WO2016204385A1

WO2016204385A1 - Method and apparatus for detecting vibration information of electric railway vehicle

Info

Publication number: WO2016204385A1
Application number: PCT/KR2016/002816
Authority: WO
Inventors: 박영; 이기원; 조용현; 권삼영; 박철민
Original assignee: 한국철도기술연구원
Priority date: 2015-06-15
Filing date: 2016-03-21
Publication date: 2016-12-22
Also published as: CN107743577B; CN107743577A

Abstract

A pantograph-based vibration information detection method for an electric railway vehicle according to an embodiment of the present invention comprises the steps of: determining a pantograph template; comparing the pantograph template with an input image obtained using a camera, and detecting a pantograph; and detecting vibration information of the pantograph based on changes in the position of the pantograph that is detected by comparing the pantograph template with each frame of the input image.

Description

Method and apparatus for detecting vibration information of electric railway vehicle

The present invention relates to a method and apparatus for detecting vibration information of a pantograph-based electric railway vehicle.

In general, the pantograph is a core facility of an electric rail vehicle that supplies electric energy to a vehicle by contacting a catenary. The pantograph is mechanically in contact with the tramline that supplies the electric energy during operation, thereby causing abrasion and vibration, and in non-contact, an arc phenomenon in which the electric energy is discharged is generated. In particular, the abnormal vibration is caused by various causes such as an abnormality of the pantograph or an overspeed, a line anomaly, and cause an arc phenomenon by causing non-contact between the pantograph and the tramline. In addition, the abnormal vibration causes the tram line to be fatigued, thereby causing fatigue of the tram line-related parts, causing damage to the tram line and the related parts.

The tramline is a facility for stably supplying electricity to the railway body, and it is necessary to detect the deformation and damage of the tramline due to the vehicle or external factors and maintain the optimal state according to the regulations of the electric railway facilities.

The horizontal distance from the trajectory center of the tram line is called the deviation, and if the deviation of the tram line is too large, the current collector will leave the tank line and cause an accident. Therefore, the deviation of the tramline is prescribed with a certain limit, and the deviation of the tramline is usually within 250 mm from the center of the track perpendicular to the trajectory. Normally, even in a straight line, the current collector needs to be distributed on the effective surface to collect current to evenly wear the pantograph. The catenary is composed of a catenary in direct contact with the electric vehicle, a support supporting the same, a feeder, and a return line. The catenary is the part that supplies electric vehicles. Since the high voltage is always flowing, the performance should be excellent. Dynamic deviation, which indicates the alignment of contact points between trains and tram lines on electric railways, is one of the criteria for determining whether a train can be supplied with a stable current and is one of the important criteria for evaluating the safety performance of a train.

In the related literature, Korean Patent Publication No. 2014-0111712 (Pantron Graph Measuring Method and Pantograph Measuring Apparatus) acquires an image of a marker installed on a pantograph from a line sensor, generates a construction image from the acquired image, and performs image processing. Disclosed is a method of estimating the position of the height of the tramline by measuring the position of the pantograph.

However, in the conventional image processing-based pantograph measuring method, since the position of the pantograph is measured only by using a laser sensor, the dynamic deviation of the front line cannot be obtained.

In addition, as a method of detecting abnormal vibration, conventionally, a sensor for monitoring vibration such as an accelerometer is attached to the pantograph and insulated therefrom, and then measured through the sensor to detect vibration of the pantograph. However, since the pantograph transmits electric energy to the vehicle, high voltage and high current are always applied, which makes it difficult to attach a sensor for vibration detection.

In addition, as a method of monitoring the contact point between the pantograph and the tramline, there is a method of visually confirming the video by installing the upper part of the vehicle so as to monitor the contact point between the pantograph and the tramline. However, it is difficult to derive accuracy and quantitative values because of visual discrimination.

Regarding the method for monitoring the contact state between the pantograph and the catenary, Korean Patent No. 1058179 (name of the invention: Pantograph Defect Monitoring System), which is a prior art, uses a reference image to remove a noise of an image obtained from a camera. Compared with the present invention, a technique for determining whether a defect is present is disclosed. In addition, Japanese Patent No. 5534058 (Invention: Wear Measurement Apparatus and Method) discloses a wear measurement apparatus and a method for obtaining a wear measurement value of an electric vehicle in consideration of an inclination angle of a pantograph.

In order to solve the above-mentioned problems, the present invention uses a general camera capable of acquiring continuous images to increase the accuracy of dynamic deviation measurement by detecting the position of the pantograph and the position of the tramline without being affected by the brightness conditions. To provide a method.

It is also an object of the present invention to provide a method and apparatus for detecting pantograph vibration by comparing a photographed image with a pantograph template and using an image processing technique.

However, the technical problem to be achieved by the present embodiment is not limited to the technical problems as described above, and further technical problems may exist.

According to an aspect of the present invention, there is provided a method for detecting vibration information of a pantograph-based electric railway vehicle, including: determining a pantograph template; Comparing the pantograph template with the input image acquired by the camera and detecting the pantograph; And detecting vibration information of the pantograph based on the detected positional change of the pantograph according to the comparison of each frame of the input image and the pantograph template.

In addition, the vibration information detection apparatus for a pantograph-based electric railway vehicle according to an embodiment of the present invention is a communication module for receiving the image captured by the pantograph, a memory for storing the vibration detection program of the pantograph and executing the vibration detection program of the pantograph The processor includes a processor, the processor determines a pantograph template according to the execution of the program, compares the pantograph template and the input image acquired by the camera, detects the pantograph, and detects the pantograph template by comparing each frame of the input image with the pantograph template. The vibration information of the pantograph is detected based on the changed position of the pantograph.

According to any one of the problem solving means of the present invention described above, there is an advantage of detecting the dynamic deviation accurately without the need of a separate illumination device that uniformly adjusts the brightness of the image. In addition, there is an advantage of reducing the amount of calculation by utilizing a marker for reducing the detection area of the pantograph.

In addition, in one embodiment of the present invention, by detecting the vibration of the pantograph using an image processing technique in the existing video monitoring method, it is very economical by reducing the cost of installing additional equipment.

In addition, according to an embodiment of the present invention, the cause of the abnormality can be determined during operation of the electric railway vehicle because the abnormality of the current collector plate of the pantograph, the abnormality of the line, or the abnormality caused by the change of the tension of the electric cable line is different according to the inherent frequency. After the operation, it is easy to check the suspected parts if necessary.

FIG. 1A is a block diagram of a method for detecting a dynamic deviation of a catenary vehicle that is not affected by a change in brightness according to a first embodiment of the present invention.

FIG. 1B is a block diagram illustrating detailed steps constituting step S10 in FIG. 1A.

2 shows an apparatus for detecting a dynamic deviation of a tram line according to a first embodiment of the present invention.

3 illustrates a process of calculating a feature vector and classifying a reference image into classes based on the feature vector, according to the first embodiment of the present invention.

4 is a diagram showing a reference image divided by class according to the first embodiment of the present invention.

5 is a view illustrating a process of updating and resetting a classified class according to the first embodiment of the present invention.

6 illustrates a case where a feature vector acquired according to the first embodiment of the present invention is different for each class.

7 illustrates a state in which the detection unit detects the pantograph from the pantograph template according to the first embodiment of the present invention.

FIG. 8 is a diagram illustrating a method of detecting a catenary due to a fusion of a Hough transform and a binarization according to a first embodiment of the present invention.

9A shows a correctly detected pantograph image according to the first embodiment of the present invention.

9B illustrates an incorrectly detected pantograph image according to the first embodiment of the present invention.

10A illustrates a process of detecting a contact surface and a center point by using an attachment marker according to a first embodiment of the present invention.

10B shows a marker for attachment according to the first embodiment of the present invention.

11 is a configuration diagram of a vibration detection apparatus of a pantograph of an electric railway vehicle according to a second embodiment of the present invention.

12 is a diagram for describing a method of detecting a pantograph for each image frame according to the second embodiment of the present invention.

FIG. 13 is a diagram for describing a method of measuring an angle between a horizontal line and a current collector plate in a detected pantograph according to a second embodiment of the present invention.

14 is a diagram for describing a method of calculating a vibration frequency of a pantograph based on an angle according to a second embodiment of the present invention.

15A and 15B are views for explaining a method of calculating the vibration intensity of the pantograph based on the magnitude of the angle according to the second embodiment of the present invention.

FIG. 16 is a view for explaining a method of measuring left and right displacements of a horizontal line and a current collector plate according to a second embodiment of the present invention.

FIG. 17 is a diagram for describing a method of calculating a frequency based on an average value of left and right displacements according to a second embodiment of the present invention.

18 is a flowchart illustrating a vibration detection method of a pantograph of an electric railway vehicle according to a second embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components, unless specifically stated otherwise, one or more other features It is to be understood that the present disclosure does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, parts, or combinations thereof.

The present invention determines the pantograph template, compares the pantograph template and the input image acquired by the camera to detect the pantograph, and based on the positional change of the pantograph according to the comparison of each frame and pantograph template of the input image, the vibration of the pantograph. A method and apparatus for detecting vibration information of a pantograph-based electric railway vehicle for detecting information.

The invention is divided into two embodiments. First, the first embodiment relates to a method for detecting a dynamic deviation of a catenary. In particular, an image is acquired through a measuring camera and a sensor disposed at an upper railroad, and the acquired image is analyzed to analyze the acquired image. The present invention relates to a method for detecting a dynamic deviation between a vehicle and a vehicle line. Next, the second embodiment relates to a method for detecting a pantograph by comparing a pantograph template with an image photographed by a camera disposed on an upper railroad, and detecting pantograph vibration of an electric railway vehicle using an image processing technique.

Hereinafter, the first embodiment will be described.

1A and 1B are block diagrams showing the overall steps in order according to the first embodiment of the present invention, and FIG. 2 shows an apparatus 1 for detecting a dynamic deviation of a tram line according to the first embodiment of the present invention. Referring to FIG. 2, the apparatus for detecting a dynamic deviation of the tramline 1 includes a training unit 10, a detection unit 30, and a contact intersection calculation unit 50. The apparatus for detecting the dynamic deviation of the tramline 1 may detect the dynamic deviation of the pantograph 70 and the tramline 90 of the input image by comparing the brightness of the reference image. The training unit 10 may acquire a plurality of reference images by dividing similar types with different brightness conditions and obtaining an optimal feature vector 101. The training unit 10 may previously determine a pantograph template 80 representing a reference image to be contrasted by comparing the feature vector generated from the selected reference image with the feature vector acquired from the input image. The detector 30 may detect the pantograph 70 and the tramline 90 existing in the background image from the pantograph template 80. The contact intersection calculation unit 50 detects the contact surface 709 and the center point 707 from the pantograph template 80, and uses the contact surface 709 and the center point 707 to dynamically adjust the vehicle line 90 and the pantograph 70. The deviation can be calculated. The apparatus for detecting the dynamic deviation of the tram line 1 may detect the dynamic deviation of the input image without interference with brightness.

The training unit 10 may be defined by matching different brightness conditions to a predetermined number of reference images 80 according to the acquisition conditions of the image. The training unit 10 may calculate the feature vector 101 by digitizing brightness, variance, correlation, etc. of the reference image, and classify the reference image 80 into a class 103 based on the feature vector 101. The training unit 10 may acquire a plurality of similar images for defining the reference image 80 by using a camera and a sensor installed on the vehicle, and the obtained images may have different degrees of light, exposure value of the lens, and focus. Can be. For example, when sunlight is reflected onto the pantograph 70, the image of the pantograph 70 having a high brightness is obtained, and the pantograph 70 may appear relatively dark in a clouded state. In this case, since there is a possibility that the detection performance of the pantograph 70 is greatly reduced, the process of collecting the reference image 80 for each type must be performed first by defining a case where the obtained pantograph image is significantly different. The training unit 10 collects reference images for each defined type, and needs to condition the class 103 in a situation where the feature vector 101 is different from the same reference image. It is a Vector Machine (SVM). The support vector machine may store the feature information of the quantifiable image, such as the average of the brightness of the reference image 80, the contrast ratio, etc. in the form of the feature vector 101. The feature vector 101 stores quantifiable information in a vector form, and the stored information may be different depending on lightness conditions.

3 illustrates a process of calculating the feature vector 101 and classifying a reference image into a class 103 based on the feature vector 101. Referring to FIG. 3, the training unit 10 may minimize an error in classifying the class 103 using the support vector machine. The training unit 10 may perform a linear classification process for performing training to classify the reference image. The training unit 10 may extract a feature from a reference image including a plurality of pantographs 70 and a chariot line 90 obtained under various brightness conditions and digitize it according to the brightness conditions. The training unit 10 may provide a numerical brightness condition and may provide information for the detection unit 30 to determine the pantograph template 80 according to the numerical value.

The training unit 10 may quantify and store the average of the brightness, the brightness of the tramline 90, and the contrast ratio with the pantograph 70 in the reference image as the feature vector 101. The feature vector 101 may be digitized to represent one reference image, and the training unit 10 may classify the reference image for each class 103 with reference to the feature vector 101.

4 is a diagram illustrating a reference image divided by class 103 according to a first embodiment of the present invention. Referring to FIG. 4, the support vector machine calculates a brightness condition from the reference image, stores it as the feature vector 101, and classifies the reference image for each class 103 with reference to the stored feature vector 101. The support vector machine may classify a plurality of reference images measured by the camera into classes 103 such as a bright section, a dark section, a tunnel section, and a background interference. However, the present invention is not limited thereto, and the class 103 may be divided and set according to the brightness condition. The training unit 10 may repeat the above classification process whenever reference images are acquired. Since the training unit 10 may classify the class 103 through the feature vector 101, the process of calculating the feature vector 101 is important.

5 is a view showing a process of resetting the class 103 according to the first embodiment of the present invention. Referring to FIG. 5, when the difference between the average brightness of the pantograph region 104 and the average brightness of the class 103 of the updated feature vectors 101 exceeds a set value, the updated feature vector 101 is calculated. The process of resetting the class 103 is performed. In an embodiment of the present invention, a difference in average brightness between classes 103 is obtained, and when half or more of the difference is set as the reset threshold 105, and the brightness difference of the current image exceeds the corresponding reset threshold 105, Reset class 103.

6 shows a simplified two-dimensional example of the feature vector 101 for each class 103 according to the first embodiment of the present invention. When the average brightness of the pantograph region 104 and the pantograph lower region is plotted in each of the image acquired inside the tunnel and the normal situation image against the clear sky, a two-dimensional feature vector 101 is formed.

The training unit 10 of the present invention can set a decision boundary for which class 103 the feature vector 101 of the class 103 corresponds to using a support vector machine algorithm. However, in the present invention, the method for obtaining the crystal boundary of the feature vector 101 for the class 103 is not limited to the support vector machine.

The training unit 10 selects a class 103 such as a normal situation, a tunnel situation, a background interference situation, an arc occurrence situation, etc. to collect a reference image; Constructing a feature vector 101 by quantifying features such as brightness, correlation, and dispersion for each zone of the input image; A reset step for updating the class 103; Comparing the feature vector of the input image with the feature vector 101 of the current class to determine a class 103 most suitable for the input image; The method may include setting a pantograph template 80 corresponding to the determined class 103. The detector 30 detects the position of the pantograph 70 by using the reference pantograph image 80 determined by the training unit 10, and calculates the dynamic deviation of the tramline 90 based on the position of the pantograph.

7 illustrates a state in which the detection unit 30 according to the first embodiment of the present invention detects the pantograph 70 from the pantograph template 80. Referring to FIG. 7, the detector 30 may detect the pantograph 70 from the pantograph template 80 determined by the training unit 10. The detector 30 may extract the pantograph 70 from the pantograph template 80 by using Equation 1 below.

Here, I is an input image, T is a pantograph template image, w is an input vector, X is a coordinate in a pantograph template image, and p is a linear transformation parameter of the input vector.

The detector 30 may determine an optimal pantograph template 80 through the identification process and perform a linear transformation w (x, p) of the input image. The detector 30 may obtain a point having the highest similarity in the pantograph template 80 through this operation.

FIG. 8 illustrates the detection of the tramline 90 according to the fusion of Hough transform, which is a method of detecting a straight line, and binarization, which is a method of distinguishing a background from a foreground, according to a first embodiment of the present invention. Referring to FIG. 8, the detector 30 performs binarization of an input image; And limiting brightness, height, width, area, and angle of the tramline 90, and comparing the binarized value with the pantograph template 80. When detecting the pantograph 70 and the tramline 90, the detector 30 may use a template matching technique that extracts the brightness of the input image and compares it with the pantograph template 80 using [Equation 1].

9A shows an accurately detected pantograph 70 image according to the first embodiment of the present invention. 9B illustrates an incorrectly detected pantograph 70 image according to the first embodiment of the present invention. Referring to FIG. 9A, when the brightness conditions are similar, the detector 30 may detect the actual position and the detected position to be almost identical. In this case, it is possible to accurately calculate the dynamic deviation of the tramline 90. Referring to FIG. 9B, when the brightness condition is not met, the detector 30 may detect the actual position and the detected position differently, and incorrectly calculate the dynamic deviation. Therefore, it can be seen that the reference pantograph template 80 must be set correctly in order to find the correct pantograph 70 and the catenary line 90.

The contact intersection calculator 50 may calculate the dynamic deflection of the tramline 90 using the detected pantograph 70 and the tramline 90. The contact intersection calculation unit 50 detects a contact surface 709 corresponding to a horizontal plane in which the detected tramline 90 and the pantograph 70 contact each other; Detecting a center point 707 of the pantograph 70 from the contact surface 709; And obtaining an intersection point of the catenary line 90 and the contact surface 709. The contact intersection calculator 50 may calculate a dynamic deviation of the intersection from the center point 707.

The detecting of the contact surface 709 by the contact intersection calculator 50 may include: obtaining a straight line of the pantograph 70 using a Hough transform from an input image; And estimating a point where the straight line rises to contact the catenary line 90 as the contact surface 709. That is, since the pantograph 70 is in close contact with the chariot line 90 suspended in the air using pneumatic pressure, if the horizontal plane of the pantograph 70 and the chariot line 90 intersect through the binarization image, the actual contact point and Similar data can be obtained. In this case, a gap may occur between the pantograph 70 and the tramline 90 due to vibration. However, since the gap is very weak, the gap may be included in the error range even if approximated. Therefore, the contact intersection calculator 50 may detect the contact surface 709, the center point 707, and the intersection point, and calculate a dynamic deviation of the tramline 90 by calculating the distance from the center point 707 to the intersection point. By substituting a proportional expression using the length of the pantograph 70 at the detected intersection point, an accurate value may be measured by converting the detected distance in pixels by mm.

As described above, the measurement may be performed by using the dynamic deviation detection apparatus 1 of the tank line, but there is also a method of simplifying the pattern graph detection by using the attachment marker.

10A illustrates a process of detecting the contact surface 709 and the center point 707 by using the attaching marker according to the first embodiment of the present invention. 10B shows a marker for attachment according to the first embodiment of the present invention. Referring to FIG. 10A, a separate marker such as FIG. 10B may be attached to the pantograph 70. In this case, the method of detecting the pantograph 70 and the detection of the contact surface 709 can be simplified. While the detection unit 30 must find a detection area corresponding to the image size of the pantograph 70 in the entire image as described above, when the marker is attached, only the portion to which the marker is attached needs to be detected, thereby greatly reducing the amount of computation.

The detecting of the contact surface 709 by the detector 30 may include: obtaining a straight line from a marker attached to an upper end of the pantograph 70; And estimating a point of contact with the catenary line 90 by raising the straight line as the contact surface 709. The detecting of the center point 707 by the detector 30 may include extracting a marker attached in the middle from a marker attached to the upper end of the pantograph 70 in a straight line; And estimating a point at which the marker attached in the middle is located as the center point 707, thereby reducing the amount of computation.

In the embodiment of the present invention, three markers are attached to the pantograph 70. The first marker 701 may be attached to the left side of the pantograph 70, the second marker 703 may be attached to the middle, and the third marker 705 may be attached to the right side. The detection unit 30 may estimate, as the contact surface 709, the position at which the contact is made by linearly following the three detected points when detecting three horizontally placed markers. The detector 30 may estimate a place where the marker located in the middle is the center point 707. Therefore, the amount of computation can be reduced by simplifying the procedure of estimating the contact surface 709 and the center point 707 by extracting the marker.

Hereinafter, the second embodiment will be described.

FIG. 11 is a block diagram illustrating a vibration detection apparatus of a pantograph of an electric railway vehicle according to a second embodiment of the present invention, and FIG. 12 is a diagram illustrating a method of detecting a pantograph for each image frame according to a second embodiment of the present invention. FIG. 13 is a diagram for describing a method of measuring an angle between a horizontal line and a current collector plate in a detected pantograph according to a second embodiment of the present invention, and FIG. 14 is a second embodiment of the present invention. 15A and 15B illustrate a method of calculating the vibration intensity of the pantograph based on the magnitude of the angle according to the second embodiment of the present invention. It is a figure for demonstrating.

Referring to FIG. 11, the vibration detecting apparatus 11 of the pantograph of an electric railway vehicle may include a communication module 100, a memory 200, and a processor 300.

The communication module 100 receives a captured image of the pantograph.

The communication module 100 receives a photographed image of the pantograph through data communication with a camera photographing an image of the pantograph. At this time, the camera may be located on the upper portion of the electric railway vehicle so as to secure the image of the pantograph. Such a camera may be arranged as a high speed or general camera, and the higher the resolution, the more accurately the pantograph may be detected.

The memory 200 stores the vibration detection program of the pantograph.

Here, the memory 200 refers to a flash memory that maintains stored information even when power is not supplied, a nonvolatile storage device such as an SSD, and a DRAM and an SRAM volatile storage device requiring power to maintain stored information.

The processor 300 executes the vibration detection program of the pantograph.

The processor 300 may detect the pantograph for each image frame by comparing the pantograph template and the captured image of the pantograph received through the communication module according to the execution of the program.

Referring to FIG. 12, a pantograph template includes a plurality of pantograph templates having different brightness and contrast ratios in order to accurately detect pantographs from photographed images of pantographs in which brightness of an image may be different depending on light intensity, lens exposure value, and focus. This can be specified in advance.

Accordingly, by matching the pantograph template having the highest similarity among the plurality of pantograph templates to the pantograph photographed image in which the brightness of the image is variously photographed according to weather, tunnel conditions, obstacles, etc., the pantograph can be accurately detected for each image frame.

For example, as illustrated in FIG. 3A, the processor 300 matches the pantograph template having the highest similarity among the plurality of pantograph templates to the pantograph photographed image, thereby accurately detecting the pantograph 310 for each image frame. can do.

Referring to FIGS. 13 and 14, the processor 300 detects the center point 325 of the current collector plate on the detected pantograph 310 according to the execution of the program, and the horizontal line 330 extending from the center point 325. The angle between the extension lines 320 of the current collector plate may be measured, and the vibration frequency of the pantograph may be calculated based on the angle calculated for each frame.

The processor 300 may detect a straight line corresponding to the current collector through Hough transform of the captured image. In other words, the processor 300 may obtain a straight line corresponding to the pantograph 310 through Hough transform for each frame of the captured image. In this case, the straight line corresponding to the current collector plate may be detected by estimating the straight line of the upper end of the pantograph 310 obtained through the Hough transform as the current collector plate.

For example, as illustrated in FIGS. 13B and 13C, the processor 300 may include a current collector plate extending from the center point 325 of the current collector plate and the center point 325 of the current collector plate in the detected current collector plate. The horizontal line 330 and the extension line 320 of the current collector plate may be detected.

Subsequently, the processor 300 may measure an angle between the horizontal line 330 intersecting at the center point 325 and the extension line 320. In this case, an angle between the horizontal line 330 and the extension line 320 may be calculated for each frame of the captured image.

Referring to FIG. 14, the processor 300 may calculate the vibration frequency of the pantograph based on the angle calculated for each frame. Here, the vibration frequency may be calculated based on a value obtained by dividing the number of pantograph frames in which the measured angle is zero-crossed by the total pantograph frames (frames per second).

As shown in FIG. 14, the processor 300 measures the angle between the horizontal line 330 measured in each frame of the captured image received through the communication module 100 and the extension line 320 of the collector plate in the order of the image frame number. By arranging as is, it is possible to detect the point where the measured angle crosses zero. In addition, the processor 300 may calculate the zero crossing frame number at which the zero crossing point is detected among the total number of frames (frames per second) and the number of frames per second of the image photographed for one second. The processor 300 may calculate the frequency obtained by dividing the calculated number of zero crossing frames by two and the number of frames per second.

15A and 15B, the processor 300 may calculate the vibration intensity of the pantograph based on the magnitude of the angle.

As shown in FIG. 15A, the processor 300 changes the amount of change in the angle between the horizontal line 330 measured in each frame of the captured image received through the communication module 100 and the extension line 320 of the collector plate. The waveform of the vibration intensity can be detected by arranging the image frame numbers in order.

For example, referring to FIG. 15B, a method of calculating the vibration intensity from the magnitude of the angle may be performed. The processor 300 may detect the pantograph 310 separated from the background for each image frame. In this case, only the pantograph 310 may be detected through a binarization imaging technique which is generally used to separate the background of the image. Subsequently, the bottom line 320a of the current collector plate extending from the bottom surface of the current collector plate is detected based on the center point 325 of the current collector plate, and the current collector plate inclination is detected at the bottom line 320a of the current collector plate. By rotating by the illustrated current collector plate angle), the vibration intensity reference line 330a parallel to the horizontal line 330 of the current collector plate can be detected. In addition, the processor 300 may measure left and right displacements of the bottom line 320a and the vibration intensity reference line 330a of the current collector plate. Here, the current collector plate is a rigid body with almost no bending, and thus, when the left side is raised, the right side is lowered, and thus the size of the vertical displacement of the left and right sides of the current collector plate may be the same.

Thus, as shown in FIG. 15B, the vibration intensity can be calculated by the difference between the left displacement and the right displacement of the current collector plate. At this time, the left and right reference of the current collector plate may be obtained by a template matching technique, but is not limited thereto. In addition, the processor 300 may calculate the difference between the left and right reference of the current collector plate in mm unit by using the ratio information per image pixel mm, and the left displacement in mm unit calculated for each image frame. The difference between and the right displacement can be converted into the vibration intensity in mm.

Meanwhile, a method of calculating the vibration frequency of the pantograph based on the left and right displacements calculated for each frame will be described below.

FIG. 16 is a view for explaining a method of measuring left and right displacements of a horizontal line and a current collector plate according to a second embodiment of the present invention, and FIG. 17 is an average value of left and right displacements according to a second embodiment of the present invention. It is a figure for demonstrating the method of calculating a frequency based on.

Referring to FIG. 16, the processor 300 detects the center point 325 of the current collector plate in the detected pantograph 310 for each image frame, and the horizontal line 330 extending from the center point 325 and the extension line of the current collector plate. Left and right displacements of 320 can be measured.

For example, referring to FIGS. 16 and 17, the processor 300 includes a horizontal line 330 and a collector of a current collector plate extending from the center point 325 of the current collector plate and the center point 325 of the current collector plate in the detected current collector plate. The extension line 320 of the front plate may be detected. In addition, the processor 300 may measure left and right displacements of the horizontal line 330 intersecting at the center point 325 and the extension line 320 of the current collector plate. In this case, the left and right displacements of the horizontal line 330 and the extension line 320 may be calculated for each frame of the captured image.

Referring to FIG. 17, the processor 300 may calculate the vibration frequency of the pantograph 310 based on the displacement calculated for each frame. Here, the vibration frequency may be calculated based on the average value of each of the left and right displacements measured.

As illustrated in FIG. 17, the processor 300 may measure left and right displacements and right and left displacements of the current collector plate for each frame of one second of the captured image received through the communication module 100. In addition, the processor 300 may calculate a frequency by using a Fourier transform on each of the average vertical displacements of the left and right sides thus measured.

For example, when a frequency is calculated using a Fast Fourier Transform (FFT) algorithm that converts an acquired signal into a frequency component and an intensity of a corresponding component, the fast Fourier determines that the sampling rate is determined by the image acquisition frequency. The frequency can be calculated by reflecting the conversion algorithm.

18 is a flowchart illustrating a vibration detection method of a pantograph of an electric railway vehicle according to a second embodiment of the present invention. Hereinafter, a description of a configuration that performs the same function among the components illustrated in FIGS. 11 to 17 will be omitted.

First, a pantograph is detected for each image frame by comparing a pantograph template with an image photographed by a camera (S110).

Subsequently, for each image frame, the center point of the current collector plate is detected on the detected pantograph, and the angle between the horizontal line extending from the center point and the extension line of the current collector plate is measured (S120).

Next, the vibration frequency of the pantograph is calculated based on the angle calculated for each frame (S130).

In the detecting of the pantograph (S110), the pantograph may be detected for each image frame by comparing the pantograph template with the image captured by the camera. For example, since the camera is disposed on the upper portion of the electric railway vehicle and photographs an image of the pantograph provided on the upper portion of the electric railway vehicle, the brightness of the captured image may be different according to an external environment. That is, the pantograph image may be photographed differently according to weather conditions, tunnel conditions, obstacles, and the like. Accordingly, in order to accurately detect the pantograph despite the condition of the image appearing differently from frame to frame, a plurality of pantograph templates having various brightness and contrast ratios may be specified in advance. Therefore, when detecting the pantograph for each frame, a pantograph with high accuracy can be detected by matching the pantograph photographed image with the pantograph template having the highest similarity of brightness and contrast ratio among the plurality of pantograph templates.

In the detecting of the pantograph (S110), a straight line corresponding to the current collector may be detected through Hough transformation of the photographed image.

For example, in the detecting of the pantograph (S110), a straight line corresponding to the pantograph may be obtained from the pantograph detected for each image frame using Hough transform. Subsequently, the straight line corresponding to the collector plate can be detected by estimating the straight line at the upper end of the pantograph as the collector plate.

Measuring the angle (S120) may detect the center point of the straight line of the current collector plate detected through the Hough transform. The horizontal line extending from the detected center point can then be detected. Next, the angle between the horizontal line crossing at the center point and the extension line of the collector plate can be measured.

In the calculating of the vibration frequency (S130), the frequency may be calculated based on a value obtained by dividing the number of pantograph frames in which the measured angle is zero-crossed by the total pantograph frames (frames per second).

In the calculating of the vibration frequency (S130), when the angles between the horizontal line measured in each frame of the image taken for one second and the current collector are arranged in the order of the image frame number, the point at which the measured angle is zero-crossed is detected. Can be. Subsequently, a zero crossing frame number at which a zero crossing point is detected among the total number of frames (frames per second) and the number of frames per second of the image photographed for one second may be calculated. Next, the frequency may be calculated based on a value obtained by dividing the number of zero crossing frames by two by the total number of frames (frames per second) of the captured image for one second.

After calculating the vibration frequency (S130), the vibration intensity of the pantograph may be calculated based on the magnitude of the angle.

The calculating of the vibration intensity may detect the waveform of the vibration intensity by arranging the amount of change in the angle between the horizontal line measured in each frame of the image taken for one second and the current collector in the order of the image frame number. The vibration intensity can be calculated by such a waveform.

In operation S130, the vibration frequency of the pantograph may also be calculated by the left displacement and the right displacement calculated for each frame.

Before calculating the vibration frequency (S130), for each image frame, the center point of the collector plate is detected on the detected pantograph, the horizontal line extending from the center point and the left and right displacements of the extension line of the collector plate are measured, and the vibration frequency In operation S130, the vibration frequency of the pantograph may be calculated based on the displacement calculated for each frame.

For example, before the step of calculating the vibration frequency (S130), the extension line of the current collector plate and the center point of the current collector plate detected through Hough transformation may be detected for each frame of the captured image. The horizontal line extending from the detected center point can then be detected. Next, the left and right displacements of the horizontal line and the collector plate intersecting at the center point can be measured.

In the calculating of the vibration frequency (S130), the frequency may be calculated based on the average value of each of the left and right displacements thus measured.

For example, in the calculating of the vibration frequency (S130), a frequency may be calculated by using a Fourier transform on each of the average vertical displacements of the left and right sides measured for each frame of the captured image.

The apparatus for detecting vibration information of a pantograph-based electric railway vehicle described above may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery media.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

Claims

In the vibration information detection method of an electric railway vehicle,

Determining a pantograph template;

Detecting a pantograph by comparing the pantograph template with an input image acquired by the camera; And

And detecting vibration information of the pantograph based on a change in the position of the pantograph according to the comparison of each frame of the input image and the pantograph template.
The method of claim 1,

Determining the pantograph template

Acquiring a reference image with different brightness conditions and setting the reference image by matching the brightness condition; And

Determining a pantograph template representing a reference image to be contrasted with the input image in the set reference image;

Detecting the pantograph,

Detecting the pantograph and the catenary line from the pantograph template;

Detecting vibration information of the pantograph,

Comprising the step of calculating the dynamic deviation of the tram line and the pantograph.
The method of claim 2,

Setting the reference image,

And collecting the reference image for each class of a different class such as a normal situation, a background interference situation, an arc situation, a tunnel situation, and the like.
The method of claim 3,

When the update of the class is necessary due to the difference of the input image

And comparing the pantograph region of the input image with the average brightness of the class and resetting a pantograph template which is a reference for detecting the pantograph in the input image.
The method according to any one of claims 2 to 4,

Determining the pantograph template,

Calculating a feature vector of the input image by digitizing brightness, variance, and correlation features of each region of the input image; And

Comparing a feature vector of the input image with a feature vector of the pantograph template to find a feature vector of the pantograph template that is the same as or most similar to the feature vector of the input image to determine a target class and a target pantograph template; Vibration information detection method of an electric railway vehicle.
The method according to any one of claims 2 to 4,

The detecting of the pantograph and the catenary line may include:

Simultaneously performing binarization and Hough transform of the image digitizing the input image; And

And setting the brightness, height, width, area, and angle of the tramline, and comparing the binarized value with the pantograph template.
The method of claim 6,

Detecting the pantograph and the tramline, in order to detect the pantograph,

And a template matching technique for extracting brightness values of the input image and comparing them with the pantograph template.
The method according to any one of claims 2 to 4,

The step of calculating the dynamic deviation,

Detecting a contact surface corresponding to a horizontal plane in which the tank line is in contact with the pantograph;

Detecting a center point of the pantograph from the contact surface; And

Obtaining an intersection point of the tank line and the contact surface;

The vibration information detection method of the electric railway vehicle which calculates the dynamic deviation of the said intersection from the said center point.
The method of claim 8,

Detecting the contact surface,

Obtaining a straight line corresponding to the contact surface between the pantograph and the catenary using a Hough transform from the input image; And

And estimating a point of contact with the tramline by raising the straight line as a contact surface.
The method according to claim 8 or 9,

Detecting the contact surface,

Obtaining a straight line by detecting a plurality of markers attached to a top of the pantograph in a straight line; And

And estimating a point where the straight line rises to contact the tram line as a contact surface.
The method of claim 10,

Detecting the center point,

Extracting a position of a marker attached in the middle of the plurality of markers arranged in a straight line on the top of the pantograph; And

And estimating a point at which the marker attached to the middle is located as the center point.
The method of claim 1,

Detecting the pantograph,

Comparing the pantograph template and the input image, detecting the pantograph for each image frame,

Detecting vibration information of the pantograph,

Detecting a center point of a current collector plate on the detected pantograph for each image frame, and measuring an angle between a horizontal line extending from the center point and an extension line of the current collector plate; And

And calculating the vibration frequency of the pantograph based on the angle calculated for each frame.
The method of claim 12,

The detecting of the vibration information of the pantograph may further include calculating a vibration intensity of the pantograph based on the magnitude of the angle.
The method of claim 12,

Detecting the pantograph,

And detecting a straight line corresponding to the current collector plate through a Hough transform of the obtained image.
The method of claim 12,

The step of calculating the vibration frequency,

And calculating the frequency based on a value obtained by dividing the number of pantograph frames by which the measured angle is zero-crossed by the number of pantograph frames.
The method of claim 12,

Prior to calculating the vibration frequency,

Detecting a center point of a current collector plate in the detected pantograph for each image frame, and measuring left and right displacements of a horizontal line extending from the center point and an extension line of the current collector plate;

Calculating the vibration frequency,

And calculating the vibration frequency of the pantograph based on the displacement calculated for each frame.
The method of claim 16,

The step of calculating the vibration frequency,

And calculating the frequency based on the average value of the measured left and right displacements.
In the vibration information detecting apparatus of an electric railway vehicle,

Communication module for receiving a pantograph image,

Memory for storing the vibration information detection program of the pantograph

Including a processor for executing the vibration information detection program of the pantograph,

The processor determines a pantograph template according to the execution of the program, compares the pantograph template with the input image acquired by the camera, detects the pantograph, and compares each frame of the input image with the pantograph template. And vibration information of the pantograph is detected based on the detected change in the position of the pantograph.