JP2016191649A - Wear amount measurement device, wear amount measurement method, and wear amount measurement program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a wear amount measurement device, a wear amount measurement method, and a wear amount measurement program capable of presenting more effective wear amounts without increasing the scale or instruction costs of a system.SOLUTION: A wear amount measurement device includes: an imaging part for acquiring a plurality of photographic images; a wear amount calculation part 202 for calculating the wear amounts of an object to be measured from the plurality of photographic images; a shield area detection part 203 for detecting an area where the object to be measured is shielded by a shield object from the photographic images, and for setting the detected area as a shield area; a shield area correction part 204 for interpolating the wear amounts of the shield area from the wear amounts of an adjacent area adjacent to the shield area among the wear amounts calculated by the wear amount calculation part 202, and for correcting the calculated wear amounts; a display data generation part 205 for generating data in which the interpolated wear amounts and the non-interpolated wear amounts are presented so as to be identifiable as presentation data for presenting the wear amounts to an operator; and a display part for presenting the wear amounts of the object to be measured on the basis of the presentation data.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a wear amount measuring device, a wear amount measuring method, and a wear amount measuring program for measuring a wear amount of a measurement target in a state where the measurement target is shielded by a predetermined shielding object, The present invention relates to a wear amount measuring apparatus, a wear amount measuring method, and a wear amount measuring program in consideration of a shielding area by an object.

An overhead-line train travels by taking power, which is a power source, from the overhead line via a pantograph. Specifically, the electric power transmitted from the substation is sent to the overhead line of each section through feeders and feeder branches. The electric power sent to the overhead line is transmitted to the running train by contact between the overhead line and the pantograph. More detailed power flow in the overhead line and pantograph is in the order of overhead line, sliding board, boat body, upper frame, lower frame, underframe, and main circuit.
The pantograph slide plate receives power by keeping in contact with the overhead wire while the train is running. For this reason, the sliding plate is gradually worn due to friction with the overhead wire. When wear progresses beyond a certain level, there is a possibility that problems such as the inability to supply electric power may occur. Therefore, it is necessary to detect the wear amount and replace the sliding plate.
It is not realistic for the operator to visually check all the sliding plates and determine whether or not replacement is necessary. For this reason, it is desirable to automatically measure the wear amount of the sliding plate and to provide information regarding the replacement determination to the operator.

For example, Patent Document 1 uses a plurality of distance sensors (ultrasonic sensors, etc.) installed above the overhead line to measure the distance between the upper surface of the sliding plate and the reference surface when the sliding plate passes directly below. And the automatic measuring device of the sliding board which detects the abrasion amount of a sliding board from the distance difference is disclosed.
Further, in Patent Document 2, as an automatic measurement device using an imaging device, a damaged region is determined based on a luminance difference between the upper and lower borders (edges) of a top surface and a side surface of a ground plate among captured images. A slip plate inspection device is disclosed that calculates the wear amount of a slip plate based on edge positions excluding a roughened region.

JP-A-4-353709 JP 2006-078355 A

However, when considering the actual traveling environment of a train, the sliding plate is in contact with the overhead wire, and the contact area is shielded by the overhead wire, so that measurement as described in Patent Literature 1 and Patent Literature 2 is performed. It is difficult to directly calculate the wear amount of the sliding plate in the contact area with the overhead wire (hereinafter referred to as “shielding area”) by a device, that is, a measuring device using a distance sensor or an imaging device. Therefore, there are the following problems.
(1) There is a high possibility of calculating an incorrect wear amount of the sliding plate.
(2) As described above, when the wear progresses beyond a certain level, it is desirable to provide the worker with information regarding the replacement decision. However, there is a possibility that inaccurate information may be provided to the worker. high.

  As a solution to the above problem, for example, the wear amount of the shield plate is calculated by measuring the wear amount of the slip plate at two or more places where the contact positions with the overhead line are different and integrating the measurement results. It is possible to do. However, in that case, it is necessary to install measuring devices at a plurality of locations or make them movable within a range where there is no difference in the wear amount of the sliding plate, which increases the scale and introduction cost of the system.

  An object of the present invention is to measure a wear amount of a measurement target in a state where the measurement target is shielded by a predetermined shielding object and present a result of the measurement, a wear amount measurement device, a wear amount measurement method, A wear amount measuring device, a wear amount measuring method, and a wear amount measuring program capable of presenting a more effective wear amount without increasing the scale and introduction cost of the system. It is to be.

In order to solve the above problems, the wear amount measuring device of the present invention is:
A wear amount measuring device that measures the wear amount of the measurement target in a state where the measurement target is shielded by a predetermined shielding object,
An imaging means for acquiring a plurality of captured images;
Wear amount calculating means for calculating the wear amount of the measurement object from the plurality of captured images;
A shielding area detecting means for detecting an area where the measurement target is shielded by the shielding object from the captured image, and setting the detected area as a shielding area;
By interpolating the wear amount of the shielding area, shielding area correction means for correcting the wear amount calculated by the wear amount calculation means;
Presenting data generating means for generating presenting data for presenting the wear amount to an operator;
Presenting means for presenting the amount of wear of the measurement object based on the presentation data,
The shielding region correction means interpolates the wear amount of the shielding region from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated by the wear amount calculation unit,
The presentation data generation means is configured to generate presentation data such that the interpolated wear amount and the non-interpolated wear amount are presented in an identifiable manner.

  In this way, since the area shielded by the shielding object can be detected and the wear amount can be calculated as the shielding area, there is no need to install measurement devices at a plurality of locations or make them movable. Therefore, a more effective wear amount can be presented without increasing the scale of the system and the introduction cost.

Preferably,
The shielding area detection unit is configured to detect a plurality of straight lines from the captured image by straight line detection processing, determine a representative straight line from the plurality of straight lines, and set a shielding area based on the representative straight line. It is possible.
With this configuration, the shielding area can be set more accurately.

Preferably,
The presentation data generation means can be configured to generate presentation data that presents at least one of the wear distribution of the entire measurement target, the maximum wear position, and the wear amount at the position. .
With this configuration, the measurement result can be presented in an easily understandable manner.

Preferably,
When the maximum wear position is within the shielding area, the presentation data generating means determines the maximum wear position and the wear amount at the position, and the maximum wear position and the wear amount at the position other than the shield area. Can be configured to generate presentation data that is presented.
By comprising in this way, the measurement result which can assist the final determination of the amount of wear by an operator can be shown.

Preferably,
The shielding area correction means includes
The intersection of the first straight line obtained by linearly approximating the wear amount change of one adjacent region adjacent to the shielding region and the second straight line obtained by approximating the wear amount change of the other adjacent region by a straight line Find the position of
When the estimated wear amount at the position of the intersection is not larger than the wear amount of the adjacent region, the wear amount of the shielding region is interpolated by a linear interpolation method,
When the estimated wear amount at the position of the intersection is larger than the wear amount in the adjacent area, the wear amount in the shielding area can be interpolated by an interpolation method other than the linear interpolation method.
With this configuration, it is possible to accurately interpolate the amount of wear in the shielding area while reducing the calculation cost.

Preferably,
A smoothing processing means for performing a smoothing process on the wear amount distribution data calculated by the wear amount calculation means;
The smoothing processing unit corrects the wear amount calculated by the wear amount calculation unit by interpolating the wear amount of the shielding region from the wear amount of the adjacent region as the smoothing processing, and then performs the correction. It is possible to perform a process of smoothing the distribution data of the amount of wear.
With this configuration, it is possible to present a wear distribution that is not affected by the error of the shielding region.

Preferably,
Storage means for storing a shielding area detection result by the shielding area detection means;
A shielding area resetting means for resetting the shielding area,
The shielding area resetting means is configured to reset the shielding area based on a shielding area detection result from the shielding area detection means and a past shielding area detection result stored in the storage means. Is possible.
With this configuration, even when the shielding area detection unit fails to detect the shielding area due to a change in the shooting environment or the like, it is possible to set the shielding area and present the wear amount.

The wear amount measuring method of the present invention is
A wear amount measuring method for measuring a wear amount of a measurement target in a state where the measurement target is shielded by a predetermined shielding object,
An imaging step of acquiring a plurality of captured images;
A wear amount calculating step of calculating a wear amount of the measurement object from the plurality of captured images;
A shielding region detection step of detecting a region where the measurement target is shielded by the shielding object from the captured image, and setting the detected region as a shielding region;
By interpolating the amount of wear of the shielding area, a shielding area correction step for correcting the wear amount calculated in the wear amount calculation step;
A presentation data generating step for generating presentation data for presenting the wear amount to an operator;
A presentation step of presenting the wear amount of the measurement object based on the presentation data;
In the shielding region correction step, the wear amount of the shielding region is interpolated from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated in the wear amount calculation step,
In the presentation data generation step, presentation data is generated so that the interpolated wear amount and the non-interpolated wear amount are presented in an identifiable manner.
Therefore, a more effective wear amount can be presented without increasing the scale of the system and the introduction cost.

In addition, the wear amount measurement program of the present invention is
In a state where the measurement target is shielded by a predetermined shielding object, a computer that measures the wear amount of the measurement target,
An imaging step of acquiring a plurality of captured images;
A wear amount calculating step of calculating a wear amount of the measurement object from the plurality of captured images;
A shielding region detection step of detecting a region where the measurement target is shielded by the shielding object from the captured image, and setting the detected region as a shielding region;
Shielding region correction that corrects the calculated wear amount by interpolating the wear amount of the shielding region from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated in the wear amount calculation step. Steps,
A presentation data generation step for generating data such that the interpolated wear amount and the non-interpolated wear amount are identifiable as presentation data for presenting the wear amount to an operator,
Based on the presentation data, a presentation step for presenting the amount of wear of the measurement target;
Is configured to execute.
Therefore, a more effective wear amount can be presented without increasing the scale of the system and the introduction cost.

  It is possible to provide a wear amount measuring device, a wear amount measuring method, and a wear amount measuring program capable of presenting a more effective wear amount without increasing the scale of the system and the introduction cost.

It is a figure which shows one structural example of the measuring device of this invention. It is a figure which shows one structural example of the measurement process part in 1st Embodiment. It is the figure which showed an example of the hull assembly simply. It is a graph which shows an example of the measurement result of a wear amount of a slab. It is a figure which shows an example of the detection method of a shielding area. It is a flowchart which shows an example of an interpolation process. It is a figure which shows an example of the correction method of a shielding area. It is a figure which shows an example of the wear amount measurement result shown to an operator. It is a figure which shows one structural example of the measurement process part in 2nd Embodiment. It is a flowchart which shows an example of a smoothing process. It is a figure for demonstrating the difference between the smoothing process in 2nd Embodiment, and another smoothing process. It is a figure for demonstrating the difference between the smoothing process in 2nd Embodiment, and another smoothing process. It is a figure which shows one structural example of the measurement process part in 3rd Embodiment. It is a figure which shows one structural example of the measurement process part in 4th Embodiment. It is a figure which shows the example of 1 structure of the measurement process part in 5th Embodiment.

  Embodiments according to the present invention will be described below with reference to the drawings.

(First embodiment)
In the present embodiment, a basic configuration in the present invention will be described.
Specifically, the shielding area (that is, the area shielded by the shielding object (the overhead line C) in the measurement target (pantograph sliding board)) is detected, and the wear amount of the sliding board in the shielding area is appropriately determined from the surrounding area. Means for interpolating and specifying the interpolated area will be described.

  FIG. 1 is a diagram illustrating a configuration example of the measurement apparatus 100 according to the present embodiment. The measurement apparatus 100 includes, for example, an imaging unit 101 for capturing a subject, a measurement processing unit 102 for processing a captured image captured by the imaging unit 101, and a display for outputting and displaying a captured image and a measurement processing result. A unit 103, a storage unit 104 that stores captured images, measurement processing results, parameters for measurement processing, and the like, a control unit 105 that controls the entire measurement apparatus 100, and exchanges data between the units. And a data bus 106.

The imaging unit 101 includes an imaging device including an imaging element such as a CMOS (Complementary Metal Oxide Semiconductor) or a CCD (Charge Coupled Device) and an optical component such as a lens, and each image data obtained by photoelectric conversion. Is output to the data bus 106. One imaging device may be provided and the subject may be photographed multiple times. Alternatively, a plurality of imaging devices may be provided. In that case, the plurality of imaging devices are arranged in parallel so that an image having a parallax can be taken, for example, configured as a stereo camera (two eyes). Is done. Note that three or more imaging devices may be provided, and each combination of two eyes may be regarded as a stereo camera.
That is, the imaging unit 101 serves as an imaging unit that acquires a plurality of captured images.

  The measurement processing unit 102 can be configured by, for example, an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a CPU (Central Processing Unit), or the like, and the imaging unit 101 or a storage unit 104 in which image data is stored. The image data is acquired from the data, and the measurement processing result is output to the data bus 106. Details of the measurement processing unit 102 will be described later.

  The display unit 103 can be configured by, for example, an LCD (Liquid Crystal Display) or an organic EL display (OELD: Organic Electroluminescence Display), and is stored in the measurement processing result output from the measurement processing unit 102 or the storage unit 104. Displayed image data. The display unit 103 may be installed outside the measuring apparatus 100.

  The storage unit 104 includes, for example, a main storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory) that stores a wear amount measurement program of the present invention, and an auxiliary storage device such as a hard disk. The main storage device is used to temporarily hold image data, measurement processing results, and the like. The auxiliary storage device stores data for long-term storage as storage, such as image data and measurement processing results.

The control unit 105 includes, for example, a CPU, and performs various commands and controls such as execution of imaging processing in the imaging unit 101 and execution of measurement processing in the measurement processing unit 102.
The above is the overall configuration of the present embodiment.

FIG. 2 is a diagram illustrating a configuration example of the measurement processing unit 102.
The measurement processing unit 102 includes, for example, an edge detection unit 201 that detects the edge position of the sliding plate, a wear amount calculation unit 202 that calculates a wear amount (slip plate wear amount) at the edge position of the sliding plate, A shielding area detection unit 203 that detects an area where the overhead line C and the sliding board intersect from the image, and sets the shielding area on the edge of the sliding board, and a shielding area correction unit that corrects the wear amount of the area set as the shielding area 204, and a display data generation unit 205 that generates data for presenting the measurement result of the wear amount of the wear to the operator.

The edge detection unit 201 detects the edge position of the sliding plate on the image.
For the edge position of the sliding plate, for example, the reaction intensity for the Sobel filter is calculated, and the position on the sliding board where the reaction intensity is equal to or higher than a predetermined threshold is detected as the edge position. The edge detection method is not limited to the Sobel filter, and may be a Prewitt filter, a Laplacian filter, a Canny filter, or the like. It is also possible to perform edge detection processing using multiple types of edge detection methods and use each edge detection result or a combination of these results, and this configuration enables edge detection. The position can be stabilized.
Then, the edge position data of the sliding plate obtained by the edge detection unit 201 is sent to the subsequent wear amount calculation unit 202 and the shielding region detection unit 203.

The wear amount calculation unit 202 calculates the wear amount at the edge position of the sliding plate.
Specifically, the wear amount calculation unit 202 receives a stereo image and edge position data from the edge detection unit 201 and performs stereo matching processing to calculate a parallax between the images, and based on the principle of triangulation A three-dimensional position at each edge position of the plate is calculated. The parallax can be calculated using a method using block matching or the like.
For example, in a method using block matching, two images captured by a stereo camera are used as a standard image and a reference image, and parallax can be calculated by searching for a target pixel and peripheral pixels of the standard image on the reference image. it can. The search is performed by evaluating the degree of similarity or dissimilarity, and includes a reference area composed of a target pixel and peripheral pixels set in the reference image, and a reference area having the same size as the reference area set in the reference image. It can be realized by evaluating SAD (Sum of Absolute Difference) or SSD (Sum of Squared Difference).
That is, the wear amount calculation unit 202 serves as a wear amount calculation unit that calculates a wear amount of a measurement target (in the case of the present embodiment, a sliding plate) from a plurality of captured images.

In the present embodiment, an example of an image taken with a stereo camera (a twin-lens camera) is described. For example, one of images taken with a camera with three or more eyes is a reference image, and the other is a reference image. Thus, it is obvious that the present invention can be applied even when three or more imaging devices are provided. In that case, a plurality of parallaxes or three-dimensional positions can be calculated, and by integrating them, a more accurate result can be obtained.
The wear amount of the wear plate is obtained by defining a reference plane position and calculating the distance from the three-dimensional position of the plane position. The reference plane is estimated from, for example, the boundary plane between the sliding plate and the hull and the three-dimensional measurement result of the auxiliary sliding plate portion.

FIG. 3 is a diagram simply showing an example of a hull assembly.
In one hull assembly, a main sliding plate 302 and an auxiliary sliding plate 303 are arranged on the upper portion of the hull 301. The main sliding plate 302 is arranged so as to be sandwiched between the auxiliary sliding plates 303, and this row of sliding plate sets is arranged in two rows. In the case of the sliding plate configuration as shown in FIG. 3, it has four sliding plate edges extending in the longitudinal direction (left-right direction), and the wear amount of these four sliding plate edges is calculated as the sliding plate wear amount. The

  For example, the wear amount of the sliding plate is calculated as shown in the graph of FIG. The horizontal axis of the graph is the position in the longitudinal direction (left-right direction) of the sliding plate, and the vertical axis is the wear amount of the sliding plate. The measurement result of the wear amount of the sliding plate shown in FIG. 4A is an ideal result when the measurement is performed in a state where the overhead wire C is not in contact with the upper surface of the sliding plate. However, in the actual measurement of the wear amount of the sliding plate, since the overhead wire C is in contact with the sliding plate, a part of the sliding plate is shielded by the overhead wire C. For this reason, it is difficult to accurately measure the wear amount of the sliding plate. For example, it is conceivable that the measurement results as shown in FIGS. 4B and 4C are obtained.

When the measurement result as shown in FIG. 4B is obtained, there is a problem that when the shielding region is most worn, the operator cannot be notified of the fact.
In addition, when a measurement result as shown in FIG. 4C is obtained, an edge that is visible on one image but is not visible on the other image (also called occlusion) in a stereo image. There is a problem in that the amount of wear at the position is erroneously calculated and erroneously determined as the maximum wear position.
Therefore, in the present invention, the above-described problem is solved by detecting a shielding area and performing interpolation / correction processing on the shielding area.

The shielding area detection unit 203 detects the overhead line C that intersects the sliding board edge and sets it as a shielding area on the sliding board edge.
Specifically, the shielding area detection unit 203 receives edge position data from the edge detection unit 201 and detects a straight line in a direction intersecting the extending direction of the sliding plate edge. Specifically, for example, a straight line that crosses the edge of the sliding plate is detected by Hough transform or the like. The detected straight line (overhead candidate straight line) does not necessarily include straight lines at both ends in the width direction of the overhead line C. Therefore, as shown in FIG. 5, a representative straight line is determined from the plurality of detected straight lines. For example, the representative straight line is determined by averaging each of the inclination and intercept of the overhead line candidate straight line, or selecting the median value of the slope and intercept of the overhead line candidate straight line. Setting an area with an arbitrary margin from the representative straight line position as the shielding area is preferable because the probability of including the actual shielding area increases. Further, depending on the image capturing conditions, it is conceivable that only a straight line at either end in the width direction of the overhead line C is detected as a detection result of the overhead line C. Therefore, the overhead line in which the margin width is captured. By setting the width larger than the width of C, it is possible to reduce the influence of errors due to overhead line shielding.
That is, the shielding area detection unit 203 detects, from the captured image, an area where the measurement target (slipboard in the case of the present embodiment) is shielded by the shielding object (the overhead line C in the case of the present embodiment). Shielding area detecting means for setting the performed area as the shielding area is provided.

The shielding region correction unit 204 performs an interpolation process based on the wear amount measurement results on both sides of the shielding region, and corrects the wear amount of the sliding plate calculated by the wear amount calculation unit 202.
That is, the shielding area correction unit 204 serves as a shielding area correction unit that corrects the wear amount calculated by the wear amount calculation unit (wear amount calculation unit 202) by interpolating the wear amount of the shielding region.
Here, when there is a high possibility that the maximum wear position exists in the shielding area, it is necessary to accurately interpolate the shielding area, but when the possibility that the maximum wear position exists in the shielding area is low. If simple linear interpolation is performed, the calculation cost can be reduced, which is preferable. The flow of the interpolation process will be described with reference to FIG.

As shown in FIG. 6, the shielding area correction unit 204 first performs linear approximation on the measurement results of the arbitrary number of points in the right adjacent area and the left adjacent area adjacent to the shielding area. A straight line (first straight line and second straight line) is detected (step S601).
Next, the shielding area correction unit 204 calculates an intersection P between the left and right straight lines detected in step S601 (step S602).
Next, the shielding area correction unit 204 determines whether the intersection point P calculated in step S602 is at a position (worn position) below the point group (left and right adjacent areas adjacent to the shielding area) used for linear approximation. It is determined whether or not (step S603).

If it is determined in step S603 that the intersection point P is at the lower position (step S603: Y), specifically, for example, as shown in the upper diagram of FIG. Therefore, the shielding region correction unit 204 performs advanced interpolation such as spline interpolation, Lagrangian interpolation, and Bezier interpolation, because there is a high possibility that the maximum wear position exists in the shielding region. Is performed (step S604). As a result, for example, as shown in the lower diagram of FIG. Note that the intersection point P calculated in step S602 may be used for the above-described interpolation.
On the other hand, when it is determined in step S603 that the intersection point P is not at the lower position (step S603; N), specifically, for example, as shown in the upper diagram of FIG. Since there is a low possibility that the maximum wear position is present in the area, the shielding area correction unit 204 simply performs linear interpolation from the positions of both end points of the shielding area, for example (step S605). As a result, for example, as shown in the lower diagram of FIG.
With the above interpolation processing, the wear amount of the shielding area can be calculated by interpolation while reducing the calculation cost.

The display data generation unit 205 extracts and processes data to be presented to the worker from the amount of wear of the sliding plate corrected by the shielding region correction unit 204, and notifies the worker via the display unit 103. The display data generation unit 205 generates data that can display at least one of the wear distribution of the entire sliding plate, the maximum wear position, and the wear amount thereof as display data.
That is, the display data generation unit 205 serves as presentation data generation means for generating presentation data (in the case of this embodiment, display data) for presenting the wear amount to the worker.
In addition, the display unit 103 serves as a presentation unit that presents the wear amount of the measurement target (in the case of the present embodiment, a sliding board) based on the presentation data.

As the wear distribution of the entire sliding plate, for example, the distribution of the wear amount is presented as a graph. At this time, in order to clearly indicate that the shielding area is interpolated, for example, as shown in the lower diagrams of FIGS. 7A and 7B, the line type, the line color, the background color, and the like are drawn differently from the other areas. If set to, it is preferable because it can be easily distinguished from other areas.
As the maximum wear position and the amount of wear, the maximum wear position and the maximum amount of wear are detected from the entire distribution of the wear amount of the slip plate after correction. When the maximum wear position is outside the shielding area, the maximum wear position and the maximum wear amount are presented to the operator as they are. When the maximum wear position is in the shielding area, in addition to the maximum wear position and the maximum wear amount, the operator is notified that the maximum wear position is in the shielding area. At this time, if the maximum wear position and the maximum wear amount in the region other than the shielding region are also detected and presented to the operator as auxiliary information, it is helpful for the operator to finally determine the wear amount of the sliding plate. is there.

FIG. 8 is a diagram illustrating an example of a wear amount measurement result presented to the worker.
In the area 801, the edge position indicating the wear distribution in the area 802 and the maximum wear position are displayed superimposed on the captured image. For example, the icon 803 indicating the maximum wear position in the shielding area and the icon 804 indicating the maximum wear position in the other area are formed in different shapes. Further, the wear amount display window 805 displays the wear amount at the maximum wear position.
In the area 802, the wear distribution is displayed, and icons 803 and 804 are displayed at corresponding positions. When the maximum wear amount exceeds the allowable value, an alert “replacement” is displayed on the alert display unit 806 (see FIG. 8). When the maximum wear amount exceeds the warning value, the alert display unit By displaying an alert “Warning” in 806, the operator is notified of the replacement timing.

In the example shown in FIG. 8, the maximum wear position in the overhead line region and the maximum wear position in other regions are displayed. However, the display method is not limited to this. It may be possible to display only one of the maximum wear positions determined to be the most advanced without being distinguished from the region.
Further, FIG. 8 shows a display example of the wear amount measurement result for one edge, but in the case of a sliding plate as shown in FIG. 4, the wear amount measurement result for a total of four edges is obtained. The wear amount measurement result does not need to be notified to the operator for all of the plurality of edges. For example, the position of the most worn edge among the four edges and the wear amount (or whether or not the wear is more than specified). ).

Here, a rough flow of the measurement of the wear amount of the sliding plate in the present embodiment will be described.
First, the imaging unit 101 acquires a plurality of captured images (imaging step).
Next, the wear amount calculation unit 202 calculates the wear amount of the measurement target (slide plate) from the plurality of captured images (wear amount calculation step).
Next, the shielding area detection unit 203 detects an area where the measurement target is shielded by the shielding object (overhead line C) from the captured image, and sets the detected area as a shielding area (shielding area detection step).

Next, the shielding region correction unit 204 corrects the wear amount calculated in the wear amount calculation step by interpolating the wear amount of the shielding region (shielding region correction step). In this shielding region correction step, the wear amount of the shielding region is interpolated from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated in the wear amount calculation step.
Next, the display data generation unit 205 generates display data for presenting the wear amount to the worker (presentation data generation step). In this presentation data generation step, the interpolated wear amount (that is, the wear amount of the shielding region) and the non-interpolated wear amount (that is, the wear amount of the region other than the shielding region) are presented in an identifiable manner. Such display data is generated.
Then, the display unit 103 presents the wear amount to be measured based on the display data (presentation step).

According to the first embodiment described above, the calculated wear amount is corrected by interpolating the wear amount of the shielding region from the wear amount of the adjacent region adjacent to the shielding region among the calculated wear amounts. Therefore, the wear that can calculate a more effective wear amount as the wear amount of the shielding area shielded by the shielding object (the overhead line C in this embodiment) without increasing the scale of the system and the introduction cost. A quantity measuring device (measuring device 100), a wear amount measuring method, and a wear amount measuring program can be provided.
Also, presentation data (display data) is presented so that the interpolated wear amount (wear amount of the shielding region) and the non-interpolated wear amount (wear amount of the region other than the shielding region) are presented in an identifiable manner. Since it is generated, it is possible to easily grasp which of the presented wear amounts is interpolated.

  Further, according to the first embodiment, a plurality of straight lines are detected from the captured image by the straight line detection process, a representative straight line is determined from the plurality of straight lines, and a shielding area is set based on the representative straight line. The shielding area can be set more accurately.

  In addition, according to the first embodiment, the presentation that presents at least one of the wear distribution of the entire measurement target (in the case of the present embodiment, the sliding plate), the maximum wear position, and the wear amount at the position is presented. Since the data (display data) is generated, the measurement result can be presented in an easy-to-understand manner.

  Further, according to the first embodiment, when the maximum wear position is within the shielding area, the maximum wear position and the wear amount at the position, the maximum wear position of the area other than the shield area, and the wear at the position. Since the presentation data (display data) that presents the amount is generated, it is possible to present a measurement result that can assist the final determination of the wear amount by the operator.

  In addition, according to the first embodiment, the first straight line obtained by linearly approximating the wear amount change in one adjacent region (in the present embodiment, the right adjacent region) adjacent to the shielding region, and the other The position of the intersection point P with the second straight line obtained by linearly approximating the wear amount change of the adjacent region (the adjacent region on the left side in this embodiment) is obtained, and the estimated wear amount at the position of the intersection point P is When it is not larger than the wear amount of the adjacent region (left and right adjacent regions in this embodiment), the wear amount of the shielding region is interpolated by linear interpolation, and the estimated wear amount at the position of the intersection P is If it is larger than the wear amount of the area, the wear amount of the shielding area is interpolated by an interpolation method other than the linear interpolation method (in this embodiment, spline interpolation, Lagrange interpolation, Bezier interpolation, etc.), thereby reducing the calculation cost. While It can be accurately interpolate the wear amount of the shielding region.

(Second Embodiment)
The first embodiment has been described on the assumption that a smooth wear amount distribution is obtained as shown in FIG. However, in actual measurement, the detected edge position shifts due to the influence of fine scratches and shadows on the sliding plate surface, and the calculated wear amount has a distorted distribution, which is difficult for the operator to check. It often becomes. Further, when a simple smoothing process is performed to make the data easy to confirm, it is affected by the error of the shielding area.
Therefore, in the second embodiment, a smoothing method that takes into account the influence of the shielding area will be described.

  FIG. 9 is a diagram illustrating a configuration example of the measurement processing unit 900 according to the second embodiment. A measurement apparatus 100 according to the second embodiment includes a measurement processing unit 900 illustrated in FIG. 9 instead of the measurement processing unit 102. The measurement processing unit 900 includes a smoothing processing unit 901 in addition to the configuration of the measurement processing unit 102 in the first embodiment. A flow of processing (smoothing processing) of the smoothing processing unit 901 will be described with reference to FIG.

As shown in FIG. 10, the smoothing processing unit 901 first performs an outlier removal process on the data on the wear amount of the sliding plate calculated by the wear amount calculation unit 202 (step S1001). In this outlier removal processing, outliers are removed by, for example, a median filter or a Kolmogorov-Smirnov test.
Next, the smoothing processing unit 901 performs provisional interpolation processing on the shielding area (step S1002). In this temporary interpolation process, the same process as the interpolation process by the shielding area correction unit 204 is performed.
Next, the smoothing processing unit 901 performs a smoothing process on the entire wear amount distribution data (step S1003). In this smoothing process, for example, an addition average filter or a Gaussian filter is used.

Here, the difference between the smoothing process in the present embodiment and other smoothing processes will be described with reference to FIGS. 11 and 12.
FIG. 11A shows the result of performing the smoothing process without removing the value of the wear amount of the shielding area, and it can be seen that the error of the shielding area affects the adjacent area.
FIG. 11B is an example in which smoothing is performed with the value of the shielding area set to a non-number (Not a Number), and the result of the method of reducing the smoothing filter size as the boundary between the shielding area and the adjacent area is approached. It is.
FIG. 11C is an example in which smoothing is performed with the value of the shielding area being an innumerable value, and is a result of a method of smoothing the wear amount of the shielding area assuming that the end point of the adjacent area continues.
FIG. 11D shows the result of the smoothing process in the present embodiment. A broken line in FIG. 11D is a result of the provisional interpolation process performed on the shielding area.

  FIG. 12 is a diagram comparing the smoothing results of FIGS. 11B, 11C, and 11D, and it can be seen that the smoothing process in the present embodiment is not affected by the error of the shielding region. Therefore, as shown in the present embodiment, as the smoothing process for the wear amount distribution data, after the interpolation process of the shielding area (that is, the temporary interpolation process in step S1002) is performed once, the wear amount distribution data is obtained. It is preferable to perform a process of smoothing.

  According to the second embodiment described above, the smoothing processing means (smoothing processing section 901) that performs the smoothing process on the wear amount distribution data calculated by the wear amount calculation means (wear amount calculation section 202). The smoothing processing unit corrects the wear amount calculated by the wear amount calculating unit (wear amount calculating unit 202) by interpolating the wear amount of the shielding region from the wear amount of the adjacent region as the smoothing processing. Later, processing for smoothing the distribution data of the corrected wear amount is performed, so that it is possible to present a wear distribution that is not affected by the error of the shielding region.

(Third embodiment)
In the first and second embodiments, the shielding area detection unit 203 detects a plurality of overhead line candidate straight lines by straight line detection processing, determines a representative straight line from the detected plurality of straight lines, and sets a shielding area. explained.
In the third embodiment, a method for performing a shielding area resetting process using past shielding area detection results will be described.

  FIG. 13 is a diagram illustrating a configuration example of the measurement processing unit 1300 according to the third embodiment. A measurement apparatus 100 according to the third embodiment includes a measurement processing unit 1300 illustrated in FIG. 13 instead of the measurement processing units 102 and 900. The measurement processing unit 1300 includes a shielding area resetting unit 1301 in addition to the configuration of the measurement processing unit 900 in the second embodiment. The shielding area resetting unit 1301 can also be applied to the configuration of the measurement processing unit 102 in the first embodiment.

The shielding area resetting unit 1301 detects the shielding area detection result (current shielding area detection result) from the shielding area detection unit 203 and one or more shieldings detected in the past measurement process stored in the storage unit 104. The area detection result (past occlusion area detection result) is received, and the occlusion area is reset.
In the shielding area resetting process, the representative straight line in the current shielding area detection and the representative straight line in the past shielding area detection are used as overhead line candidate straight lines, and a new representative straight line is determined, thereby resetting the shielding area. Do. The new representative straight line is the same as that of the shielding area detecting unit 203, that is, for example, each of the averages of the overhead line candidate straight lines is averaged or the median of the overhead line candidate straight line and the intercept is selected. To decide.

Thereby, for example, even when the current shielding area detection fails due to a change in the photographing environment such as the illumination condition, the wear amount can be detected by setting the shielding area, which is preferable. In particular, when the measurement apparatus 100 is installed so as to capture the same imaging space, the position of the overhead line on the captured image is substantially the same, which is preferable.
Also, the shielding area resetting process is not necessarily performed. For example, if the number of overhead line candidate straight lines obtained by the current shielding area detection is equal to or greater than the threshold value, it is determined that the detection result is highly reliable, and the representative straight line in the current shielding area detection is used as it is. However, when the number of overhead line candidate straight lines obtained by the current shielding area detection is less than the threshold, it is preferable to perform the shielding area resetting process because the calculation cost can be reduced.

  According to the second embodiment described above, the storage unit (storage unit 104) that stores the shielding region detection result by the shielding region detection unit (shielding region detection unit 203), and the shielding region reset that resets the shielding region. Setting means (shielding area resetting unit 1301), and the shielding area resetting means includes a shielding area detection result (current shielding area detection result) from the shielding area detection means and a past stored in the storage means. Since the shielding area is reset based on the shielding area detection result, even if the shielding area detection unit fails to detect the shielding area due to a change in the shooting environment, the shielding area is set and the wear amount is presented. be able to.

(Fourth embodiment)
In the third embodiment, the method for performing the shielding area resetting process using the past shielding area detection result has been described.
In the fourth embodiment, a description will be given of a method of notifying a worker when a shielding region abnormality is determined by using a past shielding region detection result and the abnormality is determined.
FIG. 14 is a diagram illustrating a configuration example of the measurement processing unit 1400 according to the fourth embodiment. The measurement apparatus 100 according to the fourth embodiment includes a measurement processing unit 1400 illustrated in FIG. 14 instead of the measurement processing unit 1300. The measurement processing unit 1400 includes an abnormality determination unit 1401 in addition to the configuration of the measurement processing unit 1300 in the third embodiment.

The abnormality determination unit 1401 includes a shielding area detection result (a representative straight line in the current shielding area detection) from the shielding area detection unit 203 and one or more shieldings detected in the past measurement process stored in the storage unit 104. The region detection result (representative straight line in the past shielding region detection) is received and outlier determination processing is performed. When it is determined by this outlier determination process that the representative straight line in the current shielding area detection is an outlier, the abnormality determination unit 1401 determines that the overhead line position is abnormal, and notifies the operator that the overhead line position is abnormal. ”Alert.
In the fourth embodiment, the shielding area resetting unit 1301 does not determine a new representative line when the abnormality determination unit 1401 determines that the representative line in the current shielding area detection is an outlier. Then, the shielding area is set using the representative straight line in the current shielding area detection. Otherwise, it is determined that the current shielding area detection result is equivalent to the past shielding area detection result, and the same processing as in the third embodiment is performed.

  As a result, even if the shielding area is deviated from the assumed position, it is possible to measure the amount of wear in consideration of the shielding area deviated from the assumed position and Can be notified that the position is deviated from the expected position.

(Fifth embodiment)
In the first to fourth embodiments, the case where one shielding area is detected has been described.
In the fifth embodiment, a processing method in the case where two or more candidate shielding areas are detected will be described.
FIG. 15 is a diagram illustrating a configuration example of the measurement processing unit 1500 according to the fifth embodiment. The measurement apparatus 100 according to the fifth embodiment includes a measurement processing unit 1500 illustrated in FIG. 15 instead of the measurement processing units 102, 900, 1300, and 1400. The measurement processing unit 1500 includes a candidate region classification unit 1502 and an abnormal region classification unit 1503 in addition to the configuration of the measurement processing unit 1300 in the third embodiment, and the shielding region detection unit 1501 has two or more. It has a function of detecting a shielding area.

  The shielding area detection unit 1501 according to the present embodiment first performs straight line detection processing in the same manner as the shielding area detection unit 203 according to the first embodiment, and detects a plurality of overhead line candidate straight lines. Next, the Ward method, the k-means method, or the like is applied to a plurality of overhead line candidate straight lines, and clustering processing is performed to set a representative straight line for each cluster. Here, if the number of clusters is one, the same processing as in the first to fourth embodiments is performed. On the other hand, when the number of clusters is two or more, each is sent to the candidate area classification unit 1502 as a shielding area candidate.

Candidate area classification unit 1502 classifies one of the two or more occluded area candidates as a occluded area. Specifically, the candidate area classification unit 1502 receives the representative straight line of the occluded area candidate and the representative straight line in one or more past occluded area detections stored in the storage unit 104, and performs outlier determination processing. Do. Among the shielding area candidates, a shielding area candidate whose representative straight line is not determined as an outlier is determined as a shielding area. If the representative straight lines of all the shielding area candidates are determined as outliers, the shielding area candidate having the closest distance from the average position of the representative straight lines in the past shielding area detection is determined as the shielding area, and To present an “overhead position error” alert.
Also, the candidate area classification unit 1502 sets a shielding area candidate that has not been determined to be a shielding area as an abnormal area, and sends it to the abnormal area classification unit 1503.

  The abnormal region classification unit 1503 receives the wear amount from the shielding region correction unit 204 (the amount of wear of the sliding plate corrected by the shielding region correction unit 204) and the abnormal region from the candidate region classification unit 1502, and performs a determination process. Do. If it is determined that the wear amount in the abnormal region is greater than the wear amount in the peripheral region of the abnormal region (that is, it is determined that the abnormal region is worn more than the peripheral region), it is determined that a defect has occurred, A “missing” alert to the person. On the other hand, if it is determined that the amount of wear in the abnormal region is not larger than the amount of wear in the peripheral region of the abnormal region (that is, it is determined that the abnormal region is not worn more than the peripheral region) It is determined that there is an “attachment” alert to the worker.

Thereby, even when an area other than the shielding area has been detected as a shielding area candidate, it can be detected as an abnormality and notified to the operator, which is preferable.
Here, the sliding plate may be damaged due to a separation line during traveling, contact with flying objects, or the like. When a defect of a certain size or larger is generated, there is a possibility that a defect such as abrupt wear of the part progresses due to the defective part or an overhead wire is cut. Therefore, in addition to detecting the amount of wear, by detecting the defect state, more accurate information can be provided to the operator as information regarding the replacement determination.

In each of the above-described embodiments, the configuration and the like illustrated in the accompanying drawings are merely examples, and are not limited thereto, and can be appropriately changed within the scope of the effects of the present invention. is there. In addition, various modifications can be made without departing from the scope of the object of the present invention.
For example, the measurement target is not limited to the sliding plate and can be changed as appropriate.
Further, the shielding object is not limited to the overhead line C and can be changed as appropriate. Note that the shielding object may or may not be in contact with the measurement target.

In addition, a program (wear amount measurement program) for realizing the function of the measurement device 100 according to the present invention is recorded on a computer-readable recording medium, and the computer reads and executes this program to perform measurement processing. You may comprise.
Examples of the computer-readable recording medium include a magnetic disk, a magneto-optical disk, a BD-ROM, a DVD-ROM, and a CD-ROM. In addition, the recording medium dynamically holds a program for a short time, such as a communication line when transmitting a program via a communication line such as a network or a telephone line, and a server or client in that case Such as a volatile memory inside a computer system, which holds a program for a certain period of time. The program may be for realizing a part of the functions described above, and may be configured to be realized in combination with the program already recorded in the computer.

100 Measuring device (wear amount measuring device)
101 Imaging unit (imaging means)
103 Display unit (presentation means)
104 Storage unit (storage means)
202 Wear amount calculation unit (wear amount calculation means)
203, 1501 Shielding area detecting unit (shielding area detecting means)
204 Shielding area correction unit (shielding area correction means)
205 Display data generation unit (presentation data generation means)
901 Smoothing processing unit (smoothing processing means)
1301 Shielding area resetting unit (shielding area resetting means)
C overhead line P intersection

Claims (9)

A wear amount measuring device that measures the wear amount of the measurement target in a state where the measurement target is shielded by a predetermined shielding object,
An imaging means for acquiring a plurality of captured images;
Wear amount calculating means for calculating the wear amount of the measurement object from the plurality of captured images;
A shielding area detecting means for detecting an area where the measurement target is shielded by the shielding object from the captured image, and setting the detected area as a shielding area;
By interpolating the wear amount of the shielding area, shielding area correction means for correcting the wear amount calculated by the wear amount calculation means;
Presenting data generating means for generating presenting data for presenting the wear amount to an operator;
Presenting means for presenting the amount of wear of the measurement object based on the presentation data,
The shielding region correction means interpolates the wear amount of the shielding region from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated by the wear amount calculation unit,
The wear data measuring device characterized in that the presentation data generating means generates presentation data in which the interpolated wear amount and the non-interpolated wear amount are presented in an identifiable manner.   The shielding area detecting means detects a plurality of straight lines from the captured image by straight line detection processing, determines a representative straight line from the plurality of straight lines, and sets a shielding area based on the representative straight line. The wear amount measuring apparatus according to claim 1.   The presentation data generating means generates presentation data that presents at least one of a wear distribution of the entire measurement target, a maximum wear position, and a wear amount at the position. The wear amount measuring apparatus according to claim 2.   When the maximum wear position is within the shielding area, the presentation data generating means determines the maximum wear position and the wear amount at the position, and the maximum wear position and the wear amount at the position other than the shield area. The wear amount measuring apparatus according to claim 3, wherein presentation data is generated so as to be presented. The shielding area correction means includes
The intersection of the first straight line obtained by linearly approximating the wear amount change of one adjacent region adjacent to the shielding region and the second straight line obtained by approximating the wear amount change of the other adjacent region by a straight line Find the position of
When the estimated wear amount at the position of the intersection is not larger than the wear amount of the adjacent region, the wear amount of the shielding region is interpolated by a linear interpolation method,
The wear amount of the shielding region is interpolated by an interpolation method other than a linear interpolation method when the estimated wear amount at the position of the intersection is larger than the wear amount of the adjacent region. The wear amount measuring apparatus according to any one of Items 4 to 5. A smoothing processing means for performing a smoothing process on the wear amount distribution data calculated by the wear amount calculation means;
The smoothing processing unit corrects the wear amount calculated by the wear amount calculation unit by interpolating the wear amount of the shielding region from the wear amount of the adjacent region as the smoothing processing, and then performs the correction. The wear amount measuring apparatus according to claim 1, wherein the wear amount distribution data is smoothed. Storage means for storing a shielding area detection result by the shielding area detection means;
A shielding area resetting means for resetting the shielding area,
The shielding area resetting means resets the shielding area based on a shielding area detection result from the shielding area detection means and a past shielding area detection result stored in the storage means. The wear amount measuring apparatus according to any one of claims 1 to 6. A wear amount measuring method for measuring a wear amount of a measurement target in a state where the measurement target is shielded by a predetermined shielding object,
An imaging step of acquiring a plurality of captured images;
A wear amount calculating step of calculating a wear amount of the measurement object from the plurality of captured images;
A shielding region detection step of detecting a region where the measurement target is shielded by the shielding object from the captured image, and setting the detected region as a shielding region;
By interpolating the amount of wear of the shielding area, a shielding area correction step for correcting the wear amount calculated in the wear amount calculation step;
A presentation data generating step for generating presentation data for presenting the wear amount to an operator;
A presentation step of presenting the wear amount of the measurement object based on the presentation data;
In the shielding region correction step, the wear amount of the shielding region is interpolated from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated in the wear amount calculation step,
In the presenting data generation step, the wear amount measuring method is characterized in that the presenting data is generated so that the interpolated wear amount and the non-interpolated wear amount are presented in an identifiable manner. In a state where the measurement target is shielded by a predetermined shielding object, a computer that measures the wear amount of the measurement target,
An imaging step of acquiring a plurality of captured images;
A wear amount calculating step of calculating a wear amount of the measurement object from the plurality of captured images;
A shielding region detection step of detecting a region where the measurement target is shielded by the shielding object from the captured image, and setting the detected region as a shielding region;
Shielding region correction that corrects the calculated wear amount by interpolating the wear amount of the shielding region from the wear amount of the adjacent region adjacent to the shielding region among the wear amounts calculated in the wear amount calculation step. Steps,
A presentation data generation step for generating data such that the interpolated wear amount and the non-interpolated wear amount are identifiable as presentation data for presenting the wear amount to an operator,
Based on the presentation data, a presentation step for presenting the amount of wear of the measurement target;
Wear amount measurement program to execute.

Images