WO2010131696A1 - パンタグラフ変位測定装置及びトロリ線硬点検出方法 - Google Patents
パンタグラフ変位測定装置及びトロリ線硬点検出方法 Download PDFInfo
- Publication number
- WO2010131696A1 WO2010131696A1 PCT/JP2010/058083 JP2010058083W WO2010131696A1 WO 2010131696 A1 WO2010131696 A1 WO 2010131696A1 JP 2010058083 W JP2010058083 W JP 2010058083W WO 2010131696 A1 WO2010131696 A1 WO 2010131696A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pantograph
- template
- input image
- marker
- pattern matching
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L5/00—Current collectors for power supply lines of electrically-propelled vehicles
- B60L5/18—Current collectors for power supply lines of electrically-propelled vehicles using bow-type collectors in contact with trolley wire
- B60L5/22—Supporting means for the contact bow
- B60L5/26—Half pantographs, e.g. using counter rocking beams
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60M—POWER SUPPLY LINES, AND DEVICES ALONG RAILS, FOR ELECTRICALLY- PROPELLED VEHICLES
- B60M1/00—Power supply lines for contact with collector on vehicle
- B60M1/12—Trolley lines; Accessories therefor
- B60M1/28—Manufacturing or repairing trolley lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2200/00—Type of vehicles
- B60L2200/26—Rail vehicles
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
Definitions
- the present invention relates to a pantograph displacement measuring device and a trolley wire hard spot detection method, and in particular, measures a trolley wire hard spot by pattern matching using an image obtained by photographing a pantograph with a marker for hard spot measurement with a line sensor camera.
- the present invention relates to a pantograph displacement measuring device and a trolley wire hard spot detection method.
- one of the inspection items is the measurement of hard points on trolley wires.
- the trolley wire is in a state of being hung from a hanging wire with a hanger.
- the trolley wire weight is partially increased compared to other parts where this hanger is installed, as well as other parts where the trolley wire is connected or where there is a curved line. Called.
- the pantograph which is a current collector installed on the roof of the vehicle and slides on the trolley line, passes through the hard point of the trolley line, the pantograph may drop rapidly due to the weight of the trolley line.
- the trolley wire is separated from the pantograph, and a discharge phenomenon called an arc occurs.
- the trolley wire is locally worn by heat generated by the arc. Therefore, at the hard point of the trolley wire, it is conceivable that the progress of wear is accelerated as compared with other portions.
- the vertical acceleration of the pantograph whose displacement is equivalent to that of the trolley line may be monitored.
- the acceleration of the pantograph can be obtained by measuring the displacement of the pantograph and performing a second order differentiation thereof.
- A) Laser sensor system This system is a system in which a pantograph is scanned with a laser using a mirror or the like, and the displacement of the pantograph is measured by the phase difference of reflected waves or the deformation of the shape of the reflected laser.
- B) Optical cutting sensor system This system is a system in which striped light is projected onto the pantograph, the striped irregularities are received according to the shape of the pantograph, and the displacement of the pantograph is measured.
- (C) Image processing method In this method, a pantograph is photographed with a line sensor camera installed on the roof of the vehicle, and processing such as model matching and pattern matching is performed on the photographed image on a processing computer, and the displacement of the pantograph is performed.
- processing such as model matching and pattern matching is performed on the photographed image on a processing computer, and the displacement of the pantograph is performed.
- the image processing method extracts the pixel position on the image that matches the pantograph model prepared in advance from the pantograph image taken by the line sensor camera, and then the pantograph from the line sensor camera.
- the actual height of the pantograph is calculated from the pixel position on the image based on the distance to the lens and the focal length of the lens of the photographing instrument.
- This image processing method detects a pixel position that matches a previously acquired pantograph model from a photographed pantograph image, or attaches a black and white striped marker to a pantograph installed on the roof of the vehicle,
- the marker position that is, the position of the pantograph is detected from the image captured by the line sensor camera by pattern matching.
- the pixel position on the image is converted into an actual pantograph displacement from the relationship such as the distance to the pantograph and the focal length of the lens.
- the acceleration is calculated by second-order differentiation of the displacement of the pantograph thus obtained.
- the use of a line sensor camera can increase the spatial resolution and improve the accuracy. This method has an advantage that it can be mounted not only on a test vehicle manufactured exclusively for measurement but also on a commercial vehicle because the device is smaller than the laser sensor method and the light cutting method.
- the line sensor camera 2 looks up obliquely upward on the roof of the vehicle 1 in order to photograph the marker 4 attached to the pantograph 1 a. Installed.
- the line sensor camera indicated by the solid line and the line sensor camera 2 indicated by the broken line in FIG. 13 are referred to as line sensor cameras 2A and 2B, respectively.
- FIGS. 14 (a) and 14 (b) Examples of input images of the marker 4 taken by the line sensor camera 2A and the line sensor camera 2B are shown in FIGS. 14 (a) and 14 (b), respectively.
- the line sensor camera 2A since the camera elevation angle ⁇ A is small, the marker trajectory M has almost the same width in the input image 6A, and the resolution depends on the height of the pantograph 1a. There is almost no difference.
- the line sensor camera 2B is used as shown in FIG. 14B, since the camera elevation angle ⁇ B is large, the marker trajectory M differs depending on the height, and the height of the pantograph 1a in the input image 6B. Difference in resolution due to
- the pattern matching process is likely to succeed when the pattern matching process is performed on the image 6A captured by the line sensor camera 2A as shown in FIG.
- pattern matching processing is performed on the image 6B photographed by the sensor camera 2B, there is a problem that the pattern matching may fail because the size of the template 7 does not match.
- the present invention is characterized by providing a pantograph displacement measuring apparatus and a trolley wire hard point detecting method capable of improving the accuracy of pattern matching processing.
- a pantograph displacement measuring apparatus for solving the above-described problems is obtained by performing image processing on an input image photographed by the photographing means, which is installed on a roof of a train, and photographs the pantograph.
- a pantograph displacement measuring apparatus including an image processing unit that acquires a displacement of a pantograph, the image processing unit creates an input image using an image signal input from the photographing unit, and a template.
- the image division processing means for dividing the input image into a predetermined number of sections based on the resolution of each pixel obtained by the calibration means, and the resolution for each section on the input image
- a template enlargement / reduction processing means for enlarging or reducing the template, and the template.
- Pattern matching processing means for detecting a pixel position of the marker in the input image from the input image and the input image, a pantograph displacement calculating means for calculating an actual displacement of the pantograph based on the pixel position of the marker, and the pantograph Filtering processing means for smoothing the displacement data, and acceleration output means for outputting acceleration of the pantograph calculated based on the displacement data of the pantograph smoothed by the smoothing processing means It is characterized by that.
- calibration means here means means for obtaining the resolution of each pixel using the calibration method according to Japanese Patent Application No. 2009-011648, for example.
- a pantograph displacement measuring device is the pantograph displacement measuring device according to the first invention, wherein the pattern matching processing means performs the input based on the result of the pattern matching processing performed on the immediately preceding line.
- the pattern matching process is performed only for a predetermined range of the image.
- a pantograph displacement measuring device is the pantograph displacement measuring device according to the first invention, wherein the pattern matching processing means moves the template according to a correlation value with the template detected from the input image. It is characterized by setting an amount.
- the pantograph displacement measuring device is the pantograph displacement measuring device according to any one of the first to third aspects, wherein the pattern matching processing means straddles two adjacent sections where the locus of the marker is adjacent. In this case, the position of the section is automatically corrected so that the locus of the marker is included in one section with reference to the position of the marker detected in the immediately preceding line.
- a pantograph displacement measuring device is the pantograph displacement measuring device according to any one of the first to fourth inventions, wherein the pattern matching processing means roughly detects the center position of the locus of the marker, An average luminance value in a range half the width of the template is calculated from the center position, and the locus of the marker is extracted using the value as a threshold value.
- rough here refers to the extent to which the marker center position is detected within a range in which no error occurs in the matching result in the pattern matching process.
- a trolley-line hard point detection method for obtaining a displacement of a pantograph by performing image processing on an input image photographed by the photographing means installed on a train roof and photographing the pantograph.
- a trolley wire hard spot detection method for detecting a hard point of a trolley line using a pantograph displacement measuring device provided with an image processing means, a first step of setting a template in advance, and an image signal input from the photographing means
- a second step of creating an input image using a third step a third step of dividing the input image into a predetermined number of sections based on the resolution of each pixel obtained by the calibration means, and a step on the input image
- calibration means here means means for obtaining the resolution of each pixel using the calibration method according to Japanese Patent Application No. 2009-011648, for example.
- a trolley wire hard spot detection method is the trolley wire hard spot detection method according to the sixth invention, wherein the fifth step is based on a result of a pattern matching process performed on the immediately preceding line. Then, it is performed only for a predetermined range of the input image.
- a trolley wire hard spot detection method is the trolley wire hard spot detection method according to the sixth invention, wherein the fifth step is a correlation for each pixel position with the template detected from the input image.
- the movement amount of the template is set based on the value.
- a trolley wire hard spot detection method is the trolley wire hard spot detection method according to any one of the sixth to eighth trolley wire hard spot detection methods, wherein the fifth step is performed on two sections where the locus of the marker is adjacent.
- the position of the section is automatically corrected so that the locus of the marker is included in one section. To do.
- a trolley wire hard spot detection method is the trolley wire hard spot detection method according to any one of the sixth to ninth trolley wire hard spot detection methods, wherein the fifth step roughly detects the center position of the locus of the marker.
- An average luminance value in a range half the width of the template is calculated from the center position, and the value is used as a threshold value.
- rough here refers to the extent to which the marker center position is detected within a range in which no error occurs in the matching result in the pattern matching process.
- the image processing means includes an input image creating means for creating an input image using an image signal inputted from the photographing means, a template setting means for setting a template, Image division processing means for dividing the input image into a predetermined number of sections based on the resolution of each pixel obtained by the calibration means, and template enlargement for enlarging or reducing the template based on the resolution for each section on the input image ⁇ Detection of pixel position of marker from reduction processing means, template and input image Pattern matching processing means, pantograph displacement calculating means for calculating actual displacement of the pantograph based on the pixel position of the marker, filtering processing means for performing smoothing processing on the displacement data of the pantograph, and smoothing
- the pattern matching processing means performs patterning only on a predetermined range of the input image based on the result of the pattern matching processing performed on the immediately preceding line. Since the matching process is performed, the processing time can be shortened and the probability of detecting noise or the like can be reduced.
- the pattern matching processing means sets the movement amount of the template according to the correlation value with the template detected from the input image, the correlation value is low. If the correlation value is high compared to the above, the pattern matching process can be performed efficiently by setting the template movement amount small.
- the pattern matching processing means detects the marker detected in the immediately preceding line when the marker trajectory in the input image straddles two adjacent sections. Since the position of the section is automatically corrected so that the marker trajectory is included in one section on the basis of the position, the template switching process is performed within the processing range due to the presence of the separation position within the pattern matching processing range. Can be prevented, and the pattern matching process can be performed efficiently.
- the pattern matching processing means roughly detects the center position of the marker trajectory, and calculates an average luminance value in a range half the width of the template from the center position. Since the marker trajectory is extracted using this value as a threshold value, it is possible to prevent the pattern matching result from being shifted by several pixels due to the template size being changed at the image separation position, and to eliminate the error at the separation position. In addition, the edge extraction can be stably performed with respect to a change in luminance of the entire image.
- the photographing means installed on the roof of the train to photograph the pantograph, and the displacement of the pantograph by performing image processing on the input image photographed by the photographing means
- a trolley line hard spot detection method for detecting a hard point of a trolley line using a pantograph displacement measuring device provided with an image processing means for acquiring image data, a first step of setting a template in advance and input from an imaging means A second step of creating an input image using the image signal, a third step of dividing the input image into a predetermined number of sections based on the resolution of each pixel obtained by the calibration means, and a step on the input image
- the fourth step of enlarging or reducing the template based on the resolution for each section, and the pattern matching processing from the template and the input image A fifth step of detecting a pixel position, a sixth step of calculating an actual displacement of the pantograph based on the pixel position of the marker, and a seventh step of performing a
- the fifth step is performed on the predetermined range of the input image based on the result of the pattern matching process performed on the immediately preceding line. Therefore, the processing time can be shortened and the probability of detecting noise or the like can be reduced.
- the fifth step is performed by setting the amount of movement of the template based on the correlation value for each pixel position with the template detected from the input image. Therefore, the pattern matching process can be efficiently performed by setting the template movement amount large when the correlation value is low and setting the template movement amount small when the correlation value is high.
- the fifth step is detected in the immediately preceding line when the locus of the marker in the input image straddles two adjacent sections. Since the position of the section is automatically corrected so that the marker trajectory is included in one section on the basis of the marker position, there is a delimiter position within the pattern matching processing range. Template switching processing can be prevented from occurring, and pattern matching processing can be performed efficiently.
- the fifth step is to roughly detect the center position of the marker trajectory, and to obtain an average luminance value in a range that is half the width of the template from the center position. Since this value is used as a threshold value, it is possible to prevent the pattern matching result from being shifted by several pixels due to the template size being changed at the image break position, and to eliminate the error at the break position. At the same time, edge extraction can be stably performed with respect to a change in luminance of the entire image.
- FIG. 14A is an explanatory diagram illustrating an example of an input image when the elevation angle of the line sensor camera is small
- FIG. 14B is an explanatory diagram illustrating an example of an input image when the elevation angle of the line sensor camera is large.
- FIG. 1 is an explanatory view showing an installation example of a pantograph displacement measuring apparatus according to this embodiment
- FIG. 2 is a front view of a marker used in this embodiment
- FIG. 3 shows a schematic configuration of the pantograph displacement measuring apparatus according to this embodiment.
- FIG. 4 is an explanatory diagram showing an example of an input image
- FIG. 5 is an explanatory diagram showing an example of a template
- FIG. 6 is an explanatory diagram showing an example of dividing an input image
- FIG. 7 is a pantograph measurement according to this embodiment. It is a flowchart which shows the flow of a process.
- the pantograph height measuring device is installed inside the vehicle 1 with a line sensor camera 2, a lighting device 3, a marker 4 as photographing means fixed on the roof of the vehicle 1. And a processing computer 5 to be processed.
- the line sensor camera 2 is installed on the roof of the vehicle 1 so as to photograph the pantograph 1a. That is, the direction of the line sensor camera 2 is set so that the optical axis thereof is obliquely upward and the scanning line direction is orthogonal to the longitudinal direction of the pantograph 1a.
- the image signal acquired by the line sensor camera 2 is input to the processing computer 5.
- the lighting device 3 has its direction and irradiation angle set so as to irradiate light to a portion photographed by the line sensor camera 2.
- the marker 4 is formed of a material that reflects light and a material that does not reflect light, and is installed at an arbitrary position on the end surface of the pantograph 1 a on the line sensor camera 2 side within a range that can be photographed by the line sensor camera 2.
- the marker 4 used in the present embodiment is configured by alternately arranging white portions 4w made of a material that reflects two lights and black portions 4b made of a material that does not reflect three lights. Has been.
- the size of the marker 4 is arbitrarily determined.
- the processing computer 5 analyzes an image input from the line sensor camera 2 to detect a vertical displacement of the pantograph 1a, and includes an arithmetic processing unit 5A and a monitor 5B as arithmetic processing means. Yes.
- the arithmetic processing unit 5A includes an input image creation unit 5a, a template setting unit 5b, an image division processing unit 5c, a template enlargement / reduction processing unit 5d, a pattern matching processing unit 5e, a pantograph displacement calculation unit 5f, and filtering.
- a processing unit 5g, an acceleration output unit 5h, and memories m1 and m2 are provided.
- the input image creation unit 5a as an input image creation means creates an input image 6 as shown in FIG. 4 in which image signals input from the line sensor camera 2 are arranged in time series. As shown in FIG. 4, since the marker 4 reflects the light of the illumination device 3, the locus of the white portion of the marker 4 in the input image 6 is in a black region (portion shown with a dot in the figure) 6b. It is displayed as a strip-shaped white area 6a. The input image 6 is sent to the template setting unit 5b or the image division processing unit 5c as necessary through the memories m1 and m2.
- the template setting unit 5b as the template setting means acquires in advance a marker pattern as shown in FIG. 5 as a matching template (hereinafter referred to as a reference template) 7A from the input image 6 as shown in FIG. Specifically, a marker pattern used for extracting the marker 4 in the input image 6 during the processing in the pattern matching processing unit 5e is acquired in advance as the reference template 7A, and is registered in the memory m2.
- the reference template 7A is sent to the template enlargement / reduction processing unit 5d via the memory m2.
- the reference template 7A is one-dimensional luminance value data including a white region 7a and a black region 7b obtained by extracting a marker portion from an image acquired in advance for creating the reference template 7A.
- the black portions 4b on both sides of the white portion 4w are partially shown as shown in FIG. It is desirable to divide the image to include it. By doing in this way, the feature-value of the reference
- the template setting unit 5b registers the offset width W OS and the template size W T (see FIG. 4) at the same time as the reference template 7A.
- the image division processing unit 5c as the image division processing means provides a delimiter position 8 as shown in FIG. 6 for the input image 6 inputted from the input image creation unit 5a, and the input image 6 is divided into a predetermined number of sections A 1. , a 2, ⁇ ⁇ ⁇ , divided into a N (hereinafter, the arbitrary section of the section a i). Information on all the sections A i is sent to the template enlargement / reduction processing unit 5d via the memory m2. At this time, the number of sections N is automatically calculated based on the resolution of each pixel obtained in advance by the calibration method in Japanese Patent Application No. 2009-011648, and the section with the lowest resolution is Assume that the setting is made so as not to exceed 1.1 times the resolution of the section where the resolution is highest. By doing so, the resolution can be accurately calculated.
- the most resolution was set to not less than 1.1 times the resolution of the section comprising the section is the highest resolution lower reason, verification experiments on template size W T Based on the results. That is, the size W T of the reference template 7A acquired from the image obtained by photographing the markers 4 is varied, the matching to those which were much enlarged or reduced when performing pattern matching with respect to the acquired image the reference template 7A success It is based on the result of examining what to do.
- Template scaling processing section 5d as a template scaling processing means, based on the information of the section A i input from the reference template 7A and the image dividing unit 5c input from the template setting unit 5b, respectively It performs a process of changing the size W T to expand or shrink the reference template 7A for each section a i. Segment A i is resized W T for each template (hereinafter, referred to as scaled template) data 7B i are sent through the memory m2 to pattern matching unit 5e.
- an enlargement / reduction ratio (hereinafter referred to as an enlargement / reduction ratio) with respect to the reference template 7A is calculated, and a reference is made using bilinear interpolation, which is a general technique for enlarging / reducing an image.
- the template 7A is enlarged or reduced to create an enlarged / reduced template 7B i corresponding to each section A i .
- the size W Ti of the enlargement / reduction template 7B i can be obtained by multiplying the size W T of the reference template 7A by the enlargement / reduction rate because the size W T is also registered when the reference template 7A is registered.
- the expansion / contraction rate is obtained from the following formulas (1) to (3).
- the approximate expression (4) for converting the pixel position of the image into the actual height is, for example, the one obtained by the calibration method of Japanese Patent Application No. 2009-011648.
- p n [a (n + 1) 2 + b (n + 1) + c] ⁇ (an 2 + bn + c) (1)
- p ori [a (ori + 1) 2 + b (ori + 1) + c] ⁇ [a (ori) 2 + b (ori) + c] (2)
- scale p ori / p n ⁇ (3)
- y ax 2 + bx + c (4)
- p n is the resolution [mm at the pixel position n to be enlarged / reduced] / pix]
- p ori is the resolution [mm / pix] at the pixel position ori of the reference template 7A
- scale is the scaling ratio.
- the resolution can be obtained as the height [mm] per pixel. That is, the height [mm] of the pixel position n and the height [mm] of the next pixel position n + 1 are obtained, and then the height at the pixel position n + 1 is subtracted from the height at the pixel position n + 1. By doing so, the resolution [mm / pix] can be obtained.
- the enlargement / reduction ratio is set to 1 when the size W Ti of the enlargement / reduction template 7B i is the same as the size W T of the reference template 7A.
- the pattern matching processing unit 5e as a pattern matching processing unit is based on the information on the section A i input from the image division processing unit 5c and the data of the expansion / contraction template 7B i input from the template expansion / reduction processing unit 5d. Pattern matching processing is performed for each section A i to detect the pixel position of the marker 4 on the input image 6. The pixel position of the marker 4 obtained by the pattern matching processing unit 5e is sent to the pantograph displacement calculation unit 5f via the memory m2.
- the pantograph displacement calculation unit 5f as the pantograph displacement calculation means calculates the displacement of the marker 4 on the input image 6 based on the pixel position of the marker 4 on the input image 6 input from the pattern matching processing unit 5e. Convert to displacement.
- a calculation formula for converting the displacement of the trajectory of the pantograph 1a on the input image 6 into the actual displacement of the pantograph 1a for example, an approximate expression obtained by Japanese Patent Application No. 2009-011648 is obtained in advance and used. Shall.
- the actual displacement data of the pantograph 1a obtained by the pantograph displacement calculator 5f is sent to the filtering processor 5g via the memory m2.
- the filtering processing unit 5g as a filtering processing unit performs a smoothing process on the displacement data input from the pantograph displacement calculation unit 5f.
- the actual displacement of the pantograph 1a is in a state where an image quantization error is put. Therefore, a filtering process is performed on the actual displacement data to smooth the displacement data. Thereby, the quantization error included in the displacement data is reduced.
- Smoothed displacement data (hereinafter referred to as smoothed displacement data) is sent to the acceleration output unit 5h via the memory m2.
- the acceleration output unit 5h serving as an acceleration output unit performs second-order differentiation on the smoothed displacement data input from the filtering processing unit 5g, and calculates the acceleration in the vertical direction of the marker 4, that is, the pantograph 1a. Specifically, the acceleration is obtained by second-order differentiation of the displacement data smoothed by the filtering process, and this is output to the monitor 5B.
- the monitor 5B For example, a position where the acceleration of the pantograph 1a is 20G or more is detected as a hard point.
- the calculated acceleration data is output / displayed on the monitor 5B via the memory m2.
- the processing computer 5 first performs a process of registering the reference template 7A (step P1) in the template setting unit 5b, and subsequently output from the line sensor camera 2 in the input image creation unit 5a.
- the image division processing unit 5c converts the input image 6 into a desired number N of sections A 1 as shown in FIG. , A 2 ,..., A N (step P3).
- the template enlargement / reduction processing unit 5d performs a process (step P4) for enlarging or reducing the reference template 7A registered in step P1 in accordance with each section A i , and then the pattern matching processing unit 5e.
- enlarged or pattern matching processing for detecting a position (pixel position) of the reduced scaled template 7B i and the input image 6 and by comparing the input image 6 on the marker 4 was in each section a i of the input image 6 (step P5 ) Is performed, it is determined whether or not the pattern matching processing for one section A i has been completed (step P6). As a result of the determination, if the section A i has not ended (NO), the process proceeds to Step P7. On the other hand, when the section A i is completed (YES), the process returns to Step P4.
- Step P7 it is determined whether or not the pattern matching process has been completed for all input image data. As a result of the determination, if the pattern matching process is completed for all input image data (YES), the process proceeds to step S8. On the other hand, if the pattern matching process has not been completed for all input image data (NO), the process returns to step P5.
- step P8 the process of converting the pixel position of the marker 4 on the input image 6 into the actual displacement of the pantograph 1a is performed on all the input images 6 based on the marker position detected by the pantograph displacement calculator 5f.
- filtering processing (step P9) is performed in the filtering processing unit 5g, and finally processing for outputting the pantograph acceleration (step P10) is performed in the acceleration output unit 5h.
- a second embodiment of the pantograph displacement measuring apparatus (Efficient processing time by reducing the pattern matching processing range)
- This embodiment is different from the first embodiment in the processing in the pattern matching processing unit 5e.
- Other configurations are generally the same as those described in the first embodiment, and hereinafter, processing units having the same functions are denoted by the same reference numerals, and redundant descriptions are omitted, and different points will be mainly described.
- Step P5 the following processing is performed as the processing of Step P5 shown in FIG.
- pattern matching processing similar to that in the first embodiment is performed on the first line of the input image 6, and the detected marker position is stored in the memory m2.
- the pattern is processed only for the range of ⁇ N P [pix] based on the pixel position of the marker obtained as a result of performing the pattern matching process on the immediately preceding line. Perform the matching process.
- the pattern matching process is performed only for a predetermined range based on the pixel position on the next line.
- the range ⁇ N P [pix] for performing the pattern matching process may be determined in consideration of the amount of movement of the marker per unit time (up-and-down displacement width of the pantograph) in photographing by the line sensor camera 2.
- the trolley wire gradient must be 5/1000, otherwise 15/1000 or less. It is stipulated in Article 62 of the Ordinary railway Structure Rules. A gradient of 5/1000 means that the height changes 5m at a distance of 1000m.
- the sampling frequency of the line sensor camera 2 is set to 1000 Hz (images taken at 1000 lines (1 ms interval) per second), for example, when the vehicle 1 travels at a speed of 50 km / h, The distance traveled is about 13.888m, and in 1ms it is about 0.013888m.
- the gradient due to the vertical displacement of the pantograph 1a is 15/1000
- the variation in the height of the pantograph per unit time (1 ms) is about 0.00021 mm.
- the acceleration serving as a reference for detecting the hard point is set to 20G. This is the acceleration when changing 0.1 mm per unit time (1 ms). Considering the above-mentioned “Regular Railway Structure Rule Article 62”, it is sufficient to allow for a change of 10 mm per unit time. Therefore, the pixel position of the marker 4 detected in the immediately preceding line is used as a reference according to the image resolution. Then, the pixel width N P [pix] when changing by 10 mm in 1 ms is calculated, and the range may be set as the range for pattern matching.
- this embodiment shows an example of expected changes in the 10mm per unit time as a condition for calculating the pixel width N P [pix], it is not limited to this as a condition for calculating the pixel width N P [pix], You may set arbitrarily as needed.
- the amount of movement of the marker 4 is small because the vertical displacement width of the pantograph 1a per unit time of photographing is small.
- the pattern matching process may be performed within the range ⁇ N P [pix] with reference to the position. Assuming that the width of the input image 6 photographed by the line sensor camera 2 is “WIDTH”, the time t required for the pattern matching process in the present embodiment is expressed by the following equation (5) using the time t 0 required for the pattern matching process in the first embodiment. ).
- the pattern matching process is performed only for the range of ⁇ N P [pix] with reference to the pixel position of the marker 4 of the immediately preceding line detected by pattern matching.
- the processing time can be shortened compared to the first embodiment.
- the possibility of detecting noise or the like can be reduced by narrowing the range for performing the pattern matching process.
- FIG. 8 is an explanatory diagram showing the level of the correlation value with the template in the input image.
- the present embodiment is different from the first embodiment in the processing in the pattern matching processing unit 5e.
- Other configurations are substantially the same as those described in the first embodiment.
- processing units having the same functions as those shown in FIGS. Omitted and the description will focus on the differences.
- a correlation value R that is an index as to whether or not it is similar to the registered reference template 7A is calculated, and the enlargement / reduction template 7B i is calculated.
- the pattern matching process is performed while changing the amount of movement in accordance with the correlation value R.
- step S5 shown in FIG. 7 the following processing is performed before performing the processing in step P5 described in the first embodiment.
- a correlation value R with the reference template 7A is calculated for each pixel position i of the input image 6.
- the correlation value R can be obtained by calculating the following equation (6). Since the line sensor camera 2 is a camera that takes a one-dimensional image, the calculation is for one dimension.
- R represents the correlation value
- L is the width of the template image (smaller than the width of the search image)
- W i is the brightness value at the pixel position i of the search image
- T i is the luminance value at the pixel position i of the template image is there.
- the correlation value is 1 at the maximum and 0 at the minimum.
- the correlation value R is considered to be about 0.8 when it is low and 0.99 when it is high. Therefore, each time the correlation value R increases by 0.05 according to the correlation value R, the movement amount increases by 1 [pix].
- the correlation value R is 0.95 or more
- the movement amount of the expansion / contraction template 7B i is 1 [pix]
- the correlation value etc. R is a movement amount of the expansion template 7B i for 0.9 ⁇ 0.85 2 [pix], may be set to the amount of movement of the scaled template 7B i during the pattern matching process based on the correlation value R.
- step P5 described in the first embodiment is performed.
- a threshold value (0.05 in this embodiment) for changing the movement amount of the correlation value R is manually set.
- the movement amount of the expansion / contraction template 7B i is not limited to the above, and may be arbitrarily set as necessary.
- the movement amount is changed in accordance with the level of the correlation value R, as compared with the first embodiment in which the pattern matching process is performed every 1 [pix]. By doing so, the pattern matching process can be performed efficiently.
- FIG. 9 is an explanatory diagram illustrating an example in the case where a delimiter position exists in the pattern matching processing range
- FIG. 10 is an explanatory diagram illustrating an example in which the delimiter position illustrated in FIG. 9 is reset.
- the present embodiment is different from the first and second embodiments in the pattern matching processing method in step P5 shown in FIG.
- Other configurations are substantially the same as those shown in the first and second embodiments.
- the processing units having the same functions as those described in the first and second embodiments are denoted by the same reference numerals. Therefore, the description which overlaps is abbreviate
- the processing efficiency is improved by limiting the range in which the pattern matching process is performed based on the pixel position of the marker 4 detected by the pattern matching process for the immediately preceding line.
- the pattern matching processing range of the input image 6 ( ⁇ N P [pix] with reference to the pixel position of the marker 4 obtained by the pattern matching processing for the previous line)
- the delimiter position 8 exists in the range (B)
- the enlargement / reduction ratio of the enlargement / reduction template 7B i must be switched for each section (section A i , A i + 1 in this embodiment).
- the break position 8 when the pattern matching process is performed, if the break position 8 is included in the pattern matching processing range B as shown in FIG. 9, the break position 8 is not included in the process range B. In this way, the delimiter position 8 is automatically reset, and the size of the enlargement / reduction template 7B i is reset so as to correspond to the newly set section A i .
- Step P5 the following processing is performed as the processing of Step P5 shown in FIG.
- pattern matching processing similar to that in the first embodiment is performed on the first line of the input image 6, and the detected pixel position of the marker 4 is stored in the memory m2.
- the pattern matching processing range B is set to ⁇ N P [pix] with reference to the pixel position of the marker 4 detected by the pattern matching processing for the previous line.
- the pixel position P [pix] of the marker 4 obtained from the immediately preceding line is checked for the presence or absence of a delimiter position 8 included in the processing range B of P ⁇ N P [pix]. If not, pattern matching is performed using the same expansion / contraction template 7B i as the previous line.
- the reference template 7A is set manually, and the subsequent enlargement / reduction template 7B i is automatically set based on the resolution of each image position.
- the pixel position of the marker 4 obtained from the immediately preceding line is used as a reference. Since the position of the enlargement / reduction template 7B i and the separation position 8 is automatically set so that the separation position 8 is not included in the pattern position, the pattern matching processing is made more efficient in addition to the effect of the second embodiment. It can be carried out.
- FIG. 11 is an explanatory diagram showing an example of the template size set for each section
- FIG. 12 is an explanatory diagram showing an example of extracting the edge of the white region 6a that is the locus of the white portion 4w of the marker 4 on the input image. .
- the pattern matching process is performed on two marker segments A i and A i + 1 using two expansion / contraction templates 7B i and 7B i + 1 .
- the pattern matching result may be shifted by several pixels at the break position 8. In calculating the acceleration, a shift of several pixels leads to a large error.
- the edge of the marker trajectory M can be extracted using an arbitrary threshold value.
- the threshold value is a constant, the input image 6 becomes dark or bright as a whole. Edges cannot be extracted accurately. Therefore, it is preferable to calculate an average value of luminance within the processing range and use this as a threshold value. In this way, edge extraction can be performed stably even when the luminance value of the image changes as a whole.
- Step P5 the following processing is performed as the processing of Step P5 shown in FIG.
- the marker center position P C is roughly detected by pattern matching processing using the expansion / contraction template 7B i .
- an average luminance value B A is calculated in a range of half of the current template size W T from the marker center position P C.
- the maximum pixel position (edge of the highest position) P E of the area having a higher luminance value than the average luminance value B A is obtained, and that position is extracted as the pixel position of the marker locus M.
- the “rough” in the present embodiment is a range in which the marker center position is detected to the extent that no error occurs in the matching result in the pattern matching process.
- Margin of error of template size W T will ⁇ 10% experimentally.
- the marker position is roughly detected by pattern matching, and the edge of the marker 4 is extracted with reference to the pixel position of the detected marker 4. in delimiting position set in the input image 6, without template size is changed, eliminating the pattern matching result shift due to a change in template size W T in the break position of the image, it is possible to improve the accuracy. Further, by calculating an average luminance value in the range of half of the current template size W T from the marker center position detected by pattern matching and using the value as a threshold value for edge extraction, the luminance of the entire input image 6 is calculated. Edge extraction can be performed stably against changes.
- the present invention can be applied to a pantograph displacement measuring device and a trolley wire hard spot detection method, and in particular, a trolley wire can be detected by pattern matching using an image obtained by photographing a pantograph with a marker for hard spot measurement with a line sensor camera.
- the present invention is suitable for application to a pantograph displacement measuring device and a trolley wire hard spot detection method for measuring hard spots.
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Transportation (AREA)
- Power Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Current-Collector Devices For Electrically Propelled Vehicles (AREA)
- Image Processing (AREA)
Abstract
Description
(イ)レーザセンサ方式
この方式は、パンタグラフをミラー等によりレーザで走査し、反射波の位相差や反射したレーザの形状の変形などにより、パンタグラフの変位を測定する方式である。
(ロ)光切断センサ方式
この方式は、パンタグラフに縞状の光を投光し、パンタグラフの形状に応じて凹凸になった縞を受光し、パンタグラフの変位を測定する方式である。
(ハ)画像処理方式
この方式は、車両の屋根上に設置したラインセンサカメラでパンタグラフを撮影し、撮影した画像に対して処理用コンピュータにおいてモデルマッチングやパタンマッチング等の処理を行い、パンタグラフの変位を測定する方式である(例えば、特許文献1,2参照)。
図1乃至図7を用いて本発明に係るパンタグラフ変位測定装置の第1の実施例について説明する。図1は本実施例に係るパンタグラフ変位測定装置の設置例を示す説明図、図2は本実施例で用いるマーカの正面図、図3は本実施例に係るパンタグラフ変位測定装置の概略構成を示すブロック図、図4は入力画像の例を示す説明図、図5はテンプレートの例を示す説明図、図6は入力画像を分割する例を示す説明図、図7は本実施例に係るパンタグラフ測定処理の流れを示すフローチャートである。
pori=[a(ori+1)2+b(ori+1)+c]-[a(ori)2+b(ori)+c] ・・・(2)
scale=pori/pn ・・・(3)
y=ax2+bx+c ・・・(4)
ここで、「a」,「b」,「c」はピクセル位置から実際の変位を求めるための近似式(4)の係数、「pn」は拡大・縮小したいピクセル位置nでの分解能[mm/pix]、「pori」は基準テンプレート7Aのピクセル位置oriでの分解能[mm/pix]、「scale」は拡縮率である。
本発明に係るパンタグラフ変位測定装置の第2の実施例について説明する。本実施例は、実施例1とはパタンマッチング処理部5eにおける処理が異なるものである。その他の構成は実施例1において説明したものと概ね同様であり、以下、同様の作用を奏する処理部には同一の符合を付して重複する説明は省略し、異なる点を中心に説明する。
まず、入力画像6の1ライン目に対しては実施例1と同様のパタンマッチング処理を行い、検出したマーカ位置をメモリm2に保存する。その後、2ライン目以降のラインに対してはその直前のラインに対してパタンマッチング処理を行った結果得られたマーカのピクセル位置を基準とする±NP[pix]の範囲に対してのみパタンマッチング処理を行う。
図8を用いて本発明に係るパンタグラフ変位測定装置の第3の実施例について説明する。図8は入力画像におけるテンプレートとの相関値の高低を示す説明図である。
図9及び図10を用いて本発明に係るパンタグラフ変位測定装置の第4の実施例について説明する。図9はパタンマッチングの処理範囲に区切り位置が存在する場合の例を示す説明図、図10は図9に示す区切り位置を設定し直した例を示す説明図である。
図11乃至図12を用いて本発明に係るパンタグラフ変位測定装置の第5の実施例について説明する。図11は区間毎に設定されるテンプレートサイズの例を示す説明図、図12は入力画像上のマーカ4の白色部分4wの軌跡である白色領域6aのエッジを抽出する例を示す説明図である。
Claims (10)
- 列車の屋根上に設置されパンタグラフを撮影する撮影手段と、前記撮影手段によって撮影された入力画像を画像処理することによりパンタグラフの変位を取得する画像処理手段とを備えたパンタグラフ変位測定装置において、前記画像処理手段が、前記撮影手段から入力される画像信号を用いて入力画像を作成する入力画像作成手段と、テンプレートを設定するテンプレート設定手段と、キャリブレーション手段によって得られた各画素の分解能に基づいて前記入力画像を所定数の区間に分割する画像分割処理手段と、前記入力画像上の前記区間ごとの分解能に基づいて前記テンプレートの拡大又は縮小を行うテンプレート拡大・縮小処理手段と、前記テンプレートと前記入力画像とから前記入力画像中のマーカのピクセル位置を検出するパタンマッチング処理手段と、前記マーカのピクセル位置に基づいて前記パンタグラフの実際の変位を算出するパンタグラフ変位計算手段と、前記パンタグラフの変位のデータに対して平滑化処理を行うフィルタリング処理手段と、前記平滑化処理手段によって平滑化された前記パンタグラフの変位データに基づいて算出した前記パンタグラフの加速度を出力する加速度出力手段とを有することを特徴とするパンタグラフ変位測定装置。
- 前記パタンマッチング処理手段が、直前のラインに対して行ったパタンマッチング処理の結果に基づいて、前記入力画像の所定の範囲に対してのみパタンマッチング処理を行うことを特徴とする請求項1記載のパンタグラフ変位測定装置。
- 前記パタンマッチング処理手段が、前記入力画像から検出した前記テンプレートとの相関値に応じて前記テンプレートの移動量を設定することを特徴とする請求項1記載のパンタグラフ変位測定装置。
- 前記パタンマッチング処理手段が、前記マーカの軌跡が隣接する二つの前記区間に跨っている場合に、直前のラインにおいて検出した前記マーカの位置を基準にして、前記マーカの軌跡が一つの前記区間に含まれるように前記区間の位置を自動で修正することを特徴とする請求項1記載のパンタグラフ変位測定装置。
- 前記パタンマッチング処理手段が、前記マーカの軌跡の中心位置を大まかに検出し、前記中心位置から前記テンプレートの幅の半分の範囲の平均輝度値を算出し、その値をしきい値として前記マーカの軌跡を抽出することを特徴とする請求項1記載のパンタグラフ変位測定装置。
- 列車の屋根上に設置されパンタグラフを撮影する撮影手段と、前記撮影手段によって撮影された入力画像を画像処理することによりパンタグラフの変位を取得する画像処理手段とを備えたパンタグラフ変位測定装置を用いてトロリ線の硬点を検出するトロリ線硬点検出方法において、予めテンプレートを設定する第一の工程と、前記撮影手段から入力される画像信号を用いて入力画像を作成する第二の工程と、キャリブレーション手段によって得られた各画素の分解能に基づいて前記入力画像を所定数の区間に分割する第三の工程と、前記入力画像上の前記区間ごとの分解能に基づいて前記テンプレートの拡大又は縮小を行う第四の工程と、前記テンプレートと前記入力画像とからパタンマッチング処理により前記入力画像中のマーカのピクセル位置を検出する第五の工程と、前記マーカのピクセル位置に基づいて前記パンタグラフの実際の変位を算出する第六の工程と、前記パンタグラフの変位のデータに対して平滑化処理を行う第七の工程と、前記平滑化処理手段によって平滑化された前記パンタグラフの変位データに基づいて算出した前記パンタグラフの加速度を出力する第八の工程とからなることを特徴とするトロリ線硬点検出方法。
- 前記第五の工程を、直前のラインに対して行ったパタンマッチング処理の結果に基づいて、前記入力画像の所定の範囲に対してのみ行うことを特徴とする請求項6記載のトロリ線硬点検出方法。
- 前記第五の工程を、前記入力画像から検出した前記テンプレートとのピクセル位置ごとの相関値に基づいて前記テンプレートの移動量を設定して行うことを特徴とする請求項6記載のトロリ線硬点検出方法。
- 前記第五の工程を、前記マーカの軌跡が隣接する二つの前記区間に跨っている場合に、直前のラインにおいて検出した前記マーカの位置を基準にして、前記マーカの軌跡が一つの前記区間に含まれるように前記区間の位置を自動で修正して行うことを特徴とする請求項6記載のトロリ線硬点検出方法。
- 前記第五の工程を、前記マーカの軌跡の中心位置を大まかに検出し、前記中心位置から前記テンプレートの幅の半分の範囲の平均輝度値を算出し、その値をしきい値として行うことを特徴とする請求項6記載のトロリ線硬点検出方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP10774953.3A EP2431706B1 (en) | 2009-05-15 | 2010-05-13 | Device for measuring displacement of pantograph and method for detecting hard spot of trolley wire |
CN201080021166.1A CN102428341B (zh) | 2009-05-15 | 2010-05-13 | 受电弓位移测定装置以及滑触线硬点检测方法 |
KR1020117027069A KR101292897B1 (ko) | 2009-05-15 | 2010-05-13 | 팬터그래프 변위 측정 장치 및 트롤리선 경점 검출 방법 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2009118285A JP5321235B2 (ja) | 2009-05-15 | 2009-05-15 | パンタグラフ変位測定装置及びトロリ線硬点検出方法 |
JP2009-118285 | 2009-05-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010131696A1 true WO2010131696A1 (ja) | 2010-11-18 |
Family
ID=43085069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/058083 WO2010131696A1 (ja) | 2009-05-15 | 2010-05-13 | パンタグラフ変位測定装置及びトロリ線硬点検出方法 |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP2431706B1 (ja) |
JP (1) | JP5321235B2 (ja) |
KR (1) | KR101292897B1 (ja) |
CN (1) | CN102428341B (ja) |
WO (1) | WO2010131696A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104833904A (zh) * | 2015-04-13 | 2015-08-12 | 东莞市诺丽电子科技有限公司 | 跨座式单轨受电弓拉弧检测方法 |
CN105539206A (zh) * | 2015-12-24 | 2016-05-04 | 湖南华宏铁路高新科技开发有限公司 | 一种电气化铁路接触网杆位信息的获取方法 |
CN113320445A (zh) * | 2020-02-28 | 2021-08-31 | 中铁二院工程集团有限责任公司 | 一种接触网在线监测及隐患、故障智能判别预警系统 |
CN117309875A (zh) * | 2023-09-20 | 2023-12-29 | 北京运达华开科技有限公司 | 一种非接触式弓网接触硬点检测装置和方法 |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5861318B2 (ja) * | 2011-08-26 | 2016-02-16 | 株式会社明電舎 | トロリ線データ比較装置 |
JP5534058B1 (ja) | 2013-02-19 | 2014-06-25 | 株式会社明電舎 | 摩耗測定装置及びその方法 |
EP3194882B1 (en) | 2014-09-15 | 2021-02-17 | DTI Group Limited | Arcing filtering using multiple image capture devices |
CN105158257B (zh) * | 2015-05-21 | 2018-07-20 | 苏州华兴致远电子科技有限公司 | 滑板测量方法及装置 |
JP6223601B1 (ja) * | 2015-12-15 | 2017-11-01 | 三菱電機株式会社 | トロリ線計測装置およびトロリ線計測方法 |
ITUA20162698A1 (it) * | 2016-04-19 | 2017-10-19 | Mer Mec S P A | Sistema ottico per la misura della forza di contatto tra il pantografo e la catenaria |
KR102402639B1 (ko) | 2017-11-24 | 2022-05-26 | 삼성전자주식회사 | 전자 장치 및 그의 통신 방법 |
CN111091525A (zh) * | 2018-10-18 | 2020-05-01 | 株洲中车时代电气股份有限公司 | 一种接触网硬点检测系统及其方法 |
CN109186469B (zh) * | 2018-10-18 | 2019-11-15 | 北京华开领航科技有限责任公司 | 弓网动态监测系统 |
JP6858742B2 (ja) * | 2018-12-17 | 2021-04-14 | 株式会社フジタ | 変位計測装置 |
JP6669294B1 (ja) | 2019-03-07 | 2020-03-18 | 株式会社明電舎 | パンタグラフ変位測定装置及びトロリ線硬点検出方法 |
CN110849885B (zh) * | 2019-11-27 | 2022-08-23 | 苏州华兴致远电子科技有限公司 | 一种弓网系统中的硬点监测方法、装置及系统 |
KR102276634B1 (ko) | 2020-09-15 | 2021-07-13 | 엠아이엠테크 주식회사 | 차상 설치식 전동차 팬터그래프 이상 검지 시스템 및 그의 처리 방법 |
CN112161577B (zh) * | 2020-09-21 | 2021-05-25 | 北京运达华开科技有限公司 | 一种接触网硬点检测方法及系统 |
CN113256723B (zh) * | 2021-06-29 | 2023-03-21 | 西南交通大学 | 一种受电弓升降弓时间及弓头位移曲线自动检测方法 |
DE102022208846A1 (de) | 2022-08-26 | 2024-02-29 | Siemens Mobility GmbH | Straßenfahrzeug mit einem Stromabnehmer |
KR102649465B1 (ko) * | 2023-11-22 | 2024-03-20 | 주식회사 미래건설안전 | 객체에 대한 이미지 분석을 기반으로 객체 변위를 결정하는 시스템과 방법 및 마커 모듈 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08336204A (ja) * | 1995-06-06 | 1996-12-17 | Hitachi Electron Eng Co Ltd | パンタグラフの運動姿態解析装置 |
JPH1163976A (ja) * | 1997-08-26 | 1999-03-05 | Honda Motor Co Ltd | 車両用距離測定装置 |
JP2002279409A (ja) * | 2001-03-22 | 2002-09-27 | Meidensha Corp | 画像処理によるパンタグラフ測定方式及びこの方式による測定装置 |
JP2006250774A (ja) | 2005-03-11 | 2006-09-21 | Meidensha Corp | 画像処理によるパンタグラフ動作測定装置 |
JP2008104312A (ja) | 2006-10-20 | 2008-05-01 | Meidensha Corp | 画像処理によるパンタグラフ測定装置 |
JP2009011648A (ja) | 2007-07-06 | 2009-01-22 | Panasonic Electric Works Co Ltd | 洗面ボウルの取付け構造 |
JP2009244023A (ja) * | 2008-03-31 | 2009-10-22 | Railway Technical Res Inst | ラインセンサを利用した計測装置 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3198267B2 (ja) * | 1997-04-30 | 2001-08-13 | 株式会社東芝 | 画像処理装置と画像形成装置 |
JP4258340B2 (ja) * | 2003-10-15 | 2009-04-30 | 株式会社明電舎 | パンタグラフ検出装置 |
JP4635657B2 (ja) * | 2005-03-11 | 2011-02-23 | 株式会社明電舎 | 画像処理によるトロリ線摩耗測定装置 |
-
2009
- 2009-05-15 JP JP2009118285A patent/JP5321235B2/ja active Active
-
2010
- 2010-05-13 CN CN201080021166.1A patent/CN102428341B/zh active Active
- 2010-05-13 EP EP10774953.3A patent/EP2431706B1/en active Active
- 2010-05-13 WO PCT/JP2010/058083 patent/WO2010131696A1/ja active Application Filing
- 2010-05-13 KR KR1020117027069A patent/KR101292897B1/ko active IP Right Grant
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08336204A (ja) * | 1995-06-06 | 1996-12-17 | Hitachi Electron Eng Co Ltd | パンタグラフの運動姿態解析装置 |
JPH1163976A (ja) * | 1997-08-26 | 1999-03-05 | Honda Motor Co Ltd | 車両用距離測定装置 |
JP2002279409A (ja) * | 2001-03-22 | 2002-09-27 | Meidensha Corp | 画像処理によるパンタグラフ測定方式及びこの方式による測定装置 |
JP2006250774A (ja) | 2005-03-11 | 2006-09-21 | Meidensha Corp | 画像処理によるパンタグラフ動作測定装置 |
JP2008104312A (ja) | 2006-10-20 | 2008-05-01 | Meidensha Corp | 画像処理によるパンタグラフ測定装置 |
JP2009011648A (ja) | 2007-07-06 | 2009-01-22 | Panasonic Electric Works Co Ltd | 洗面ボウルの取付け構造 |
JP2009244023A (ja) * | 2008-03-31 | 2009-10-22 | Railway Technical Res Inst | ラインセンサを利用した計測装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2431706A4 |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104833904A (zh) * | 2015-04-13 | 2015-08-12 | 东莞市诺丽电子科技有限公司 | 跨座式单轨受电弓拉弧检测方法 |
CN105539206A (zh) * | 2015-12-24 | 2016-05-04 | 湖南华宏铁路高新科技开发有限公司 | 一种电气化铁路接触网杆位信息的获取方法 |
CN113320445A (zh) * | 2020-02-28 | 2021-08-31 | 中铁二院工程集团有限责任公司 | 一种接触网在线监测及隐患、故障智能判别预警系统 |
CN113320445B (zh) * | 2020-02-28 | 2022-12-30 | 中铁二院工程集团有限责任公司 | 一种接触网在线监测及隐患、故障智能判别预警系统 |
CN117309875A (zh) * | 2023-09-20 | 2023-12-29 | 北京运达华开科技有限公司 | 一种非接触式弓网接触硬点检测装置和方法 |
CN117309875B (zh) * | 2023-09-20 | 2024-04-09 | 北京运达华开科技有限公司 | 一种非接触式弓网接触硬点检测装置和方法 |
Also Published As
Publication number | Publication date |
---|---|
JP5321235B2 (ja) | 2013-10-23 |
JP2010266341A (ja) | 2010-11-25 |
CN102428341B (zh) | 2014-05-28 |
EP2431706B1 (en) | 2017-08-16 |
EP2431706A1 (en) | 2012-03-21 |
EP2431706A4 (en) | 2014-04-02 |
CN102428341A (zh) | 2012-04-25 |
KR101292897B1 (ko) | 2013-08-02 |
KR20120022943A (ko) | 2012-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5321235B2 (ja) | パンタグラフ変位測定装置及びトロリ線硬点検出方法 | |
JP4697480B2 (ja) | 車線認識装置、車線認識方法および車線認識プログラム | |
JP6206957B2 (ja) | トロリ線測定装置及びトロリ線測定方法 | |
JP5619348B2 (ja) | 成形シートの欠陥検査装置 | |
JP2007164636A (ja) | 道路区画線検出装置 | |
EP2927710B1 (en) | Ranging system, information processing method and program thereof | |
JP2008104312A (ja) | 画像処理によるパンタグラフ測定装置 | |
JP5271227B2 (ja) | 群衆監視装置および方法ならびにプログラム | |
JP5287177B2 (ja) | 画像処理によるトロリ線の摩耗および偏位測定装置 | |
US11210773B2 (en) | Information processing apparatus, information processing method, and storage medium for defect inspection and detection | |
WO2016047510A1 (ja) | 線条計測装置及びその方法 | |
JP5900018B2 (ja) | パンタグラフ測定方法及びパンタグラフ測定装置 | |
JP6685704B2 (ja) | 車種判別装置および車種判別方法 | |
JP2004028727A (ja) | 監視システムおよび監視方法、当該監視システムにおける距離補正装置および距離補正方法 | |
JP2006318059A (ja) | 画像処理装置、画像処理方法、および画像処理用プログラム | |
JP5162874B2 (ja) | トロリ線の摩耗測定装置 | |
JP2009276910A (ja) | 画像処理装置、方法及びプログラム | |
JP2007011490A (ja) | 道路パラメータ検出装置および道路パラメータ検出方法 | |
JP6669294B1 (ja) | パンタグラフ変位測定装置及びトロリ線硬点検出方法 | |
EP4082867A1 (en) | Automatic camera inspection system | |
JP2007271445A (ja) | 画像処理によるトロリ線摩耗測定装置 | |
JP2011033428A (ja) | パンタグラフ高さ測定装置 | |
JP2009169618A (ja) | 路側境界面検出装置 | |
JP2009292351A (ja) | 摩耗測定装置及び摩耗測定方法 | |
JPH11259792A (ja) | 車輌認識方法およびその装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080021166.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10774953 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20117027069 Country of ref document: KR Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2010774953 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010774953 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |