power transmission line.
Drawings
Fig. 1 is a flowchart illustrating a method for monitoring damage of a potential fault of a power transmission line tree according to an exemplary embodiment;
fig. 2 is a schematic diagram illustrating a monitoring device for monitoring potential hazards of a power transmission line tree obstacle according to an exemplary embodiment;
FIG. 3 illustrates a power transmission channel surveillance image in accordance with an exemplary embodiment;
FIG. 4 illustrates a cloud of transmission lines in a transmission channel according to an exemplary embodiment;
FIG. 5 is a point cloud diagram illustrating a tree in a power transmission channel according to an exemplary embodiment;
FIG. 6 is a schematic diagram illustrating an acquisition of eligible tree regions in accordance with an exemplary embodiment;
fig. 7 is a diagram illustrating the mapping effect of trees in a power transmission channel point cloud onto a surveillance image according to an exemplary embodiment;
FIG. 8 is a diagram illustrating tree region identification effects in a surveillance image according to an exemplary embodiment
Fig. 9 is a graph illustrating a ranging result of a tree and a power transmission line conductor according to an exemplary embodiment.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
in order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
As shown in fig. 1, the method for monitoring the potential hazards of the tree-obstacle of the power transmission line provided by the embodiment of the invention is used for monitoring the potential hazards of the tree-obstacle based on the power transmission channel monitoring image and the power transmission channel point cloud, and the method comprises the following steps:
dividing trees in the point cloud of the power transmission channel into a plurality of groups through connectivity;
mapping each group of trees in the power transmission channel point cloud to the monitoring image;
identifying a tree area in the monitored image, and comparing the tree area mapped to the monitored image by the point cloud;
and calculating the height of the trees in the image according to the comparison result, and calculating the distance between the trees in the image and the wire of the power transmission line.
As a possible implementation manner of this embodiment, the dividing trees in the point cloud of the power transmission channel into multiple groups by connectivity includes:
a1: setting a segmentation threshold s, target point p 0 Set of tree points T = { p = { (p) 0 }；
a2: adding all points with a distance less than s from the target point into the set T, namely T = { p = { (p) 0 ,p 1 ,p 2 A look, and remove points added to the collection from the point cloud;
a3: setting the target point as the next point of the current target point;
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a divided tree region;
a5: reselecting a target point p in a point cloud 0 Repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: and (5) forming a Tree set Tree by using all sets T with more than 100 points.
As a possible implementation manner of this embodiment, the mapping each group of trees in the power transmission channel point cloud onto the monitoring image includes:
mapping each group of trees in the power transmission channel point cloud to a monitoring image, and recording pixel points and three-dimensional points corresponding to the pixel points, wherein the mapping formula for mapping each group of trees in the power transmission channel point cloud to the monitoring image is as follows:
temp＝(p-T)·R
m＝(M·temp T ) T
m = m ÷ m (0, 2) (homogeneous transformation)
Wherein p is a three-dimensional point, M is a two-dimensional point, R is a point cloud rotation matrix, T is a point cloud translation vector, and M is a camera internal reference matrix.
As a possible implementation manner of this embodiment, the identifying a tree region in the monitored image and comparing the tree region with the tree region mapped on the monitored image by the point cloud includes:
c1: a, mapping the point cloud to a tree region set on the monitored image, and D identifying the tree region set in the monitored image;
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD;
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
As a possible implementation manner of this embodiment, the corresponding pixel points refer to the pixel coordinate systems having the same x coordinate, and the matching error is considered when the y coordinate difference is smaller than 20 and the y coordinate difference is larger than 20.
As a possible implementation manner of this embodiment, the calculating the height of the tree in the image according to the comparison result, and calculating the distance between the tree in the image and the power transmission line lead includes:
d1: upper boundary t a In each pixel point is marked as m a (u a ,v a )，m a (u a ,v a ) The corresponding three-dimensional point is denoted as p a (x a ,y a ,z a )，m a (u a ,v a ) The corresponding pixel point is marked as d a (u a ,v d ) If m is a (u a ,v a ) Skipping the pixel point if the corresponding pixel point does not exist;
d2: calculating pixel difference: diff (diff) a ＝(v d -v a )；
d3: according to the camera imaging principle
Calculating diff a Corresponding true height H a Where f is the focal length, L is the distance of the object plane from the camera plane, H is the pixel height, and H is the true height;
d4: calculating tree three-dimensional point p a (x a ,y a ,z a ) Corresponding three-dimensional coordinate p d (x a ,y a ,z a +H a )；
d5: calculating all conducting wire points and three-dimensional coordinates p d (x a ,y a ,z a +H a ) Finding the nearest wire point and the nearest distance;
d6: upper boundary t a All the corresponding nearest points of the leads form a set Near, and all the nearest distances form a set Dis;
d7: and selecting the minimum value in the set Dis as the shortest distance between the tree area and the wire.
As shown in fig. 2, the monitoring device for monitoring potential hazards of a power transmission line tree-obstacle provided by the embodiment of the present invention monitors potential hazards of a tree-obstacle based on a power transmission channel monitoring image and power transmission channel point cloud, and the device includes:
the tree grouping module is used for dividing the trees in the point cloud of the power transmission channel into a plurality of groups through connectivity;
the point cloud mapping module is used for mapping each group of trees in the point cloud of the power transmission channel to the monitoring image;
the tree area comparison module is used for identifying a tree area in the monitored image and comparing the tree area with the tree area mapped to the monitored image by the point cloud;
and the distance calculation module is used for calculating the height of the trees in the image according to the comparison result and calculating the distance between the trees in the image and the wire of the power transmission line.
The monitoring device for the potential tree-obstacle hazard damage of the power transmission line provided by the embodiment of the invention is adopted to monitor the potential tree-obstacle hazard based on the power transmission channel monitoring image and the power transmission channel point cloud as follows.
Firstly, an image and a point cloud file shot by a certain section of power transmission line channel are obtained, camera internal reference, a rotation matrix and a translation vector are obtained, the distance between the hidden danger of the tree obstacle and a lead in the power transmission line channel is calculated, and the error of the ranging result of the hidden danger of the tree obstacle is about 1m through field actual measurement. The device image and the point cloud image are shown in fig. 3 and 4, wherein the point cloud of the tree is shown in fig. 5.
a. Dividing the trees in the point cloud into a plurality of groups to form a Tree set Tree through connectivity;
a1: setting a tree segmentation threshold s to be 1 and a target point p 0 (-25.33, 122.19, 9.97), tree point set T = { [ -25.33,122.19, 9.97)]}；
a2: adding all points with the distance less than s from the target point into the set T;
T＝{
[-25.33,122.19,9.97]
[-25.38,122.32,9.92]
[-25.11,122.54,10.37]
[-25.07,122.55,9.96]
[-24.94,122.55,9.94]
[-24.77,122.54,10.11]
[-25.07,122.58,8.63]
[-25.01,122.43,9.82]
[-24.92,122.75,10.18]
[-24.76,122.75,10.28]
……
}
a3: setting the target point to be the next point of the current target point, namely (-25.38, 122.32, 9.92);
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a tree area; t = Back
[-25.33,122.19,9.97]
[-25.38,122.32,9.92]
[-25.11,122.54,10.37]
[-25.07,122.55,9.96]
[-24.94,122.55,9.94]
[-24.77,122.54,10.11]
[-25.07,122.58,8.63]
[-25.01,122.43,9.82]
[-24.92,122.75,10.18]
[-24.76,122.75,10.28]
[-25.36,122.3,10.75]
[-25.11,122.3,10.56]
[-25.54,122.17,10.88]
[-25.44,122.18,10.78]
[-25.31,122.18,10.72]
[-25.47,122.06,10.85]
[-25.42,123.15,14.28]
[-25.29,123.15,14.3]
[-25.46,123.05,14.34]
[-25.31,123.04,14.32]
……
}
a5: repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: filtering out a set of less than 100 points, and forming a Tree set Tree by using all sets T of more than 100 points; and finally obtaining 15 qualified tree areas, as shown in fig. 6.
b. Mapping each group of trees in the point cloud to a monitoring image;
input the method
M＝[[2.23722737e+03 0.00000000e+00 1.31100000e+03]
[0.00000000e+00 2.24053809e+03 9.84000000e+02]
[0.00000000e+00 0.00000000e+00 1.00000000e+00]]
R＝[[0.99564296 -0.01460996 -0.09209719]
[0.09235461 0.01804687 0.99556243]
[-0.01288306 -0.99973053 0.01931754]]
T＝[-8.60000134 0.15.20000362]
Calculating to obtain mapping coordinates:
img＝{
[923,1111]
[925,1115]
[926,1117]
[923,1151]
[926,1150]
[932,1138]
[934,1139]
[923,1150]
[925,1151]
[929,1143]
[932,1143]
[923,1112]
[925,1115]
[926,1119]
[924,1151]
[927,1146]
[932,1139]
[934,1139]
[935,1146]
[937,1147]
……
}
the mapping effect is shown in fig. 7.
c. Identifying a tree area in the image and comparing the tree area mapped by the point cloud;
the tree recognition effect is shown in fig. 8.
c1: the area set mapped by the tree is marked as A, and the area set identified by the tree is marked as D; a = &
[
[923,1111]
[925,1115]
[926,1117]
[923,1151]
[926,1150]
[932,1138]
[934,1139]
[923,1150]
[925,1151]
[929,1143]
[932,1143]
[923,1112]
[925,1115]
[926,1119]
[924,1151]
[927,1146]
[932,1139]
[934,1139]
[935,1146]
[937,1147]
……
],
……
}
D＝{
[
[2440,979]
[2441,979]
[2442,979]
[2443,979]
[2444,979]
[2445,979]
[2446,979]
[2447,979]
[2448,979]
[2435,980]
[2436,980]
[2437,980]
[2438,980]
[2439,980]
[2440,980]
[2441,980]
[2442,980]
[2443,980]
[2444,980]
[2445,980]
[476,1071]
[477,1071]
[478,1071]
[479,1071]
[480,1071]
[481,1071]
[482,1071]
[483,1071]
[484,1071]
[485,1071]
[486,1071]
[487,1071]
[488,1071]
[489,1071]
[490,1071]
[467,1072]
[468,1072]
[469,1072]
[470,1072]
[471,1072]
……
],
……
}
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD; topA = pen
[
[922.0,1114.0][923.0,1111.0][924.0,1099.0][925.0,1113.0][926.0,1098.0][927.0,1101.0][928.0,1090.0][929.0,1095.0][930.0,1089.0][931.0,1090.0][932.0,1087.0][933.0,1088.0][934.0,1083.0][935.0,1088.0][936.0,1092.0][937.0,1090.0][938.0,1094.0][939.0,1083.0][940.0,1091.0][941.0,1094.0]……
],
……
}
topD＝{
[
[1312,1131]
[1313,1126]
[1314,1118]
[1315,1113]
[1316,1111]
[1317,1110]
[1318,1109]
[1319,1108]
[1320,1107]
[1321,1106]
[1322,1105]
[1323,1104]
[1324,1103]
[1325,1102]
[1326,1102]
[1327,1101]
[1328,1100]
[1329,1100]
[1330,1099]
[1331,1099]
……
],
……
}
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
Calculating corresponding pixel points, taking a certain area as an example:
[1887.0,1040.0--1887.0,1021.0]
[1888.0,1038.0--1888.0,1021.0]
[1889.0,1037.0--1889.0,1021.0]
[1890.0,1025.0--1890.0,1021.0]
[1891.0,1020.0--1891.0,1020.0]
[1892.0,1019.0--1892.0,1020.0]
[1893.0,1027.0--1893.0,1020.0]
[1894.0,1025.0--1894.0,1019.0]
[1895.0,1023.0--1895.0,1019.0]
[1896.0,1021.0--1896.0,1019.0]
[1897.0,1021.0--1897.0,1018.0]
[1898.0,1024.0--1898.0,1018.0]
[1899.0,1020.0--1899.0,1018.0]
[1900.0,1025.0--1900.0,1017.0]
[1901.0,1022.0--1901.0,1017.0]
[1902.0,1025.0--1902.0,1017.0]
[1903.0,1023.0--1903.0,1016.0]
[1904.0,1021.0--1904.0,1016.0]
[1905.0,1023.0--1905.0,1016.0]
[1906.0,1019.0--1906.0,1015.0]
d. and estimating the height of the tree in the image, and calculating the distance between the tree in the image and the wire. d1: calculating the pixel difference diff a ＝(v d -v a )；
diff a ＝{
[
19.0
17.0
16.0
4.0
0.0
-1.0
7.0
6.0
4.0
2.0
3.0
6.0
2.0
8.0
5.0
8.0
7.0
5.0
7.0
4.0
……
],
……
}
d2: calculating diff a Corresponding true height H a ；H a ＝{
[
1.3341273588935565
1.1914322374349566
1.1228954561405977
0.2807293782645598
0.0
-0.07026752087335532
0.4922052273603588
0.42116230979914093
0.28078449024776175
0.14099327325780173
0.21150660605547192
0.4217128725003192
0.140506851335485
0.5617674111632006
0.35129759896940277
0.561422246826717
0.4909542744842129
0.35091494695242587
0.4913209231743029
0.28235064992427994
……
],
……
}
d3: calculating tree three-dimensional coordinate p d ；
p d ＝{
[
[19.09,172.13,15.044127358893558]
[19.09,171.8,15.021432237434956]
[19.18,172.03,15.062895456140597]
[19.3,172.02,15.060729378264561]
[19.37,172.21,15.22]
[19.490000000000002,172.21,15.169732479126646][19.56,172.32,15.122205227360359]
[19.55,172.02,15.231162309799142]
[19.69,172.01,15.200784490247761]
[19.830000000000002,172.74,15.240993273257802][19.95,172.74,15.281506606055473]
[19.88,172.21,15.30171287250032]
[19.97,172.12,15.310506851335484]
[20.05,172.03,15.371767411163201]
[20.1,172.12,15.401297598969403]
[20.16,171.91,15.391422246826718]
[20.22,171.8,15.410954274484213]
[20.27,171.91,15.420914946952426]
[20.39,171.91,15.401320923174303]
[20.650000000000002,172.87,15.522350649924281]……
],
……
}
d5: calculating Euclidean distances between all the lead points and all the three-dimensional coordinates, and finding out the nearest lead point and the nearest distance;
a minimum distance is calculated for each tree region, with the end result as follows:
[{'distance':61.6,'line':[[1911,1013],[1768,215]]},{'distance':60.46,'line':[[1943,1005],[1860,-83]]},{'distance':60.75,'line':[[1924,1008],[1804,99]]},{'distance':67.18,'line':[[1334,1096],[1468,183]]},{'distance':69.48,'line':[[2256,1017],[1780,178]]},{'distance':64.02,'line':[[2121,1021],[1811,76]]},{'distance':62.91,'line':[[1693,1041],[1789,119]]}]
the final ranging result is shown in fig. 9.
The height of the tree line distance measured by the embodiment is estimated from the actual tree line distance measured on site, and the error is about 1 m.
The method adopts the technologies of tree division, image and point cloud mapping amount area comparison and the like, realizes automatic division of trees in the power transmission line channel, calculates the shortest distance between each tree area and a wire, infers the tree growth condition in the image according to the tree identification result, can perform risk grade division according to the tree distance measurement result, timely finds and processes the hidden danger of the tree obstacle which may cause harm to the power transmission channel line, enhances the control strength of the power transmission channel, and the operation and inspection personnel can more accurately control the height of the trees, thereby reducing the accident caused by the hidden danger of the tree obstacle.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for monitoring potential tree obstacle hazards of a power transmission line is characterized by being used for monitoring the potential tree obstacle hazards based on a power transmission channel monitoring image and power transmission channel point cloud, and comprising the following steps:
dividing trees in the point cloud of the power transmission channel into a plurality of groups through connectivity;
mapping each group of trees in the power transmission channel point cloud to the monitoring image;
identifying a tree area in the monitored image, and comparing the tree area mapped to the monitored image by the point cloud;
and calculating the height of the trees in the image according to the comparison result, and calculating the distance between the trees in the image and the wire of the power transmission line.
2. The method for monitoring the hazards of the potential hazards of the transmission line tree barriers as claimed in claim 1, wherein the step of dividing the trees in the point cloud of the transmission channel into a plurality of groups through connectivity comprises:
a1: setting a segmentation threshold s, target point p 0 Set of tree points T = { p = { (p) 0 }；
a2: adding all points with a distance less than s from the target point into the set T, namely T = { p = { (p) 0 ,p 1 ,p 2 A look, and remove points added to the collection from the point cloud;
a3: setting the target point as the next point of the current target point;
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a divided tree region;
a5: reselecting a target point p from the point cloud 0 Repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: and (5) forming a Tree set Tree by using all sets T with more than 100 points.
3. The method for monitoring the potential hazards of the power transmission line tree barriers according to claim 1, wherein the step of mapping each group of trees in the power transmission channel point cloud to the monitoring image comprises the following steps:
mapping each group of trees in the power transmission channel point cloud to the monitoring image, and recording pixel points and three-dimensional points corresponding to the pixel points, wherein the mapping formula for mapping each group of trees in the power transmission channel point cloud to the monitoring image is as follows:
temp＝(p-T)·R
m＝(M·temp T ) T
m = m ÷ m (0, 2) (homogeneous transformation)
Wherein p is a three-dimensional point, M is a two-dimensional point, R is a point cloud rotation matrix, T is a point cloud translation vector, and M is a camera internal reference matrix.
4. The method for monitoring the hidden danger of the power transmission line tree obstacle according to any one of claims 1 to 3, wherein the step of identifying the tree region in the monitored image and comparing the tree region with the tree region mapped to the monitored image by the point cloud comprises the following steps:
c1: a, mapping the point cloud to a tree region set on the monitored image, and D identifying the tree region set in the monitored image;
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD;
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
5. The method for monitoring the potential hazards of the electric transmission line tree barriers according to claim 4, wherein the step of calculating the height of the trees in the image according to the comparison result and calculating the distance between the trees in the image and the electric transmission line conductor comprises the following steps:
d1: upper boundary t a In each pixel point is marked as m a (u a ,v a )，m a (u a ,v a ) The corresponding three-dimensional point is denoted as p a (x a ,y a ,z a )，m a (u a ,v a ) The corresponding pixel point is marked as d a (u a ,v d ) If m is a (u a ,v a ) Skipping the pixel point if the corresponding pixel point does not exist;
d2: calculating pixel difference: diff (diff) a ＝(v d -v a )；
d3: according to the camera imaging principle
Calculating diff a Corresponding true height H a Where f is the focal length, L is the distance of the object plane from the camera plane, H is the pixel height, and H is the true height;
d4: calculating tree three-dimensional point p a (x a ,y a ,z a ) Corresponding three-dimensional coordinate p d (x a ,y a ,z a +H a )；
d5: calculating all conducting wire points and three-dimensional coordinates p d (x a ,y a ,z a +H a ) Finding the nearest wire point and the nearest distance;
d6: upper boundary t a All corresponding wire closest points form a set Near, and all the closest distances form a set Dis;
d7: and selecting the minimum value in the set Dis as the shortest distance between the tree area and the wire.
6. The utility model provides a monitoring devices of transmission line tree barrier hidden danger harm which characterized in that, carries out tree barrier hidden danger monitoring based on transmission channel prison image and transmission channel point cloud, the device includes:
the tree grouping module is used for dividing the trees in the power transmission channel point cloud into a plurality of groups through connectivity;
the point cloud mapping module is used for mapping each group of trees in the point cloud of the power transmission channel to the monitoring image;
the tree region comparison module is used for identifying a tree region in the monitored image and comparing the tree region with the tree region mapped to the monitored image by the point cloud;
and the distance calculation module is used for calculating the height of the trees in the image according to the comparison result and calculating the distance between the trees in the image and the wire of the power transmission line.
7. The device for monitoring the potential hazards of the power transmission line tree barriers according to claim 6, wherein the specific process of dividing the trees in the point cloud of the power transmission channel into a plurality of groups by the tree grouping module through connectivity is as follows:
a1: setting a segmentation threshold s, target point p 0 Set of tree points T = { p = { (p) 0 }；
a2: adding all points with a distance less than s from the target point into the set T, namely T = { p = { (p) 0 ,p 1 ,p 2 A survey, and removing points added to the set from the point cloud;
a3: setting the target point as the next point of the current target point;
a4: repeating the steps a2 and a3 until the set T is not increased any more, wherein the set T is a divided tree region;
a5: reselecting a target point p in a point cloud 0 Repeating the steps a1 to a4 until all points in the point cloud are removed;
a6: and (5) forming a Tree set Tree by using all sets T with more than 100 points.
8. The device for monitoring the hidden danger of the tree obstacle of the power transmission line according to claim 6, wherein the point cloud mapping module maps each group of trees in the point cloud of the power transmission channel to the monitoring image according to a mapping formula:
temp＝(p-T)·R
m＝(M·temp T ) T
m = m ÷ m (0, 2) (homogeneous transformation)
Wherein p is a three-dimensional point, M is a two-dimensional point, R is a point cloud rotation matrix, T is a point cloud translation vector, and M is a camera internal reference matrix.
9. The device for monitoring the potential hazards of the power transmission line tree barriers according to any one of claims 6 to 8, wherein the tree region comparison module identifies a tree region in the monitored image and compares the tree region with a tree region mapped on the monitored image by point cloud:
c1: a, mapping the point cloud to a tree region set on the monitored image, and D identifying the tree region set in the monitored image;
c2: searching the upper boundary of each tree mapping area in the set A to form a set topA, and searching the upper boundary of each tree identification area in the set D to form a set topD;
c3: each upper boundary in topA is denoted t a And searching pixel points corresponding to each pixel point ta in all upper boundaries in the topD.
10. The device for monitoring the damage of the hidden danger of the tree obstacle of the electric transmission line according to claim 9, wherein the distance calculating module calculates the height of the tree in the image according to the comparison result, and the specific process of calculating the distance between the tree in the image and the wire of the electric transmission line is as follows:
d1: upper boundary t a In each pixel point is marked as m a (u a ,v a )，m a (u a ,v a ) The corresponding three-dimensional point is denoted as p a (x a ,y a ,z a )，m a (u a ,v a ) The corresponding pixel point is marked as d a (u a ,v d ) If m is a (u a ,v a ) Skipping the pixel point if the corresponding pixel point does not exist;
d2: calculating pixel difference: diff (diff) a ＝(v d -v a )；
d3: according to the camera imaging principle
Calculating diff a Corresponding true height H a Where f is the focal length, L is the distance of the object plane from the camera plane, H is the pixel height, and H is the true height;
d4: calculating tree three-dimensional point p a (x a ,y a ,z a ) Corresponding three-dimensional coordinate p d (x a ,y a ,z a +H a )；
d5: calculating all conducting wire points and three-dimensional coordinates p d (x a ,y a ,z a +H a ) Finding the nearest wire point and the nearest distance;
d6: upper boundary t a All the corresponding nearest points of the leads form a set Near, and all the nearest distances form a set Dis;
d7: and selecting the minimum value in the set Dis as the shortest distance between the tree area and the wire.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534803.6A CN115830450A (en) | 2022-11-30 | 2022-11-30 | Method and device for monitoring potential hazard of power transmission line tree obstacle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534803.6A CN115830450A (en) | 2022-11-30 | 2022-11-30 | Method and device for monitoring potential hazard of power transmission line tree obstacle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115830450A true CN115830450A (en) | 2023-03-21 |
Family
ID=85544833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211534803.6A Pending CN115830450A (en) | 2022-11-30 | 2022-11-30 | Method and device for monitoring potential hazard of power transmission line tree obstacle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115830450A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116091493A (en) * | 2023-04-07 | 2023-05-09 | 智洋创新科技股份有限公司 | Distance measurement method for hidden danger of tree obstacle of power transmission line |
| CN117092631A (en) * | 2023-10-19 | 2023-11-21 | 江苏翰林正川工程技术有限公司 | Target positioning and ranging method and system for power transmission channel construction machinery |
-
2022
- 2022-11-30 CN CN202211534803.6A patent/CN115830450A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116091493A (en) * | 2023-04-07 | 2023-05-09 | 智洋创新科技股份有限公司 | Distance measurement method for hidden danger of tree obstacle of power transmission line |
| CN117092631A (en) * | 2023-10-19 | 2023-11-21 | 江苏翰林正川工程技术有限公司 | Target positioning and ranging method and system for power transmission channel construction machinery |
| CN117092631B (en) * | 2023-10-19 | 2024-04-19 | 江苏翰林正川工程技术有限公司 | Target positioning and ranging method and system for power transmission channel construction machinery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115830450A (en) | Method and device for monitoring potential hazard of power transmission line tree obstacle | |
| CN112686938B (en) | Power transmission line clear distance calculation and safety alarm method based on binocular image ranging | |
| CN108269281B (en) | Obstacle avoidance technical method based on binocular vision | |
| CN109631776B (en) | Automatic measurement method for icing thickness of high-voltage transmission line conductor | |
| CN105203210A (en) | Fault detection device and detection method of ultra-high voltage (UHV) substation transformer based on 360-degree infrared panoramic view and support vector machine (SVM) | |
| CN107179479A (en) | Transmission pressure broken lot defect inspection method based on visible images | |
| CN112489130A (en) | Distance measuring method and device for power transmission line and target object and electronic equipment | |
| CN113345019A (en) | Power transmission line channel hidden danger target ranging method, equipment and medium | |
| CN104281857A (en) | Insulator detecting method based on orthogonal direction projection | |
| CN115512252B (en) | Unmanned aerial vehicle-based power grid inspection automation method and system | |
| CN111951520A (en) | System and method for detecting icing thickness of transmission line conductor | |
| CN114255405A (en) | Hidden danger target identification method and device | |
| CN111507975A (en) | Method for detecting abnormity of outdoor insulator of traction substation | |
| CN113469178A (en) | Electric power meter identification method based on deep learning | |
| CN112595936A (en) | Power transmission line composite insulator intelligent detection system based on unmanned aerial vehicle patrols and examines | |
| CN117274722A (en) | Intelligent detection method for distribution box based on infrared image | |
| CN113965733A (en) | Binocular video monitoring method, system, computer equipment and storage medium | |
| CN116958841A (en) | Unmanned aerial vehicle inspection system for power distribution line based on image recognition | |
| CN115620239B (en) | Point cloud and video combined power transmission line online monitoring method and system | |
| CN114625166B (en) | Intelligent positioning method for shooting position of unmanned aerial vehicle | |
| CN112967257B (en) | Subway nut looseness detection method based on visual angle conversion | |
| CN111079852B (en) | Method for detecting icing thickness of insulator of power transmission line | |
| CN114666550A (en) | Contact point parameter detection device and method of close contact checker based on image processing | |
| CN114179093A (en) | Transformer substation inspection robot system and obstacle avoidance method thereof | |
| Chen et al. | Detection and localization of untwisted strands in transmission lines using cascaded shape filtering and color filtering |
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 |