Trolley wire inspection device and trolley wire inspection method

Abstract

Provided are a trolley wire inspection device and a trolley wire inspection method for accurately detecting a worn region of a trolley wire. A line sensor image generation unit 30 generates a line sensor image from an image captured by a line sensor 22. A worn region extraction image generation unit 32: extracts a worn region of a trolley wire by performing image processing in accordance with a plurality of image processing execution procedures M registered in an image processing execution procedure storage unit 33; corrects the worn region by scanning outward from the extracted worn region and setting a boundary of the worn region at positions where the brightness value falls to or below a previously set brightness value; and generates a plurality of worn region extraction images corresponding respectively to the plurality of image processing execution procedures M. A worn region extraction image evaluation unit 34 selects a worn region extraction image with the highest evaluation value, from among the plurality of worn region extraction images. A trolley wire deviation calculation unit 35 and a trolley wire residual diameter calculation unit 36 calculate the deviation and the residual diameter of the trolley wire on the basis of the selected worn region extraction image.

Description

Contact wire inspection device and contact wire inspection method

[0001] The present invention relates to a trolley wire inspection device and a trolley wire inspection method.

[0002] When electric railway vehicles travel on tracks, they are powered by electricity supplied from contact wires installed above the tracks via current collectors such as pantographs. Each time an electric railway vehicle passes, the current collector slides against the underside of the contact wire. As a result, with continued operation of an electric railway vehicle, the contact wire gradually wears and eventually breaks. Therefore, a wear limit is set for contact wires, and if the remaining diameter of the contact wire falls below a controlled value, the contact wire is replaced with a new one. Meanwhile, because the contact points of the current collectors also wear, the contact wire is installed with a zigzag offset perpendicular to the rail to prevent the contact points from concentrating in one place, and the amount of this offset is also controlled. Manual inspection and measurement of contact wires requires a great deal of effort.

[0003] For example, Patent Document 1 discloses an automatic inspection device that includes a light that illuminates a worn area located below the trolley wire above an electric railway vehicle and a line sensor that captures an image of the worn area of ​​the trolley wire illuminated by the light (the sliding surface where the pantograph contacts). More specifically, the line sensor is installed with its scanning line facing upward and crossing the trolley wire, and images captured by the line sensor are arranged in chronological order to generate a line sensor image. Then, image processing is applied to the line sensor image, and known data related to the specifications of the trolley wire, such as its height and thickness, are used to calculate the deflection and remaining diameter of the trolley wire.

[0004] Patent No. 5287177

[0005] However, in the above-mentioned device, there may be differences in the brightness of the worn area of ​​the trolley wire in the line sensor image due to lighting, the condition of the worn area of ​​the trolley wire, the shooting environment, etc., which results in the problem that the worn area cannot be accurately acquired.

[0006] Therefore, an object of the present invention is to provide a trolley wire inspection device and a trolley wire inspection method that can accurately detect worn areas of a trolley wire.

[0007] In order to solve the above problems, the present invention employs the following means: That is, a trolley wire inspection device according to a first aspect of the present invention is a trolley wire inspection device that includes a line sensor that captures an image of a trolley wire, and inspects the trolley wire based on an image captured by the line sensor as an input image, the trolley wire inspection device including a line sensor image generation unit that arranges the input images in time series to generate a line sensor image, an image processing execution procedure storage unit that registers a plurality of execution orders as image processing execution procedures when sequentially executing a plurality of image processing functions on the line sensor image, and an image processing execution procedure storage unit that executes the plurality of image processing functions using the line sensor image as an input in accordance with each of the plurality of image processing execution procedures, thereby detecting the trolley wire. a wear area extraction image generation unit that extracts a wear area of ​​the trolley wire, scans outward from the extracted wear area of ​​the trolley wire, and corrects the wear area by setting the position where the brightness value becomes equal to or lower than a predetermined brightness value as the boundary of the wear area, thereby generating a plurality of wear area extraction images corresponding to each of the plurality of image processing execution procedures; a wear area extraction image evaluation unit that calculates an evaluation value for each of the plurality of wear area extraction images and selects the wear area extraction image with the highest evaluation value; and a trolley wire inspection unit that calculates either the remaining diameter or the deviation of the trolley wire or both based on the selected wear area extraction image with the highest evaluation value.

[0008] In addition, the trolley wire inspection device of the second invention is characterized in that each of the multiple image processing execution procedures is registered to be executed in this order: zero or more contrast adjustment processes, zero or more background / noise removal processes, one or more binarization processes, and zero or more interpolation processes.

[0009] In addition, the trolley wire inspection device of the third invention is characterized in that each of the multiple image processing execution procedures is stored with a priority associated with it, and when the same evaluation value is calculated for multiple wear area extraction images, the wear area extraction image evaluation unit selects the wear area extraction image corresponding to the image processing execution procedure with the highest priority as the wear area extraction image with the highest evaluation value.

[0010] In addition, the trolley wire inspection device of the fourth invention is characterized in that the wear area extraction image evaluation unit calculates the number of wear areas for each of the multiple wear area extraction images, and calculates the evaluation value so that the evaluation value is high when the difference between the number of wear areas and the actual number of trolley wires is small.

[0011] In addition, the trolley wire inspection device of the fifth invention is characterized in that the wear area extraction image evaluation unit calculates a trolley wire likelihood, which is an indicator that the wear area has image features that are similar to the trolley wire, for each of the multiple wear area extraction images, and calculates the evaluation value so that the evaluation value is high when the trolley wire likelihood is high.

[0012] In addition, the trolley wire inspection device of the sixth invention is characterized in that the image processing execution procedure memory unit registers the image processing execution procedure corresponding to each of a plurality of different environments when the image is captured by the line sensor, and further includes an environment determination unit that determines the environment in which the input image was captured based on the line sensor image, and the wear area extraction image generation unit generates the wear area extraction image according to the image processing execution procedure corresponding to the determined environment.

[0013] In addition, a trolley wire inspection method according to a seventh invention is a trolley wire inspection method that uses an image captured by a line sensor that images a trolley wire as an input image and inspects the trolley wire based on the input image, and is characterized by including: arranging the input images in chronological order to generate a line sensor image; when sequentially executing a plurality of image processing functions on the line sensor image, the execution orders are registered as multiple image processing execution procedures, and extracting a worn area of ​​the trolley wire by executing the multiple image processing functions using the line sensor image as an input according to each of the multiple image processing execution procedures; correcting the worn area by scanning outward from the extracted worn area of ​​the trolley wire and setting the position where the brightness value is below a predetermined brightness value as the boundary of the worn area, and generating a plurality of wear area extraction images corresponding to each of the multiple image processing execution procedures; calculating an evaluation value for each of the multiple wear area extraction images and selecting the wear area extraction image with the highest evaluation value; and calculating either or both of the remaining diameter and deviation of the trolley wire based on the selected wear area extraction image with the highest evaluation value.

[0014] According to the present invention, even if a difference in brightness occurs in the worn area, the worn area of ​​the trolley wire can be accurately detected.

[0015] FIG. 1 is an explanatory diagram showing the running environment of an electric railway vehicle equipped with a trolley wire inspection device according to an embodiment of the present invention. FIG. 2 is a block diagram showing the functional configuration of the trolley wire inspection device according to the embodiment. FIG. 3 is a schematic diagram showing an example of a line sensor image generated based on an image captured by a line sensor of the trolley wire inspection device according to the embodiment. FIG. 4 is a schematic diagram showing an example of a worn area extraction image temporarily acquired by the trolley wire inspection device according to the embodiment. FIG. 5 is a schematic diagram showing an example of a worn area extraction image finally acquired by the trolley wire inspection device according to the embodiment. FIG. 6 is an explanatory diagram of an image processing execution procedure storage unit of the trolley wire inspection device according to the embodiment. FIG. 7(a) is an explanatory diagram of a trolley wire deviation calculation unit of the trolley wire inspection device, and FIG. 7(b) is an explanatory diagram of a trolley wire remaining diameter calculation unit of the trolley wire inspection device. FIG. 8 is a flowchart for explaining the operation of the trolley wire inspection method using the trolley wire inspection device according to the embodiment.

[0016] An embodiment of the present invention will now be described with reference to the accompanying drawings. Fig. 1 is an explanatory diagram showing the traveling environment of an inspection vehicle 1 equipped with a contact wire inspection device 20 according to this embodiment and performing contact wire inspection. In Fig. 1, the inspection vehicle 1 travels on a pair of tracks 2 laid on the ground. A plurality of utility poles 3 are erected along the tracks 2 at intervals. The utility poles 3 are provided with beams 5 and curved pulleys 6. Above the beams 5, a feeder line 4, which is a power line for supplying power to the inspection vehicle 1, extends along the direction R of the tracks 2 and is supported by the beams 5. Below the beams 5 and curved pulleys 6, a suspension line 7 for suspending a contact wire 9 (described below) is supported by the beams 5 and curved pulleys 6 so as to also extend along the direction R of the tracks 2. A plurality of hangers 8 are suspended from the suspension line 7 at approximately regular intervals in the direction R of the tracks 2.

[0017] The contact wire 9 is suspended from these hangers 8 with a constant tension, and is provided below the suspension wire 7 so as to be approximately parallel to the suspension wire 7. Power is supplied to the contact wire 9 from the feeder line 4 via a power feeder branch line (not shown). A current collector 1b such as a pantograph is provided on the top surface 1a of the inspection vehicle 1, and power is supplied to the inspection vehicle 1 from the contact wire 9 when the current collector 1b comes into contact with the contact wire 9 while the inspection vehicle 1 is traveling.

[0018] For example, one or two trolley wires 9 are provided running parallel to a pair of tracks 2. To prevent a section from being left unsupplied with power when the trolley wire 9, which serves as the power supply source, transitions to the next adjacent trolley wire 9 in the direction R of extension of the tracks 2 while an electric railway vehicle such as the inspection vehicle 1 is running, the trolley wire 9 is provided so that its end overlaps with another adjacent trolley wire 9 along the direction R of extension of the tracks 2. For this reason, in this embodiment, there may be a section where up to four trolley wires 9 overlap with each other for a pair of tracks 2. In addition, when photographing a branch point of the trolley wire 9 corresponding to a track branch, a larger number of trolley wires 9 than in a normal section may be photographed.

[0019] If the contact wire 9 were installed parallel to the tracks 2, the contact area of ​​the current collector 1b with the contact wire 9 would be limited, which could result in uneven wear and damage to that limited area of ​​the current collector 1b. To prevent this, the contact wire 9 is installed so that it gently zigzags along the direction R of extension of the tracks 2. The deviation of the contact wire 9, which is the deviation of the contact wire 9 to the left or right with respect to the center between the pair of tracks 2 caused by this meandering, is strictly controlled.

[0020] Each time an electric railway vehicle, such as the inspection vehicle 1, passes, the current collector 1b slides against the underside of the trolley wire 9. As a result, with continued operation of the electric railway vehicle, the trolley wire 9 gradually wears and eventually breaks. Therefore, a wear limit is set for the trolley wire 9, and when the remaining diameter of the trolley wire 9 falls below a control value, the trolley wire 9 is replaced with a new one.

[0021] The trolley wire inspection device 20 in this embodiment inspects the trolley wire 9 by measuring the remaining diameter and deviation of the trolley wire 9. The trolley wire inspection device 20 includes a light 21, a line sensor 22, and a control device 23. The light 21 is provided to irradiate light upward onto the upper surface 1a of the inspection vehicle 1. When the trolley wire 9 is imaged by the line sensor 22, which will be described next, the worn area on the underside of the trolley wire 9, which has been formed as a flat surface due to wear of the trolley wire 9 caused by the sliding of the current collector 1b, is imaged so that it reflects the light of the light 21 and appears as a bright area.

[0022] The line sensor 22, like the lighting 21, is provided on the upper surface 1a of the inspection vehicle 1. The line sensor 22 is a camera that captures an image composed of one pixel in the vertical direction and multiple pixels in the horizontal direction, for example, 8192 pixels. In this embodiment, the line sensor 22 captures a grayscale image, so each pixel has one luminance value.

[0023] The line sensor 22 is disposed so as to face vertically upward and so that the direction 22b of the scanning line 22a is perpendicular to the extending direction R of the track 2 and is the same as the extending direction of the sleepers (not shown). This allows the scanning line 22a of the line sensor 22 to cross the trolley wire 9. The line sensor 22 continuously captures images of the trolley wire 9 at short time intervals while the inspection vehicle 1 is traveling. The images captured by the line sensor 22 are transmitted as input images to the control device 23. The control device 23 is, for example, an information processing device such as a personal computer. The control device 23 is mounted on the inspection vehicle 1.

[0024] 2 is a block diagram showing the functional configuration of the trolley wire inspection device 20 according to this embodiment. In Fig. 2, the control device 23 includes a line sensor image generating unit 30, an environment determining unit 31, a worn area extraction image generating unit 32, an image processing execution procedure storing unit 33, a worn area extraction image evaluating unit 34, a trolley wire deflection calculating unit (trolley wire inspection unit) 35, and a trolley wire remaining diameter calculating unit (trolley wire inspection unit) 36.

[0025] The line sensor image generating unit 30 receives the input image from the line sensor 22, and arranges it in time series vertically, for example, 1000 lines, to generate a line sensor image.

[0026] 3 is a schematic diagram showing an example of a line sensor image 50 generated based on an image captured by the line sensor of the trolley wire inspection device according to this embodiment. In the line sensor image 50, the horizontal direction X is the direction 22b of the scanning line 22a of the line sensor 22, and the vertical direction Y is the time series direction, i.e., the direction in which the input images are arranged.

[0027] In the line sensor image 50 shown in Figure 3, the trolley wire 9 is captured in the foreground. When new, the trolley wire 9 has a substantially circular cross section, and its underside has been worn away by the sliding of the current collector 1b, leaving a flat wear area 9a. The wear area 9a is illuminated by light from the illumination 21, and is therefore captured brightly. On both sides of the wear area 9a, the surface 9b of the trolley wire 9 is captured, which curves outward from the widthwise end of the wear area 9a and continues upward. In the line sensor image 50 shown in Figure 3, the portion of the trolley wire 9 where it is bent by the curved pulling fitting 6 is captured. Furthermore, brightness differences may occur in the wear area 9a due to lighting conditions, the state of the wear area of ​​the trolley wire, the imaging environment, and other factors, resulting in dark areas 9c and 9d with partially lower brightness.

[0028] Behind the contact wire 9, the overhead catenary wire 7 is imaged. Further behind the contact wire 7, the feeder wire 4 and the beam 5 and curved pull fitting 6 that support it are imaged. The beam 5 and curved pull fitting 6 are imaged thinner than they actually are due to the influence of the imaging interval of the line sensor 22. The sky 10 is imaged as the background to the contact wire 9, overhead catenary wire 7, feeder wire 4, beam 5, and curved pull fitting 6. As this line sensor image 50 was taken in bright daylight, the sky 10 is displayed brightly with a high luminance value.

[0029] The line sensor image generating unit 30 generates such a line sensor image 50 and transmits it to the wear area extraction image generating unit 32 .

[0030] The environment determination unit 31 determines the environment in which the input image was captured based on the line sensor image 50 generated by the line sensor image generation unit 30. The environment determination unit 31 determines five types of environments: night or tunnel, dark daytime, bright daytime, the moment when entering a tunnel in daytime, and other situations. To make this determination, the environment determination unit 31 calculates a histogram of the line sensor image 50 and calculates the average value, the mode, the second most frequent luminance value, and the third most frequent luminance value. Then, the environment determination unit 31 compares each of the calculated values ​​with a preset night determination threshold, dark daytime determination threshold, and bright daytime determination threshold as follows to determine the environment.

[0031] The environment determination unit 31 determines that the environment corresponding to the line sensor image 50 is night or a tunnel when all of the following determination formulas are simultaneously satisfied: 0≦average value≦night determination threshold 0≦mode≦night determination threshold 0≦second most frequently occurring luminance value≦night determination threshold 0≦third most frequently occurring luminance value≦night determination threshold

[0032] The environment determination unit 31 determines that the environment corresponding to the line sensor image 50 is dark daytime when all of the following determination formulas are simultaneously satisfied: Night determination threshold < average value ≦ dark daytime determination threshold Night determination threshold < mode ≦ dark daytime determination threshold Night determination threshold < second most frequent luminance value ≦ dark daytime determination threshold Night determination threshold < third most frequent luminance value ≦ dark daytime determination threshold

[0033] The environment determination unit 31 determines that the environment corresponding to the line sensor image 50 is bright daytime when all of the following determination formulas are simultaneously satisfied: Bright daytime determination threshold < average value Bright daytime determination threshold < mode Bright daytime determination threshold < second most frequent luminance value Bright daytime determination threshold < third most frequent luminance value

[0034] The environment determination unit 31 determines that the environment corresponding to the line sensor image 50 is daytime and the moment when the vehicle enters a tunnel when all of the following determination formulas are simultaneously satisfied: Night determination threshold < average value ≦ maximum brightness value (e.g., 255) 0 ≦ most frequent value ≦ night determination threshold 0 ≦ second most frequent brightness value ≦ night determination threshold 0 ≦ third most frequent brightness value ≦ night determination threshold

[0035] If the environment does not fall into any of the above-mentioned environments, the environment determination unit 31 determines that the environment is other. The environment determination unit 31 transmits the determined environment to the wear area extraction image generation unit 32.

[0036] The wear area extraction image generation unit 32 receives the line sensor image 50 from the line sensor image generation unit 30 and the judgment result (environment) from the environment judgment unit 31, and performs various image processing functions on the line sensor image 50 to extract the wear area 9a of the trolley wire 9 and generate a wear area extraction image.

[0037] The wear area extraction image generation unit 32 includes an image processing unit 40 and a post-processing unit 41. The image processing unit 40 is configured to selectively execute various image processing functions. The image processing unit 40 includes a contrast adjustment processing unit 40A, a background / noise removal processing unit 40B, a binarization processing unit 40C, an interpolation processing unit 40D, and a wear area correction unit 40E.

[0038] The contrast adjustment processing unit 40A is configured to be able to selectively execute one or more image processing functions for the purpose of adjusting the gradation of an image. Examples of contrast adjustment processing include gamma correction processing, which corrects the gradation of an image to an appropriate curve according to a gamma value, and processing that adjusts the gradation by normalizing brightness values. The contrast adjustment processing included in the contrast adjustment processing unit 40A is not limited to the above.

[0039] The background / noise removal processor 40B is configured to selectively execute one or more image processing functions for the purpose of removing noise and objects other than overhead lines, such as buildings captured in the background. For example, the background / noise removal process can be GSTH (grayscale top-hat) processing, which shrinks and expands a grayscale image to open it, and then subtracts the original image from which the expansion and contraction is performed. Note that the background / noise removal process included in the background / noise removal processor 40B is not limited to the one described above.

[0040] The binarization processing unit 40C is configured to selectively execute one or more image processing functions for converting an image with multiple gradations into two gradations, for example, black and white, and extracting only the worn region 9a. For example, the binarization process can be a discriminant analysis binarization process that generates a histogram of brightness values ​​for the image and determines a binarization threshold value according to the image so as to maximize the variance ratio between the intra-class variance and the inter-class variance for each of the background and the worn region 9a. The binarization processes included in the binarization processing unit 40C are not limited to those described above.

[0041] The interpolation processing unit 40D is configured to be able to selectively execute one or more image processing functions for the purpose of interpolating the shape of the wear area 9a by connecting together an image in which the binarization processing unit 40C has performed binarization processing and an area assumed to be the wear area 9a has been extracted, in cases where an area originally assumed to be a single wear area 9a has been divided into multiple areas.

[0042] The interpolation process may be a closing process in which an image is expanded or contracted in the horizontal direction X to join areas that are separated and close together in the horizontal direction X, or a corrugation interpolation process in which areas that are separated in stripes or waves in the vertical direction Y are joined together. Note that the interpolation process included in the interpolation processing unit 40D is not limited to the above.

[0043] 4 is a schematic diagram showing an example of a wear area extraction image temporarily acquired by the trolley wire inspection device according to this embodiment, which is a wear area extraction image 50A processed by the interpolation processing unit 40D as described above. In the wear area extraction image 50A, as shown in FIG. 3, due to lighting, the state of the wear area 9a of the trolley wire 9, the shooting environment, etc., brightness differences may occur in the wear area 9a, resulting in dark areas 9c and 9d that are lower in brightness than other areas. In other words, in the wear area extraction image 50A processed by the interpolation processing unit 40D, the dark areas 9c and 9d are not detected as wear areas 9a, and therefore the wear area 9a cannot be accurately detected.

[0044] As shown in Figure 4, in the wear area extraction image 50A processed by the interpolation processing unit 40D, only the bright wear area 9a is extracted. Therefore, in this embodiment, the wear area extraction image 50A processed by the interpolation processing unit 40D is corrected so that the dark areas 9c and 9d are detected as wear areas 9a. The wear area correction unit 40E uses a raster scan to search outward from the position of the wear area extracted in the wear area 9a extraction process for each line in the vertical direction of the image, and determines the position where the brightness value is equal to or less than a predetermined brightness value as the boundary between the sliding surface and the non-sliding surface, i.e., the boundary of the wear area 9a.

[0045] Figure 5 is a schematic diagram showing an example of a wear area extraction image finally acquired by the trolley wire inspection device according to this embodiment. As a result of the above-described correction, the dark areas 9c and 9d shown in Figure 4 are detected as wear areas 9a, and the wear areas 9a are accurately detected, as shown in Figure 5. The wear area correction unit 40E transmits the corrected wear area extraction image 50B to the post-processing unit 41 together with the number of corresponding wear areas 9a, length information including the start and end coordinates of each wear area 9a in the vertical direction Y, and information on the image processing execution procedure (or processing pattern) M corresponding to the wear area extraction image.

[0046] In this way, the wear area extraction image generation unit 32 accurately extracts the wear area of ​​the trolley wire 9 by executing image processing functions using the line sensor image 50 as input in accordance with each of the multiple image processing execution procedures M using the image processing unit 40 and post-processing unit 41, and generates multiple wear area extraction images 50B corresponding to each of the multiple image processing execution procedures M.

[0047] Each image processing function included in the contrast adjustment processing unit 40A, background / noise removal processing unit 40B, binarization processing unit 40C, interpolation processing unit 40D, and wear area correction unit 40E is executed in accordance with a processing pattern (image processing execution procedure) M, which is the execution order for executing each image processing function, registered in the image processing execution procedure memory unit 33.

[0048] 6 is an explanatory diagram of the image processing execution procedure storage unit 33 of the trolley wire inspection device of this embodiment. In FIG. 6, the image processing execution procedure storage unit 33 includes a processing storage unit 33a, a parameter set storage unit 33b, and a processing pattern registration unit 33c.

[0049] The processing storage unit 33a stores the image processing functions executed by the contrast adjustment processing unit 40A, background / noise removal processing unit 40B, binarization processing unit 40C, interpolation processing unit 40D, and wear area correction unit 40E, which have already been described. The processing storage unit 33a in FIG. 6 stores X image processing functions PR1 to PRX, which are included in any of the processing units 40A, 40B, 40C, 40D, and 40E.

[0050] The parameter set storage unit 33b stores parameter sets that can be used during actual execution of each of the image processing functions PR1 to PRX stored in the processing storage unit 33a. The parameter set storage unit 33b in Fig. 6 stores Y types of parameter sets, PS1 to PSY, that are used in any one or more of the X image processing functions PR1 to PRX stored in the processing storage unit 33a.

[0051] The processing pattern registration unit 33c stores a plurality of processing patterns M for executing the above-mentioned image processing functions when processing the line sensor image 50. In the processing pattern registration unit 33c in FIG. 6, L processing patterns M1 to ML are stored.

[0052] 6 focuses on the first processing pattern M1 of these L processing patterns M1 to ML. Processing pattern M1 is registered to execute Z image processing functions P1 to PZ in order. Here, image processing function P1 in processing pattern M1 references image processing function PR1 in processing storage unit 33a and parameter set PS2 in parameter set storage unit 33b. This indicates that image processing function P1 in processing pattern M1 is actually executed by applying parameter set PS2 to image processing function PR1 stored in processing storage unit 33a.

[0053] Furthermore, in the image processing function P2 that is executed second in the first processing pattern M1, only the image processing function PRX stored in the processing storage unit 33a is referenced, and the parameter set in the parameter set storage unit 33b is not referenced. In this way, when the image processing functions PR1 to PRX stored in the processing storage unit 33a are registered in the processing pattern M, the parameter set in the parameter set storage unit 33b does not necessarily need to be associated with and referenced.

[0054] Although detailed description will be omitted, similar to the processing pattern M1, the processing patterns M2 to ML are configured by expressing image processing functions that are executed by referring to the processing storage unit 33a and the parameter set storage unit 33b.

[0055] In each of the processing patterns M1 to ML stored in the processing pattern registration unit 33c, the number of image processing functions to be executed is not fixed but variable, i.e., the number of image processing functions to be executed in each of the processing patterns M1 to ML is basically different from one another.

[0056] In this way, the processing pattern M is configured by registering a plurality of ordered image processing functions or combinations of image processing functions and parameter sets used in the image processing functions. In this way, the processing pattern M can be said to be an image processing execution procedure M in which the execution order of each image processing function when processing the line sensor image 50 is registered together with a parameter set that indicates how each image processing function is actually executed. Hereinafter, the processing pattern M will be referred to as the image processing execution procedure M.

[0057] As described above, each image processing function is classified into a process for which the purpose is one of contrast adjustment, background / noise removal, binarization, and interpolation. In each image processing execution procedure M, the image processing functions are registered so that they are executed in the order of this processing classification. For example, since it is basically meaningless to execute contrast adjustment after executing binarization, an image processing execution procedure M in which an image processing function included in the contrast adjustment processing unit 40A is executed after executing an image processing function included in the binarization processing unit 40C is basically not registered.

[0058] Furthermore, to extract the worn area 9a, at least the binarization process must be performed. In other words, the image processing execution procedure M registers an order of image processing functions such that the image processing function included in the binarization processing unit 40C is executed at least once, and the image processing functions included in the other processing units 40A, 40B, 40D, and 40E are executed as needed, i.e., zero or more times. In this way, each of the multiple image processing execution procedures M is registered with zero or more contrast adjustment processes, zero or more background / noise removal processes, one or more binarization processes, and zero or more interpolation processes to be executed in this order.

[0059] Furthermore, the order of the image processing functions included in each of the processing units 40A, 40B, 40C, 40D, and 40E may be registered so that each of the image processing functions is executed multiple times. For example, the image processing execution procedure M may be constructed so that in the interpolation processing unit 40D, the closing process joins together areas that are separated in the horizontal direction X, and then the corrugation interpolation process joins together areas that are separated in the vertical direction Y.

[0060] Alternatively, the same image processing function may be registered in the image processing execution procedure M so that it is executed multiple times with the same parameter set or with different parameter sets, either consecutively or interspersed with the execution of other image processing functions included in the same processing classification.

[0061] A plurality of image processing execution procedures M are registered so that all combinations of processing procedures can be realized between the image processing functions in each of the processing units 40A, 40B, 40C, 40D, and 40E. Each of these image processing execution procedures M has different accuracy in extracting the wear area 9a and different suitability for the background of the line sensor image 50 and other conditions. Therefore, a priority is associated with each of the image processing execution procedures M and stored. For example, an image processing execution procedure M that is not significantly affected by the brightness value of the background and can consistently achieve a certain level of accuracy in extracting the wear area 9a may be assigned a high priority. Thus, the priority is set higher for an image processing execution procedure M that is considered to have higher accuracy in extracting the wear area 9a.

[0062] As described above, the image processing unit 40 executes each of the image processing execution procedures M, generates a processed image corresponding to each image processing execution procedure M, and transmits the processed image to the post-processing unit 41 .

[0063] The post-processing unit 41 receives the processed image from the image processing unit 40, performs edge extraction to extract wear areas 9a, and, if multiple wear areas 9a are extracted in the processed image, calculates the length of each wear area 9a in the vertical direction Y. As described above, in this embodiment, up to four overlapping trolley wires 9 may be present. That is, up to four trolley wires 9 may be captured in a single line sensor image 50. Therefore, if five or more wear areas 9a are extracted, the post-processing unit 41 treats the four longest areas as wear areas 9a and considers any other areas shorter than these as not wear areas 9a. The post-processing unit 41 transmits the image after edge extraction as a wear area extraction image 50A to the wear area extraction image evaluation unit 34, along with the number of corresponding wear areas 9a, length information for each wear area 9a in the vertical direction Y, including the start and end coordinates, and information on the image processing execution procedure M corresponding to the wear area extraction image.

[0064] The wear area extraction image evaluation unit 34 receives the corrected wear area extraction images 50B corresponding to each of the multiple image processing execution procedures M and related information, calculates an evaluation value for each of the received multiple wear area extraction images 50B, and selects the wear area extraction image with the highest evaluation value. The wear area extraction image generation unit 32 associates each wear area extraction image with a determination of how many wear areas 9a are captured in the wear area extraction image and transmits the result to the wear area extraction image evaluation unit 34. For each wear area extraction image, the wear area extraction image evaluation unit 34 compares the number of wear areas 9a in the wear area extraction image with the number of trolley wires 9 at the actual site where the wear area extraction image was captured, and calculates an evaluation value for the wear area extraction image.

[0065] The evaluation value of the wear area extraction image is determined by using the fact that the number of contact wires in the image is known from pre-registered facility information and calculating the cost for each time series (line) of images, and then using either cost evaluation (the lower the cost, the higher the evaluation) to adopt the wear area extraction image with the lowest cost processing pattern, or likelihood evaluation (the higher the likelihood, the higher the evaluation) which is an index indicating that the wear area 9a has image features similar to the contact wire 9 for each of the multiple wear area extraction images. For details of cost evaluation and likelihood evaluation, please refer to Japanese Patent No. 7196806.

[0066] The wear area extraction image evaluation unit 34 calculates the center of gravity coordinates and wear surface width of each wear area 9a for the wear area extraction image with the highest evaluation value based on cost evaluation or likelihood evaluation, and transmits them to the trolley wire deviation calculation unit 35 and the trolley wire remaining diameter calculation unit 36 ​​along with the wear area extraction image with the highest evaluation value.

[0067] The trolley wire deviation calculation unit 35 receives the wear area extraction image selected as the one with the highest evaluation value and calculates the deviation of the trolley wire 9 based on this. Figure 7(a) is an explanatory diagram of the deviation calculation principle. The deviation D (unit: mm) is expressed by the following equation using the centroid coordinate d (unit: pixel) of the wear area 9a received from the wear area extraction image evaluation unit 34, and pre-set parameters: the distance hs (mm) from the track 2 to the sensor surface 22c of the line sensor 22, the focal length f (mm) of the lens of the line sensor 22, the length s (mm) of the sensor surface 22c of the line sensor 22, the number of pixels p (pixels) of the line sensor 22, and the distance h (mm) from the track 2 to the trolley wire 9 calculated by a measurement device other than the trolley wire inspection device 20.

[0068]

[0069] The trolley wire deviation calculation unit 35 calculates the deviation of the trolley wire 9 as described above and determines whether the trolley wire 9 is located within the allowable deviation range at the actual location corresponding to the wear area extraction image. If the trolley wire 9 is not located within the allowable deviation range, it is determined to be abnormal and recorded.

[0070] The trolley wire remaining diameter calculation unit 36 ​​receives the wear area extraction image selected as the one with the highest evaluation value and calculates the remaining diameter of the trolley wire 9 based on this. Figure 7(b) is an explanatory diagram of the principle of calculating the remaining diameter. In this embodiment, the remaining diameter of the trolley wire 9, i.e., the height of the trolley wire 9 after wear, is calculated as the remaining diameter. Based on the same principle as the trolley wire deviation calculation unit 35, the trolley wire remaining diameter calculation unit 36 ​​calculates the actual wear surface width W (mm) of the trolley wire 9 based on the centroid coordinate d (pixels) and wear surface width w (pixels) of the wear area 9a received from the wear area extraction image evaluation unit 34. The remaining diameter Dr (mm) of the trolley wire 9 is expressed by the following equation using this wear surface width W (mm) and the radius of the trolley wire 9.

[0071]

[0072] The remaining diameter calculation unit 36 ​​calculates the remaining diameter of the trolley wire 9 as described above and determines whether the remaining diameter is below the control value. If the remaining diameter is below the control value, it is determined to be abnormal and records that fact.

[0073] 8 is a flowchart for explaining the operation of the trolley wire inspection method by the trolley wire inspection device 20 according to this embodiment. When the process starts, the line sensor image generating unit 30 arranges, for example, 1,000 lines vertically in chronological order, the input image from the line sensor 22 to generate a line sensor image 50 as shown in FIG. 3 and transmits it to the wear area extraction image generating unit 32. At the same time, the environment determining unit 31 determines the environment in which the input image was captured based on the line sensor image 50 generated by the line sensor image generating unit 30 (step S10).

[0074] Next, in the wear area extraction image generation unit 32, the contrast adjustment processing unit 40A adjusts the gradation of the line sensor image 50 (step S12), the background / noise removal processing unit 40B removes noise and objects other than overhead lines, such as buildings imaged in the background (step S14), and the binarization processing unit 40C converts the image with multiple gradations into two gradations, for example, black and white, and extracts only the wear area 9a (step S16).

[0075] Next, the interpolation processing unit 40D targets the image in which the binarization processing unit 40C has performed binarization processing and extracted the area assumed to be the wear area 9a, and if the area originally assumed to be a single wear area 9a is divided into multiple areas, it connects these together to interpolate the shape of the wear area 9a (step S18).

[0076] Next, the wear area correction unit 40E uses a raster scan to search for the boundary between the sliding surface and the non-sliding surface outward from the position extracted in the extraction process of the wear area 9a for each line in the vertical direction of the image, and by determining the position where the brightness value is below a predetermined brightness value as the sliding surface boundary, corrects the wear area extraction image 50A and detects the accurate wear area 9a (step S20).

[0077] Next, the post-processing unit 41 generates the corrected wear area extraction image 50B, including the number of corresponding wear areas 9a and length information including the start and end coordinates of each wear area 9a in the vertical direction Y, and transmits this to the wear area extraction image evaluation unit 34 together with information regarding the image processing execution procedure M corresponding to the wear area extraction image (step S22).

[0078] Next, the wear area extraction image evaluation unit 34 uses the image after edge extraction from the wear area extraction image generation unit 32 as a wear area extraction image and calculates an evaluation value (likelihood evaluation or cost evaluation) for each of the received multiple wear area extraction images based on the number of corresponding wear areas 9 a, length information including the start and end coordinates of each wear area 9 a in the vertical direction Y, and information on the image processing execution procedure M corresponding to the wear area extraction image (step S24). The generation and evaluation of the wear area extraction images are performed for all image processing execution procedures M stored in the image processing execution procedure storage unit 33.

[0079] Next, it is determined whether the generation and evaluation of wear area extraction images have been performed for all image processing execution procedures M (step S26), and if there are any image processing execution procedures M that have not been performed (NO in step S26), the process proceeds to step S10 and processing for the unexecuted image processing execution procedures M continues.

[0080] On the other hand, if there is no unexecuted image processing execution procedure M (YES in step S26), the wear area extraction image evaluation unit 34 determines the image with the highest evaluation value among all the wear area extraction images as the image in which the wear area 9a is most appropriately extracted (step S28).The wear area extraction image evaluation unit 34 calculates the centroid coordinates and wear surface width of each wear area 9a for the wear area extraction image with the highest evaluation value, and transmits them together with the wear area extraction image with the highest evaluation value to the trolley wire deflection calculation unit 35 and the trolley wire remaining diameter calculation unit 36.

[0081] Next, the trolley wire deflection calculation unit 35 receives the wear area extraction image selected as the one with the highest evaluation value, and calculates the deflection of the trolley wire 9 based on this (step S30). Also, the trolley wire remaining diameter calculation unit 36 ​​receives the wear area extraction image selected as the one with the highest evaluation value, and calculates the remaining diameter of the trolley wire 9 based on this (step S32). Then, the process ends.

[0082] According to the above-described embodiment, the trolley wire inspection device 20 includes a line sensor 22 that captures an image of the trolley wire 9, and detects the trolley wire 9 based on an image captured by the line sensor 22 as an input image. The trolley wire inspection device 20 includes a line sensor image generating unit 30 that generates a line sensor image 50 by arranging the input images in time series, an image processing execution procedure storage unit 33 in which, when sequentially executing a plurality of image processing functions on the line sensor image 50, the execution order of the functions is registered as a plurality of image processing execution procedures M, and the trolley wire 9 is detected by executing the image processing functions using the line sensor image 50 as an input in accordance with each of the plurality of image processing execution procedures M. a wear area extraction image generating unit 32 that extracts a wear area 9a of the trolley wire, scans outward from the extracted wear area of ​​the trolley wire, and corrects the wear area by setting the position where the brightness value becomes equal to or lower than a predetermined brightness value as the boundary of the wear area, thereby generating a plurality of wear area extraction images corresponding to each of a plurality of image processing execution procedures M; a wear area extraction image evaluating unit 34 that calculates an evaluation value for each of the plurality of wear area extraction images and selects the wear area extraction image with the highest evaluation value; a trolley wire deviation calculating unit 35 that calculates the deviation of the trolley wire 9 based on the selected wear area extraction image; and a trolley wire remaining diameter calculating unit 36 ​​that calculates the remaining diameter of the trolley wire 9.

[0083] In addition, the trolley wire inspection method in this embodiment is a trolley wire inspection method that uses an image captured by a line sensor 22 that images the trolley wire 9 as an input image and inspects the trolley wire 9 based on this, and arranges the input images in chronological order to generate a line sensor image 50, and when sequentially executing multiple image processing functions on the line sensor image 50, the execution order is registered as multiple image processing execution procedures M, and the line sensor image 50 is used as input to execute the image processing functions according to each of the multiple image processing execution procedures M to extract a worn area 9a of the trolley wire 9, and correct the worn area 9a by scanning outward from the extracted worn area 9a and setting the position where the brightness value is below a predetermined brightness value as the boundary of the worn area 9a, and generates multiple wear area extraction images corresponding to each of the multiple image processing execution procedures M, calculates an evaluation value for each of the multiple wear area extraction images, selects the wear area extraction image with the highest evaluation value, and calculates both the remaining diameter and deviation of the trolley wire 9 based on the selected wear area extraction image.

[0084] With the above-described configuration, even if there is a difference in brightness in the wear area 9a due to lighting, the condition of the wear area 9a of the trolley wire 9, the shooting environment, etc., the wear area 9a of the trolley wire 9 can be accurately detected, improving the accuracy of extracting the wear area 9a of the trolley wire 9 and also improving the accuracy of calculating the remaining diameter and deviation.

[0085] Furthermore, according to this embodiment, a wear area extraction image is generated for each of the multiple image processing execution procedures M, an evaluation value is calculated for each of these wear area extraction images, the wear area extraction image with the highest evaluation value is selected, and both the remaining diameter and deviation of the trolley wire 9 are calculated based on this. That is, a number of wear area extraction images corresponding to the number of image processing execution procedures M are generated, and from among them, the wear area extraction image most suitable for evaluating the remaining diameter and deviation is selected as the evaluation target for the remaining diameter and deviation. As a result, from among the multiple registered image processing execution procedures M, the processing result of the image processing execution procedure M suitable for processing the line sensor image 50 to be processed is selected as the wear area extraction image.

[0086] In this way, an extracted image of the wear area suitable for calculating the remaining diameter and deviation of the trolley wire 9 can be generated and the remaining diameter and deviation can be measured without the worker having to go through trial and error to select a combination of image processing functions suitable for the line sensor image 50 to be processed, thereby reducing the amount of work required for the worker to select and select image processing functions suitable for the input image.

[0087] Furthermore, according to this embodiment, a priority is associated with each of the multiple image processing execution procedures M and stored, and when the same evaluation value is calculated for multiple wear area extraction images, the wear area extraction image evaluation unit 34 selects the wear area extraction image corresponding to the image processing execution procedure M with the highest priority as the wear area extraction image with the highest evaluation value. Therefore, when the same evaluation value is calculated for multiple wear area extraction images, the wear area extraction image corresponding to the image processing execution procedure M with the highest priority is selected as the wear area extraction image with the highest evaluation value. Therefore, even when there are multiple wear area extraction images with similar evaluation values, the wear area extraction image corresponding to the image processing execution procedure M with the highest priority is selected, making it easier to select a wear area extraction image suitable for evaluating the remaining diameter and deviation.

[0088] Furthermore, according to this embodiment, the wear area extraction image evaluation unit 34 calculates the number of wear areas 9 a for each of the multiple wear area extraction images, and calculates the evaluation value so that the evaluation value is higher when the difference between the number of wear areas 9 a and the actual number of trolley wires 9 is small. Therefore, a wear area extraction image in which the number of wear areas 9 a matches the actual number of trolley wires 9 is more likely to be selected as a wear area extraction image for calculating the remaining diameter and deviation. This improves the accuracy of extracting the wear areas 9 a of the trolley wire 9, and also improves the accuracy of calculating the remaining diameter and deviation.

[0089] Furthermore, according to this embodiment, an appropriate image processing execution procedure is selected depending on the environment, and a corresponding wear area extraction image is generated, thereby improving the calculation accuracy of the remaining diameter and deviation, and reducing the processing time and processing load. Furthermore, since an image processing execution procedure M that does not correspond to the selected environment is not executed, the processing time and memory required to run the trolley wire inspection device 20 can be reduced.

[0090] In addition, according to this embodiment, the wear area extraction image with the highest evaluation value, i.e., the highest trolley wire likelihood, is selected, so that the wear area extraction image whose image features of the wear area 9a are closest to the appearance of the actual trolley wire 9 is more likely to be selected as the wear area extraction image for calculating the remaining diameter and deviation, thereby improving the accuracy of extracting the wear area 9a of the trolley wire 9 and also improving the accuracy of calculating the remaining diameter and deviation.

[0091] In the above embodiment, for convenience of explanation, the post-processing unit 41 is described as being included in the wear area extraction image generating unit 32, but this is not limited thereto. The post-processing unit 41 may be included in the wear area extraction image evaluating unit 34, or may be configured as a function independent of the wear area extraction image generating unit 32 and the wear area extraction image evaluating unit 34. Needless to say, the configuration of the control device 23 may be changed without departing from the spirit of the present invention. In addition, in the above embodiment, the trolley wire inspection device includes both the trolley wire deviation calculating unit 35 and the trolley wire remaining diameter calculating unit 36 ​​and is configured to calculate both the remaining diameter and deviation of the trolley wire 9, but this is not limited thereto. The trolley wire inspection device may be configured to calculate only either the remaining diameter or deviation of the trolley wire, for example.

[0092] In addition to this, the present invention is not limited to the above-mentioned embodiments and each modified example described with reference to the drawings, and it is possible to select and discard the configurations listed in the above-mentioned embodiments and each modified example, or to change them to other configurations as appropriate, as long as this does not deviate from the gist of the present invention.

[0093] DESCRIPTION OF SYMBOLS 1 Inspection vehicle 9 Trolley wire 9a Wear area 9c, 9d Dark area 20 Trolley wire inspection device 21 Lighting 22 Line sensor 23 Control device 30 Line sensor image generation unit 31 Environment determination unit 32 Wear area extraction image generation unit 33 Image processing execution procedure memory unit 34 Wear area extraction image evaluation unit 35 Trolley wire deviation calculation unit (trolley wire inspection unit) 36 Trolley wire remaining diameter calculation unit (trolley wire inspection unit) 40 Image processing unit 40A Contrast adjustment processing unit 40B Background / noise removal processing unit 40C Binarization processing unit 40D Interpolation processing unit 40E Wear area correction unit 41 Post-processing unit 50 Line sensor image 50A, 50B Wear area extraction image M, M1, M2, M3 Image processing execution procedure

Claims

1. A trolley wire inspection device comprising a line sensor for capturing an image of a trolley wire, and inspecting the trolley wire based on an input image captured by the line sensor, comprising: a line sensor image generating unit for arranging the input images in chronological order to generate a line sensor image; an image processing execution procedure storage unit for storing a plurality of image processing functions for sequentially executing the line sensor image, the execution orders of which are registered as a plurality of image processing execution procedures; a wear area extraction image generating unit for extracting a worn area of ​​the trolley wire by executing the plurality of image processing functions using the line sensor image as an input according to each of the plurality of image processing execution procedures, and for correcting the worn area by scanning outward from the extracted wear area of ​​the trolley wire and setting the position where the brightness value becomes equal to or lower than a predetermined brightness value as the boundary of the worn area, thereby generating a plurality of wear area extraction images corresponding to each of the plurality of image processing execution procedures; and a wear area extraction image evaluation unit for calculating an evaluation value for each of the plurality of wear area extraction images and selecting the wear area extraction image with the highest evaluation value. and a trolley wire inspection unit that calculates either or both of a remaining diameter and a deviation of the trolley wire based on the selected wear area extraction image with the highest evaluation value.

2. A trolley wire inspection device as described in claim 1, characterized in that each of the multiple image processing execution procedures is registered to be executed in the following order: zero or more contrast adjustment processes, zero or more background / noise removal processes, one or more binarization processes, and zero or more interpolation processes.

3. A trolley wire inspection device as described in claim 1 or 2, characterized in that each of the multiple image processing execution procedures is stored with a priority associated therewith, and when the same evaluation value is calculated for multiple wear area extraction images, the wear area extraction image evaluation unit selects the wear area extraction image corresponding to the image processing execution procedure with the highest priority as the wear area extraction image with the highest evaluation value.

4. The trolley wire inspection device described in claim 3, characterized in that the wear area extraction image evaluation unit calculates the number of wear areas for each of the multiple wear area extraction images, and calculates the evaluation value so that the evaluation value is high when the difference between the number of wear areas and the actual number of trolley wires is small.

5. The trolley wire inspection device described in claim 3, characterized in that the wear area extraction image evaluation unit calculates a trolley wire likelihood, which is an index showing that the wear area has image features similar to the trolley wire, for each of the multiple wear area extraction images, and calculates the evaluation value so that the evaluation value is high when the trolley wire likelihood is high.

6. The trolley wire inspection device described in claim 1, further comprising an environment determination unit that determines the environment in which the input image was captured based on the line sensor image, wherein the image processing execution procedure memory unit registers the image processing execution procedure corresponding to each of a plurality of different environments when the image is captured by the line sensor, and the wear area extraction image generation unit generates the wear area extraction image according to the image processing execution procedure corresponding to the determined environment.

7. A trolley wire inspection method for inspecting a trolley wire based on an input image captured by a line sensor that captures a trolley wire, comprising the steps of: arranging the input images in chronological order to generate a line sensor image; sequentially executing a plurality of image processing functions on the line sensor image, the execution orders of which are registered as a plurality of image processing execution procedures, and extracting a worn area of ​​the trolley wire by executing the plurality of image processing functions using the line sensor image as an input according to each of the plurality of image processing execution procedures; correcting the worn area by scanning outward from the extracted worn area of ​​the trolley wire and setting the position where the brightness value becomes equal to or lower than a predetermined brightness value as the boundary of the worn area, thereby generating a plurality of wear area extraction images corresponding to each of the plurality of image processing execution procedures; calculating an evaluation value for each of the plurality of wear area extraction images and selecting the wear area extraction image with the highest evaluation value; and calculating either or both of the remaining diameter and deviation of the trolley wire based on the selected wear area extraction image with the highest evaluation value.

Images