CN110717409B - Real-time accurate detection method for state of split type disconnecting link - Google Patents

Real-time accurate detection method for state of split type disconnecting link Download PDF

Info

Publication number
CN110717409B
CN110717409B CN201910895604.XA CN201910895604A CN110717409B CN 110717409 B CN110717409 B CN 110717409B CN 201910895604 A CN201910895604 A CN 201910895604A CN 110717409 B CN110717409 B CN 110717409B
Authority
CN
China
Prior art keywords
disconnecting link
arm
edge
state
knife switch
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.)
Active
Application number
CN201910895604.XA
Other languages
Chinese (zh)
Other versions
CN110717409A (en
Inventor
任大明
汪辉
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.)
Shanxi Jinzhi Hongyang Technology Co ltd
Original Assignee
Shanxi Jinzhi Hongyang 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 Shanxi Jinzhi Hongyang Technology Co ltd filed Critical Shanxi Jinzhi Hongyang Technology Co ltd
Priority to CN201910895604.XA priority Critical patent/CN110717409B/en
Publication of CN110717409A publication Critical patent/CN110717409A/en
Application granted granted Critical
Publication of CN110717409B publication Critical patent/CN110717409B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention provides a real-time accurate detection method for the state of a split disconnecting link, which comprises the following steps: collecting a real-time monitoring video and establishing a model file; obtaining sample images, training the sample images by deep learning to obtain a training model, detecting each frame of image to obtain a disconnecting link area, a disconnecting link state and an insulator area, positioning a disconnecting link arm and an insulator in the images by combining model files, and calculating the disconnecting link credibility according to positioning results; detecting the image meeting the credibility condition according to the positioning result, and calculating an initial included angle between the left disconnecting link arm and the right disconnecting link arm; estimating a system error, determining a correction included angle between a left disconnecting link arm and a right disconnecting link arm in each frame of image, judging the real-time state of a disconnecting link in each frame of image until the disconnecting link is detected to stop moving, and verifying the final state of the disconnecting link movement in a video; the invention solves the problem of low real-time detection precision of the state of the split knife switch.

Description

Real-time accurate detection method for state of split type disconnecting link
Technical Field
The invention relates to the technical field of image recognition, in particular to a real-time accurate detection method for the state of a split knife switch.
Background
The disconnecting link is an electric appliance which is used frequently in the high-voltage switch electric appliance and plays an isolating role in a circuit. In practice, due to the long-term operation of the knife switch, the knife switch is closed or opened in place, which results in an arc between the left and right knife switch arms of the knife switch. Arcing is a gas discharge phenomenon, and instantaneous sparks generated by current passing through certain insulating media can cause fires or threaten personal safety; in addition, the arc temperature is extremely high, so that insulating materials are easy to burn out, and leakage events or damage to knife switch equipment are caused; therefore, the closing state of the knife switch needs to be accurately detected.
Detecting the real-time state of the split type disconnecting link, wherein manual observation is mainly needed in practice; in the prior art, the state of the knife switch is also judged by calculating the angle between the left and right knife switch arms. At present, the angle between the left knife switch arm and the right knife switch arm is calculated, and a plurality of calculation schemes appear at home and abroad, one is to change the inside of a circuit and add a sensor or a signal lamp; in the method based on digital image processing, the angle calculation precision between the left knife switch arm and the right knife switch arm is lower due to complex background, and the actual requirement cannot be met.
Disclosure of Invention
In order to solve the problem of low real-time detection precision of the state of the disconnecting link in the prior art, the invention provides a real-time accurate detection method of the state of the split disconnecting link.
The technical scheme of the invention is realized as follows:
A real-time accurate detection method for the state of a split disconnecting link comprises the following steps: acquiring a real-time monitoring video of a split type disconnecting link, acquiring any frame of image of the video, establishing a boundary line model of a disconnecting link arm of the model according to the frame of image, storing the boundary line model as a model file, and calculating a left midpoint, a right midpoint, a midpoint and a center line of the disconnecting link arm according to the model file;
Obtaining sample images of the split type disconnecting link through multiple ways, training the sample images by utilizing deep learning to obtain a training model, detecting a first frame image of a video by utilizing the training model, obtaining all disconnecting link areas, disconnecting link states and insulator areas in the first frame image, positioning disconnecting link arms and insulators in the first frame image by combining model files, calculating the reliability of the disconnecting link according to positioning results, giving a reliability threshold, judging that the current disconnecting link state is undetectable if the reliability is lower than the reliability threshold, continuously detecting the next frame image until obtaining an image with the reliability of the first frame being higher than the reliability threshold, and marking the image as an initial frame image;
According to the positioning result of the knife switch arm, edge detection is carried out on an initial frame image of the video, an edge line set is obtained, the distance from the left middle point and the right middle point of the knife switch arm in the initial frame image to each edge line in the edge line set is calculated, and the edge line corresponding to the distance which is not in the threshold range is removed, so that an updated edge line set is obtained;
Dividing the updated edge line set left and right by using a central line, respectively acquiring a left knife switch arm edge line set and a right knife switch arm edge line set, symmetrically matching, determining the left knife switch arm edge line and the right knife switch arm edge line, calculating an included angle between the left knife switch arm and the right knife switch arm, and judging the real-time state of the knife switch in the initial frame image;
Processing a second frame image after the initial frame image in the same way, judging that the current disconnecting link state is undetectable if the reliability is lower than the reliability threshold, otherwise, determining a correction included angle between a left disconnecting link arm and a right disconnecting link arm in the second frame image according to a central line estimation system error, and judging the real-time state of the disconnecting link in the second frame image;
and processing the next frame of image in sequence in the same way as the second frame of image until the movement of the disconnecting link is detected to stop, and verifying the final state of the movement of the disconnecting link in the video.
Preferably, the updated edge line set is distinguished from left to right by utilizing a central line, after the left and right disconnecting link arm edge line sets are respectively obtained, the left and right disconnecting link arm edge line sets are subjected to weight distribution, and the left and right disconnecting link arm edge line sets after weight distribution are symmetrically paired.
Preferably, the specific way of positioning the knife switch in the first frame image by combining the model file is as follows:
Detecting a first frame image by using a training model, and acquiring all knife gate areas and knife gate states corresponding to each knife gate area in the first frame image, wherein the areas corresponding to the knife gates in the 'closed' and 'virtual' states are integral rectangular frame areas containing left and right knife gate arms, and the areas corresponding to the knife gates in the 'open' state are left rectangular frame areas containing left and right rectangular frame areas containing right knife gate arms; for the knife switches in the 'closed' and 'virtual' states, the rectangular frames at the contact point positions of the left and right knife switch arms are obtained simultaneously;
Acquiring closed quadrilateral frame areas of a disconnecting link in a closed state according to the two left side endpoints and the two right side endpoints, and calculating overlapping areas of the whole rectangular frame area, the left rectangular frame area and the right rectangular frame area in the first frame image and the closed quadrilateral frame area respectively; traversing the areas where all the disconnecting links in the 'closed' and 'virtual-closed' states in the first frame image, giving an overlapping area threshold value, acquiring an area which comprises a left midpoint and a right midpoint and has the largest overlapping area and is larger than the overlapping area threshold value as a final left and right disconnecting link arm integral area, simultaneously calculating the center point of a rectangular frame at the contact point position of the left and right disconnecting link arms and marking the center point as a contact point, taking the center straight line which passes the contact point and is parallel to the short sides of the rectangular frame of the left and right disconnecting link arm integral area as a limit, wherein the left rectangular frame is a left disconnecting link arm rectangular frame, and the right rectangular frame is a right disconnecting link arm rectangular frame, so as to realize the positioning of the disconnecting link in the 'closed' or 'virtual-closed' state in the first frame image;
If the region which comprises the left midpoint and the right midpoint and has the largest overlapping area and is larger than the overlapping area threshold value does not exist, the condition that the state of the disconnecting link to be detected in the first frame image is not a closed state or a virtual closed state is indicated, the disconnecting link positioning is realized from all disconnecting links in the open state, the region where all disconnecting links in the open state and having the largest overlapping area and larger than the overlapping area threshold value in the first frame image is traversed, and the region which comprises the left midpoint and has the largest overlapping area is acquired and is recorded as a first open left disconnecting link arm region; acquiring a region which comprises a right midpoint and has the largest overlapping area and recording the region as a first opening right disconnecting link arm region; traversing all areas where the knife switches are in an open state and the overlapping area is smaller than or equal to the overlapping area threshold value in the first frame image, and acquiring the first two areas which contain the left midpoint and have the largest overlapping area and marking the first two areas as left knife switch arm matching areas; acquiring the first two areas which comprise the right midpoint and have the largest overlapping area and marking the areas as right disconnecting link arm matching areas;
Calculating the distance from 4 vertexes of any left disconnecting link arm matching region to the left midpoint, selecting the left minimum distance, and comparing the two left minimum distances with the left minimum distance, and marking the left disconnecting link arm matching region corresponding to the smaller left minimum distance as a second left disconnecting link arm opening region; calculating the distance from 4 vertexes of any right disconnecting link arm matching region to the right midpoint, selecting the right minimum distance, and comparing the two right minimum distances with the right minimum distance, and marking the right disconnecting link arm matching region corresponding to the smaller right minimum distance as a second right disconnecting link arm opening region;
A knife switch arm area threshold is given, a first left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area, and a second left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area; and the first opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, and the second opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, so that the knife switch in the 'open' state in the first frame image is positioned.
Preferably, the method of positioning the insulator in the first frame image in combination with the model file is as follows:
Acquiring a left insulator standard center line and a right insulator standard center line according to a model file, detecting a first frame image by using a training model, acquiring insulator rectangular frames of all insulator areas in the first frame image, traversing all insulator rectangular frames, and respectively acquiring a left insulator set of all left insulator rectangular frames containing a left midpoint and a right edge subset of all right insulator rectangular frames containing a right midpoint;
Calculating the actual center line of each rectangular insulator frame, giving a left distance threshold value, counting the number of points, of which the distance from the point on each actual center line in the left insulator set to the standard center line of the left insulator is smaller than the left distance threshold value, counting the difference value between the slope of each actual center line and the slope of the standard center line of the left insulator, giving a left slope difference threshold value and a left point number threshold value, wherein the slope difference is smaller than the left slope difference threshold value, and the rectangular insulator frame with the largest point number and the point number larger than the left point number threshold value is the final rectangular left insulator frame, so that the left insulator positioning is realized;
And (3) giving a right distance threshold, counting the number of points, in which the distance from each point on the actual central line in the right insulator set to the right insulator standard central line is smaller than the right distance threshold, counting the difference value between the slope of each actual central line and the slope of the right insulator standard central line, giving a right slope difference threshold and a right point number threshold, wherein the slope difference is smaller than the right slope difference threshold, and the rectangular insulator frame with the maximum point number and the point number larger than the right point number threshold is the final rectangular right insulator frame, so that the right insulator positioning is realized.
Preferably, the manner of calculating the reliability of the knife switch according to the positioning result is as follows: determining the distance between the left midpoint and the right midpoint according to the model file and marking the distance as left midpoint distance and right midpoint distance; for the current frame image, acquiring a left disconnecting link arm, a right disconnecting link arm, a left insulator, a right insulator and a rectangular frame of a contact point of the left disconnecting link arm and the right disconnecting link arm according to a positioning result, wherein the short side length of the rectangular frame of the left insulator and the short side length of the rectangular frame of the right insulator are the width of the left insulator and the width of the right insulator;
If a rectangular frame of the left insulator exists, a left proportion threshold value is given, the proportion of half of the width of the left insulator to the left and right midpoint spacing is calculated, if the proportion is smaller than the left proportion threshold value, the contribution rate of the left insulator to the credibility is 0.2, and otherwise, the contribution rate is 0;
If a right insulator rectangular frame exists, a right proportion threshold value is given, the proportion of half of the width of the right insulator to the left-right midpoint distance is calculated, if the proportion is smaller than the right proportion threshold value, the contribution rate of the right insulator to the credibility is 0.2, and otherwise, the contribution rate is 0;
If a contact point rectangular frame exists, a proportion threshold value is given, the proportion of half of the width of the left and right disconnecting link arm contact point rectangular frames to the left and right midpoint spacing is calculated, if the proportion is smaller than the proportion threshold value, the contribution rate of the contact point to the credibility is 0.2, otherwise, the contribution rate is 0;
If a left disconnecting link arm rectangular frame exists, the contribution rate of the left disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0; if a right disconnecting link arm rectangular frame exists, the contribution rate of the right disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0;
for a knife switch in an open state, the contribution rate is additionally increased by 0.2 because no contact point exists;
The sum of the contribution rate of the left disconnecting link arm, the right disconnecting link arm, the left insulator, the right insulator and the contact point of the left disconnecting link arm and the right disconnecting link arm to the credibility is the credibility of the disconnecting link, a credibility threshold value is given, if the credibility is larger than the credibility threshold value, the state of the disconnecting link of the current frame is detected, and if the credibility is smaller than the given threshold value, the state of the disconnecting link of the current frame is judged to be undetectable.
Preferably, the specific way of determining the correction included angle between the left knife switch arm and the right knife switch arm in the second frame image according to the center line estimation system error is as follows:
Calculating the included angles between the edge line of the final left knife switch arm and the edge line of the right knife switch arm in the current frame image and the line of the edge line of the final right knife switch arm in the previous frame image in real time, respectively, and the line of the edge line of the final left knife switch arm and the line of the knife switch arm in the closed state in the current frame image are set to be alpha 1, the included angle between the edge line of the final right knife switch arm and the line of the knife switch arm in the closed state is gamma 1, the included angle between the edge line of the final left knife switch arm and the line of the knife switch arm in the previous frame image is alpha 2, the included angle between the edge line of the final right knife switch arm and the line of the knife switch arm in the closed state is gamma 2, and the system error is recorded as noise= | (alpha 1-α2)-(γ1-γ2); and combining the system errors, determining that the correction included angle between the left knife switch arm and the right knife switch arm of the current frame is theta correct＝|γ1-α1 |+noise, wherein the correction included angle is the included angle between the left knife switch arm and the right knife switch arm in the second frame image.
Preferably, the specific mode for judging the real-time state of the knife switch in the initial frame image is as follows:
two angle thresholds T-o and T-c of the split knife switch in an 'open' state and a 'closed' state are given according to the user requirement;
if the included angle between the left knife arm and the right knife arm is larger than T-o, judging that the knife switch in the initial frame image is in an open state, if the actual included angle between the left knife arm and the right knife arm is smaller than T-c, judging that the knife switch in the initial frame image is in a closed state, and if the actual included angle between the left knife arm and the right knife arm is between T-o and T-c, judging that the knife switch in the initial frame image is in a virtual closing state.
Preferably, the specific mode for judging the real-time state of the knife switch in the second frame image is as follows:
Two angle threshold values T-o and T-c of a split type disconnecting link in an 'open' state and a 'closed' state are given according to the requirement of a user, a high threshold value hT-o and a low threshold value lT-o of the open state are set, the T-o is between the high threshold value hT-o and the low threshold value lT-o, and hT-o > T-o > lT-o; setting a high threshold hT-c and a low threshold lT-c of the closed state, T-c being between the high threshold hT-c and the low threshold lT-c, hT-c > T-c > lT-c, and lT-o > hT-c;
If the correction included angle between the left knife gate arm and the right knife gate arm is larger than hT-o, judging that the knife gate in the second frame image is in an open state, if the correction included angle between the left knife gate arm and the right knife gate arm is smaller than lT-c, judging that the knife gate in the second frame image is in a closed state, and if the correction included angle between the left knife gate arm and the right knife gate arm is between hT-c and lT-o, judging that the knife gate in the second frame image is in a virtual closing state; if the correction included angle between the left knife switch arm and the right knife switch arm is between lT-o and hT-o or between lT-c and hT-c, judging that the state of the knife switch in the second frame image is the same as the state of the knife switch in the previous frame image.
Preferably, the next frame of image is processed in turn in the same way as the second frame of image until the stop of the movement of the knife switch is detected, and the specific way of verifying the final state of the movement of the knife switch in the video is as follows: judging the real-time state of the knife switch in the current frame image and then recording the real-time state; setting a continuous frame number threshold, if the state of the disconnecting link in the continuous frame images is kept unchanged and the continuous frame number is larger than the continuous frame number threshold, indicating that the disconnecting link maintains the same state, stopping detection at the moment, and verifying the final state;
If the initial state of the disconnecting link is an open state, the operation is completed when the disconnecting link is in a closed state in the final state, and the disconnecting link is in a virtual state in the final state, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a closed state, the operation is completed when the disconnecting link is in an open state in the final state, and the disconnecting link is in a virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a virtual closing state, the operation is completed when the disconnecting link is in a closing or opening state in the final state, and the disconnecting link is in the virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually.
Preferably, the left knife switch arm edge line set is assigned a weight in the following manner: traversing all edge lines in the left disconnecting link arm edge line set, calculating the angle of each left disconnecting link arm edge line, classifying the left disconnecting link arm edges according to the angles, setting a high angle threshold and a low angle threshold, setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge line angles larger than the high angle threshold as vertical edge lines, setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge lines angles smaller than the low angle threshold as horizontal edge lines, and setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge lines between the low angle threshold and the high angle threshold as inclined edge lines;
Setting an x coordinate value L_x of a left midpoint of the left disconnecting link arm for all vertical edge lines of the left disconnecting link arm, respectively searching two edge points corresponding to x coordinates with the smallest difference with the L_x on the left side and the right side of the left midpoint of the left disconnecting link arm, wherein the x coordinate values of the two left edge points are marked as L_x1 and L_x2, and L_x1 is larger than L_x2; the x coordinate values of the two edge points on the right are denoted as R_x1 and R_x2, and R_x1 is greater than R_x2;
Setting the y coordinate value of the left midpoint of the left disconnecting link arm as L_y for all horizontal edge lines of the left disconnecting link arm, respectively searching two edge points corresponding to the y coordinates with the smallest difference with the L_y on the upper side and the lower side of the left midpoint of the left disconnecting link arm, and recording the y coordinate values of the two upper edge points as T_y1 and T_y2, wherein T_y1 is larger than T_y2; the y coordinate values of the two edge points at the lower side are denoted as B_y1 and B_y2, and B_y1 is larger than B_y2;
For all inclined edge lines of the left knife switch arm, setting x coordinate values and y coordinate values of a left middle point of the left knife switch arm as L_xx and L_yy, respectively searching two edge points corresponding to the x coordinate with the smallest difference between L_xx and the y coordinate with the smallest difference between L_yy on the left upper side and the right lower side of the left middle point of the left knife switch arm, wherein the x coordinate values of the two edge points on the left upper side are marked as L_xx1 and L_xx2, L_xx1 is larger than_xx2, the y coordinate values are marked as T_yy1 and T_yy2, and T_yy1 is larger than T_yy2; the x coordinate values of the two edge points on the lower right side are denoted as R_xx1 and R_xx2, R_xx1 is larger than R_xx2, and the y coordinate values are denoted as B_yy1 and B_y2, B_y1 is larger than B_y2;
The manner of obtaining the weight of each vertical edge line is as follows: traversing each edge point on each vertical edge line positioned at the left side of the left midpoint of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_x1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_x2 and less than L_x1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each vertical edge line positioned on the right side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_x2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_x2 and smaller than or equal to L_x1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current vertical edge line;
The manner of obtaining the weight of each horizontal edge line is as follows: traversing each edge point on each horizontal edge line positioned on the upper side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_y1, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each horizontal edge line positioned at the lower side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is less than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is greater than B_y2 and less than or equal to B_y1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current horizontal edge line;
The manner of acquiring the weight of each inclined edge line is as follows: traversing each edge point on each inclined edge line positioned at the left upper side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_xx1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_xx2 and less than L_xx1, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_yy1, and the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, otherwise, the contribution weight of the edge point is 0; traversing each edge point on each inclined edge line positioned at the right lower side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_xx2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_xx2, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is smaller than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is larger than or equal to B_y2, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current inclined edge line;
The right switch arm edge line set is assigned the same weight as the left switch arm edge line set.
The beneficial effects of the invention are as follows: the real-time accurate detection method of the split type disconnecting link state of the invention takes the middle point and the middle line of the disconnecting link arm in the model file as references in the processed image. The knife switch arm and the insulator in each frame of image are positioned through the training model, the aimed area is clearer when the subsequent processing is carried out, and the accuracy of determining the edge line of the left knife switch arm and the edge line of the right knife switch arm in each frame of image is improved. The sample images collect different opening and closing states of the split type disconnecting link under different environments, which is beneficial to improving the applicability and detection accuracy of a training model and helping to realize automatic positioning of the disconnecting link.
Meanwhile, the reliability of the disconnecting link is calculated according to the positioning result, whether the disconnecting link to be detected is abnormal or not is judged according to the reliability, and as the substation acquisition equipment can be controlled by multiple people, the situation that the acquisition equipment is moved away can occur when the disconnecting link state analysis is carried out, feedback needs to be timely given according to the real-time video situation of the disconnecting link, when most parts of the disconnecting link moving or shooting by a camera cannot be detected in a fuzzy manner, the reliability of the disconnecting link is lower, the current disconnecting link state is judged to be undetectable, and the stability of an algorithm is improved.
In actual use, on the basis of positioning the knife switch in each frame of image, the matching of the edge lines of the left and right knife switch arms in the frame of image can be effectively implemented by utilizing a midpoint and midline calculation mode and then by weight distribution, so that the detection precision and the detection speed are improved. According to the method, different states of the disconnecting link in actual use are combined, the disconnecting link in each frame of image is identified more quickly and accurately through training a model and a model file, all frame disconnecting links with the credibility lower than the credibility threshold value are judged to be undetectable, correction angles among disconnecting link arms are obtained for all frame disconnecting links with the credibility higher than the credibility threshold value according to a central line estimation system error, angle errors are reduced, real-time states of the disconnecting link in each frame of image are judged, final states of movement of the disconnecting link in a video are verified, and real-time detection accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a first frame image in a video of the present invention;
FIG. 2 is a schematic diagram of the paired edge lines of the left and right knife switch arms according to the present invention;
FIG. 3 is a schematic view of the vertical edge line on the left switch arm of the present invention;
FIG. 4 is a schematic view of the horizontal edge line on the left switch arm of the present invention;
FIG. 5 is a schematic view of the structure of the inclined edge line on the left switch arm according to the present invention;
FIG. 6 is a view of the area corresponding to the knife switch in the "closed" state in the first frame image according to the present invention;
FIG. 7 is a view of the area corresponding to the knife switch in the "virtual" state in the first frame image according to the present invention;
Fig. 8 is a view of the area corresponding to the knife switch in the "on" state in the first frame image according to the present invention.
In the figure:
1. the left midpoint of the left knife switch arm; 2. the right midpoint of the right knife switch arm; 3. a vertical edge line; 4. a horizontal edge line; 5. tilting the edge line; 6. a left knife switch arm; 7. a right knife switch arm; 8. an overall rectangular frame region; 9. a left rectangular frame area; 10. a right rectangular frame region; 11. a contact point position rectangular frame; 12. a center straight line; 13. the rectangular frame area is closed.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: a real-time accurate detection method for the state of a split disconnecting link comprises the following steps: acquiring a real-time monitoring video of a split type disconnecting link, acquiring any frame of image of the video, establishing a boundary line model of a disconnecting link arm of the model according to the frame of image, storing the boundary line model as a model file, and calculating a left midpoint, a right midpoint, a midpoint and a center line of the disconnecting link arm according to the model file; obtaining sample images of the split type disconnecting link through multiple ways, training the sample images by using deep learning to obtain a training model, detecting a first frame image of a video by using the training model, obtaining all disconnecting link areas, disconnecting link states and insulator areas in the first frame image, positioning disconnecting link arms and insulators in the first frame image by combining model files, calculating the reliability of the disconnecting link according to positioning results, setting a reliability threshold, and continuously detecting the next frame image if the reliability is lower than the reliability threshold until an image with the reliability of the first frame being higher than the reliability threshold is obtained, and marking the image as an initial frame image; according to the positioning result of the knife switch arm, edge detection is carried out on an initial frame image of the video, an edge line set is obtained, the distance from the left middle point and the right middle point of the knife switch arm in the initial frame image to each edge line in the edge line set is calculated, and the edge line corresponding to the distance which is not in the threshold range is removed, so that an updated edge line set is obtained; dividing the updated edge line set left and right by using a central line, respectively acquiring a left knife switch arm edge line set and a right knife switch arm edge line set, symmetrically matching, determining the left knife switch arm edge line and the right knife switch arm edge line, calculating an included angle between the left knife switch arm and the right knife switch arm, and judging the real-time state of the knife switch in the initial frame image; processing a second frame image with the reliability higher than the reliability threshold after the initial frame image in the same way, displaying that the second frame image cannot be judged if the reliability is lower than the reliability threshold, determining a correction included angle between a left knife switch arm and a right knife switch arm in the second frame image according to a central line estimation system error, and judging the real-time state of the knife switch in the second frame image; and sequentially processing images with the reliability higher than the reliability threshold value of the next frame in the same mode as the second frame image, if the reliability of the current disconnecting link is judged to be lower than the reliability threshold value in the detection process, performing no other processing on the current frame image, displaying the state of the current frame image as undetectable, and continuously detecting the next frame image until the disconnecting link is detected to stop moving, and verifying the final state of the disconnecting link movement in the video.
And detecting all the disconnecting link areas, disconnecting link states and insulator areas in each frame of image by using a training model, and preliminarily knowing whether the disconnecting link states are closed, virtually closed or opened, wherein the disconnecting link states are general and different from the disconnecting link states acquired according to the included angles, and the disconnecting link states acquired according to the included angles are final states of the disconnecting links in each frame of image. Positioning a disconnecting link arm and an insulator in each frame of image sequentially from a first frame of image of a real-time video by using a training model and a model file, calculating the reliability of the disconnecting link, and acquiring an initial frame of image according to the reliability of the disconnecting link; and starting from the initial frame image, judging the real-time state of the next frame image in sequence. The initial frame image may coincide with the first frame image or may lag behind the first frame image in order to more accurately detect each frame image. And when the reliability is lower than the reliability threshold value in the image after the initial frame image, directly outputting the image, wherein the image is undetectable by a knife switch, and performing no other processing on the frame image.
The mode of establishing the boundary line model of the type of knife switch arm according to any frame image of the video and storing the boundary line model as a model file is as follows: setting a program on a computer, opening any frame of image of a video by using the program, carrying out edge tracing on upper and lower boundary lines of a knife switch arm in the image, drawing a left insulator center line and a right insulator center line, and storing line segment endpoint coordinates corresponding to the edge tracing and line segment endpoint coordinates corresponding to the left and right insulator center lines as model files; if the disconnecting link in any frame of image is in a closed state, the upper and lower boundaries of the whole disconnecting link arm are traced; if the disconnecting link in any frame of image is in an opened or virtual closing state, tracing edges according to the upper and lower boundaries of the actual left and right disconnecting link arms; the efficiency of establishing the model file is improved, an image used for establishing the model file is marked as a template image, the states of the disconnecting link in the template image are manually identified, the states of the disconnecting link in the manually identified template image are unified, and the final states of the disconnecting link in the template image are processed in the same mode as other frame images.
The mode of calculating the left midpoint, the right midpoint and the middle point of the knife switch arm according to the model file is as follows: when the disconnecting link arm is in a closed state, respectively acquiring two intersection points of an upper boundary line extension line, a lower boundary line extension line and a left insulator central line extension line of the whole disconnecting link arm according to a model file, marking the two intersection points as two left side end points, wherein the midpoints of the two left side end points are left midpoints, acquiring two intersection points of the upper boundary line extension line, the lower boundary line extension line and the right insulator central line extension line of the whole disconnecting link arm, marking the two intersection points as two right side end points, and the midpoints of the two right side end points are right midpoints; the midpoint of a closed frame formed by the two left side endpoints and the two right side endpoints is the midpoint of the disconnecting link arm or the midpoint of a line segment between the left midpoint and the right midpoint is the midpoint of the disconnecting link arm; when the disconnecting link arm is in an open or virtual closing state, respectively acquiring two intersection points of an upper boundary line extension line, a lower boundary line extension line and a left insulator central line extension line of the left disconnecting link arm according to a model file, marking the two intersection points as two left side end points, wherein the middle points of the two left side end points are left middle points, acquiring two intersection points of the upper boundary line extension line, the lower boundary line extension line and the right insulator central line extension line of the right disconnecting link arm, marking the two intersection points as two right side end points, and the middle points of the two right side end points are right middle points; the midpoint of the closed frame formed by the two left side endpoints and the two right side endpoints is the midpoint of the knife switch arm or the midpoint of the line segment between the left midpoint and the right midpoint is the midpoint of the knife switch arm.
The mode of calculating the center line of the knife switch arm according to the model file is as follows: the method comprises the steps of marking an image used for establishing a model file as a template image, acquiring a distortion coefficient of a camera for collecting video when a knife switch is in a closed state, and calculating a camera matrix = [ focal_length,0, center. X according to the size of the template image; 0, focal_length, center. 0,1], wherein focal_length is the template image width, and center. X and center. Y are the x-coordinate and y-coordinate of the camera corresponding to the midpoint in the template image, respectively; acquiring coordinate positions of a camera relative to a knife switch according to two left side endpoints, two right side endpoints, distortion coefficients and a camera matrix, wherein the projection direction of a Z axis of the camera on a template image is the center line direction of the knife switch arm, and determining the center line of the knife switch arm by combining the center point of the knife switch arm; when the knife switch arm is in a virtual closing or opening state, a left central line is obtained according to the average slope of the left middle point and the upper and lower boundary lines of the left knife switch arm, a right central line is obtained according to the average slope of the right middle point and the upper and lower boundary lines of the right knife switch arm, and the left central line and the right central line are prolonged to form an intersection point; the line passing through the intersection point and the midpoint is the center line of the knife switch arm.
Because the disconnecting link is generally in a closed or fully opened state in the power station site, a large number of images of the opening and closing processes of the split disconnecting link are difficult to acquire, in order to enrich sample training, sample images of the split disconnecting link are acquired through various ways, including site acquisition, software simulation and physical model ways, and the specific way of site acquisition is to acquire sample images of the split disconnecting link in different states; the specific mode of software simulation is to model a sample image acquired on site by using design software, obtain a corresponding three-dimensional model, configure different environmental conditions in the three-dimensional model, set opening and closing actions and render, obtain opening and closing motion videos of a split type disconnecting link, and obtain disconnecting link sample images under different conditions and different angles of different environments according to the motion videos; the physical model is put in different environments to manually open and close the knife switch and shoot videos, and knife switch images in different states are obtained according to the shot videos. And a large number of sample images ensure that the training model has stronger adaptability.
As shown in fig. 6 to 8, the training model is used to detect the first frame image, and the specific way of locating the knife switch in the first frame image is that: detecting a first frame image by using a training model, and acquiring all knife gate areas and knife gate states corresponding to each knife gate area in the first frame image, wherein the areas corresponding to the knife gates in the 'closed' and 'virtual' states are an integral rectangular frame area 8 containing left and right knife gate arms, and the areas corresponding to the knife gates in the 'open' state are a left rectangular frame area 9 containing left knife gate arms and a right rectangular frame area 10 containing right knife gate arms; for the knife switches in the 'closed' and 'virtual' states, the rectangular frames 11 at the contact point positions of the left and right knife switch arms are obtained at the same time; the detection result after deep learning is different from the mode of establishing a model file; acquiring a closed rectangular frame area 13 of a knife switch in a closed state according to a model file, and calculating overlapping areas of the whole rectangular frame area 8, the left rectangular frame area 9 and the right rectangular frame area 10 and the closed rectangular frame area 13 respectively in a first frame image, wherein the shaded parts in fig. 6 to 8 are overlapping areas; traversing the areas where all the disconnecting links in the 'closed' and 'virtual-closed' states in the first frame image, acquiring a final left and right disconnecting link arm integral area which comprises a left midpoint and a right midpoint and has the largest overlapping area, calculating the center point of a rectangular frame 11 at the contact point position of the left and right disconnecting link arms and marking the center point as a contact point, and positioning the disconnecting link in the 'closed' or 'virtual-closed' state in the first frame image by taking a center straight line 12 which passes through the contact point and is parallel to the short sides of the rectangular frame of the left and right disconnecting link arm integral area as a boundary, wherein the left rectangular frame is a left disconnecting link arm rectangular frame, and the right rectangular frame is a right disconnecting link arm rectangular frame; giving an overlapping area threshold value, traversing all areas where the knife switches in the 'open' state in the first frame image are located, wherein the overlapping area is larger than the overlapping area threshold value, and acquiring an area which contains a left midpoint and has the largest overlapping area as a first left-opening knife switch arm area; acquiring a region which comprises a right midpoint and has the largest overlapping area and recording the region as a first opening right disconnecting link arm region; traversing all areas where the knife switches are in an open state and the overlapping area is smaller than or equal to the overlapping area threshold value in the first frame image, and acquiring the first two areas which contain the left midpoint and have the largest overlapping area and marking the first two areas as left knife switch arm matching areas; acquiring the first two areas which comprise the right midpoint and have the largest overlapping area and marking the areas as right disconnecting link arm matching areas; calculating the distance from 4 vertexes of any left disconnecting link arm matching region to the left midpoint, selecting a left minimum distance, and comparing the two left minimum distances with the left minimum distance, and marking the left disconnecting link arm matching region corresponding to the smaller left minimum distance as a second left disconnecting link arm opening region; calculating the distances from 4 vertexes of any right disconnecting link arm matching region to the right midpoint, selecting a right minimum distance, and comparing the two right minimum distances with the right minimum distance, and marking the right disconnecting link arm matching region corresponding to the smaller right minimum distance as a second right disconnecting link arm opening region; the left minimum distance and the right minimum distance are actually minimum distances, here in order to distinguish between the left and right switch arm sides; a knife switch arm area threshold is given, a first left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area, and a second left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area; and the first opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, and the second opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, so that the knife switch in the 'open' state in the first frame image is positioned. The same is done for knife gate positioning in each frame of image in the acquired video.
And the left midpoint and the right midpoint of the split type disconnecting link in the model file are corresponding to the initial frame image, so that the left midpoint and the right midpoint of the disconnecting link arm of the initial frame image are obtained, the distance between the left midpoint and the right midpoint of the disconnecting link arm in the initial frame image and each edge line in the edge line set is calculated, and the edge line corresponding to the distance which is not in the threshold range is removed, so that the updated edge line set is obtained. The way to acquire the updated edge line set in each frame image with the reliability higher than the reliability threshold is the same as the way to acquire the updated edge line in the initial frame image.
The complete split type disconnecting link mainly comprises four parts, namely a left disconnecting link arm, a right disconnecting link arm, a left insulator and a right insulator, and further comprises contact points of the left disconnecting link arm and the right disconnecting link arm for the disconnecting link in the closed state and the virtual closed state.
The specific mode for calculating the reliability of the disconnecting link according to the positioning result is as follows: determining the distance between the left midpoint and the right midpoint according to the model file and marking the distance as left midpoint distance and right midpoint distance; the complete split type disconnecting link mainly comprises 4 parts, namely a left disconnecting link arm, a right disconnecting link arm, a left insulator and a right insulator, wherein the disconnecting link in a closed state and a virtual closed state also comprises contact points of the left disconnecting link arm and the right disconnecting link arm, and a rectangular frame of the left disconnecting link arm, the right disconnecting link arm, the left insulator, the right insulator and the contact points of the left disconnecting link arm and the right disconnecting link arm is obtained according to a positioning result for a current frame image, and the short side length of the rectangular frame of the left insulator and the short side length of the rectangular frame of the right insulator are the width of the left insulator and the right insulator; if a rectangular frame of the left insulator exists, a left proportion threshold value is given, the proportion of half of the width of the left insulator to the left and right midpoint spacing is calculated, if the proportion is smaller than the left proportion threshold value, the contribution rate of the left insulator to the credibility is 0.2, and otherwise, the contribution rate is 0; if a right insulator rectangular frame exists, a right proportion threshold value is given, the proportion of half of the width of the right insulator to the left-right midpoint distance is calculated, if the proportion is smaller than the right proportion threshold value, the contribution rate of the right insulator to the credibility is 0.2, and otherwise, the contribution rate is 0; if a contact point rectangular frame exists, a proportion threshold value is given, the proportion of half of the width of the left and right disconnecting link arm contact point rectangular frames to the left and right midpoint spacing is calculated, if the proportion is smaller than the proportion threshold value, the contribution rate of the contact point to the credibility is 0.2, otherwise, the contribution rate is 0; if a left disconnecting link arm rectangular frame exists, the contribution rate of the left disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0; if a right disconnecting link arm rectangular frame exists, the contribution rate of the right disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0; for a knife switch in an open state, the contribution rate is additionally increased by 0.2 because no contact point exists; the sum of the contribution rate of the left disconnecting link arm, the right disconnecting link arm, the left insulator, the right insulator and the contact point of the left disconnecting link arm and the right disconnecting link arm to the credibility is the credibility of the disconnecting link, a credibility threshold value is given, if the credibility is larger than the credibility threshold value, the state of the disconnecting link of the current frame is detected, if the credibility is smaller than the given threshold value, the state of the disconnecting link of the current frame is judged to be undetectable, other processing is not carried out, and the next frame image is processed.
The specific modes of differentiating the updated edge line set left and right by utilizing the central line and respectively obtaining the left knife switch arm edge line set and the right knife switch arm edge line set are as follows: directly corresponding the neutral line of the knife switch arm calculated according to the template image to an initial frame image, and calculating a unit direction vector which takes the midpoint as a starting point and is perpendicular to the neutral line and is in a left direction or a right direction on the initial frame imageTraversing edge lines in the updated edge line set, marking two end points of any one edge line as T1 and T2, and marking a vector of T1 and a midpoint as/>Let the vector of T2 and midpoint be the/>Calculation/>And/>For unit direction vector to the rightIf/>T1 is to the right of the midline, otherwise to the left of the midline, if/>T2 is to the right of the midline, otherwise to the left of the midline; unit direction vector/> for direction to the leftIf/>T1 is to the left of the midline, otherwise to the right of the midline; if/>T2 is to the left of the midline, otherwise to the right of the midline; if T1 and T2 are both on the left side of the central line, the edge line is a left knife switch arm edge line, if T1 and T2 are both on the right side of the central line, the edge line is a right knife switch arm edge line, if T1 and T2 are respectively on the two sides of the central line, the left and right line segment lengths of the edge line taking the central line as a parting line are calculated, and the edge line is the edge line on the longer sides of the left and right side line segments; thus, a left knife switch arm edge line set and a right knife switch arm edge line set are obtained. In example 1, the left and right blade edge line sets were symmetrically paired to determine the final left and right blade edge lines in the following specific manner:
the method comprises the steps of marking a given angle threshold value, namely, marking an angle of any edge line in a left disconnecting link edge line set relative to a horizontal position as M h, wherein h represents different left disconnecting link edge lines, dividing the angle difference value of any two left disconnecting link edge lines within the angle threshold value into the same group, and sequencing the left disconnecting link edge lines in the same group from long to short; for any edge line in the right knife switch arm edge line set, the angle of the edge line relative to the horizontal position is recorded as N m, m represents different right knife switch arm edge lines, the angle difference value of any two right knife switch arm edge lines is divided into the same group within the angle threshold value, and the right knife switch arm edge lines in the same group are ordered from long to short; as shown in fig. 2, traversing all the same groups of the left knife arm edge line set and all the same groups of the right knife arm edge line set, calculating the average angle of each group, and acquiring the corrected left knife arm edge line of each group of the left knife arm edge line set by combining the average angle of each group of the left knife arm edge line set with the left midpoint, wherein the intersection point of the corrected left knife arm edge line and the central line is marked as a point a; the average angle of each group of the right disconnecting link arm edge line set is combined with the right midpoint to obtain the corrected right disconnecting link arm edge line of each group of the right disconnecting link arm edge line set, the intersection point of the corrected right disconnecting link arm edge line and the central line is marked as a point B, and the distance d AB between the point A and the point B is calculated; the smaller the distance between the left midpoint and the right midpoint of the knife switch arm is d 0,dAB/d0, the greater the probability that the paired correction left knife switch arm edge line and correction right knife switch arm edge line are the actual left knife switch arm edge line and the actual right knife switch arm edge line, and d AB/d0 is more than 0.5, the same group where the point A is located and the same group where the point B is located are removed; setting any two groups of calculation formulas of pairing scores as Wherein the coefficient S L represents the sum of squares of the lengths of any of the same-group inner edge lines of the left-hand knife arm edge line set, and S R represents the sum of squares of the lengths of any of the same-group inner edge lines of the right-hand knife arm edge line set; beta is an adjustable sensitivity parameter, different scores can be obtained by taking different beta values in actual use, a pairing result is determined according to the different scores, the corresponding beta value with the best pairing result is selected as a final beta value, and different users can also determine the beta value according to actual conditions; the corrected left knife switch arm edge line where the point A corresponding to the highest pairing score S is located and the corrected right knife switch arm edge line where the point B is located are the final left knife switch arm edge line and right knife switch arm edge line.
Example 2: the left and right knife arm edge line sets are assigned weights first, as shown in fig. 3 to 5, and the left knife arm edge line set is assigned weights in the following manner: traversing all edge lines in the left disconnecting link arm edge line set, calculating the angle of each left edge line, classifying the left edges according to the angles, giving a high angle threshold value and a low angle threshold value, setting a left edge line corresponding to the left edge line with the angle larger than the high angle threshold value as a vertical edge line 3, setting a left edge line corresponding to the left edge line with the angle smaller than the low angle threshold value as a horizontal edge line 4, and setting a left edge line corresponding to the left edge line with the angle between the low angle threshold value and the high angle threshold value as an inclined edge line 5;
Setting an x coordinate value L_x of a left midpoint of the left disconnecting link arm for all vertical edge lines 3 of the left disconnecting link arm, respectively searching two edge points corresponding to x coordinates with the smallest difference with the L_x on the left side and the right side of the left midpoint of the left disconnecting link arm, wherein the x coordinate values of the two left edge points are marked as L_x1 and L_x2, and L_x1 is larger than L_x2; the x coordinate values of the two edge points on the right are denoted as R_x1 and R_x2, and R_x1 is greater than R_x2;
Setting the y coordinate value of the left midpoint of the left disconnecting link arm as L_y for all horizontal edge lines 4 of the left disconnecting link arm, respectively searching two edge points corresponding to the y coordinates with the smallest difference with the L_y on the upper side and the lower side of the left midpoint of the left disconnecting link arm, and recording the y coordinate values of the two upper edge points as T_y1 and T_y2, wherein T_y1 is larger than T_y2; the y coordinate values of the two edge points at the lower side are denoted as B_y1 and B_y2, and B_y1 is larger than B_y2;
For all inclined edge lines 5 of the left knife switch arm, setting x coordinate values and y coordinate values of a left middle point of the left knife switch arm as L_xx and L_yy, respectively searching two edge points corresponding to the x coordinate with the smallest difference with L_xx on the left upper side and the right lower side of the left middle point of the left knife switch arm, and respectively searching the edge points corresponding to the y coordinate with the smallest difference with L_yy, wherein the x coordinate values of the two edge points on the left upper side are marked as L_xx1 and L_xx2, L_xx1 is larger than_xx2, and the y coordinate values are marked as T_y1 and T_yy2, and T_yy1 is larger than T_y2; the x coordinate values of the two edge points on the lower right side are denoted as R_xx1 and R_xx2, R_xx1 is larger than R_xx2, and the y coordinate values are denoted as B_yy1 and B_y2, B_y1 is larger than B_y2;
The weight of each vertical edge line 3 is obtained by: traversing each edge point on each vertical edge line positioned at the left side of the left midpoint of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_x1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_x2 and less than L_x1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each vertical edge line positioned on the right side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_x2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_x2 and smaller than or equal to L_x1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current vertical edge line;
The manner of acquiring the weight of each horizontal edge line 4 is: traversing each edge point on each horizontal edge line positioned on the upper side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_y1, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each horizontal edge line positioned at the lower side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is less than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is greater than B_y2 and less than or equal to B_y1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current horizontal edge line;
The weight of each oblique edge line 5 is obtained by: traversing each edge point on each inclined edge line positioned at the left upper side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_xx1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_xx2 and less than L_xx1, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_yy1, and the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, otherwise, the contribution weight of the edge point is 0; traversing each edge point on each inclined edge line positioned at the right lower side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_xx2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_xx2, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is smaller than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is larger than or equal to B_y2, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current inclined edge line;
The right switch arm edge line set is assigned the same weight as the left switch arm edge line set.
On the basis of the embodiment 2, the "symmetrically pairing the left edge line set and the right edge line set after weight assignment" is that: adding weight distribution of edge lines in a specific mode of symmetrically pairing the left knife switch arm edge line set and the right knife switch arm edge line set, calculating the weight w_L of each same group of corrected left knife switch arm edge lines, and calculating the weight w_R of each same group of corrected right knife switch arm edge lines; calculating the angle of the left rectangular frame area 9 and the angle of the right rectangular frame area 10 of the knife gate positioning in the initial frame image, calculating the difference d_A_L between the angle of the left rectangular frame area and the angle of the correction left edge line, calculating the difference d_A_R between the angle of the right rectangular frame area and the angle of the correction right edge line, setting the pairing score of the symmetrical pairing as S 2, the final pairing score of the knife gate positioning is S 3,
The ratio = d AB/d0 is set,
S2＝a*exp(-(ratio*ratio*a2))*w_L*w_R
A is the adjustment parameter of the device,
Meaning of pairing formula: the smaller the distance d AB between the intersection point of the correction left knife arm edge line and the central line and the intersection point of the correction right knife arm edge line and the central line, the larger the weights of the correction left knife arm edge line and the correction right knife arm edge line, the smaller the difference between the angle of the left rectangular frame area 9 positioned by the knife switch and the angle of the correction left knife arm edge line, the smaller the difference between the angle of the right rectangular frame area 10 positioned by the knife switch and the angle of the correction right knife arm edge line, the higher the pairing score, and the higher the probabilities that the corresponding correction left knife arm edge line and the correction right knife arm edge line are the final left knife arm edge line and the right knife arm edge line; the corrected left knife arm edge line and the corrected right knife arm edge line corresponding to the pairing combination with the highest score are the final left knife arm edge line and right knife arm edge line. The value of the adjustment parameter a can be determined through experiments and a priori knowledge. The angle of the left rectangular frame area 9 refers to the included angle between the long side of the left rectangular frame area and the horizontal position; the angle of the right rectangular frame area 10 refers to the angle between the long side of the right rectangular frame area and the horizontal position.
In examples 1 and 2, the specific way to calculate the initial angle between the left and right knife arms is: taking the final left knife arm edge line and the right knife arm edge line as references, if the angle of the final left knife arm edge line relative to the straight line where the closed state knife arm is positioned is alpha, the angle of the final right knife arm edge line relative to the straight line where the closed state knife arm is positioned is gamma, and the included angle between the final left knife arm edge line and the right knife arm edge line is theta= |gamma-alpha|, and the included angle between the left knife arm and the right knife arm is theta= |gamma-alpha|.
In embodiments 1 and 2, the specific way to determine the corrected included angle between the left and right knife switch arms in the second frame image according to the center line estimation system error is: calculating the included angles of a left knife arm and a right knife arm in a current frame image in a real-time video and a straight line where the closed state knife arm is located respectively, calculating the included angles of the left knife arm and the right knife arm in a previous frame image of the current frame image and the straight line where the closed state knife arm is located respectively in the real-time video, setting the included angle of a final left knife arm edge line and the straight line where the closed state knife arm is located in the current frame image as alpha 1, the included angle of a final right knife arm edge line and the straight line where the closed state knife arm is located as gamma 1, the included angle of a final left knife arm edge line and the straight line where the closed state knife arm is located in the previous frame image as alpha 2, the included angle of a final right knife arm edge line and the straight line where the closed state knife arm is located as gamma 2, and recording a system error as noise= | (alpha 1-α2)-(γ1-γ2) |; and combining the system errors, determining that the correction included angle between the left knife switch arm and the right knife switch arm of the current frame is theta correct＝|γ1-α1 |+noise, wherein the correction included angle is the included angle between the left knife switch arm and the right knife switch arm in the second frame image. The calculation mode of the correction included angle between the left knife switch arm and the right knife switch arm in each frame image except the initial frame image is the same as the calculation mode of the correction included angle between the left knife switch arm and the right knife switch arm in the second frame image.
The specific mode for judging the real-time state of the knife switch in the initial frame image is as follows: two angle thresholds T-o and T-c of the split knife switch in an 'open' state and a 'closed' state are given according to the user requirement; if the included angle between the left knife arm and the right knife arm is larger than T-o, judging that the knife switch in the initial frame image is in an open state, if the included angle between the left knife arm and the right knife arm is smaller than T-c, judging that the knife switch in the initial frame image is in a closed state, and if the actual included angle between the left knife arm and the right knife arm is between T-o and T-c, judging that the knife switch in the initial frame image is in a virtual closing state. The state of the knife switch in the initial frame image is recorded as the initial state of the knife switch.
The specific mode for judging the real-time state of the knife switch in the second frame image is as follows: two angle threshold values T-o and T-c of a split type disconnecting link in an 'open' state and a 'closed' state are given according to the requirement of a user, a high threshold value hT-o and a low threshold value lT-o of the open state are set, the T-o is between the high threshold value hT-o and the low threshold value lT-o, and hT-o > T-o > lT-o; setting a high threshold value hT-c and a low threshold value lT-c of a closed state, wherein T-c is between the high threshold value hT-c and the low threshold value lT-c, hT-c > T-c > lT-c, and lT-o > hT-c, namely the low threshold value of the open state is higher than the high threshold value of the closed state; if the correction included angle between the left knife gate arm and the right knife gate arm is larger than hT-o, judging that the knife gate in the second frame image is in an open state, if the correction included angle between the left knife gate arm and the right knife gate arm is smaller than lT-c, judging that the knife gate in the second frame image is in a closed state, and if the correction included angle between the left knife gate arm and the right knife gate arm is between hT-c and lT-o, judging that the knife gate in the second frame image is in a virtual closing state; if the correction included angle between the left knife switch arm and the right knife switch arm is between lT-o and hT-o or between lT-c and hT-c, judging that the state of the knife switch in the second frame image is the same as the state of the knife switch in the previous frame image. The second frame image here is a second frame image after the initial frame image.
In the process of judging the real-time state of the disconnecting link in the second frame image and each subsequent frame image, a high threshold value and a low threshold value are set for the opening state and the closing state of the disconnecting link, so that an error range is given, and the detected angles of the left disconnecting link arm and the right disconnecting link arm are prevented from having errors. For example, the threshold for the angle of the open state is 20 degrees, the threshold for the angle of the closed state is 3 degrees, the high threshold for the open state is 22 degrees and the low threshold for the open state is 18 degrees, the high threshold for the closed state is 4 degrees and the low threshold for the closed state is 2 degrees, and the low threshold for the open state is 18 degrees that also needs to be greater than the high threshold for the closed state by 4 degrees.
And sequentially processing the next frame of image in the same way as the second frame of image until the movement of the disconnecting link is detected to stop, and verifying the final state of the movement of the disconnecting link in the video: judging the real-time state of the knife switch in the current frame image and then recording the real-time state; setting a continuous frame number threshold, if the state of the disconnecting link in the continuous frame images is kept unchanged and the continuous frame number is larger than the continuous frame number threshold, indicating that the disconnecting link maintains the same state, stopping detection at the moment, and verifying the final state; if the initial state of the knife switch is judged to be an open state through the initial frame image, the operation is completed when the knife switch is in a closed state during verification, and the knife switch is in a virtual state during verification, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a closed state, the operation is completed when the disconnecting link is in an open state in the final state, and the disconnecting link is in a virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a virtual closing state, the operation is completed when the disconnecting link is in a closing or opening state in the final state, and the disconnecting link is in the virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually.
Because the movement state of the knife switch in the real-time video of the knife switch to be processed is unidirectional from open to close or from close to open, the final state is verified to be relatively single, and the knife switch has only three states in the movement process: open, closed, and virtually closed. The method detects the opening and closing movement state of the split type disconnecting link, monitors the movement state of the disconnecting link in the video in real time, and if the split type disconnecting link in the video does not move, the state of the split type disconnecting link is an initial state and is in a safe state.
When a model file is built and a disconnecting link state is obtained according to a training model, the closed state of the disconnecting link means that the left disconnecting link arm and the right disconnecting link arm are on the same straight line, the virtual state means that contact exists between the left disconnecting link arm and the right disconnecting link arm but not on the same straight line, and the open state means that contact does not exist between the left disconnecting link arm and the right disconnecting link arm. The state of the knife switch is general, and is different from the state of the knife switch obtained according to the included angle between the knife switch arms, and the state of the knife switch obtained according to the included angle between the knife switch arms is the final state of the knife switch in each frame of image.
The left and right knife switch arms in the invention refer to left and right knife switch arms, and the knife switch in the invention refers to a split knife switch.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (8)

1. The real-time accurate detection method for the state of the split knife switch is characterized by comprising the following steps of: acquiring a real-time monitoring video of a split type disconnecting link, acquiring any frame of image of the video, establishing a boundary line model of a disconnecting link arm of the model according to the frame of image, storing the boundary line model as a model file, and calculating a left midpoint, a right midpoint, a midpoint and a center line of the disconnecting link arm according to the model file;
Obtaining sample images of the split type disconnecting link through multiple ways, training the sample images by utilizing deep learning to obtain a training model, detecting a first frame image of a video by utilizing the training model, obtaining all disconnecting link areas, disconnecting link states and insulator areas in the first frame image, positioning disconnecting link arms and insulators in the first frame image by combining model files, calculating the reliability of the disconnecting link according to positioning results, giving a reliability threshold, judging that the current disconnecting link state is undetectable if the reliability is lower than the reliability threshold, continuously detecting the next frame image until obtaining an image with the reliability of the first frame being higher than the reliability threshold, and marking the image as an initial frame image;
According to the positioning result of the knife switch arm, edge detection is carried out on an initial frame image of the video, an edge line set is obtained, the distance from the left middle point and the right middle point of the knife switch arm in the initial frame image to each edge line in the edge line set is calculated, and the edge line corresponding to the distance which is not in the threshold range is removed, so that an updated edge line set is obtained;
Dividing the updated edge line set left and right by using a central line, respectively acquiring a left knife switch arm edge line set and a right knife switch arm edge line set, symmetrically matching, determining final left knife switch arm edge lines and right knife switch arm edge lines, calculating an initial included angle between the left knife switch arm and the right knife switch arm, and judging the real-time state of a knife switch in an initial frame image;
Processing a second frame image after the initial frame image in the same way, judging that the current disconnecting link state is undetectable if the reliability is lower than the reliability threshold, otherwise, determining a correction included angle between a left disconnecting link arm and a right disconnecting link arm in the second frame image according to a central line estimation system error, and judging the real-time state of the disconnecting link in the second frame image;
sequentially processing the next frame of image in the same mode as the second frame of image until the knife switch is detected to stop moving, and verifying the final state of the knife switch movement in the video;
Dividing the updated edge line set left and right by using a central line, respectively obtaining a left disconnecting link arm edge line set and a right disconnecting link arm edge line set, carrying out weight distribution on the left disconnecting link arm edge line set and the right disconnecting link arm edge line set, and symmetrically pairing the left disconnecting link arm edge line set and the right disconnecting link arm edge line set after the weight distribution;
The specific mode for positioning the knife switch in the first frame image by combining the model file is as follows:
Detecting a first frame image by using a training model, and acquiring all knife gate areas and knife gate states corresponding to each knife gate area in the first frame image, wherein the areas corresponding to the knife gates in the 'closed' and 'virtual' states are integral rectangular frame areas containing left and right knife gate arms, and the areas corresponding to the knife gates in the 'open' state are left rectangular frame areas containing left and right rectangular frame areas containing right knife gate arms; for the knife switches in the 'closed' and 'virtual' states, the rectangular frames at the contact point positions of the left and right knife switch arms are obtained simultaneously;
Acquiring closed quadrilateral frame areas of a disconnecting link in a closed state according to the two left side endpoints and the two right side endpoints, and calculating overlapping areas of the whole rectangular frame area, the left rectangular frame area and the right rectangular frame area in the first frame image and the closed quadrilateral frame area respectively; traversing the areas where all the disconnecting links in the 'closed' and 'virtual-closed' states in the first frame image, giving an overlapping area threshold value, acquiring an area which comprises a left midpoint and a right midpoint and has the largest overlapping area and is larger than the overlapping area threshold value as a final left and right disconnecting link arm integral area, simultaneously calculating the center point of a rectangular frame at the contact point position of the left and right disconnecting link arms and marking the center point as a contact point, taking the center straight line which passes the contact point and is parallel to the short sides of the rectangular frame of the left and right disconnecting link arm integral area as a limit, wherein the left rectangular frame is a left disconnecting link arm rectangular frame, and the right rectangular frame is a right disconnecting link arm rectangular frame, so as to realize the positioning of the disconnecting link in the 'closed' or 'virtual-closed' state in the first frame image;
If the region which comprises the left midpoint and the right midpoint and has the largest overlapping area and is larger than the overlapping area threshold value does not exist, the condition that the state of the disconnecting link to be detected in the first frame image is not a closed state or a virtual closed state is indicated, the disconnecting link positioning is realized from all disconnecting links in the open state, the region where all disconnecting links in the open state and having the largest overlapping area and larger than the overlapping area threshold value in the first frame image is traversed, and the region which comprises the left midpoint and has the largest overlapping area is acquired and is recorded as a first open left disconnecting link arm region; acquiring a region which comprises a right midpoint and has the largest overlapping area and recording the region as a first opening right disconnecting link arm region; traversing all areas where the knife switches are in an open state and the overlapping area is smaller than or equal to the overlapping area threshold value in the first frame image, and acquiring the first two areas which contain the left midpoint and have the largest overlapping area and marking the first two areas as left knife switch arm matching areas; acquiring the first two areas which comprise the right midpoint and have the largest overlapping area and marking the areas as right disconnecting link arm matching areas;
Calculating the distance from 4 vertexes of any left disconnecting link arm matching region to the left midpoint, selecting the left minimum distance, and comparing the two left minimum distances with the left minimum distance, and marking the left disconnecting link arm matching region corresponding to the smaller left minimum distance as a second left disconnecting link arm opening region; calculating the distance from 4 vertexes of any right disconnecting link arm matching region to the right midpoint, selecting the right minimum distance, and comparing the two right minimum distances with the right minimum distance, and marking the right disconnecting link arm matching region corresponding to the smaller right minimum distance as a second right disconnecting link arm opening region;
A knife switch arm area threshold is given, a first left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area, and a second left-opening knife switch arm area larger than the knife switch arm area threshold is marked as a final left knife switch arm area; and the first opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, and the second opening right knife arm area larger than the knife arm area threshold is recorded as a final right knife arm area, so that the knife switch in the 'open' state in the first frame image is positioned.
2. The method for accurately detecting the opening and closing state of the split type disconnecting link in real time according to claim 1, wherein the method for positioning the insulator in the first frame image by combining the model file is as follows:
Acquiring a left insulator standard center line and a right insulator standard center line according to a model file, detecting a first frame image by using a training model, acquiring insulator rectangular frames of all insulator areas in the first frame image, traversing all insulator rectangular frames, and respectively acquiring a left insulator set of all left insulator rectangular frames containing a left midpoint and a right edge subset of all right insulator rectangular frames containing a right midpoint;
Calculating the actual center line of each rectangular insulator frame, giving a left distance threshold value, counting the number of points, of which the distance from the point on each actual center line in the left insulator set to the standard center line of the left insulator is smaller than the left distance threshold value, counting the difference value between the slope of each actual center line and the slope of the standard center line of the left insulator, giving a left slope difference threshold value and a left point number threshold value, wherein the slope difference is smaller than the left slope difference threshold value, and the rectangular insulator frame with the largest point number and the point number larger than the left point number threshold value is the final rectangular left insulator frame, so that the left insulator positioning is realized;
And (3) giving a right distance threshold, counting the number of points, in which the distance from each point on the actual central line in the right insulator set to the right insulator standard central line is smaller than the right distance threshold, counting the difference value between the slope of each actual central line and the slope of the right insulator standard central line, giving a right slope difference threshold and a right point number threshold, wherein the slope difference is smaller than the right slope difference threshold, and the rectangular insulator frame with the maximum point number and the point number larger than the right point number threshold is the final rectangular right insulator frame, so that the right insulator positioning is realized.
3. The method for accurately detecting the opening and closing states of the split type disconnecting link in real time according to claim 1, wherein the method for calculating the credibility of the disconnecting link according to the positioning result is as follows: determining the distance between the left midpoint and the right midpoint according to the model file and marking the distance as left midpoint distance and right midpoint distance; for the current frame image, acquiring a left disconnecting link arm, a right disconnecting link arm, a left insulator, a right insulator and a rectangular frame of a contact point of the left disconnecting link arm and the right disconnecting link arm according to a positioning result, wherein the short side length of the rectangular frame of the left insulator and the short side length of the rectangular frame of the right insulator are the width of the left insulator and the width of the right insulator;
If a rectangular frame of the left insulator exists, a left proportion threshold value is given, the proportion of half of the width of the left insulator to the left and right midpoint spacing is calculated, if the proportion is smaller than the left proportion threshold value, the contribution rate of the left insulator to the credibility is 0.2, and otherwise, the contribution rate is 0;
If a right insulator rectangular frame exists, a right proportion threshold value is given, the proportion of half of the width of the right insulator to the left-right midpoint distance is calculated, if the proportion is smaller than the right proportion threshold value, the contribution rate of the right insulator to the credibility is 0.2, and otherwise, the contribution rate is 0;
If a contact point rectangular frame exists, a proportion threshold value is given, the proportion of half of the width of the left and right disconnecting link arm contact point rectangular frames to the left and right midpoint spacing is calculated, if the proportion is smaller than the proportion threshold value, the contribution rate of the contact point to the credibility is 0.2, otherwise, the contribution rate is 0;
If a left disconnecting link arm rectangular frame exists, the contribution rate of the left disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0; if a right disconnecting link arm rectangular frame exists, the contribution rate of the right disconnecting link arm to the credibility is 0.2, otherwise, the contribution rate is 0;
For a knife switch in an open state, the contribution rate is additionally increased by 0.2 because no contact point exists; the sum of the contribution rate of the left disconnecting link arm, the right disconnecting link arm, the left insulator, the right insulator and the contact point of the left disconnecting link arm and the right disconnecting link arm to the credibility is the credibility of the disconnecting link, a credibility threshold value is given, if the credibility is larger than the credibility threshold value, the state of the disconnecting link of the current frame is detected, and if the credibility is smaller than the given threshold value, the state of the disconnecting link of the current frame is judged to be undetectable.
4. The method for accurately detecting the state of a split knife switch in real time according to claim 1, wherein the specific method for determining the correction included angle between the left knife switch arm and the right knife switch arm in the second frame image according to the center line estimation system error is as follows:
Calculating the included angles between the edge line of the final left knife switch arm and the edge line of the right knife switch arm in the current frame image and the previous frame image in the real-time video and the straight line where the knife switch arm in the closed state is positioned respectively, and setting the included angle between the edge line of the final left knife switch arm and the straight line where the knife switch arm in the closed state is positioned in the current frame image as follows The final included angle between the edge line of the right knife switch arm and the straight line where the knife switch arm in the closed state is positioned is/>The final included angle between the edge line of the left knife switch arm and the straight line where the knife switch arm in the closed state is in the previous frame image is/>The final included angle between the edge line of the right knife switch arm and the straight line where the knife switch arm in the closed state is positioned is/>The systematic error is recorded asCombining the system error to determine that the correction included angle between the left knife switch arm and the right knife switch arm of the current frame isThe correction included angle is the included angle between the left knife switch arm and the right knife switch arm in the second frame image.
5. The method for accurately detecting the state of a split type disconnecting link in real time according to claim 1, wherein the specific way of judging the state of the disconnecting link in the initial frame image is as follows:
two angle thresholds T-o and T-c of the split knife switch in an 'open' state and a 'closed' state are given according to the user requirement;
if the included angle between the left knife arm and the right knife arm is larger than T-o, judging that the knife switch in the initial frame image is in an open state, if the actual included angle between the left knife arm and the right knife arm is smaller than T-c, judging that the knife switch in the initial frame image is in a closed state, and if the actual included angle between the left knife arm and the right knife arm is between T-o and T-c, judging that the knife switch in the initial frame image is in a virtual closing state.
6. The method for accurately detecting the state of a split type disconnecting link in real time according to claim 1, wherein the specific way of judging the state of the disconnecting link in the second frame image is as follows:
Two angle threshold values T-o and T-c of a split type disconnecting link in an 'open' state and a 'closed' state are given according to the requirement of a user, a high threshold value hT-o and a low threshold value lT-o of the open state are set, the T-o is between the high threshold value hT-o and the low threshold value lT-o, and hT-o > T-o > lT-o; setting a high threshold hT-c and a low threshold lT-c of the closed state, T-c being between the high threshold hT-c and the low threshold lT-c, hT-c > T-c > lT-c, and lT-o > hT-c;
If the correction included angle between the left knife gate arm and the right knife gate arm is larger than hT-o, judging that the knife gate in the second frame image is in an open state, if the correction included angle between the left knife gate arm and the right knife gate arm is smaller than lT-c, judging that the knife gate in the second frame image is in a closed state, and if the correction included angle between the left knife gate arm and the right knife gate arm is between hT-c and lT-o, judging that the knife gate in the second frame image is in a virtual closing state; if the correction included angle between the left knife switch arm and the right knife switch arm is between lT-o and hT-o or between lT-c and hT-c, judging that the state of the knife switch in the second frame image is the same as the state of the knife switch in the previous frame image.
7. The method for accurately detecting the state of a split type disconnecting link in real time according to claim 1, wherein the method for sequentially processing the next frame of image in the same manner as the second frame of image until the disconnecting link is detected to stop moving is characterized in that the specific manner for verifying the final state of the disconnecting link movement in the video is as follows: judging the real-time state of the knife switch in the current frame image and then recording the real-time state; setting a continuous frame number threshold, if the state of the disconnecting link in the continuous frame images is kept unchanged and the continuous frame number is larger than the continuous frame number threshold, indicating that the disconnecting link maintains the same state, stopping detection at the moment, and verifying the final state;
If the initial state of the disconnecting link is an open state, the operation is completed when the disconnecting link is in a closed state in the final state, and the disconnecting link is in a virtual state in the final state, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a closed state, the operation is completed when the disconnecting link is in an open state in the final state, and the disconnecting link is in a virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually; if the initial state of the disconnecting link is a virtual closing state, the operation is completed when the disconnecting link is in a closing or opening state in the final state, and the disconnecting link is in the virtual closing state in the final state, an alarm is given and a worker is asked to confirm and process manually.
8. The method for precisely detecting the state of the split knife switch in real time according to claim 1, wherein,
The method for distributing weight to the left knife gate arm edge line set is as follows: traversing all edge lines in the left disconnecting link arm edge line set, calculating the angle of each left disconnecting link arm edge line, classifying the left disconnecting link arm edges according to the angles, setting a high angle threshold and a low angle threshold, setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge line angles larger than the high angle threshold as vertical edge lines, setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge lines angles smaller than the low angle threshold as horizontal edge lines, and setting left disconnecting link arm edge lines corresponding to the left disconnecting link arm edge lines between the low angle threshold and the high angle threshold as inclined edge lines;
Setting an x coordinate value L_x of a left midpoint of the left disconnecting link arm for all vertical edge lines of the left disconnecting link arm, respectively searching two edge points corresponding to x coordinates with the smallest difference with the L_x on the left side and the right side of the left midpoint of the left disconnecting link arm, wherein the x coordinate values of the two left edge points are marked as L_x1 and L_x2, and L_x1 is larger than L_x2; the x coordinate values of the two edge points on the right are denoted as R_x1 and R_x2, and R_x1 is greater than R_x2;
Setting the y coordinate value of the left midpoint of the left disconnecting link arm as L_y for all horizontal edge lines of the left disconnecting link arm, respectively searching two edge points corresponding to the y coordinates with the smallest difference with the L_y on the upper side and the lower side of the left midpoint of the left disconnecting link arm, and recording the y coordinate values of the two upper edge points as T_y1 and T_y2, wherein T_y1 is larger than T_y2; the y coordinate values of the two edge points at the lower side are denoted as B_y1 and B_y2, and B_y1 is larger than B_y2;
For all inclined edge lines of the left knife switch arm, setting x coordinate values and y coordinate values of a left middle point of the left knife switch arm as L_xx and L_yy, respectively searching two edge points corresponding to the x coordinate with the smallest difference between L_xx and the y coordinate with the smallest difference between L_yy on the left upper side and the right lower side of the left middle point of the left knife switch arm, wherein the x coordinate values of the two edge points on the left upper side are marked as L_xx1 and L_xx2, L_xx1 is larger than_xx2, the y coordinate values are marked as T_yy1 and T_yy2, and T_yy1 is larger than T_yy2; the x coordinate values of the two edge points on the lower right side are denoted as R_xx1 and R_xx2, R_xx1 is larger than R_xx2, and the y coordinate values are denoted as B_yy1 and B_y2, B_y1 is larger than B_y2;
The manner of obtaining the weight of each vertical edge line is as follows: traversing each edge point on each vertical edge line positioned at the left side of the left midpoint of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_x1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_x2 and less than L_x1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each vertical edge line positioned on the right side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_x2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_x2 and smaller than or equal to L_x1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current vertical edge line;
The manner of obtaining the weight of each horizontal edge line is as follows: traversing each edge point on each horizontal edge line positioned on the upper side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_y1, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, and otherwise, the contribution weight of the edge point is 0; traversing each edge point on each horizontal edge line positioned at the lower side of the left middle point of the left disconnecting link arm, wherein the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is less than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is greater than B_y2 and less than or equal to B_y1, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current horizontal edge line;
The manner of acquiring the weight of each inclined edge line is as follows: traversing each edge point on each inclined edge line positioned at the left upper side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is more than or equal to L_xx1, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is more than or equal to L_xx2 and less than L_xx1, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is more than or equal to T_yy1, and the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is more than or equal to T_y2 and less than T_y1, otherwise, the contribution weight of the edge point is 0; traversing each edge point on each inclined edge line positioned at the right lower side of the left middle point of the left knife switch arm, wherein the contribution weight of the edge point is value_W when the x coordinate Value of the edge point is smaller than or equal to L_xx2, the contribution weight of the edge point is value_W/2 when the x coordinate Value of the edge point is larger than or equal to L_xx2, otherwise, the contribution weight of the edge point is 0, the contribution weight of the edge point is value_W when the y coordinate Value of the edge point is smaller than or equal to B_y2, the contribution weight of the edge point is value_W/2 when the y coordinate Value of the edge point is larger than or equal to B_y2, otherwise, the contribution weight of the edge point is 0, and the sum of the contribution weights of all the edge points is the weight of the current inclined edge line;
The right switch arm edge line set is assigned the same weight as the left switch arm edge line set.
CN201910895604.XA 2019-09-21 2019-09-21 Real-time accurate detection method for state of split type disconnecting link Active CN110717409B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910895604.XA CN110717409B (en) 2019-09-21 2019-09-21 Real-time accurate detection method for state of split type disconnecting link

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910895604.XA CN110717409B (en) 2019-09-21 2019-09-21 Real-time accurate detection method for state of split type disconnecting link

Publications (2)

Publication Number Publication Date
CN110717409A CN110717409A (en) 2020-01-21
CN110717409B true CN110717409B (en) 2024-06-18

Family

ID=69210698

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910895604.XA Active CN110717409B (en) 2019-09-21 2019-09-21 Real-time accurate detection method for state of split type disconnecting link

Country Status (1)

Country Link
CN (1) CN110717409B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111814742A (en) * 2020-07-29 2020-10-23 南方电网数字电网研究院有限公司 Knife switch state identification method based on deep learning
CN113487559A (en) * 2021-07-02 2021-10-08 南京杰迈视讯科技有限公司 Method for detecting opening and closing states of disconnecting switch of transformer substation in real time
CN113569819B (en) * 2021-09-23 2021-12-24 泰豪软件股份有限公司 Method and system for identifying opening and closing states of disconnecting link, storage medium and computer equipment

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106203398B (en) * 2016-07-26 2019-08-13 东软集团股份有限公司 A kind of method, apparatus and equipment detecting lane boundary
CN106339722A (en) * 2016-08-25 2017-01-18 国网浙江省电力公司杭州供电公司 Line knife switch state monitoring method and device
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
CN110163833B (en) * 2018-02-12 2021-11-09 杭州海康威视数字技术股份有限公司 Method and device for determining opening and closing state of disconnecting link

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
变电站机器人自动巡检中的刀闸开合状态分析;马啸川;李庆武;刘静;钱荣;;电子测量与仪器学报;20180615(第06期);全文 *

Also Published As

Publication number Publication date
CN110717409A (en) 2020-01-21

Similar Documents

Publication Publication Date Title
CN110717409B (en) Real-time accurate detection method for state of split type disconnecting link
CN112819804B (en) Insulator defect detection method based on improved YOLOv convolutional neural network
CN111191641B (en) Accurate detection method for motion state of split type disconnecting link
CN110689574B (en) Method for detecting motion state of split type disconnecting link
CN109190446A (en) Pedestrian's recognition methods again based on triple focused lost function
CN110705571A (en) Scissor type knife switch opening and closing state detection method
CN107843818B (en) High-voltage insulation fault diagnosis method based on heterogeneous image temperature rise and partial discharge characteristics
CN110689528B (en) Automatic positioning-based opposite-opening type disconnecting link opening and closing angle detection method
CN112017173B (en) Power equipment defect detection method based on target detection network and structured positioning
CN108537829A (en) A kind of monitor video personnel state recognition methods
CN112749656B (en) ORB feature matching and yolo-based air switch state detection method and device
CN103247057A (en) Road target multi-hypothesis tracking algorithm under target-echo-road network data association
CN109146880A (en) A kind of electric device maintenance method based on deep learning
CN110717932B (en) Real-time tracking detection method for scissor type knife switch state
CN111008951B (en) Calculation method of opening and closing angle of split type disconnecting link based on positioning identification
CN110675452A (en) Real-time tracking split type disconnecting link state detection method
CN106887014B (en) A kind of pedestrian track matching process across camera
CN105741326A (en) Target tracking method for video sequence based on clustering fusion
CN110942443B (en) Real-time detection method for state of split type disconnecting link
CN116503957B (en) Gas household operation behavior identification method
CN117214606A (en) Method for determining lightning stroke position through multi-source data fusion of lightning stroke disturbance identification
CN110717923B (en) Knife switch state detection method capable of rapidly identifying electric wire
CN111862023A (en) Pantograph structure abnormity detection method based on computer vision
CN115861407B (en) Safety distance detection method and system based on deep learning
CN116896670A (en) Remote cloud video conference platform

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
TA01 Transfer of patent application right

Effective date of registration: 20240517

Address after: Room 2307, Block C, Torch Building, No. 306 Changzhi Road, Xuefu Industrial Park, Taiyuan City, Shanxi Province, 030000, China

Applicant after: Shanxi Jinzhi Hongyang Technology Co.,Ltd.

Country or region after: China

Address before: 210032 room 501A, block a, software building, No.9 Xinghuo Road, high tech Zone, Nanjing City, Jiangsu Province

Applicant before: NANJING XINHEHUITONG ELECTRON TECHNOLOGY CO.,LTD.

Country or region before: China

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant