CN112634223A - Method and device for detecting state of train brake pad - Google Patents
Method and device for detecting state of train brake pad Download PDFInfo
- Publication number
- CN112634223A CN112634223A CN202011499212.0A CN202011499212A CN112634223A CN 112634223 A CN112634223 A CN 112634223A CN 202011499212 A CN202011499212 A CN 202011499212A CN 112634223 A CN112634223 A CN 112634223A
- Authority
- CN
- China
- Prior art keywords
- brake pad
- brake
- edge line
- image
- brake lining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000001514 detection method Methods 0.000 claims abstract description 72
- 230000008859 change Effects 0.000 claims description 53
- 230000006870 function Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000003247 decreasing effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 abstract description 12
- 238000012545 processing Methods 0.000 description 5
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention relates to the technical field of train operation safety guarantee, and particularly discloses a method and a device for detecting the state of a train brake pad. According to the detection method for the train brake pad state, the train brake pad image is received; extracting a brake lining area image from the train brake lining image according to a preset brake lining area template; the method for judging whether the brake pad is reversely installed or not by combining the characteristics of the edge and the gray scale realizes the accurate detection of the reverse installation of the brake pad, and the maintainer directly checks the detection result to determine the next operation plan.
Description
Technical Field
The invention relates to the field of train operation safety guarantee, in particular to a method and a device for detecting the state of a train brake pad.
Background
The brake pad is one of the core components of the train braking device, and when a train is braked, the brake pad is tightly attached to a brake disc under the action of a brake clamp, so that huge friction force is generated to decelerate the train. The brake pad has the risk of losing, the installation is anti-in the train actual motion, and the driving safety can be seriously threatened to the above-mentioned phenomenon appears. The prior art adopts the traditional mode, and the train stops in the operation area of the overhaul trench after being put in storage, and the manual operation of going into the trench roughly observes whether the brake lining is lost or reversely installed, and the defects of the mode are that the speed is slow, the manual operation intensity is very high, and the mode can not be used for dynamic detection.
Disclosure of Invention
In view of the above, the present application provides a method and a device for detecting a state of a train brake pad, which can solve or at least partially solve the above existing problems.
In order to solve the technical problems, the technical scheme provided by the invention is a method for detecting the state of a train brake pad, which comprises the following steps:
receiving a train brake lining image;
extracting a brake lining area image from the train brake lining image according to a preset brake lining area template;
extracting a brake lining edge line from the brake lining area image, calculating the position of an extreme value point of a brake lining edge line pixel point coordinate change curve, and obtaining a detection result of whether the train brake lining is installed reversely or not according to the relation between the position of the extreme value point of the brake lining edge line pixel point coordinate change curve and the position of a preset extreme value point; or extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line; or acquiring the gap position of the brake pad in the brake pad area image, and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
Preferably, the method for extracting the brake lining edge line from the brake lining area image, calculating the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line, and obtaining the detection result of whether the train brake lining is installed reversely according to the relationship between the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line and the preset position of the extreme point comprises the following steps:
extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image;
obtaining the position of an extreme point of a horizontal and vertical coordinate change curve of the edge line pixel points of the brake pad according to the horizontal and vertical coordinate change characteristics of the edge line pixel points of the brake pad;
and judging whether the extreme point position of the horizontal and vertical coordinate change curve of the edge line pixel point of the brake pad is located at a preset extreme point position in the brake pad area image, if so, obtaining a detection result that the brake pad is not installed reversely, and if not, obtaining a detection result that the brake pad is installed reversely.
Preferably, the method for finding the edge line of the brake pad according to the monotonicity change of the gray value of the pixel point of the edge line of the brake pad in the image of the brake pad area and obtaining the extreme point position of the variation curve of the horizontal and vertical coordinates of the pixel point of the edge line of the brake pad according to the variation characteristics of the horizontal and vertical coordinates of the pixel point of the edge line of the brake pad comprises the following steps:
traversing the gray values of all pixel points in the brake pad area image, and finding the position of the pixel point with the left gray value smaller than the right gray value in each row of the brake pad area image according to the following formula:
whereincols is the width of the brake pad area image, rows is the height of the brake pad area image, g (i, j) is the gray value of the pixel point with the coordinate (i, j) in the brake pad area image, f (i, j) is the gray value of the pixel point with the coordinate (i, j) in another new image, a curve can be obtained on the new image through the formula, and the curve is the brake pad edge line;
the method comprises the steps of counting by using the position change of the abscissa and the ordinate of a pixel point with a gray value of more than or equal to 0 and less than or equal to 255 in a new image to obtain a curve function h (x, y) representing a brake pad edge line, wherein the curve function h (x, y) has the characteristic that along with the change of the ordinate, the abscissa is monotonously increased and then decreased, and the first derivative h '(x, y) of the curve function h (x, y) is 0, and the point of the second derivative h' (x, y) of 0 is marked as an extreme point, namely the extreme point position of the abscissa and ordinate change curve of the pixel point of the brake pad edge line.
Preferably, the method for extracting the brake pad edge line and the brake disc edge line from the brake pad area image and obtaining the detection result of whether the train brake pad is installed reversely by judging whether the brake pad edge line and the brake disc edge line have the coincident point includes:
extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image;
extracting the brake disc edge line according to the monotonicity change characteristic of the edge line of the brake disc in the brake disc area image, wherein the left gray value of the pixel point of the brake disc edge line is larger than the right gray value;
and judging whether coincident points exist between the edge line of the brake pad and the edge line of the brake disc, if not, obtaining a detection result that the brake pad is not reversely installed, and if so, obtaining a detection result that the brake pad is reversely installed.
Preferably, the method for extracting the brake disc edge line in the brake pad area image according to the fact that the left gray value of the pixel point of the brake disc edge line is larger than the right gray value and the monotonicity change characteristic of the edge line comprises the following steps:
finding an area with the gray value of the left pixel larger than the gray value of the right pixel in the gate area image;
and finding a curve which changes along with the change of the ordinate and the change of the abscissa after increasing and decreasing in the pixel gray value area, wherein the curve is the edge line of the brake disc.
Preferably, the method for obtaining the gap position of the brake pad in the brake pad area image and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and a preset gap position includes:
extracting the gap position of the brake pad in the brake pad area image by using yolov3-tiny neural network algorithm, and positioning to obtain the specific position of the gap position of the brake pad in the brake pad area image;
and judging whether the gap position of the brake pad is located at a preset gap position in the brake pad area image, if so, obtaining a detection result that the brake pad is not reversely installed, and if not, obtaining a detection result that the brake pad is reversely installed.
Preferably, the method for detecting the state of the train brake pad further comprises:
calculating an image gray average value of a preset first area and an image gray average value of a preset second area in the brake pad area image;
calculating the ratio of the image gray average value of the preset first area to the image gray average value of the preset second area;
and comparing the obtained ratio with a preset ratio threshold value to obtain a detection result of whether the train brake pad is lost.
Preferably, the method for calculating the image gray level mean value of the preset first region and the image gray level mean value of the preset second region in the gate area image includes:
using formulas
And calculating, wherein mean is the pixel mean value of the image, cols is the width of the image, rows is the height of the image, and img (i, j) is the gray value of a pixel point with the coordinate of (i, j) in the image.
The invention also provides a device for detecting the state of the train brake pad, which comprises:
the brake pad image receiving module is used for receiving a train brake pad image;
the brake pad area extraction module is used for extracting a brake pad area image from the train brake pad image according to a preset brake pad area template;
the brake lining state detection module is used for extracting a brake lining edge line from the brake lining area image, calculating the position of an extreme point of a pixel point coordinate change curve of the brake lining edge line, and obtaining a detection result of whether the train brake lining is installed reversely or not according to the relation between the position of the extreme point of the pixel point coordinate change curve of the brake lining edge line and the position of a preset extreme point; or extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line; or acquiring the gap position of the brake pad in the brake pad area image, and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
The invention also provides a device for detecting the state of the train brake pad, which comprises:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the steps of the detection method of the train brake pad state.
Compared with the prior art, the beneficial effects of the method are detailed as follows: according to the detection method for the train brake pad state, the train brake pad image is received; extracting a brake lining area image from the train brake lining image according to a preset brake lining area template; the method for judging whether the brake pad is reversely installed or not by combining the characteristics of the edge and the gray scale realizes the accurate detection of the reverse installation of the brake pad, and the maintainer directly checks the detection result to determine the next operation plan.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a schematic flow chart of a method for detecting an anti-installation state of a train brake pad according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another method for detecting an anti-installation state of a train brake pad according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of another method for detecting an anti-installation state of a train brake pad according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of a method for detecting a loss state of a train brake pad according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a device for detecting a state of a train brake pad according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative work belong to the protection scope of the present invention.
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, an embodiment of the present invention provides a method for detecting a train brake pad state, which is used for detecting whether a train brake pad is installed reversely, and specifically includes:
s11: receiving a train brake lining image;
s12: extracting a brake lining area image from the train brake lining image according to a preset brake lining area template;
s13: and extracting a brake lining edge line from the brake lining area image, calculating the position of an extreme value point of a pixel point coordinate change curve of the brake lining edge line, and obtaining a detection result of whether the train brake lining is installed reversely or not according to the relation between the position of the extreme value point of the pixel point coordinate change curve of the brake lining edge line and the position of a preset extreme value point.
Specifically, after finding the edge line of the brake pad, the software can obtain the extreme point according to the monotonicity change of the coordinates of the brake pad pixel point of the brake pad area image. The extreme point of the brake pad which is not reversely arranged is at the middle position of the brake pad area image, the extreme point of the brake pad which is reversely arranged is at the non-middle position (lower position) of the brake pad area image, and whether the brake pad is reversely arranged can be judged according to the position relation.
The train brake pad image received in S11 may be a train brake pad image captured by an area-array camera and a fill light. The train brake lining image comprises a left train brake lining image and a right train brake lining image, in order to unify detection algorithms of a left brake lining and a right brake lining, the right train brake lining image is used as a reference image to perform subsequent algorithm processing, then the left train brake lining image is subjected to image horizontal mirror image processing, the left train brake lining image is converted into the right train brake lining image to perform subsequent algorithm processing, and complexity of software algorithm processing is reduced.
In addition, the method for extracting the brake lining area image from the train brake lining image according to the preset brake lining area template in S12 includes: and extracting a brake pad large area image according to a predefined brake pad large area template, and extracting a brake pad small area image according to a predefined brake pad small area template, wherein the brake pad small area image is the final brake pad area image.
Specifically, a brake lining large-area template and a brake lining small-area template are defined, a brake lining large-area image is automatically extracted from a shot original train brake lining image by using a pattern recognition technology, the brake lining large-area image comprises a brake lining clamp, a locking device and the like, a brake lining small-area image is automatically extracted from the brake lining large-area image by using the pattern recognition technology, and the pattern recognition technology comprises an edge extraction technology and a template matching technology.
It should be noted that, the method for extracting the brake lining edge line from the brake lining area image in S13, calculating the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line, and obtaining the detection result of whether the train brake lining is installed reversely according to the relationship between the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line and the preset position of the extreme point includes:
s131: extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image;
s132: obtaining the position of an extreme point of a horizontal and vertical coordinate change curve of the edge line pixel points of the brake pad according to the horizontal and vertical coordinate change characteristics of the edge line pixel points of the brake pad;
s133: and judging whether the extreme point position of the horizontal and vertical coordinate change curve of the edge line pixel point of the brake pad is located at a preset extreme point position in the brake pad area image, if so, obtaining a detection result that the brake pad is not installed reversely, and if not, obtaining a detection result that the brake pad is installed reversely.
It should be noted that, the method for extracting the edge line of the gate piece in the gate piece area image according to the fact that the gray value of the pixel point on the left side of the gate piece is smaller than that on the right side of the gate piece and according to the monotonicity change characteristic of the edge line of the gate piece includes the following steps:
traversing the gray values of all pixel points in the brake pad area image, and finding the position of the pixel point with the left gray value smaller than the right gray value in each row of the brake pad area image according to the following formula:
wherein cols is the width of the gate area image, rows is the height of the gate area image, g (i, j) is the gray value of the pixel point with the coordinate (i, j) in the gate area image, f (i, j) is the gray value of the pixel point with the coordinate (i, j) in another new image, a plurality of curves (the positions of the pixel points meeting the formula) can be obtained on the new image through the formula, but only one curve is the edge line of the gate, in order to obtain the edge line of the gateThe damper edge curves require further screening of many curves present in the new image.
The method comprises the steps of counting by using the position change of the abscissa and the ordinate of a pixel point with a gray value of more than or equal to 0 and less than or equal to 255 in a new image to obtain a curve function h (x, y) representing a brake pad edge line, wherein the curve function h (x, y) has the characteristic that along with the change of the ordinate, the abscissa is monotonously increased and then decreased, and the first derivative h '(x, y) of the curve function h (x, y) is 0, and the point of the second derivative h' (x, y) of 0 is marked as an extreme point, namely the extreme point position of the abscissa and ordinate change curve of the pixel point of the brake pad edge line.
As shown in fig. 2, an embodiment of the present invention further provides a method for detecting a state of a train brake pad, which is used for detecting whether the train brake pad is installed reversely, and the difference from the embodiment of fig. 1 is that the method for detecting whether the train brake pad is installed reversely specifically includes:
s21: receiving a train brake lining image;
s22: extracting a brake lining area image from the train brake lining image according to a preset brake lining area template;
s23: and extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line.
Specifically, the train brake lining installation is anti-back, can be higher than the brake disc, consequently can cause some to shelter from to the brake disc edge, and whether the curve through judging brake lining edge line and brake disc edge line exists alternately then can judge whether the installation of brake lining is anti-. Namely, if the brake pad is installed correctly, the intersection point of the edge line of the train brake pad and the edge line of the brake disc does not exist. If the brake pad is installed reversely, there is an intersection area between the edge line of the brake pad and the edge line of the brake disc.
It should be noted that, in the brake pad area image, in step S23, the brake pad edge line and the brake disc edge line are extracted, and the method for obtaining the detection result of whether the train brake pad is installed reversely by determining whether there is an overlapping point between the brake pad edge line and the brake disc edge line includes:
s231: extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image; it can be fitted as a blue line;
s232: extracting the brake disc edge line according to the monotonicity change characteristic of the edge line of the brake disc in the brake disc area image, wherein the left gray value of the pixel point of the brake disc edge line is larger than the right gray value; it can be fitted as a yellow line;
s233: and judging whether coincident points exist between the edge line of the brake pad and the edge line of the brake disc, if not, obtaining a detection result that the brake pad is not reversely installed, and if so, obtaining a detection result that the brake pad is reversely installed. The superposition position of the brake pad edge line (blue line) and the brake disc edge line (yellow line) on the brake pad area image is further judged, if a superposed point exists, the superposed points are proved to be mutually crossed, the brake pad installation is further proved, and if no superposed point exists, the brake pad is considered to be not installed reversely.
It should be noted that, in the brake lining area image, the method for extracting the brake disc edge line according to the monotonicity change feature of the edge line of the brake disc, where the left gray value of the pixel point of the brake disc edge line in S232 is greater than the right gray value, includes:
s2321: finding an area with the gray value of the left pixel larger than the gray value of the right pixel in the gate area image;
specifically, the step of finding the region in which the gray value of the left pixel is greater than the gray value of the right pixel in the gate area image in S2321 includes:
(1) assume that the original image is g, with width cols and height rows. The image is regarded as a rectangular coordinate system, and it is assumed that the abscissa of one pixel point position is i, the ordinate is j, and the gray value of the pixel point is g (i, j). Simultaneously creating a gray image f with the same width and height, and setting the gray values of all pixel points of the gray image f as 0;
(2) traversing all pixel points in the image g, and finding out the area with the gray value of the left pixel larger than the gray value of the right pixel according to the following formula. If a certain point (i, j) in the image g is fullAnd if the gray value of the left pixel is larger than that of the right pixel, the gray value of the (i, j) pixel point in the image f is 255. The formula is as follows:
(3) according to the above formula, an image region with a pixel gray value of 255 is obtained in the gray image f, and the region is a region with a left pixel gray value larger than a right pixel gray value.
S2322: and finding a curve which changes along with the change of the ordinate and the change of the abscissa after increasing and decreasing in the pixel gray value area, wherein the curve is the edge line of the brake disc.
Specifically, the S2322 finds a curve in the pixel gray scale value region, where the change of the abscissa increases and then decreases with the change of the ordinate, and the curve is the brake disc edge line, where the curve is a method including:
(1) and according to the image f obtained in the previous step, a pixel point with the gray value of 255 exists in the image. Suppose that the abscissa and ordinate are x and y, respectively. Obtaining a curve function h (x, y) representing the edge line of the brake lining according to the position change of the horizontal and vertical coordinates; (2) firstly, the curve function h (x, y) is differentiated, the first derivative h '(x, y) is obtained, and the derivation is continued to obtain the second derivative h' (x, y). On this basis, if h' (x, y) ≠ 0, h ″ (x, y) ≠ 0, then an extreme point can be obtained at that point. If h "(x, y) <0, then h gets the maximum point at that point. The whole curve function shows the trend of increasing first and then decreasing, and the curve function is the brake disc edge curve.
As shown in fig. 3, the present invention further provides a method for detecting a train brake pad state, which is used to detect whether a train brake pad is installed reversely, and the method is different from the method for detecting whether a train brake pad is installed reversely in the embodiments corresponding to fig. 1 and 2, and specifically includes:
s31: receiving a train brake lining image;
s32: extracting a brake lining area image from the train brake lining image according to a preset brake lining area template;
s33: and acquiring the gap position of the brake pad in the brake pad area image, and acquiring the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
Specifically, after the brake pad of the train is reversely installed, the gap position can be far away from the central area of the brake pad, and whether the brake pad is reversely installed or not can be judged through the position relation. Namely, the notch area existing on the brake pad is identified by using a pattern identification method. If the position of the gap area is at the position below the image of the brake pad area, the correct installation of the brake pad position is proved, and if the position of the gap area is at the position above the image of the brake pad area, the reverse installation of the brake pad position is proved.
The method for acquiring the gap position of the brake pad in the brake pad area image and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position in S33 includes:
s331: extracting the gap position of the brake pad in the brake pad area image by using yolov3-tiny neural network algorithm, and positioning to obtain the specific position of the gap position of the brake pad in the brake pad area image;
specifically, the method for extracting the gap position of the brake pad in the brake pad area image by using the yolov3-tiny neural network algorithm in S331, and positioning and acquiring the specific position of the gap position of the brake pad in the brake pad area image includes:
(1) firstly, collecting a large amount of image data of gap positions of a brake pad area;
(2) then marking the collected data, and training by using yolov3-tiny neural network to obtain a weight file;
(3) and loading a weight file, and processing the input brake pad area image to identify the brake pad gap position in the brake pad area image. S332: and judging whether the gap position of the brake pad is located at a preset gap position in the brake pad area image, if so, obtaining a detection result that the brake pad is not reversely installed, and if not, obtaining a detection result that the brake pad is reversely installed.
Specifically, if the notch area exists at a position below the shutter area image, it is verified that the shutter is installed at the correct position. If the gap position exists in the upper position of the brake pad area image, the brake pad position is proved to be installed reversely.
It should be noted that, as shown in fig. 4, the present invention further provides a train brake pad state detection method, for detecting whether a train brake pad is lost, which specifically includes:
s41: calculating an image gray average value of a preset first area and an image gray average value of a preset second area in the brake pad area image;
s42: calculating the ratio of the image gray average value of the preset first area to the image gray average value of the preset second area;
s43: and comparing the obtained ratio with a preset ratio threshold value to obtain a detection result of whether the train brake pad is lost.
It should be noted that, after the gate is lost, the gate position in the gate area image forms a large area of black, and the ratio of the gray level average of the left 3/5 area to the gray level average of the right 2/5 area in the gate area image is relatively large. Therefore, a threshold value is set, and when the ratio of the average value of the left 3/5 area of the shutter area image to the average value of the right 2/5 area of the shutter area image is greater than the threshold value, the loss of the shutter can be directly judged.
Specifically, the brake lining area image is processed to obtain a left 3/5 area image and a right 2/5 area image of the brake lining area image, namely, a preset first area in the brake lining area image can be an image area of three fifths of the left side, a preset second area in the brake lining area image can be an image area of two fifths of the right side, the gray average value of the two fifths of the right side is far smaller than the gray average value of the three fifths of the left side, a ratio is obtained by the two gray average values, and the ratio is compared with a preset ratio threshold value to determine whether the train brake lining is lost.
It should be noted that, the method for calculating the image gray scale mean value of the preset first region and the image gray scale mean value of the preset second region in the shutter area image in S41 includes:
using formulas
Performing a calculation, wherein mean is the pixel mean of the image, cols is the width of the image, rows is the height of the image, and img (i, j) is the gray value of the pixel point with the coordinate (i, j) in the image.
Specifically, calculating a gray value mean value of the left 3/5 area image and a gray value mean value of the right 2/5 area image of the brake pad area image, and calculating a ratio of the gray value mean value of the left 3/5 area to the gray value mean value of the right 2/5 area; the calculation method/formula is:
mean is the mean value of the image, cols is the width of the image, rows is the height of the image, and img (i, j) is the gray value of a pixel point with the coordinate (i, j) in the image. And judging whether the ratio of the gray value mean value of the left 3/5 area image of the brake pad area image to the gray value mean value of the right 2/5 area image of the brake pad area image is larger than a preset threshold value, if so, obtaining a detection result that the brake pad is lost, and if not, obtaining a detection result that the brake pad is not lost.
The invention principle of the invention is as follows: the invention relates to a brake pad loss and brake pad reverse installation detection method integrating a mode identification technology and an image feature extraction technology.
As shown in fig. 5, the present invention also provides a device for detecting the status of a train brake pad, comprising:
a brake lining image receiving module 51, configured to receive a train brake lining image;
the brake lining area extraction module 52 is configured to extract a brake lining area image from the train brake lining image according to a preset brake lining area template;
the brake lining state detection module 53 is configured to extract a brake lining edge line from the brake lining area image, calculate an extreme point position of a pixel point coordinate variation curve of the brake lining edge line, and obtain a detection result of whether the train brake lining is installed reversely according to a relationship between the extreme point position of the pixel point coordinate variation curve of the brake lining edge line and a preset extreme point position; or extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line; or acquiring the gap position of the brake pad in the brake pad area image, and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
The invention also provides a device for detecting the state of the train brake pad, which comprises: a memory for storing a computer program; and the processor is used for executing a computer program to realize the steps of the detection method of the train brake pad state.
For the description of the features in the embodiment corresponding to fig. 5, reference may be made to the related description of the embodiments corresponding to fig. 1 to fig. 4, which is not repeated here.
The method and the device for detecting the loss state of the train brake pad provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (10)
1. A method for detecting the state of a train brake pad is characterized by comprising the following steps:
receiving a train brake lining image;
extracting a brake lining area image from the train brake lining image according to a preset brake lining area template;
extracting a brake lining edge line from the brake lining area image, calculating the position of an extreme value point of a brake lining edge line pixel point coordinate change curve, and obtaining a detection result of whether the train brake lining is installed reversely or not according to the relation between the position of the extreme value point of the brake lining edge line pixel point coordinate change curve and the position of a preset extreme value point; or extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line; or acquiring the gap position of the brake pad in the brake pad area image, and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
2. The method for detecting the status of the train brake lining according to claim 1, wherein the method for extracting the brake lining edge line from the image of the brake lining area, calculating the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line, and obtaining the detection result of whether the train brake lining is installed reversely according to the relationship between the position of the extreme point of the pixel point coordinate variation curve of the brake lining edge line and the preset position of the extreme point comprises:
extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image;
obtaining the position of an extreme point of a horizontal and vertical coordinate change curve of the edge line pixel points of the brake pad according to the horizontal and vertical coordinate change characteristics of the edge line pixel points of the brake pad;
and judging whether the extreme point position of the horizontal and vertical coordinate change curve of the edge line pixel point of the brake pad is located at a preset extreme point position in the brake pad area image, if so, obtaining a detection result that the brake pad is not installed reversely, and if not, obtaining a detection result that the brake pad is installed reversely.
3. The method for detecting the state of the train brake pad according to claim 2, wherein the method for finding the edge line of the brake pad according to the monotonicity change of the gray value of the pixel points of the edge line of the brake pad in the image of the brake pad area and obtaining the extreme point position of the variation curve of the abscissa and the ordinate of the pixel points of the edge line of the brake pad according to the variation characteristics of the abscissa and the ordinate of the pixel points of the edge line of the brake pad comprises:
traversing the gray values of all pixel points in the brake pad area image, and finding the position of the pixel point with the left gray value smaller than the right gray value in each row of the brake pad area image according to the following formula:
wherein cols is the width of the brake pad area image, rows is the height of the brake pad area image, g (i, j) is the gray value of the pixel point with the coordinate (i, j) in the brake pad area image, f (i, j) is the gray value of the pixel point with the coordinate (i, j) in another new image, a curve can be obtained on the new image through the formula, and the curve is the brake pad edge line;
the method comprises the steps of counting by using the position change of the abscissa and the ordinate of a pixel point with a gray value of more than or equal to 0 and less than or equal to 255 in a new image to obtain a curve function h (x, y) representing a brake pad edge line, wherein the curve function h (x, y) has the characteristic that along with the change of the ordinate, the abscissa is monotonously increased and then decreased, and the first derivative h '(x, y) of the curve function h (x, y) is 0, and the point of the second derivative h' (x, y) of 0 is marked as an extreme point, namely the extreme point position of the abscissa and ordinate change curve of the pixel point of the brake pad edge line.
4. The train brake lining state detection method according to claim 1, wherein the method for extracting the brake lining edge line and the brake disc edge line from the brake lining area image and obtaining the detection result of whether the train brake lining is installed reversely by judging whether the brake lining edge line and the brake disc edge line have the coincident point comprises:
extracting a brake lining edge line according to the monotonicity change characteristic of the edge line of the brake lining according to the fact that the gray value of a pixel point on the left side of the brake lining is smaller than that on the right side of the brake lining in the brake lining area image;
extracting the brake disc edge line according to the monotonicity change characteristic of the edge line of the brake disc in the brake disc area image, wherein the left gray value of the pixel point of the brake disc edge line is larger than the right gray value;
and judging whether coincident points exist between the edge line of the brake pad and the edge line of the brake disc, if not, obtaining a detection result that the brake pad is not reversely installed, and if so, obtaining a detection result that the brake pad is reversely installed.
5. The train brake lining state detection method according to claim 4, wherein the method for extracting the brake disc edge line in the brake lining area image according to the fact that the left gray value of the pixel point of the brake disc edge line is larger than the right gray value and the monotonicity change feature of the edge line comprises the following steps:
finding an area with the gray value of the left pixel larger than the gray value of the right pixel in the gate area image;
and finding a curve which changes along with the change of the ordinate and the change of the abscissa after increasing and decreasing in the pixel gray value area, wherein the curve is the edge line of the brake disc.
6. The train brake lining state detection method according to claim 1, wherein the method for obtaining the gap position of the brake lining in the brake lining area image and obtaining the detection result of whether the train brake lining is installed reversely by judging the relationship between the gap position of the brake lining and a preset gap position comprises the following steps:
extracting the gap position of the brake pad in the brake pad area image by using yolov3-tiny neural network algorithm, and positioning to obtain the specific position of the gap position of the brake pad in the brake pad area image;
and judging whether the gap position of the brake pad is located at a preset gap position in the brake pad area image, if so, obtaining a detection result that the brake pad is not reversely installed, and if not, obtaining a detection result that the brake pad is reversely installed.
7. The train brake lining state detection method according to claim 1, further comprising:
calculating an image gray average value of a preset first area and an image gray average value of a preset second area in the brake pad area image;
calculating the ratio of the image gray average value of the preset first area to the image gray average value of the preset second area;
and comparing the obtained ratio with a preset ratio threshold value to obtain a detection result of whether the train brake pad is lost.
8. The train brake lining state detection method according to claim 7, wherein the method for calculating the image gray level mean value of the preset first area and the image gray level mean value of the preset second area in the brake lining area image comprises:
using formulas
And calculating, wherein mean is the pixel mean value of the image, cols is the width of the image, rows is the height of the image, and img (i, j) is the gray value of a pixel point with the coordinate of (i, j) in the image.
9. The utility model provides a detection device of train brake lining state which characterized in that includes:
the brake pad image receiving module is used for receiving a train brake pad image;
the brake pad area extraction module is used for extracting a brake pad area image from the train brake pad image according to a preset brake pad area template;
the brake lining state detection module is used for extracting a brake lining edge line from the brake lining area image, calculating the position of an extreme point of a pixel point coordinate change curve of the brake lining edge line, and obtaining a detection result of whether the train brake lining is installed reversely or not according to the relation between the position of the extreme point of the pixel point coordinate change curve of the brake lining edge line and the position of a preset extreme point; or extracting a brake pad edge line and a brake disc edge line from the brake pad area image, and obtaining a detection result of whether the train brake pad is installed reversely by judging whether coincident points exist on the brake pad edge line and the brake disc edge line; or acquiring the gap position of the brake pad in the brake pad area image, and obtaining the detection result of whether the train brake pad is installed reversely by judging the relationship between the gap position of the brake pad and the preset gap position.
10. The utility model provides a detection device of train brake lining state which characterized in that includes:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the method for detecting the status of a train brake lining as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011499212.0A CN112634223A (en) | 2020-12-17 | 2020-12-17 | Method and device for detecting state of train brake pad |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011499212.0A CN112634223A (en) | 2020-12-17 | 2020-12-17 | Method and device for detecting state of train brake pad |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112634223A true CN112634223A (en) | 2021-04-09 |
Family
ID=75316603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011499212.0A Pending CN112634223A (en) | 2020-12-17 | 2020-12-17 | Method and device for detecting state of train brake pad |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112634223A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389566A (en) * | 2018-10-19 | 2019-02-26 | 辽宁奇辉电子系统工程有限公司 | Subway height adjusting valve fastening nut defective mode detection method based on boundary characteristic |
| CN110136189A (en) * | 2019-05-22 | 2019-08-16 | 成都铁安科技有限责任公司 | A kind of train brake pad detection method and device |
| CN111080668A (en) * | 2019-12-13 | 2020-04-28 | 武汉华目信息技术有限责任公司 | Brake pad wear fault detection method and system |
-
2020
- 2020-12-17 CN CN202011499212.0A patent/CN112634223A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389566A (en) * | 2018-10-19 | 2019-02-26 | 辽宁奇辉电子系统工程有限公司 | Subway height adjusting valve fastening nut defective mode detection method based on boundary characteristic |
| CN110136189A (en) * | 2019-05-22 | 2019-08-16 | 成都铁安科技有限责任公司 | A kind of train brake pad detection method and device |
| CN111080668A (en) * | 2019-12-13 | 2020-04-28 | 武汉华目信息技术有限责任公司 | Brake pad wear fault detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张甬成: "YOLOv3算法在闸片丢失及装反检测设备中的应用", 《设备与机具》, vol. 58, no. 11, 30 November 2020 (2020-11-30), pages 1 - 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866903B (en) | Ping-pong ball identification method based on Hough circle transformation technology | |
| US11790499B2 (en) | Certificate image extraction method and terminal device | |
| JP5505410B2 (en) | Data processing apparatus, image collation method, program, and image collation system | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| US9147105B2 (en) | Image recognizing apparatus, image recognizing method, and program | |
| CN110287791B (en) | Screening method and system for face pictures | |
| CN106778659B (en) | License plate recognition method and device | |
| CN102982534B (en) | Canny edge detection dual threshold acquiring method based on chord line tangent method | |
| CN111104913B (en) | Video PPT extraction method based on structure and similarity | |
| CN106056079A (en) | Image acquisition device and facial feature occlusion detection method | |
| TWI500904B (en) | Stereo camera and automatic range finding method for measuring a distance between stereo camera and reference plane | |
| CN103455994A (en) | Method and equipment for determining image blurriness | |
| CN104268529A (en) | Judgment method and device for quality of fingerprint images | |
| CN115861325A (en) | Suspension spring defect detection method and system based on image data | |
| CN117251087B (en) | Coal mine safety simulation interaction method based on virtual reality | |
| CN112949464B (en) | Face changing counterfeiting detection method, system and equipment based on three-dimensional shape of human face | |
| CN109492647A (en) | A kind of power grid robot barrier object recognition methods | |
| CN104318266A (en) | Image intelligent analysis processing early warning method | |
| CN110929562A (en) | Answer sheet identification method based on improved Hough transformation | |
| CN111369570A (en) | Multi-target detection tracking method for video image | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| CN115830513A (en) | Method, device and system for determining image scene change and storage medium | |
| Ma et al. | A finger vein image quality assessment method using object and human visual system index | |
| CN116052152A (en) | License plate recognition system based on contour detection and deep neural network | |
| CN106600812B (en) | Paper money identification method and device |
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 |