CN111898481A - State identification method and device for pointer type opening and closing indicator - Google Patents
State identification method and device for pointer type opening and closing indicator Download PDFInfo
- Publication number
- CN111898481A CN111898481A CN202010674403.XA CN202010674403A CN111898481A CN 111898481 A CN111898481 A CN 111898481A CN 202010674403 A CN202010674403 A CN 202010674403A CN 111898481 A CN111898481 A CN 111898481A
- Authority
- CN
- China
- Prior art keywords
- pointer
- image data
- indicator
- type opening
- pointer type
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 17
- 238000002372 labelling Methods 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Abstract
The application discloses a state identification method and device of a pointer type opening and closing indicator, which are used for solving the technical problem that indication content cannot be correctly identified when a camera cannot be installed over the indicator. The method comprises the following steps: receiving first image data which are uploaded by image acquisition equipment and related to a pointer type opening and closing indicator; inputting the first image data into a pointer type opening and closing indicator detection model to obtain second image data; the second image data comprises a pointer marking frame, a sub marking frame and a combined marking frame; determining central point position information and depth corresponding to each marking frame in the second image data; the depth is used for representing the distance between each central point and the image acquisition equipment; and determining the indication state of the pointer type opening and closing indicator through a geometric algorithm based on the position information and the depth respectively corresponding to the central points. By the method, the indication state can be correctly identified when the image acquisition equipment cannot be installed right opposite to the indicator.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a state identification method and device of a pointer type opening and closing indicator.
Background
The pointer type switching-on/off indicator is a switching-on/off indicator commonly used in a transformer substation, the switching-on/off indicator indicates the current switching-on/off state of a disconnecting link through a pointer, and the switching-on/off state of the disconnecting link is one of contents of important attention of transformer substation workers.
However, due to the complex scene and special environment in the transformer substation, a lot of requirements are provided for the installation position of a camera for collecting pictures of the pointer type opening and closing indicator. Under certain scenes, due to space limitation, a camera which is used for shooting a pointer type opening and closing indicator is difficult to install, so that visual deviation is caused, and the current pointer pointing is difficult to judge whether the current pointer is in an 'opening' state or a 'closing' state by using the existing indicator state identification scheme.
Disclosure of Invention
The embodiment of the application provides a state identification method and device of a pointer type opening and closing indicator, and aims to solve the technical problem that the existing state identification method of the opening and closing indicator cannot correctly identify the 'opening' state or the 'closing' state when a camera cannot be installed over the indicator.
On the one hand, the embodiment of the application provides a state identification method of pointer type divide-shut brake indicator, including: receiving first image data which are uploaded by image acquisition equipment and related to a pointer type opening and closing indicator; inputting the first image data into a pointer type opening and closing indicator detection model to obtain second image data; the second image data comprises a pointer marking frame, a sub marking frame and a combined marking frame; determining central point position information corresponding to each marking frame in the second image data respectively, and determining the depth corresponding to each central point respectively; the depth is used for representing the distance between each central point and the image acquisition equipment; and determining the indication state of the pointer type opening and closing indicator through a geometric algorithm based on the position information and the depth respectively corresponding to the central points.
According to the embodiment of the application, the two-dimensional image and the depth image corresponding to the pointer type opening and closing indicator are collected, the two-dimensional image is input into the pointer type opening and closing indicator detection model, the pointer and the indicating content are marked in a 'separating' and 'closing' mode, and the central point position corresponding to the pointer and the indicating content respectively and the depth corresponding to each central point are determined. And then, calculating the distance by using the depth and position information through a geometric algorithm, and further obtaining the indication state of the pointer type opening and closing indicator. By the method, even if the camera cannot be installed right opposite to the indicator, the identification of the indication state can be realized according to the acquired image data, and the accuracy and the efficiency of state identification can be ensured.
In an implementation of this application, based on each central point positional information and the degree of depth that corresponds respectively, through geometric algorithm, confirm pointer-type divide-shut brake indicator's indicating state, specifically include: constructing a first coordinate system by taking a left boundary of the first image data as a longitudinal axis, an upper boundary as a transverse axis and an intersection point of the left boundary and the upper boundary as an origin; determining a first abscissa and a first ordinate of each central point in the first coordinate system according to the position information of each central point; constructing a second coordinate system based on a horizontal axis, a vertical axis and an origin of the first coordinate system; wherein, the second abscissa of each central point in the second coordinate system is the same as the first abscissa, and the second ordinate is the depth of each central point; and calculating a first distance between the center point of the pointer marking frame and the center point of the branch marking frame and a second distance between the center point of the pointer marking frame and the center point of the combined marking frame according to the geometric relationship of the center points and the connecting lines among the center points in the second coordinate system.
The state recognition method provided by the embodiment of the application actually adopts a three-dimensional visual algorithm, and when the first coordinate system constructed by the first image data is used as the data in the front-view direction, the second coordinate system constructed based on the first coordinate system is equivalent to the data obtained in the top-view direction. Thus, the abscissa in the first coordinate system represents the position information of each center point in the front view, the abscissa in the second coordinate system represents the position information, and the ordinate represents the depth, i.e., the distance between each center point and the camera head. And determining the geometric relationship of the central points and the connecting lines among the central points in the second coordinate system through a three-dimensional visual algorithm, so as to determine the distance between the central point of the pointer marking frame and the central point of the branch marking frame or the central point of the combined marking frame, and further obtain the corresponding indication state according to the distance. The camera has the advantages that the indication state can be timely and effectively identified when the visual deviation occurs due to the fact that the camera is not installed at the position right opposite to the indicator, and the accuracy of identification of the indication state is guaranteed.
In one implementation of the present application, the method further comprises: and under the condition that the first distance is smaller than a first preset threshold value, determining that the indication state of the pointer type opening and closing indicator is a separated state.
In one implementation of the present application, the method further comprises: determining a magnitude relationship between the first distance and the second distance; and determining the indication state of the pointer type opening and closing indicator according to the size relation.
In one implementation manner of the present application, before the first image data is input into the pointer-type opening/closing indicator detection model, the method further includes: acquiring image data corresponding to a plurality of pointer type opening and closing indicators, and constructing a training data set based on the image data; and training and verifying the neural network model through a training data set to obtain a pointer type opening and closing indicator detection model.
In an implementation manner of the present application, constructing a training data set based on image data specifically includes: labeling the pointer information and the indication content information contained in the image data through a Labellmg labeling tool; and constructing a training data set according to the marked image data. And training a detection model of the pointer type switching-on/off indicator through the marked image data so as to enable the obtained second image data to contain a pointer and a marking frame indicating the content when the first image data is input into the pointer type switching-on/off indicator model. And furthermore, the indication state can be determined through the position relation among the central points of the labeling frames.
In one implementation manner of the application, a pointer-type opening and closing indicator detection model is trained by using a Yolov3 object detection algorithm model.
In an implementation manner of the present application, determining the respective depths corresponding to the central points specifically includes: acquiring depth image data corresponding to the first image data through image acquisition equipment; carrying out image registration on the depth image data and the second image data to obtain a registration depth image; and determining the depth corresponding to each central point in the second image data based on the registered depth image.
In one implementation of the present application, the image capture device employs an RGB-D camera.
On the other hand, this application embodiment still provides a state identification equipment of pointer-type divide-shut brake indicator, includes: a processor; and a memory on which executable code is stored, the executable code, when executed, causing the processor to execute a state identification method of the pointer type opening and closing indicator.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a state identification method for a pointer-type opening/closing indicator according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a first coordinate system provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a second coordinate system according to an embodiment of the present application;
fig. 4 is an internal structure schematic diagram of a state identification device of a pointer type opening and closing indicator provided in the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The pointer type switching-on/off indicator is a switching-on/off indicator commonly used in a transformer substation, the switching-on/off indicator indicates the current switching-on/off state of a disconnecting link through a pointer, and the disconnecting link state is one of objects of major concern of patrol personnel of the transformer substation. But the environment is complex due to the complex scene in the transformer substation. A lot of requirements are put forward on the installation position of image acquisition equipment for acquiring pointer-type opening and closing indicator images, so that in some scenes, due to insufficient space, the image acquisition equipment cannot be installed over a pointer-type opening and closing indicator, and visual deviation is caused.
Therefore, with the existing state recognition algorithm or method, when the image acquisition device is not installed right opposite to the pointer-type opening and closing indicator, the indication state of the pointer-type opening and closing indicator cannot be correctly recognized.
The embodiment of the application provides a state identification method and device of a pointer type opening and closing indicator.
The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a state identification method for a pointer type opening and closing indicator according to an embodiment of the present application. As shown in fig. 1, the status identification process of the pointer type opening and closing indicator mainly includes the following steps:
step 101, a server receives first image data which are uploaded by image acquisition equipment and related to a pointer type opening and closing indicator.
And the server receives image data which is collected by the image collecting equipment and is related to the pointer type opening and closing indicator.
In this embodiment of the application, the image data collected by the image collecting device may be an image collected by a pointer-type opening and closing indicator, or an image of a pointer-type opening and closing indicator photographed from the side. In order to solve the technical problem mentioned above, in the embodiment of the present application, an image captured by an image capture device on a side surface is used as first image data related to a pointer-type opening/closing indicator for research.
It should be noted that, when the image acquisition device in the embodiment of the present application uploads the acquired image data to the server, a wired transmission mode may be adopted, and a wireless transmission mode such as WiFi may also be adopted, which is not limited in the embodiment of the present application.
And 102, inputting the first image data into a pointer type opening and closing indicator detection model to obtain second image data.
After the first image data is received, the first image data is input into a pointer type opening and closing indicator detection model so as to label the pointer of the pointer type opening and closing indicator and the indicating contents of opening and closing, and second image data is obtained.
Further, the second image data includes a pointer marking frame, a sub marking frame and a close marking frame.
In an embodiment of the application, the pointer-type switching-on/off indicator detection model is a neural network model, and is used for processing image data input into the model, namely, marking a pointer position and an indication content position in the first image data through a marking frame.
In another embodiment of the present application, before the first image data is input into the pointer-type switching-on/off indicator detection model, the neural network model needs to be trained by using a plurality of image data related to the pointer-type switching-on/off indicator, so as to obtain the pointer-type switching-on/off indicator detection model.
Specifically, images related to a pointer type opening and closing indicator are collected, and then the collected images are marked through a Labellmg marking tool; namely, the position of the pointer and the positions of the indicating contents of 'score' and 'close' in each image are marked in a frame marking mode, and a training data set is obtained.
The image data related to the pointer type switching on/off indicator used for constructing the neural network model training data set includes image data acquired at each angle of the pointer type switching on/off indicator.
And then, training and verifying the neural network model through a training data set to obtain a pointer type opening and closing indicator detection model.
The verification process of the pointer type opening and closing indicator detection model is also completed through the constructed training data set.
In one embodiment of the application, a pointer type opening and closing indicator detection model is built by adopting a non-graph detection algorithm Yolov 3.
And training to obtain a pointer type opening and closing indicator detection model. And outputting second image data with three labeling frames after the first image data is input. Wherein, three mark frames are respectively: the pointer marking frame, the sub marking frame and the combined marking frame.
As will be clear to those skilled in the art, the pointer marking box is used to mark the position of the pointer; the sub-marking frame is used for marking the position of the indicated content 'sub'; and the combined marking frame is used for marking the position of the indicated content 'combined'.
And 103, obtaining depth image data corresponding to the first image data through image acquisition equipment.
In one embodiment of the present application, the depth image is acquired by a particular RGB-D camera.
And the depth of each pixel point on the depth image represents the distance from the pixel point to the plane where the RGB-D camera is located.
It may be clear to those skilled in the art that the depth image data acquired in the embodiment of the present application may be obtained by using an existing image acquisition device or method, and details of the embodiment of the present application are not described herein.
And step 104, determining the position relation and the depth of the center point of each marking frame.
After the second image data are obtained, the position of the central point corresponding to each marking frame in the second image data is determined through a geometric algorithm. Namely the position of the center point of the pointer marking frame, the positions of the center points of the sub-marking frames and the position of the center point of the combined marking frame.
In an embodiment of the present application, the position information of the center point corresponding to each labeling frame can be represented by pixel coordinates.
For example, the second image data is a 200 × 200 image, and the pixel coordinate system is constructed with the upper boundary of the second image data as the horizontal axis, the left boundary as the vertical axis, and the intersection of the upper boundary and the left boundary as the origin. In a pixel coordinate system, determining the pixel coordinate of the central point of the pointer marking frame as (45, 85); the pixel coordinate of the center point of the labeling frame is (97, 99); the pixel coordinate of the center point of the labeling frame is (125, 106).
The coordinates (45,85) indicate that the center point of the pointer marking frame is located at the 45 th pixel point in the horizontal axis direction and 85 pixel points in the vertical axis direction.
Further, after obtaining the depth image data, the depth image is image registered with the second image data, even if the second image data is overlapped with the depth image data, resulting in a registered depth image.
And mapping pixel coordinates corresponding to the center point of the needle labeling frame, the center point of the sub-labeling frame and the center point of the combined labeling frame on the second image into a depth image coordinate system. The method for establishing the depth image coordinate system is consistent with the method for establishing the pixel coordinate system, and details are not repeated herein in the embodiments of the present application.
And after determining the corresponding pixel points of the central points on the depth image, calculating to obtain the depth information respectively corresponding to the central point of the pointer marking frame, the central point of the sub-marking frame and the central point of the combined marking frame according to the scale factor of the used RGB-D camera.
And determining the position information and the depth respectively corresponding to the center point of the pointer marking frame, the center point of the sub-marking frame and the center point of the combined marking frame in the second image data.
And 105, determining the indication state of the pointer type opening and closing indicator through a geometric algorithm.
After the position information and the depth of each central point are obtained, the indication state corresponding to the pointer type opening and closing indicator is determined through a geometric algorithm.
In one embodiment of the present application, a first coordinate system is constructed with the upper boundary of the second image data as the horizontal axis, the left boundary as the vertical axis, and the intersection of the left boundary and the upper boundary as the origin, as shown in fig. 2; and determining a first abscissa and a first ordinate which correspond to each central point in the second image data respectively.
Fig. 2 is a schematic diagram of a first coordinate system according to an embodiment of the present application. As shown in fig. 2, the first coordinate system is established based on the second image data, which includes a pointer, the indication content "minute", the indication content "close"; the system also comprises a pointer marking frame, a branch marking frame, a close marking frame and a central point corresponding to each marking frame.
In the first coordinate system corresponding to the second image data, the position information corresponding to each central point can be clearly obtained, but the actual position relationship between the central points is difficult to determine only through the first abscissa and/or the first ordinate, and the indication state of the pointer type opening and closing indicator cannot be accurately judged.
As shown in fig. 2, the distance between the abscissa of the center point of the pointer marking frame and the center point of the branch marking frame is closer, and the distance between the abscissa of the center point of the pointer marking frame and the center point of the close marking frame is farther, which is because the image acquisition device is not directly facing the pointer type opening and closing indicator to acquire the image, the visual deviation is caused, and the visual deviation cannot represent the real position relationship.
Further, the shooting direction of the image capturing apparatus is taken as the front view direction, image data in the top view direction corresponding to the second image data is obtained, and a second coordinate system is constructed based on the image data, as shown in fig. 3.
In a second coordinate system, a second abscissa of each central point is equal to the first abscissa, and a second ordinate is used for representing distance information between each central point and a vertical plane where the image acquisition device is located, that is, the second ordinate of each central point is the depth of each central point.
Furthermore, based on the geometric relations between the central points and the connecting lines of the central points, the distance information between the central point of the pointer marking frame and the central points of the branch marking frame and the close marking frame is determined, and the indicating state of the pointer type opening and closing indicator is further determined. Wherein, the geometric relationship between the center points and the connecting lines of the center points is shown in fig. 3.
Fig. 3 is a schematic structural diagram of a second coordinate system according to an embodiment of the present application. As shown in fig. 3, the horizontal axis is the x axis, and represents the position information of each center point; the vertical axis is the h-axis and indicates the depth corresponding to each center point. Wherein, the coordinate (x1, h1) represents the center point of the pointer marking frame; coordinates (x2, h2) indicate the center point of the labeling box; the coordinates (x3, h3) represent the center point of the callout box.
The second coordinate system in fig. 3 is established based on the image data in the image capturing device shooting direction, corresponding to the top view direction. That is, the image pickup device is in a parallel direction to a line extending in the x-axis direction of L1. Wherein, L1 is the connecting line between the center point of the sub-labeling frame and the center point of the close-labeling frame.
Therefore, the positional relationship between the respective center points in fig. 3 may represent the positional relationship between the actual pointer, the indication contents "point", "close". Therefore, b1 and b2 can represent the distance information between the center point of the pointer annotation frame and the center points of the sub annotation frame and the close annotation frame, respectively; where b1 is the first distance and b2 is the second distance.
As shown in fig. 3, the following geometric relationships exist between the center points and the center point connecting lines:
from b3 h2 h3, b4 x3 x2, and from trigonometric relationships, it can be derived:
according to the data relationship between the corners in the triangle and the parallel theorem, it can be obtained that:
w1＝w2＝w3＝w4
according to b5 ═ x2-x 1; it can be derived that:
b6＝tan(w4)*b5
from b7 h2-h1-b6, it follows:
b1＝cos(w1)*b7
then, b1+ b2 is changed to b0 according to
To obtain:
b2＝b0-b1
and after the values of b1 and b2 are obtained, the information of the distances between the pointer of the pointer type opening and closing indicator and the indicating contents of opening and closing is obtained, and the first distance and the second distance are obtained.
And the indication state corresponding to the pointer type opening and closing indicator can be determined by comparing the magnitude relation between the pointer type opening and closing indicator and the pointer type opening and closing indicator. This is because, under normal circumstances, if the pointer points to "point", the first distance is close to a zero value, i.e. b1 is 0.
For example, when the first distance is greater than the second distance, the indication state of the pointer-type opening/closing indicator is determined to be the off state.
In one embodiment of the application, when the first distance or the second distance is smaller than a preset distance threshold, the indication state of the pointer type opening and closing indicator is determined to be an opening state or a closing state.
The above is an embodiment of the method of the present application, and based on the same inventive concept, the embodiment of the present application further provides a state identification device of a pointer type opening and closing indicator, and an internal structural schematic diagram of the state identification device is shown in fig. 4.
Fig. 4 is an internal structure schematic diagram of a state identification device of a pointer type opening and closing indicator provided in the embodiment of the present application. As shown in fig. 4, the apparatus includes a processor 401, and a memory 402, on which executable code is stored, and when the executable code is executed, causes the processor 401 to execute a state identification method of a pointer type opening and closing valve actuator as described above.
In an embodiment of the present application, the processor 401 is configured to receive first image data about a pointer-type opening/closing indicator, which is uploaded by an image acquisition device; the first image data are input into a pointer type opening and closing indicator detection model to obtain second image data; the second image data comprises a pointer marking frame, a sub marking frame and a combined marking frame; the image processing device is also used for determining central point position information corresponding to each marking frame in the second image data respectively and determining the depth corresponding to each central point respectively; the depth is used for representing the distance between each central point and the image acquisition equipment; and the indicating state of the pointer type opening and closing indicator is determined through a geometric algorithm based on the position information and the depth respectively corresponding to the central points.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A state identification method of a pointer type opening and closing indicator is characterized by comprising the following steps:
receiving first image data which are uploaded by image acquisition equipment and related to a pointer type opening and closing indicator;
inputting the first image data into a pointer type opening and closing indicator detection model to obtain second image data; the second image data comprises a pointer marking frame, a sub marking frame and a combined marking frame;
determining central point position information corresponding to each marking frame in the second image data respectively, and determining the depth corresponding to each central point respectively; wherein the depth is used for representing the distance between each central point and the image acquisition equipment;
and determining the indication state of the pointer type opening and closing indicator through a geometric algorithm based on the position information and the depth respectively corresponding to the central points.
2. The method for identifying the state of the pointer-type switching on/off indicator according to claim 1, wherein the determining the indication state of the pointer-type switching on/off indicator through a geometric algorithm based on the position information and the depth respectively corresponding to the central points specifically comprises:
constructing a first coordinate system by taking the left boundary of the second image data as a longitudinal axis, the upper boundary as a transverse axis and the intersection point of the left boundary and the upper boundary as an origin;
determining a first abscissa and a first ordinate of each central point in the first coordinate system according to the position information of each central point;
constructing a second coordinate system based on the horizontal axis, the vertical axis and the origin of the first coordinate system; a second abscissa of each central point in a second coordinate system is the same as the first abscissa, and a second ordinate is the depth of each central point;
and calculating a first distance between the center point of the pointer marking frame and the center point of the branch marking frame and a second distance between the center point of the pointer marking frame and the center point of the combined marking frame according to the geometric relationship of the center points and the connecting lines among the center points in a second coordinate system.
3. The state identification method of the pointer type opening and closing indicator according to claim 2, characterized by further comprising the following steps:
and under the condition that the first distance is smaller than a first preset threshold value, determining that the indication state of the pointer type opening and closing indicator is a separated state.
4. The state identification method of the pointer type opening and closing indicator according to claim 2, characterized by further comprising the following steps:
determining a magnitude relationship between the first distance and the second distance;
and determining the indication state of the pointer type opening and closing indicator according to the size relation.
5. The method for identifying the state of the pointer-type switching-on/off indicator according to claim 1, wherein before the first image data is input to a pointer-type switching-on/off indicator detection model, the method further comprises:
acquiring image data corresponding to a plurality of pointer type opening and closing indicators, and constructing a training data set based on the image data;
and training and verifying a neural network model through the training data set to obtain the pointer type opening and closing indicator detection model.
6. The state recognition method of the pointer type switching-on/off indicator according to claim 5, wherein the constructing a training data set based on the image data specifically includes:
labeling the pointer information and the indication content information contained in the image data through a Labellmg labeling tool;
and constructing a training data set according to the marked image data.
7. The state recognition method of the pointer type switching-on/off indicator according to claim 5, wherein the pointer type switching-on/off indicator detection model is trained by using a Yolov3 object detection algorithm model.
8. The state identification method of the pointer type switching-on/off indicator according to claim 1, wherein the determining the depth corresponding to each central point specifically comprises:
acquiring depth image data corresponding to the first image data through the image acquisition equipment;
carrying out image registration on the depth image data and the second image data to obtain a registration depth image;
and determining the depth corresponding to each central point in the second image data based on the registered depth image.
9. The state recognition method of the pointer type opening and closing indicator as claimed in claim 8, wherein the image acquisition device adopts an RGB-D camera.
10. A state recognition equipment of pointer divide-shut brake indicator which characterized in that, equipment includes:
a processor;
and a memory having executable code stored thereon, which when executed causes the processor to execute a method of status recognition of a pointer switching on/off indicator as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674403.XA CN111898481A (en) | 2020-07-14 | 2020-07-14 | State identification method and device for pointer type opening and closing indicator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010674403.XA CN111898481A (en) | 2020-07-14 | 2020-07-14 | State identification method and device for pointer type opening and closing indicator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111898481A true CN111898481A (en) | 2020-11-06 |
Family
ID=73191714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010674403.XA Pending CN111898481A (en) | 2020-07-14 | 2020-07-14 | State identification method and device for pointer type opening and closing indicator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898481A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944396A (en) * | 2017-11-27 | 2018-04-20 | 国网安徽省电力有限公司经济技术研究院 | A kind of disconnecting link state identification method based on improvement deep learning |
| CN108748149A (en) * | 2018-06-04 | 2018-11-06 | 上海理工大学 | Based on deep learning without calibration mechanical arm grasping means under a kind of complex environment |
| CN111008951A (en) * | 2019-09-21 | 2020-04-14 | 南京鑫和汇通电子科技有限公司 | Method for calculating opening and closing angle of split type disconnecting link based on positioning identification |
| CN111025137A (en) * | 2019-12-13 | 2020-04-17 | 苏州华电电气股份有限公司 | Open type isolating switch state sensing device |
| CN111046943A (en) * | 2019-12-09 | 2020-04-21 | 国网智能科技股份有限公司 | Method and system for automatically identifying state of isolation switch of transformer substation |
-
2020
- 2020-07-14 CN CN202010674403.XA patent/CN111898481A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944396A (en) * | 2017-11-27 | 2018-04-20 | 国网安徽省电力有限公司经济技术研究院 | A kind of disconnecting link state identification method based on improvement deep learning |
| CN108748149A (en) * | 2018-06-04 | 2018-11-06 | 上海理工大学 | Based on deep learning without calibration mechanical arm grasping means under a kind of complex environment |
| CN111008951A (en) * | 2019-09-21 | 2020-04-14 | 南京鑫和汇通电子科技有限公司 | Method for calculating opening and closing angle of split type disconnecting link based on positioning identification |
| CN111046943A (en) * | 2019-12-09 | 2020-04-21 | 国网智能科技股份有限公司 | Method and system for automatically identifying state of isolation switch of transformer substation |
| CN111025137A (en) * | 2019-12-13 | 2020-04-17 | 苏州华电电气股份有限公司 | Open type isolating switch state sensing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102737236B (en) | Method for automatically acquiring vehicle training sample based on multi-modal sensor data | |
| CN111275759B (en) | Transformer substation disconnecting link temperature detection method based on unmanned aerial vehicle double-light image fusion | |
| Zhu et al. | Concrete column recognition in images and videos | |
| CN109918977B (en) | Method, device and equipment for determining idle parking space | |
| CN111996883B (en) | Method for detecting width of road surface | |
| CN113469178B (en) | Power meter identification method based on deep learning | |
| JP2014112055A (en) | Estimation method for camera attitude and estimation system for camera attitude | |
| CN113034586B (en) | Road inclination angle detection method and detection system | |
| CN112686877A (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
| KR101255461B1 (en) | Position Measuring Method for street facility | |
| CN110807431A (en) | Object positioning method and device, electronic equipment and storage medium | |
| CN114742905B (en) | Multi-camera parameter calibration method, device, equipment and storage medium | |
| CN114639115A (en) | 3D pedestrian detection method based on fusion of human body key points and laser radar | |
| CN109903308B (en) | Method and device for acquiring information | |
| Wang et al. | Construction Photo Localization in 3D Reality Models for Vision-Based Automated Daily Project Monitoring | |
| WO2023103883A1 (en) | Automatic object annotation method and apparatus, electronic device and storage medium | |
| CN112488022A (en) | Panoramic monitoring method, device and system | |
| CN111898481A (en) | State identification method and device for pointer type opening and closing indicator | |
| CN116386373A (en) | Vehicle positioning method and device, storage medium and electronic equipment | |
| CN115982824A (en) | Construction site worker space management method and device, electronic equipment and storage medium | |
| CN110619626B (en) | Image processing apparatus, system, method and device | |
| CN113487726A (en) | Motion capture system and method | |
| CN112380894A (en) | Video overlapping area target duplicate removal method and system based on three-dimensional geographic information system | |
| US20160086339A1 (en) | Method of providing cartograic information of an eletrical component in a power network | |
| CN112270357A (en) | VIO vision system and method |
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 |