AU2022381656A1 - Method and apparatus for determining open/closed state of knife switch, and device, medium and product - Google Patents

Method and apparatus for determining open/closed state of knife switch, and device, medium and product Download PDF

Info

Publication number
AU2022381656A1
AU2022381656A1 AU2022381656A AU2022381656A AU2022381656A1 AU 2022381656 A1 AU2022381656 A1 AU 2022381656A1 AU 2022381656 A AU2022381656 A AU 2022381656A AU 2022381656 A AU2022381656 A AU 2022381656A AU 2022381656 A1 AU2022381656 A1 AU 2022381656A1
Authority
AU
Australia
Prior art keywords
knife switch
image
position area
open position
close position
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
AU2022381656A
Other versions
AU2022381656B2 (en
Inventor
Jiacong FANG
Hao Gong
Shaojian Xiao
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuhai Unitech Power Technology Co Ltd
Original Assignee
Zhuhai Unitech Power Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhuhai Unitech Power Technology Co Ltd filed Critical Zhuhai Unitech Power Technology Co Ltd
Publication of AU2022381656A1 publication Critical patent/AU2022381656A1/en
Application granted granted Critical
Publication of AU2022381656B2 publication Critical patent/AU2022381656B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
  • Spinning Or Twisting Of Yarns (AREA)
  • Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The present disclosure provides a method and apparatus for determining the open/closed state of a knife switch, and a device, a medium and a product. The method comprises: acquiring a knife switch monitoring image; extracting image features of a plurality of preset regions in the knife switch monitoring image, wherein the plurality of preset regions at least comprise a closing position region in which a knife switch is located when same is in a closing position state and an opening position region in which the knife switch is located when same is in an opening position state; performing structural similarity comparison on the image features of the preset regions in the knife switch monitoring image with an image feature of a preset region corresponding to a preset knife switch template image; and determining the open/closed state of the knife switch according to a structural similarity comparison result.

Description

Method and Apparatus for Determining Opened or Closed State of Knife Switch,
Device, Medium and Product
Cross-Reference to Related Application
The present disclosure claims the priority of Chinese Patent Application 202111314122.4, filed in the China National Intellectual Property Administration (CNIPA) on November 08, 2021, and entitled "Method and Apparatus for Determining Opened or Closed State of Knife Switch, Device, Medium and Product", the entire contents of which are herein incorporated by reference.
Technical Field
The present disclosure relates to the technical field of rail transit, and in particular, to a method and apparatus for determining an opened or closed state of a knife switch, a device, a medium and a product.
Background
In the field of rail transit, the device state management in a rail is closely related to the safety of rail transit. The monitoring and management of a knife switch device in the rail are a relatively important part.
According to a traditional monitoring and management mode of the knife switch device, an opened or closed state of a knife switch is determined by means of detecting whether electrical communication is conducted or not, or by means of a physical mechanical sensor and the like. In order to determine the opened or closed state of the knife switch, a sensor needs to be added into a device body. Once the sensor fails, it is impossible to determine the opened or closed state of the knife switch, and it is necessary to shut down a running device during maintenance or transformation for the failed sensor.
Therefore, a new method for determining (or confirming) the opened or closed state of the knife switch is required in the field of rail transit, so as to solve the problem that the opened or closed state of the knife switch cannot be determined when the sensor fails.
Summary
Embodiments of the present disclosure provide a method and apparatus for determining an opened or closed state of a knife switch, a device, a medium and a product, which are used for providing a method for determining (or confirming) the opened or closed state of the knife switch, so as to solve the problem that the opened or closed state of the knife switch cannot be determined when a sensor fails.
A first aspect of the embodiments of the present disclosure provides a method for determining an opened or closed state of a knife switch, including: acquiring a monitoring image of the knife switch, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open; extracting image features within a plurality of preset areas from the monitoring image of the knife switch, wherein the plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located; comparing structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch; and determining the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes.
A second aspect of the embodiments of the present disclosure provides an apparatus for determining an opened or closed state of a knife switch, including: an acquisition module, configured to acquire a monitoring image of the knife switch, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open; an extraction module, configured to extract image features within a plurality of preset areas from the monitoring image of the knife switch, wherein the plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located; a comparison module, configured to determine a structural similarity index between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch; and a determination module, configured to determine the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes.
A third aspect of the embodiments of the present disclosure provides an electronic device, including: a processor, and a memory in communication connection with the processor, wherein the memory stores a computer-executable instruction; and the processor executes the computer-executable instruction stored in the memory, so as to implement the method for determining the opened or closed state of the knife switch in any item of the first aspect.
A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, wherein a computer-executable instruction is stored in the computer-readable storage medium, and the computer-executable instruction, when executed by a processor, causes the processor to implement the method for determining the opened or closed state of the knife switch in any item of the first aspect.
A fifth aspect of the embodiments of the present disclosure provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, causes the processor to implement the method for determining the opened or closed state of the knife switch in any item of the first aspect.
The embodiments of the present disclosure provide a method and apparatus for determining an opened or closed state of a knife switch, a device, a medium and a product. The method includes: acquiring a monitoring image of the knife switch, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open; extracting image features within a plurality of preset areas from the monitoring image of the knife switch, wherein the plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located; comparing structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch; and determining the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes. In the method for determining the opened or closed state of the knife switch, structural similarity indexes between the preset areas in the monitoring image of the knife switch and the preset areas in the preset template image of the knife switch are compared, and since the preset areas at least include the close position area where the knife switch in the closed state is located, and the open position area where the knife switch in the opened state is located, the opened or closed state of the knife switch can be determined according to the comparison result regardless of whether a sensor fails.
Brief Description of the Drawings
The drawings described herein are incorporated in the specification and constitute a part of the present specification, illustrate embodiments conforming to the present disclosure, and, together with the specification, serve to explain the principles of the present disclosure.
Fig. 1 is a diagram showing a scenario in which a method for determining an opened or closed state of a knife switch of the embodiments of the present disclosure may be implemented;
Fig. 2 is a schematic diagram of a flow of a method for determining an opened or closed state of a knife switch provided in a first embodiment of the present disclosure;
Fig. 3 is a schematic diagram of a flow of a method for determining an opened or closed state of a knife switch provided in a second embodiment of the present disclosure;
Fig. 4 is a schematic diagram of preset areas in the method for determining the opened or closed state of the knife switch provided in the second embodiment of the present disclosure;
Fig. 5 is a schematic diagram of an image alignment process of a method for determining an opened or closed state of a knife switch provided in a third embodiment of the present disclosure;
Fig. 6 is a schematic diagram of an interaction process of a method for determining an opened or closed state of a knife switch provided in a fourth embodiment of the present disclosure;
Fig. 7 is a schematic diagram of an image alignment process of the method for determining the opened or closed state of the knife switch provided in the fourth embodiment of the present disclosure;
Fig. 8 is a schematic diagram of the structure of an apparatus for the determining opened or closed state of a knife switch provided in a fifth embodiment of the present disclosure; and
Fig. 9 is a schematic diagram of the structure of an electronic device provided in a sixth embodiment of the present disclosure.
Through the above drawings, exemplary embodiments of the present disclosure have been shown, which will be described in more detail hereinafter. These drawings and text descriptions are not intended to limit the scope of the conception of the present disclosure in any way, but to illustrate the concepts of the present disclosure for those skilled in the art with reference to exemplary embodiments.
Detailed Description
Exemplary embodiments will be described in detail herein, examples of which are illustrated in the drawings. When the following description involve the drawings, the same numbers in different drawings represent the same or similar elements, unless otherwise represented. The embodiments described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as recited in the appended claims.
The technical solutions of the present disclosure will be described in detail below with exemplary embodiments. The following several exemplary embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present disclosure will be described below in combination with the drawings.
In order to facilitate clear understanding of the technical solutions of the present disclosure, the solutions of the related art are first described in detail. A computer vision technology is a technology of simulating a visual process of humans by a computer, and is a combination of technologies such as image processing, artificial intelligence and pattern recognition. With the continuous development of rail transit, the computer vision technology has also been more frequently applied in the device state management in rails. In the traditional monitoring and management of a knife switch device in a rail, since a sensor needs to be added into a device body, once the sensor fails, it is impossible to determine the opened or closed state of a knife switch, and it is necessary to shut down a running device during maintenance or transformation. Therefore, a new method for determining (or confirming) the opened or closed state of the knife switch is required in the field of rail transit, so as to solve, in combination with the computer vision technology, the problem that the opened or closed state of the knife switch cannot be determined when the sensor fails.
Therefore, in view of the problem in the related art that, a new method for determining (or confirming) the opened or closed state of a knife switch is required in the field of rail transit, so as to solve the problem that the opened or closed state of the knife switch cannot be determined when a sensor fails. In order to solve the problem, in the solution provided in the embodiments of the present disclosure, a monitoring image of the knife switch captured by a photographing apparatus that monitors the running state of a knife switch device is firstly acquired, and the opened or closed state of the knife switch is determined according to the monitoring image of the knife switch and a preset template image of the knife switch.
In some exemplary implementations, when a knife switch control apparatus controls the knife switch device to close or open, a monitoring image of the knife switch, which is captured within a monitoring area of the knife switch by a photographing apparatus, is acquired, and image features within a plurality of preset areas are extracted from the monitoring image of the knife switch. The plurality of preset areas at least include a close position area where the knife switch is located when a knife switch is in a closed state, and an open position area where the knife switch in an opened state is located. Then, structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch are compared. The opened or closed state of the knife switch is determined according to a comparing result of the structural similarity indexes. Therefore, the opened or closed state of the knife switch can be determined according to the comparison result regardless of whether the sensor fails.
Based on the above-mentioned inventive concept, the technical solutions of the embodiments of the present disclosure are proposed.
An application scenario of a method for determining an opened or closed state of a knife switch provided in the embodiments of the present disclosure will be described below. As shown in Fig. 1, 1 represents an electronic device, 2 represents a knife switch control apparatus, 3 represents a knife switch device, and 4 represents a photographing apparatus. A network architecture of the application scenario corresponding to the method for determining the opened or closed state of the knife switch provided in the embodiments of the present disclosure includes: an electronic device 1, a knife switch control apparatus 2, a knife switch device 3 and a photographing apparatus 4. The knife switch control apparatus 2 may control a knife switch of the knife switch device 3 to close or open, and the photographing apparatus 4 may capture a monitoring image within a monitoring area of the knife switch including the knife switch device 3.
After the knife switch control apparatus 2 controls the knife switch of the knife switch device 3 to close or open, the knife switch device 3 feeds back running information of the knife switch by means of a sensor arranged in the knife switch device 3. In addition, the knife switch control apparatus 2 sends an image sending instruction to the photographing apparatus 4 within a preset time period, such as 5 seconds, so that the photographing apparatus 4 sends, to the electronic device 1, a monitoring image of the knife switch that is captured within a monitoring area of the knife switch. After acquiring the monitoring image of the knife switch, the electronic device 1 extracts image features within a plurality of preset areas from the monitoring image of the knife switch. The plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located. The electronic device 1 compares structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch, and determines the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes. After determining the opened or closed state of the knife switch, the electronic device 1 may send the opened or closed state of the knife switch to the knife switch control apparatus 2, such that the knife switch control apparatus 2 may further determine the opened or closed state of the knife switch according to the opened or closed state of the knife switch and the running information of the knife switch.
The embodiments of the present disclosure will be described below in combination with the drawings in the specification.
Fig. 2 is a schematic diagram of a flow of a method for determining an opened or closed state of a knife switch provided in a first embodiment of the present disclosure. As shown in Fig. 2, the method in the embodiment of the present disclosure is performed by an apparatus for determining an opened or closed state of a knife switch. The apparatus for determining the opened or closed state of the knife switch may be integrated in an electronic device. The method for determining the opened or closed state of the knife switch provided in the present embodiment includes the following operations.
At Si01, a monitoring image of the knife switch is acquired. The monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus. The image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open.
In the present embodiment, the photographing apparatus may capture, in real time, the monitoring image within the monitoring area of the knife switch including the knife switch; alternatively, the photographing apparatus may capture the monitoring image within the monitoring area of the knife switch after receiving the image sending instruction, which is not limited in the present embodiment. Within the preset time period after the knife switch control apparatus controls the knife switch to close or open, the knife switch control apparatus sends the image sending instruction to the photographing apparatus, such that the photographing apparatus sends, to the apparatus for determining the opened or closed state of the knife switch, the monitoring image of the knife switch captured within the monitoring area of the knife switch.
The preset time period may be set according to actual requirements, for example, if it takes the knife switch 4 seconds to transit from a completely closed state to a completely opened state, then the preset time period may be set to be 4 seconds or 5 seconds, thereby reducing the probability that the image captured by the photographing apparatus is an image in which the knife switch is in an incompletely closed state or an incompletely opened state.
At S102, image features within a plurality of preset areas are extracted from the monitoring image of the knife switch. The plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located.
In the present embodiment, the extracted image features may be Scale-Invariant Feature Transform (SIFT) features, such that the extracted features are more stable, and subsequent structural similarity index comparison with respect to the preset template image of the knife switch may also be more stable.
The close position area where the knife switch in the closed state is located refers to a position area where the knife switch is located when the knife switch is at a complete close position. The open position area where the knife switch in the opened state is located refers to a position area where the knife switch is located when the knife switch is at a complete open position.
The preset areas are shown by dashed boxes a and b in Fig. 4, wherein the dashed box a may refer to the open position area where the knife switch in the opened state is located, and the dashed box b may refer to the close position area where the knife switch in the closed state is located. The preset areas need to at least include the close position area where the knife switch in the closed state is located, and the open position area where the knife switch in the opened state is located, therefore during subsequent comparison with the preset template image of the knife switch, it is determined whether the knife switch is in the closed state, the opened state or neither the closed state nor the opened state.
At S103, structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from the preset template image of the knife switch are compared.
In the present embodiment, the preset template image of the knife switch includes pre-captured images of the knife switch in various states, for example, a captured template image in the closed state, and a captured template image in the opened state. After a single-time configuration of the preset template image of the knife switch, this configuration may be repeatedly used without model training, thereby improving the configuration efficiency.
The structural similarity index (SSIM) is used for comparing the similarity between two images, and is an index for measuring the similarity between two images.
At S104, the opened or closed state of the knife switch is determined according to a comparing result of the structural similarity indexes.
In the present embodiment, the structural similarity index may be used for determining the similarity between the monitoring image of the knife switch and the preset template image of the knife switch, and it is possible to determine, according to the similarity, whether the knife switch in the monitoring image of the knife switch is in the state of the knife switch in the preset template image of the knife switch, so as to determine the opened or closed state of the knife switch in the monitoring image of the knife switch.
The embodiment of the present disclosure provides a method for determining an opened or closed state of a knife switch. In the method, a monitoring image of the knife switch is acquired, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open; image features within a plurality of preset areas are extracted from the monitoring image of the knife switch, wherein the plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located; structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch are compared; and the opened or closed state of the knife switch is determined according to a comparing result of the structural similarity indexes.
According to the method for determining the opened or closed state of the knife switch in the embodiment of the present disclosure, structural similarity indexes between the preset areas in the monitoring image of the knife switch and the preset areas in the preset template image of the knife switch are compared. Since the preset areas at least include the close position area where the knife switch in the closed state is located, and the open position area where the knife switch in the opened state is located, the opened or closed state of the knife switch can be determined according to the comparison result regardless of whether a sensor fails.
Fig. 3 is a schematic diagram of a flow of a method for determining an opened or closed state of a knife switch provided in a second embodiment of the present disclosure. As shown in Fig. 3, the method for determining the opened or closed state of the knife switch provided in the present embodiment further refines each operation on the basis of the method for determining the opened or closed state of the knife switch provided in the previous embodiment of the present disclosure. The method for determining the opened or closed state of the knife switch provided in the present embodiment includes the following operations.
At S201, a monitoring image of the knife switch is acquired. The monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus. The image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open.
In the present embodiment, the implementation of operation S201 is similar to that of operation Si01 in the previous embodiment of the present disclosure, and thus details will not be described herein again.
At S202, coordinate ranges of preset areas in a preset template image of the knife switch in the preset template image of the knife switch are acquired, wherein the preset template image of the knife switch includes a pre-captured close position template image when the knife switch is in a closed state, and a pre-captured open position template image when the knife switch is in an opened state. The close position template image includes a close position area when the knife switch is in the closed state, and an open position area when the knife switch is in the closed state. The open position template image includes a close position area when the knife switch is in the opened state, and an open position area when the knife switch is in the opened state.
In the present embodiment, when the preset template image of the knife switch is configured, each preset area is represented in the form of a coordinate range. The preset areas may be in the form of square areas, as shown by dashed boxes a and b in Fig. 4, and may also be set to be a circle or other shapes.
In the present embodiment, the close position template image may further include an image of the close position area when the knife switch is in the close position area, and an image of the open position area when the knife switch is in the close position area. The open position template image may further include an image of the close position area when the knife switch is in the open position area, and an image of the open position area when the knife switch is in the open position area.
At S203, image features within corresponding preset areas are extracted from the monitoring image of the knife switch according to the coordinate ranges.
In the present embodiment, since the preset areas in the monitoring image of the knife switch correspond to the preset areas in the preset template image of the knife switch, the image features within the corresponding preset areas may be extracted from the monitoring image of the knife switch according to the coordinate ranges of the preset template image of the knife switch. The image features within the corresponding preset areas may also be extracted from the monitoring image of the knife switch in other manners, which is not limited in the present embodiment.
It should be noted that, the preset areas include the close position area where the knife switch in the closed state is located, and the open position area where the knife switch in the opened state is located.
At S204, the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is compared with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine a comparison result for the close position area.
In the present embodiment, the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is compared with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine whether there is a knife switch in the close position area in the monitoring image of the knife switch. As shown in Fig. 4, the area of the dashed box b is the close position area in the preset areas, when the knife switch is in the closed state, there is a knife switch in the area of the dashed box b, and when the knife switch is in the opened state, there is no knife switch in the area of the dashed box b.
Meanwhile, an exemplary structural similarity index comparing process is as follows.
In a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is greater than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, the comparison result for the close position area is determined to be that there is a knife switch in the close position area.
In a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is less than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, the comparison result for the close position area is determined to be that there is no knife switch in the close position area.
The structural similarity index is represented in the form of a numerical value, the general numerical value is between 0 and 1, and the greater the numerical value is, the higher the similarity is. When the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is greater, it indicates that there is a knife switch in the close position area.
At S205, the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is compared with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine a comparison result for the open position area.
In the present embodiment, the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is compared with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine whether there is a knife switch in the open position area in the monitoring image of the knife switch. As shown in Fig. 4, the area of the dashed box a is the open position area in the preset areas, when the knife switch is in the opened state, there is a knife switch in the area of the dashed box a, and when the knife switch is in the closed state, there is no knife switch in the area of the dashed box a.
Meanwhile, an exemplary structural similarity index comparing process is as follows.
In a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is greater than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, the comparison result for the open position area is determined to be that there is no knife switch in the open position area.
In a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is less than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, the comparison result for the open position area is determined to be that there is a knife switch in the open position area.
The determination mode of the open position area is similar to the determination mode of the close position area, that is, when the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image is greater, it indicates that there is a knife switch in the open position area.
At S206, the opened or closed state of the knife switch is determined according to the comparison result for the close position area and the comparison result for the open position area.
In an exemplary implementation of the present embodiment, the operation of determining the opened or closed state of the knife switch according to the comparison result for the close position area and the comparison result for the open position area may be as follows.
In a case where the comparison result for the close position area is that there is a knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, it is determined that the knife switch is in the closed state.
In a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is a knife switch in the open position area, it is determined that the knife switch is in the opened state.
In a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, it is determined that the knife switch is neither in the opened state nor in the closed state.
At S207, the opened or closed state of the knife switch is sent to the knife switch control apparatus, such that the knife switch control apparatus re-determines the opened or closed state of the knife switch according to the opened or closed state of the knife switch and running information of the knife switch fed back by a sensor.
In the present embodiment, the opened or closed state of the knife switch may be sent to the knife switch control apparatus, such that the knife switch control apparatus may re-determine the opened or closed state of the knife switch according to the opened or closed state of the knife switch and the running information of the knife switch fed back by the sensor. In this way, the accuracy and stability of determining the opened or closed state of the knife switch are improved.
Fig. 5 is a schematic diagram of an image alignment process of a method for determining an opened or closed state of a knife switch provided in a third embodiment of the present disclosure.
As shown in Fig. 5, the method for determining the opened or closed state of the knife switch provided in the present embodiment adds an image alignment process on the basis of the method for determining the opened or closed state of the knife switch provided in the previous embodiments of the present disclosure, and the image alignment process includes the following operations.
At S301, image features are extracted from the monitoring image of the knife switch, and image features are extracted from the preset template image of the knife switch.
In the present embodiment, the image features extracted from the monitoring image of the knife switch are preferably SIFT features, and thus the matching degree of image feature pairs and the stability of a transformation matrix can be better improved.
At S302, the image features extracted from the monitoring image of the knife switch are matched with the image features extracted from the preset template image of the knife switch, so as to generate a plurality of matching image feature pairs.
The matching image feature pair is a feature pair composed of two matching image features.
The matching may be implemented by Fast Library for Approximate Nearest Neighbors (FlLANN) or Brute Force (BF) algorithm, so as to further improve the accuracy and stability of matching the image feature pairs.
At S303, a transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch is determined according to the plurality of matching image feature pairs and a preset projection transformation algorithm.
The preset projection transformation algorithm may be a Random Sample Consensus (RANSAC) robust solution algorithm, so as to determine a more stable transformation matrix with higher accuracy.
Meanwhile, when the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch is determined according to the plurality of matching image feature pairs and the preset projection transformation algorithm, it is possible to determine whether the number of the plurality of matching image feature pairs is greater than or equal to a preset threshold.
In a case where it is determined that the number of the plurality of matching image feature pairs is greater than or equal to the preset threshold, the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch is determined according to the plurality of matching image feature pairs and the preset projection transformation algorithm.
In a case where it is determined that the number of the plurality of matching image feature pairs is less than the preset threshold, it may be determined that the matching degree between the monitoring image of the knife switch and the preset template image of the knife switch is too low, and the next monitoring image of the knife switch may be used to perform the image alignment process.
At S304, the monitoring image of the knife switch is corrected according to the transformation matrix, such that the corrected monitoring image of the knife switch is aligned with the preset template image of the knife switch.
In the present embodiment, since relatively large vibration is easily generated during the actual operation of a railway vehicle, the photographing apparatus may have an angle offset, in order to address this problem, the correction processing is performed on the monitoring image of the knife switch. If the photographing apparatus has the angle offset, the captured monitoring image of the knife switch also has an angle offset, thus affecting the subsequent determination of the opened or closed state of the knife switch. Therefore, the angle offset problem of the photographing apparatus can be solved by correcting the monitoring image of the knife switch.
In order to facilitate the understanding of the method for determining the opened or closed state of the knife switch provided in the above embodiments of the present disclosure, a further description will be given below in combination with the drawings. As shown in Fig. 6, in the present embodiment, it is taken as an example for illustration that the knife switch control apparatus re-determines the opened or closed state of the knife switch. The knife switch control apparatus is a control apparatus in a common one-key sequential control system, and is represented by one-key sequential control in the figure. The photographing apparatus used in the present embodiment is a camera.
The overall process is as follows. The one-key sequential control system sends a signal to control the knife switch to close or open. After waiting for several seconds, the knife switch acts in place, and the sensor in the knife switch device feeds back the running information of the knife switch, that is, whether the knife switch is at a close position or an open position. Meanwhile, the one-key sequential control system sends an image sending instruction to the camera, such that the camera transmits the captured monitoring image of the knife switch to the apparatus for determining the opened or closed state of the knife switch, so as to determine the opened or closed state of the knife switch, and return a result to the one-key sequential control system. The one-key sequential control system integrates the state discrimination information of the sensor and the state discrimination information of the apparatus for determining the opened or closed state of the knife switch, so as to obtain the opened or closed state of the knife switch to complete the double confirmation of the opened or closed state of the knife switch.
The specific process is as follows.
Before the analysis of determining the opened or closed state of the knife switch, images of the knife switch at the open position and close position are intercepted and are respectively configured with labels. After a single-time configuration is completed, this configuration may be repeatedly used without model training.
In some exemplary implementations, two photos of the knife switch respectively in the opened state and in the closed state are stored as template images. Two dashed boxes at positions a and b, where a contact of the knife switch is movably connected in an opened state and a closed state respectively, are marked in the template images, as shown in Fig. 4, the state at the close position is shown at the upper side of Fig. 4, and the state at the open position is shown at the lower side of Fig. 4. Thus, four matching templates may be obtained, which are respectively a close position (there is a knife switch), a close position (there is no knife switch), an open position (there is a knife switch), and an operating position (there is no knife switch). The 4 areas will be used for identifying the opened or closed state of the knife switch.
Then, as shown in Fig. 7, the angle of the camera in the monitoring image of the knife switch is first corrected, such that the monitoring image of the knife switch is aligned with the template image. In some exemplary implementations, the apparatus for determining the opened or closed state of the knife switch obtains, from the camera, the monitoring image of the knife switch in which the opened or closed state of the knife switch needs to be determined, extracts SIFT features from the image, then matches the SIFT features extracted from the monitoring image of the knife switch with the SIFT features extracted from the template image through an FLANN or BF algorithm, so as to obtain feature points in pairs. The apparatus determines whether the number of feature point pairs is greater than or equal to 10, if not, waits for an image input by the camera next time, and if so, calculates, according to an affine or projection transformation relationship and by using an RANSAC robust solution algorithm, a transformation matrix M from the monitoring image of the knife switch to the template image. The apparatus performs affine or projection transformation on the monitoring image of the knife switch according to the transformation matrix M, aligns the two images, and corrects the angle offset of the camera, so as to complete image alignment.
After image alignment is completed, structural similarity indexes between the monitoring image of the knife switch and the template image are compared. First, according to the coordinates of the dashed box areas a and b of the template image, corresponding dashed box areas a and b on the aligned monitoring image of the knife switch are selected to be compared with the dashed box areas a and b of the stored template image. By means of the SSIM similarity comparison, whether there is a knife switch in the areas a and b are obtained, and then the opened or closed state of the knife switch is determined. The determination of the opened or closed state is as shown in Table 1, that is, a table of the opened and closed state of the knife switch.
Table 1 Table of an opened and closed state of the knife switch
State of area a State of area b State of the knife switch
There is no knife switch There is a knife switch Close position
There is a knife switch There is no knife switch Open position
There is no knife switch There is no knife switch The action is not in place
There is a knife switch There is a knife switch Analysis error
After reading the corresponding state from Table 1, the apparatus for determining the opened or closed state of the knife switch sends the opened or closed state of the knife switch to the one-key sequential control system.
Fig. 8 is a schematic diagram of the structure of an apparatus for determining an opened or closed state of a knife switch provided in a fifth embodiment of the present disclosure. As shown in Fig. 8, in the present embodiment, the apparatus 400 for determining the opened or closed state of the knife switch includes: an acquisition module 401, an extraction module 402, a comparison module 403, and a determination module 404.
The acquisition module 401 is configured to acquire a monitoring image of the knife switch. The monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus. The image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open.
The extraction module 402 is configured to extract image features within a plurality of preset areas from the monitoring image of the knife switch. The plurality of preset areas at least include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located.
The comparison module 403 is configured to determine a structural similarity index between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch.
The determination module 404 is configured to determine the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes.
The apparatus for determining the opened or closed state of the knife switch provided in the present embodiment may execute the technical solutions of the method embodiment shown in Fig. 2, and the implementation principles and technical effects thereof are similar to those of the method embodiment shown in Fig. 2, and thus will not be repeated herein again.
Meanwhile, the apparatus for determining the opened or closed state of the knife switch provided in the present disclosure further refines the apparatus 400 for determining the opened or closed state of the knife switch on the basis of the apparatus for determining the opened or closed state of the knife switch provided in the previous embodiment.
In an exemplary implementation of the present embodiment, the extraction module 402 is configured to:
acquire coordinate ranges of the preset areas in the preset template image of the knife switch, and extract image features within corresponding preset areas from the monitoring image of the knife switch according to the coordinate ranges.
In an exemplary implementation of the present embodiment, the preset areas include a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located.
The preset template image of the knife switch includes a pre-captured close position template image when the knife switch is in the closed state, and a pre-captured open position template image when the knife switch is in the opened state. The close position template image includes a close position area when the knife switch is in the closed state, and an open position area when the knife switch is in the closed state. The open position template image includes a close position area when the knife switch is in the opened state, and an open position area when the knife switch is in the opened state.
The comparison module 403 is configured to: compare the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine a comparison result for the close position area; and compare the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine a comparison result for the open position area.
In an exemplary implementation of the present embodiment, when comparing the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine the comparison result for the close position area, the comparison module 403 is configured to:
in a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is greater than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, determine the comparison result for the close position area to be that there is a knife switch in the close position area; and in a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is less than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, determine the comparison result for the close position area to be that there is no knife switch in the close position area.
In an exemplary implementation of the present embodiment, when comparing the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine the comparison result for the open position area, the comparison module 403 is configured to:
in a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is greater than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, determine the comparison result for the open position area to be that there is no knife switch in the open position area; and in a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is less than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, determine the comparison result for the open position area to be that there is a knife switch in the open position area.
In an exemplary implementation of the present embodiment, the determination module 404 is configured to:
in a case where the comparison result for the close position area is that there is a knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, determine that the knife switch is in the closed state; in a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is a knife switch in the open position area, determine that the knife switch is in the opened state; and in a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, determine that the knife switch is neither in the opened state nor in the closed state.
In an exemplary implementation of the present embodiment, the apparatus 400 for determining the opened or closed state off the knife switch further includes:
an image alignment module, configured to extract image features from the monitoring image of the knife switch and extract image features from the preset template image of the knife switch; match the image features extracted from the monitoring image of the knife switch with the image features extracted from the preset template image of the knife switch, so as to generate a plurality of matching image feature pairs; determine a transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and a preset projection transformation algorithm; and correct the monitoring image of the knife switch according to the transformation matrix, such that the corrected monitoring image of the knife switch is aligned with the preset template image of the knife switch.
In an exemplary implementation of the present embodiment, when determining the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and the preset projection transformation algorithm, the image alignment module is configured to: determine whether the number of the plurality of matching image feature pairs is greater than or equal to a preset threshold; and in a case where it is determined that the number of the plurality of matching image feature pairs is greater than or equal to the preset threshold, determine the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and the preset projection transformation algorithm.
In an exemplary implementation of the present embodiment, the apparatus 400 for determining the opened or closed state off the knife switch further includes:
a secondary determination module, configured to send the opened or closed state of the knife switch to the knife switch control apparatus, such that the knife switch control apparatus re-determines the opened or closed state of the knife switch according to the opened or closed state of the knife switch and the running information of the knife switch fed back by the sensor.
The apparatus for determining the opened or closed state of the knife switch provided in the present embodiment may execute the technical solutions of the method embodiments shown in Fig. 2 to Fig. 7, and the implementation principles and technical effects thereof are similar to those of the method embodiments shown in Fig. 2 to Fig. 7, and thus will not be repeated herein again.
The present disclosure further provides an electronic device, a computer-readable storage medium, and a computer program product.
As shown in Fig. 9, Fig. 9 is a schematic diagram of the structure of an electronic device provided in a sixth embodiment of the present disclosure. The electronic device is intended to be applicable in various forms to a digital computer, such as a laptop computer, a personal digital assistant, and other suitable computers, which are used for determining and training the opened or closed state of a knife switch. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementations of the present disclosure described and/or claimed herein.
As shown in Fig. 9, the electronic device includes a processor 501 and a memory 502. The components are connected to each other by using different buses, and may be installed on a common motherboard or installed in other manners according to requirements. The processor may process instructions executed in the electronic device.
The memory 502 is a non-transitory computer-readable storage medium provided in the embodiments of the present disclosure. The memory stores instructions executable by at least one processor, such that the at least one processor executes the method for determining the opened or closed state of the knife switch provided in the embodiments of the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores a computer instruction, and the computer instruction is used for causing a computer to execute the method for determining the opened or closed state of the knife switch provided in the embodiments of the present disclosure.
As a non-transitory computer-readable storage medium, the memory 502 may be configured to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules (for example, the acquisition module 401, the extraction module 402, the comparison module 403 and the determination module 404 shown in Fig. 8) corresponding to the method for determining the opened or closed state of the knife switch in the embodiments of the present disclosure. By means of running the non-transitory software programs, instructions and modules stored in the memory 502, the processor 501 executes various functional applications and data processing of a server, that is, implements the method for determining the opened or closed state of the knife switch in the above method embodiments.
Meanwhile, the present embodiment further provides a computer product, and when an instruction in the computer product is executed by a processor of the electronic device, the electronic device may execute the method for determining the opened or closed state of the knife switch in the above embodiment.
Other implementation solutions of the embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses or adaptive changes of the embodiments of the present disclosure, and these variations, uses or adaptive changes follow the general principles of the embodiments of the present disclosure and include common general knowledge or customary technical means in the present art, which is not disclosed in the embodiments of the present disclosure. The specification and embodiments are to be considered as exemplary only.
It should be understood that, the embodiments of the present disclosure are not limited to the precise structures that have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present disclosure is limited only by the appended claims.

Claims (14)

Claims
1. A method for determining an opened or closed state of a knife switch, comprising:
acquiring a monitoring image of the knife switch, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open;
extracting image features within a plurality of preset areas from the monitoring image of the knife switch, wherein the plurality of preset areas at least comprise a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located;
comparing structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch, wherein the preset template image of the knife switch comprises a pre-captured close position template image when the knife switch is in the closed state, and a pre-captured open position template image when the knife switch is in the opened state; the close position template image comprises a close position area in which there is a knife switch, and an open position area in which there is no knife switch; and the open position template image comprises a close position area in which there is no knife switch, and an open position area in which there is a knife switch; and
determining the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes.
2. The method according to claim 1, wherein extracting the image features within the plurality of preset areas extracted from the monitoring image of the knife switch comprises:
acquiring coordinate ranges of the preset areas in the preset template image of the knife switch; and
extracting the image features within the corresponding preset areas from the monitoring image of the knife switch according to the coordinate ranges.
3. The method according to claim 1, wherein comparing the structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and the image features within the corresponding preset areas extracted from the preset template image of the knife switch comprises:
comparing the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine a comparison result for the close position area; and
comparing the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine a comparison result for the open position area.
4. The method according to claim 3, wherein comparing the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image with the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, so as to determine the comparison result for the close position area comprises:
in a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is greater than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, determining the comparison result for the close position area to be that there is a knife switch in the close position area; and
in a case where the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the close position template image is less than the structural similarity index between the close position area in the monitoring image of the knife switch and the close position area in the open position template image, determining the comparison result for the close position area to be that there is no knife switch in the close position area.
5. The method according to claim 4, wherein comparing the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image with the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, so as to determine the comparison result for the open position area comprises:
in a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is greater than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, determining the comparison result for the open position area to be that there is no knife switch in the open position area; and
in a case where the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the close position template image is less than the structural similarity index between the open position area in the monitoring image of the knife switch and the open position area in the open position template image, determining the comparison result for the open position area to be that there is a knife switch in the open position area.
6. The method according to claim 5, wherein determining the opened or closed state of the knife switch according to the comparing result of the structural similarity indexes comprises:
in a case where the comparison result for the close position area is that there is a knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, determining that the knife switch is in the closed state;
in a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is a knife switch in the open position area, determining that the knife switch is in the opened state; and
in a case where the comparison result for the close position area is that there is no knife switch in the close position area, and the comparison result for the open position area is that there is no knife switch in the open position area, determining that the knife switch is neither in the opened state nor in the closed state.
7. The method according to any of claims 1-6, wherein before extracting the image features within the plurality of preset areas extracted from the monitoring image of the knife switch, the method further comprises:
extracting image features from the monitoring image of the knife switch, and extracting image features from the preset template image of the knife switch;
matching the image features extracted from the monitoring image of the knife switch with the image features extracted from the preset template image of the knife switch, so as to generate a plurality of matching image feature pairs;
determining a transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and a preset projection transformation algorithm; and
correcting the monitoring image of the knife switch according to the transformation matrix, such that the corrected monitoring image of the knife switch is aligned with the preset template image of the knife switch.
8. The method according to claim 7, wherein determining the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and the preset projection transformation algorithm comprises:
determining whether the number of the plurality of matching image feature pairs is greater than or equal to a preset threshold; and
in a case where it is determined that the number of the plurality of matching image feature pairs is greater than or equal to the preset threshold, determining the transformation matrix between the monitoring image of the knife switch and the preset template image of the knife switch according to the plurality of matching image feature pairs and the preset projection transformation algorithm.
9. The method according to claim 7, wherein correcting the monitoring image of the knife switch according to the transformation matrix, such that the corrected monitoring image of the knife switch is aligned with the preset template image of the knife switch comprises: performing affine or projection transformation on the monitoring image of the knife switch according to the transformation matrix, such that the monitoring image of the knife switch, which has been subjected to the affine or projection transformation, is aligned with the preset template image of the knife switch.
10. The method according to claim 1, wherein after determining the opened or closed state of the knife switch according to the comparing result of the structural similarity indexes, the method further comprises:
sending the opened or closed state of the knife switch to the knife switch control apparatus, such that the knife switch control apparatus re-determines the opened or closed state of the knife switch according to the received opened or closed state of the knife switch and running information of the knife switch fed back by a sensor.
11. An apparatus for determining an opened or closed state of a knife switch, comprising:
an acquisition module, configured to acquire a monitoring image of the knife switch, wherein the monitoring image of the knife switch is captured, within a monitoring area of the knife switch, by a photographing apparatus and is sent by the photographing apparatus according to an image sending instruction from a knife switch control apparatus, and the image sending instruction is generated by the knife switch control apparatus within a preset time period after controlling the knife switch to close or open;
an extraction module, configured to extract image features within a plurality of preset areas from the monitoring image of the knife switch, wherein the plurality of preset areas at least comprise a close position area where the knife switch in a closed state is located, and an open position area where the knife switch in an opened state is located;
a comparison module, configured to compare structural similarity indexes between the image features within the preset areas extracted from the monitoring image of the knife switch and image features within corresponding preset areas extracted from a preset template image of the knife switch, wherein the preset template image of the knife switch comprises a pre-captured close position template image when the knife switch is in the closed state, and a pre-captured open position template image when the knife switch is in the opened state; the close position template image comprises a close position area in which there is a knife switch, and an open position area in which there is no knife switch; and the open position template image comprises a close position area in which there is no knife switch, and an open position area in which there is a knife switch; and a determination module, configured to determine the opened or closed state of the knife switch according to a comparing result of the structural similarity indexes.
12. An electronic device, comprising: a processor, and a memory in communication connection with the processor, wherein
the memory stores a computer-executable instruction; and
the processor executes the computer-executable instruction stored in the memory, so as to implement the method for determining the opened or closed state of the knife switch according to any of claims 1-10.
13. A computer-readable storage medium, wherein a computer-executable instruction is stored in the computer-readable storage medium, and the computer-executable instruction, when executed by a processor, causes the processor to implement the method for determining the opened or closed state of the knife switch according to any of claims 1-10.
14. A computer program product, comprising a computer program, wherein the computer program, when executed by a processor, causes the processor to implement the method for determining the opened or closed state of the knife switch according to any of claims 1-10.
AU2022381656A 2021-11-08 2022-11-01 Method and apparatus for determining open/closed state of knife switch, and device, medium and product Active AU2022381656B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202111314122.4 2021-11-08
CN202111314122.4A CN114220068B (en) 2021-11-08 2021-11-08 Method, device, equipment, medium and product for determining disconnecting link switching state
PCT/CN2022/129042 WO2023078254A1 (en) 2021-11-08 2022-11-01 Method and apparatus for determining open/closed state of knife switch, and device, medium and product

Publications (2)

Publication Number Publication Date
AU2022381656A1 true AU2022381656A1 (en) 2023-07-06
AU2022381656B2 AU2022381656B2 (en) 2024-06-20

Family

ID=80696642

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2022381656A Active AU2022381656B2 (en) 2021-11-08 2022-11-01 Method and apparatus for determining open/closed state of knife switch, and device, medium and product

Country Status (4)

Country Link
CN (1) CN114220068B (en)
AU (1) AU2022381656B2 (en)
GB (1) GB2616993A (en)
WO (1) WO2023078254A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114220068B (en) * 2021-11-08 2023-09-01 珠海优特电力科技股份有限公司 Method, device, equipment, medium and product for determining disconnecting link switching state

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102262734B (en) * 2011-01-07 2013-05-15 浙江省电力公司 Method and system for determining turning-on or turning-off of switch
CN102509100B (en) * 2011-10-26 2013-06-19 山东电力研究院 Knife switch connecting-disconnecting reliability recognition method based on image pattern recognition
US9576221B2 (en) * 2014-07-09 2017-02-21 Ditto Labs, Inc. Systems, methods, and devices for image matching and object recognition in images using template image classifiers
CN106250902A (en) * 2016-07-29 2016-12-21 武汉大学 Power system on off state detection method based on characteristics of image template matching
JP6857586B2 (en) * 2017-10-02 2021-04-14 富士フイルム株式会社 An image extraction device, an image extraction method, an image extraction program, and a recording medium in which the program is stored.
CN108009551B (en) * 2017-11-21 2021-10-26 武汉中元华电软件有限公司 Electric knife switch opening and closing position state identification method suitable for electric power robot
CN108460727A (en) * 2018-03-28 2018-08-28 中南大学 A kind of image split-joint method based on perspective geometry and SIFT feature
CN109711567A (en) * 2018-12-14 2019-05-03 珠海优特电力科技股份有限公司 Service work safety measure Automatic generation of information method and system
CN110555824B (en) * 2019-07-22 2022-07-08 深圳供电局有限公司 Switch position judging method and control method of switch position detection system
CN110599446B (en) * 2019-07-26 2022-06-17 深圳供电局有限公司 Method for judging switching-on position of isolating switch
CN111126253A (en) * 2019-12-23 2020-05-08 国网福建省电力有限公司 Knife switch state detection method based on image recognition
CN112004012A (en) * 2020-08-26 2020-11-27 西安咏圣达电子科技有限公司 Switch cabinet running state management and detection system and method and computer equipment
US11048773B1 (en) * 2021-01-26 2021-06-29 Coupang Corp. Systems and methods for modeling item similarity and correlating item information
CN113033578B (en) * 2021-03-30 2023-05-16 上海星定方信息科技有限公司 Image calibration method, system, terminal and medium based on multi-scale feature matching
CN113592923B (en) * 2021-06-30 2024-03-29 国网浙江省电力有限公司营销服务中心 Batch image registration method based on depth local feature matching
CN114220068B (en) * 2021-11-08 2023-09-01 珠海优特电力科技股份有限公司 Method, device, equipment, medium and product for determining disconnecting link switching state

Also Published As

Publication number Publication date
WO2023078254A1 (en) 2023-05-11
GB202308674D0 (en) 2023-07-26
GB2616993A (en) 2023-09-27
CN114220068B (en) 2023-09-01
AU2022381656B2 (en) 2024-06-20
CN114220068A (en) 2022-03-22

Similar Documents

Publication Publication Date Title
KR102120241B1 (en) Face biometric verification method and device
CN109325412B (en) Pedestrian recognition method, device, computer equipment and storage medium
CN110348315B (en) Method and device for dynamically updating human face feature base and human face snapshot system
AU2022381656B2 (en) Method and apparatus for determining open/closed state of knife switch, and device, medium and product
WO2014101839A1 (en) Method for registering fingerprint image
US20200184682A1 (en) Object pose tracking method and apparatus
CN108335099A (en) Method, apparatus, mobile terminal and the storage medium of mobile payment
CN110348331A (en) Face identification method and electronic equipment
US20210034895A1 (en) Matcher based anti-spoof system
CN109002776B (en) Face recognition method, system, computer device and computer-readable storage medium
US20240257552A1 (en) Non-contact three-dimensional palm vein modeling method and apparatus, and authentication method
CN113537145B (en) Method, device and storage medium for rapidly solving false detection and missing detection in target detection
Gao et al. A rotation and scale invariant approach for dense wide baseline matching
CN109214278B (en) User instruction matching method and device, computer equipment and storage medium
CN103714544A (en) Optimization method based on SIFT feature point matching
CN105205829A (en) Transformer substation infrared image segmentation method based on improved two-dimensional Otsu algorithm
CN112836682A (en) Method and device for identifying object in video, computer equipment and storage medium
CN112215222A (en) License plate recognition method, device, equipment and storage medium
CN117148968A (en) Method and device for remotely controlling intelligent equipment, control equipment and storage medium
CN113743434A (en) Training method of target detection network, image augmentation method and device
Xu et al. Face recognition using spatially constrained earth mover's distance
CN115391596A (en) Video archive generation method and device and storage medium
CN105184244A (en) Video face detection method and apparatus
US11715300B1 (en) Systems and methods for providing product assembly step recognition using augmented reality
US12125218B2 (en) Object tracking apparatus and method

Legal Events

Date Code Title Description
FGA Letters patent sealed or granted (standard patent)