# US 2026/0065508 A1 · Method for measuring the distance between excavator and high-voltage transmission line

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065508 A1
- Document ID: US20260065508A1
- Status: Published application
- Kind: A1
- Application number: 19/384,952
- Filed: 2025-11-10
- Published: 2026-03-05
- Earliest claimed: 2024-02-29
- Assignees: Guizhou Power Grid Company Limited
- Applicants: Guizhou Power Grid Co., Ltd.
- Inventors: Qing LIU; Yi LI; Yu WU; Jibin JIANG; Xiaohu ZHENG; Youjun WANG; Yao ZHANG; Lin LI; Kun ZHANG; Xingyuan QIN; Linlin XIONG; Xianglin ZHU; Yonghong HOU; Gang NIE; Yiping ZHONG; Wei GU; Hongjie LI; Shiwei LI; Pan PAN; Xingdou DAI; Tianying HUANG; Yang SI; Xuemei RAO; Zhanjun LIU; Shuyi ZHENG
- Web page: https://patentgrep.com/patent/US20260065508A1

## CPC

- G06T 7/77: using statistical methods
- G01B 11/002: {for measuring two or more coordinates}
- G01B 11/14: for measuring distance or clearance between spaced objects or spaced apertures (G01B11/26 takes precedence; rangefinders G01C3/00)
- G01S 13/88: Radar or analogous systems specially adapted for specific applications (electromagnetic prospecting or detecting of objects, e.g. near-field detection, G01V3/00)
- G06T 7/50: Depth or shape recovery
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06T 2207/30208: Marker matrix
- G06T 2207/30261: Obstacle
- G06V 2201/08: Detecting or categorising vehicles
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present invention discloses a method for measuring the distance between an excavator and a high-voltage transmission line, comprising obtaining camera parameters through the Zhang's Checkerboard calibration method; collecting images, inputting images fully entering the field of view of the camera into a model; obtaining the pixel coordinate of a target frame through the YOLOV5 algorithm; obtaining target world coordinate; analyzing lengths, widths, and heights of 3D models of excavators by using a clustering algorithm, and calculating the geometric mean of each cluster; and measuring the height of the transmission line by a millimeter wave radar, and estimating the height of an object from the steps above, thereby obtaining the distance between the excavator and the high-voltage transmission line.

## Claims

### Claim 1

A method for measuring the distance between an excavator and a high-voltage transmission line, comprising:
defining a coordinate system, and marking an existing camera through the Zhang's Checkerboard calibration method so as to obtain an internal parameter matrix and an external parameter matrix of the camera;
fixing the installation height of the camera and the tilt angle θ of the camera, measuring the height of the camera from the ground by using an infrared ranging meter, and obtaining the tilt angle θ of the camera through PTZ (Pan, Tilt, Zoom) information of the camera in real time;
detecting images collected by the camera through the YOLOV5 algorithm, detecting and positioning targets in the images, obtaining a rectangular frame of the minimum area of the targets fully entering the field of view of the camera, and calculating depth information of the targets from the camera plane on the basis;
classifying the targets into large, medium and small through the partitioning clustering algorithm, analyzing lengths, widths and heights of 3D models of excavators in each category, calculating the geometric mean of each cluster of the excavators, and carrying out overall averaging; and
measuring the lowest height of the high-voltage transmission line through a millimeter wave radar, and obtaining the height of the target object and the distance between the high-voltage transmission line and the target through calculation.

### Claim 2 (depends on 1)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 1, wherein defining the coordinate system comprises, customizing a world coordinate system, a camera coordinate system, an image coordinate system and a pixel coordinate system;
namely drawing a vertical line from the installation position of the camera to the ground, and establishing the world coordinate system by taking the point on the ground as the origin Ow of the world coordinate system, the front perpendicular to the origin Ow as the Xw axis of the world coordinate system, the right side perpendicular to the origin as the Yw axis of the world coordinate system, and the direction of the origin Ow along the camera as the Zw axis;
establishing the camera coordinate system by taking the optical center of the camera as the origin Oc of the camera coordinate system, the optical axis of the camera as the positive direction of Zc, the direction directly above the camera as the positive direction of Yc, and the direction directly to the right of the camera as the positive direction of Xc;
establishing the image coordinate system by taking the imaging plane of the camera and the focus of the optical axis of the camera as the origin O of the image coordinate system, the direction directly below the origin O as the positive direction of the Y axis of the image coordinate system, and the direction directly to the right of the origin O as the positive direction of the X axis of the image coordinate system; and
establishing the pixel coordinate system by taking the direction to the upper left of the image as the origin O1 of the pixel coordinate system, the direction directly below O1 as the v axis of the pixel coordinate system, and the direction directly to the right of O1 as the positive direction of the u axis.

### Claim 3 (depends on 2)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 2, wherein the pixel coordinate system comprises, carrying out camera calibration on the camera so as to obtain an internal parameter matrix A and an external parameter matrix B of the camera;
A
=
[
d
x
r
u
0
d
y
v
0
1
]
B
=
[
R
T
0
1
]
dx and dy indicate scale factors of a pixel at the u axis and the v axis of the pixel coordinate system, corresponding to the focal lengths of the camera, r indicates a distortion factor u0 of an image physical coordinate, v0 refers to the pixel offset of the image origin relative to the longitudinal and transverse coordinates of an optical imaging point, R indicates the direction of the coordinate axes of the world coordinate system relative to the coordinate axes of the camera, and T indicates the position of the coordinate origin of the world coordinate system relative to the spatial origin in the camera coordinate system.

### Claim 4 (depends on 3)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 3, wherein using the infrared ranging meter comprises, fixing the installation height of the camera, and measuring the height of the camera relative to the horizontal ground as H by using the infrared ranging meter; controlling the camera to rotate in a vertical direction through software, setting each rotation time as T fixedly, measuring the rotation angle of the camera within the time T as θ by using an angle range finder so as to obtain the rotation speed of the camera within unit time as W=θ/T (°/s), thereby obtaining the deflection angle θ of the camera relative to a horizontal axis in real time.

### Claim 5 (depends on 4)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 4, wherein detecting and positioning comprises, detecting images collected by the camera through the YOLOV5 algorithm, detecting and positioning targets in the images, obtaining the rectangular frame of the minimum area of the targets fully entering the field of view of the camera, taking the midpoint Q at the bottom and the midpoint T at the top of the target frame, when the camera is not tilted, drawing vertical lines from the point Q and the point T to the Ow-Zw-Xw plane to intersect at a point P and a point S, and then, extending the intersection of the point P and the point S with the optical center to form a plane at a point P′ and a point S′, thereby obtaining the pixel coordinate information of Q′ and T′ through the defined coordinate systems;
Q
′
=
(
u
1
-
Width
2
,
Hegiht
2
-
(
v
1
+
h
2
)
)
T
′
=
(
u
1
-
Width
2
,
Hegiht
2
-
(
v
1
-
h
2
)
)
width and Height represent the horizontal and vertical resolutions of the image, sizes of which can be set in advance, (u1,v1) are the geometric centers of the target frame, and h is the width of the target frame,
when the deflection angle of the optical axis angle of the camera is θ, first a ground point Q is analyzed, after the previous step, a vertical line is drawn from the point P to the optical axis Zc to intersect the optical axis at a point D, the included angle formed by the line connecting the optical axis and OcD is ∠b, and the vertex angle of the angle is ∠b, the included angle formed by the line connecting the point P and the optical center Oc and the line connecting the point P and Ow is ∠c, the calculation method for the point T is the same.

### Claim 6 (depends on 5)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 5, wherein the deflection angle of the optical axis angle of the camera comprises, a geometrical relationship including the following relational equation:
∠
⁢
b
=
∠
⁢
b
=
arc
⁢
tan
⁡
(
OP
f
)
∠
⁢
c
=
∠
⁢
θ
+
∠
⁢
b
O
c
⁢
P
=
H
sin
⁡
(
∠
⁢
c
)
O
c
⁢
D
=
O
c
⁢
P
*
cos
⁡
(
∠
⁢
b
)
the relationship between the pixel coordinate system and the world coordinate system obtained is as follows:
[
x
w
y
w
z
w
1
]
=
B
-
1
⁢
A
-
1
⁢
z
c
[
u
v
1
]
in the equation, Zc=OcD, A−1 indicates an inverse A matrix of the internal parameter matrix, and B−1 is an inverse matrix of the external parameter matrix of the camera.

### Claim 7 (depends on 6)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 6, wherein classifying the targets into large, medium and small through the partitioning clustering algorithm comprises, analyzing lengths, widths and heights of 3D models of different categories of excavators through the K-Means clustering algorithm, calculating the geometric mean of each cluster of the excavators, and calculating the overall mean of the averaging so as to obtain O_L,O_K,O_H of the target, the K-Means clustering algorithm specifically comprises the following steps:
inputting a sample set D={X1,X2,X3, . . . Xm}, the number of clusters K=3, representing the large, medium and small categories respectively;
randomly selecting K samples from the sample set D as an initial mean vector {μ1,μ2,μ3};
setting Ci=Ø(1≤i≤K), and calculating the distance
d
ji
=

x
j
-
μ
i

2
between each sample xj and the mean vector
μ
i
(
1
≤
i
≤
K
)
;
determining a cluster label
λ
j
=
arg
min
i
∈
{
1
,
2
,
3
}
d
ji
of xj based on the mean vector in the nearest distance, and assigning xj into a corresponding cluster
C
λ
j
=
C
λ
j
⋃
{
x
j
}
;
calculating a new mean vector
μ
i
′
=
1
❘
"\[LeftBracketingBar]"
C
❘
"\[RightBracketingBar]"
⁢
∑
x
∈
C
i
x
;
judging whether the updated vector is equal to a current mean μi or not; if not, assigning μ′i to μi; if so, quitting updating the mean; repeating the above steps until small change in the mean, thereby completing classification;
outputting cluster classification
C
=
{
C
1
,
C
2
,
C
3
}
,
wherein each C represents a three-dimensional vector respectively substituted into the length, width and height of the excavator, and carrying out overall averaging on the length, width and height of three categories so as to obtain a final output Y=[O_L,O_K,O_H];
carrying out posture analysis on the target, first defining a cuboid with the length WAnchor, the width lAnchor, and the height hAnchor to enclose the target; from the top view, analyzing the included angle formed between the target and the cuboid as ω, thereby obtaining the following equation:
O
_
⁢
L
*
cos
⁢
ω
+
O
_
⁢
K
*
sin
⁢
ω
=
W
Anchor
O
_
⁢
L
*
sin
⁢
ω
+
O
_
⁢
K
*
cos
⁢
ω
=
l
Anchor
in the equation, calculating WAnchor according to the actual length of the length of the target frame in the world coordinate system, setting the lower left corner of the target frame as a point M and the lower right corner a point K so as to obtain coordinates of the point M and the point K in the pixel coordinate system as follows:
M
′
=
(
u
1
-
Width
2
-
w
2
,
Hegiht
2
-
(
v
1
+
h
2
)
)
⁢
K
′
=
(
u
1
-
Width
2
+
w
2
,
Hegiht
2
-
(
v
1
+
h
2
)
)
obtaining the world coordinate of the point M and the point K:
M
=
(
X
m
,
Y
m
,
Z
m
)
⁢
K
=
(
X
k
,
Y
k
,
Z
k
)
thereby obtaining:
W
Anchor
=
❘
"\[LeftBracketingBar]"
X
m
-
X
k
❘
"\[RightBracketingBar]"
in the equation, O_L and O_H are obtained by simplifying
cos
⁢
w
=
1
-
sin
2
⁢
w
;
(
O
_
⁢
L
2
+
O
_
⁢
K
2
)
*
sin
2
⁢
w
-
2
⁢
O
_
⁢
L
*
W
Anchor
⁢
sin
⁢
w
+
(
W
Anchor
2
-
O
_
⁢
K
)
=
0
setting
a
=
O
_
⁢
L
2
+
O
_
⁢
K
2
⁢
and
⁢
b
=
-
2
⁢
O
_
⁢
L
*
W
Anchor
,
and obtaining
b
=
-
2
⁢
O
_L
*
W
Anchor
through a quadratic formula:
from
0
⁢
°
≤
ω
≤
π
2
,
sin ω is a positive value:
sin
⁢
ω
=
❘
"\[LeftBracketingBar]"
-
b
±
b
2
-
4
⁢
a
⁢
c
2
⁢
a
❘
"\[RightBracketingBar]"
⁢
ω
=
arc
⁢
sin
⁢
❘
"\[LeftBracketingBar]"
-
b
±
b
2
-
4
⁢
a
⁢
c
2
⁢
a
❘
"\[RightBracketingBar]"
substituting ω into the equation, thereby obtain:
l
Anchor
=
O
_
⁢
L
*
sin
⁢
ω
+
O
_
⁢
K
*
cos
⁢
ω
.

### Claim 8 (depends on 7)

The method for measuring the distance between the excavator and the high-voltage transmission line according to claim 7, wherein the height of the target object and the distance between the high-voltage transmission line and the target comprises, measuring the height of the high-voltage transmission line as
H
wrie
by using the millimeter wave radar; according to the length O_L, width O_K and O_H of the target after clustering, establishing a three-dimensional cube of the target; corresponding the point Q to the point G at the top of the target cube; connecting the optical center Oc with the point T to intersect a point S at the back of the cube; forming an included angle γ by Oc-T-S and the horizontal plane; and setting the length of GT as
h
x
,
thereby obtaining the following equation according to the geometrical relationship:
tan
⁢
γ
=
h
x
l
anchor
⁢
tan
⁢
γ
=
H
-
h
D
OwQ
+
l
anchor
⁢
h
object
=
h
Anchor
-
h
wherein,
h
Anchor
is the coordinate Z
D
OwQ
=
X
wQ
2
+
Y
wQ
2
of the point T in the world coordinate system, the height of the object is estimated by integrating the target position and the posture information, and thus the distance between the excavator and the high-voltage transmission line is further obtained:
distacnce
=
H
wrie
-
h
object
.

### Claim 9 (depends on 8)

A computer device, including a memory and a processor, wherein the memory is used for storing computer programs; and the steps of the method according to claim 8 are achieved when the computer programs are executed by the processor.

### Claim 10 (depends on 8)

A computer readable storage medium, with computer programs stored thereon, wherein the steps of the method according to claim 8 are achieved when the computer programs are executed by the processor.
