JP2017215220A - Railway vehicle appearance inspection device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an inspection device for a railway vehicle capable of performing a highly accurate visual inspection using a photographed image. SOLUTION: This visual inspection device for a railroad vehicle has a normal image storage means for accumulating images of a normal railroad vehicle and a line for obtaining a photographed image by scanning a railroad vehicle moving on the railroad track in a direction intersecting the railroad track. The image of the inspection target area is selected from the scan-type photographing means, the correction means (S2) for correcting the variation of the captured image due to the fluctuation element of the railroad vehicle or the photographing environment, and the captured image corrected by the correction means. It is provided with a target area extraction means (S4) for extraction and an abnormality detecting means (S8) for detecting an abnormality by comparing an image of an inspection target area with an image stored in the normal image storage means. [Selection diagram] Fig. 3

Description

  The present invention relates to an appearance inspection apparatus for a railway vehicle that inspects the appearance of the railway vehicle for an abnormality.

  For some time, railway companies have regularly inspected the appearance of railway vehicles for abnormalities. In the appearance inspection, an inspector dives under the vehicle or climbs on the roof, and checks whether there is any abnormality mainly by visual inspection. If an abnormality is found, the relevant department will be contacted promptly and repairs will be arranged. Such inspection work requires a lot of labor and involves the risk of inspectors.

  Therefore, conventionally, it has been proposed to photograph a railway vehicle using a photographing device and to inspect the appearance of the railway vehicle from the photographed image (see, for example, Patent Documents 1 and 2). The technique of Patent Document 1 is to photograph a specific part of a railway vehicle with a dedicated camera from a predetermined angle and compare the photographed image with a reference image to determine the presence or absence of an abnormality. The technique of Patent Document 2 is to detect the presence or absence of an abnormality by photographing a train running on the track, synthesizing an image of the entire train, setting a predetermined inspection area in the train, and comparing it with a normal train image. To do. The entire train image is created by cutting and pasting a plurality of images obtained by high-speed continuous shooting from the side of the train.

  On the other hand, an inspection system using a line scan camera is generally known in the field of appearance inspection of industrial products and the like. The line scan camera captures an image of a moving subject together with an optical image of one line, and continuously stitches captured one-line captured images to obtain a two-dimensional image. According to the line scan camera, it is possible to continuously shoot a subject that is long in one direction. In addition, since the imaging process for converting an optical image into an electrical signal is performed for each one-dimensional optical image, it has a feature that an extremely high resolution can be obtained compared to an area camera that performs two-dimensional imaging.

JP-A-5-143714 JP 2013-53875 A

  The above-mentioned conventional proposal for inspecting the appearance of a railway vehicle using an imaging device has several problems. For example, the inspection apparatus of Patent Document 1 has a problem that a lot of photographing equipment is required and the cost increases because an image of a railway vehicle is photographed from a predetermined angle with a dedicated camera for each specific part. In addition, there is a problem that the imaging process becomes very complicated because the examination site is individually imaged. As the number of inspection points for railway vehicles increases, the cost and complexity double.

  Further, in the inspection apparatus of Patent Document 2, the imaging process is relatively easy, but it is difficult to obtain a train image with high resolution and low distortion, and the inspection accuracy is low compared to visual inspection. There are challenges. As shown in Patent Document 2, when high-speed continuous shooting is performed while a train is running, a portion that appears in the center of one photographed image and a side that is off the center appear due to variations in train speed and photographing timing. The location will be different for each shooting. In a general photographed image, the central part of the image displays a shape when the part is viewed straight, but the lateral part displays a shape when the part is viewed obliquely from the left and right, resulting in a difference in shape. For this reason, the train image obtained by synthesizing such images partially shows a distortion of the shape, and the portion where the distortion of the shape appears is different every time shooting is not constant. Such a distortion of the shape can be reduced by photographing the train from a distance, but in this case, the resolution of the photographed image is very low.

  On the other hand, by using a line scan camera, it is possible to avoid the shape seen from the left and right sides being included in the image. However, line scan cameras generally target subjects in a shooting environment such as industrial products that are uniformly illuminated in the line production process and transported at an accurate speed. there were. In addition, a high-resolution photographed image without distortion has been obtained by photographing in such an environment-friendly situation.

  When an appearance inspection is performed using a photographed image, for example, when photographing can be performed when a railway vehicle enters a vehicle base, it is convenient to save time and labor for moving the vehicle only for the inspection. However, it is difficult to move the railway vehicle at an accurate and constant speed under such conditions. In addition, the ground where the rails are laid includes a strong portion and a relatively soft portion. For this reason, when the railway vehicle travels on the rail, the railway vehicle is slightly displaced up and down by its own weight. Furthermore, since a suspension such as an air spring is provided between the carriage and the vehicle body, the vehicle body also moves up and down due to the action of the suspension. Therefore, without any ingenuity, it is difficult to obtain a captured image with high resolution and little distortion even when the traveling railway vehicle is imaged by a line scan camera.

  An object of the present invention is to provide a railway vehicle inspection apparatus capable of performing a high-precision appearance inspection using a photographed image.

To achieve the above objective,
The railway vehicle appearance inspection apparatus according to the present invention is:
Normal image storage means for accumulating images of normal railway vehicles;
A line scan type photographing means for obtaining a photographed image by scanning a railway vehicle moving on the rail in a direction crossing the rail;
Correction means for correcting variations in the captured image caused by a fluctuating factor of the railway vehicle or the imaging environment;
Target area extraction means for extracting an image of the inspection target area from the photographed image corrected by the correction means;
An abnormality detection means for detecting an abnormality by comparing the image of the inspection target region with the image stored in the normal image storage means;
It is characterized by having.

  According to such a configuration, the line scan type photographing means and the correcting means can photograph a high-resolution railway vehicle that is not irregularly distorted and is represented in a shape when each part is viewed from a certain direction. An image can be obtained. Therefore, by extracting an image of a region to be inspected from such a photographed image and comparing it with a normal image, it can be expected to perform an appearance inspection with the same or higher accuracy than a conventional visual inspection. Moreover, the captured image of the railway vehicle can be acquired with little effort.

Here, the correction means corrects at least the variation in the aspect ratio of each part of the photographed image due to the moving speed of the railway vehicle at the time of photographing and the correction of the photographed image due to the vertical movement of the railway vehicle at the time of photographing. It may be configured to perform correction of distortion in the vertical direction and correction of luminance of the captured image caused by brightness at the time of shooting.
According to such a configuration, for example, even when the railway vehicle is photographed during normal travel such as when the railway vehicle enters the depot, the correction means causes variations in the speed of the railway vehicle, vertical movement, and environmental conditions. A captured image in which variations due to brightness are eliminated can be obtained. Therefore, the appearance inspection with higher accuracy can be performed by these.

In addition, an appearance inspection apparatus for a railway vehicle according to the present invention includes:
A background structure having a surface serving as a background of the photographed image in an arrangement facing the photographing means across a track;
The target area extracting means may extract, as the inspection target area, at least a region where a part attached to a lower part of a railway vehicle body and a region where a railway vehicle carriage is arranged are individually extracted.
According to such a configuration, a photographed image in which a certain background is reflected by the background structure can be obtained in a region where the opposite side of the railway vehicle is reflected, such as the lower part of the vehicle body or the vicinity of the carriage. Therefore, when these portions are set as inspection target regions, the appearance of the image can be inspected with high accuracy by eliminating the influence of the background.

In addition, an appearance inspection apparatus for a railway vehicle according to the present invention includes:
It further comprises an abnormal image storage means for storing a photographed image indicating an abnormal appearance,
It is preferable that the photographed image determined to be normal by the abnormality detection unit is stored in the normal image storage unit, and the captured image determined to be abnormal by the abnormality detection unit is stored in the abnormal image storage unit.
According to such a configuration, it is possible to increase the number of normal images accumulated in the normal image storage unit by increasing the number of inspections, and to increase image data serving as a comparison reference. By increasing the comparison criteria, it is possible to increase the variations of applicable inspection methods. According to the above configuration, the captured image determined to be abnormal is accumulated in the abnormal image storage unit. Therefore, by analyzing these images, it is possible to analyze the degree of deterioration over time, analyze the tendency of abnormality for each vehicle type, and analyze various abnormalities. An efficient maintenance system can be realized according to these analysis results.

In addition, an appearance inspection apparatus for a railway vehicle according to the present invention includes:
It further comprises information acquisition means for acquiring vehicle type information of the railway vehicle to be inspected,
The normal image storage means stores a plurality of images of the same vehicle type,
The abnormality detection means compares the images of the inspection target region using a captured image of the railway vehicle to be inspected and a plurality of images of the same vehicle type as the railway vehicle to be inspected, and the plurality of images It may be configured to determine whether or not there is an abnormality based on a comparison result with an image having a smaller difference among them.

  Even if the railway vehicle is the same vehicle type, for example, the arrangement of parts such as cables is slightly different, or normal discoloration due to aging occurs, so that they are not completely the same. Therefore, even when comparing the inspection target areas as in the above configuration, the comparison is performed using a plurality of normal images of the same vehicle type, and whether or not there is an abnormality based on the comparison result with the smaller difference image. Thus, it is possible to determine whether there is an abnormality in the inspection target by excluding the difference in the normal range. Note that if the part that determines the presence or absence of an abnormality is fine and the difference in the image is relatively small, the presence or absence of the abnormality is overlooked even if there is a difference in the normal range by narrowing down the comparison target area. It can be judged with high accuracy without any problem.

  According to the present invention, there is an effect that it is possible to provide a railway vehicle inspection apparatus capable of performing a high-precision appearance inspection using a photographed image.

1 is a block diagram illustrating an overall configuration of a railcar appearance inspection apparatus according to an embodiment of the present invention. It is a figure which shows the example of arrangement | positioning of some components of the external appearance inspection apparatus of embodiment. It is a flowchart which shows the procedure of the inspection process performed by an inspection processing apparatus. It is a flowchart which shows the detailed procedure of the distortion correction process performed by step S2 of FIG. It is explanatory drawing which shows an example of a test object area | region. It is explanatory drawing which shows the comparison process of a test object area | region, and a determination threshold value.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a block diagram showing the overall configuration of a railcar appearance inspection apparatus according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an arrangement example of some components of the appearance inspection apparatus according to the embodiment.
As shown in FIGS. 1 and 2, the appearance inspection device 1 according to the embodiment of the present invention includes a vehicle proximity detection device 11, a photographing device 12, a background plate 14, an image processing device 15, and an inspection processing device 20. It has. Among these, the vehicle proximity detection device 11, the photographing device 12, the background plate 14, and the image processing device 15 are arranged, for example, beside the track for entering or leaving the vehicle base, as shown in FIG. Yes. The inspection processing device 20 is disposed indoors and connected to the vehicle proximity detection device 11 and the image processing device 15 by wire or wirelessly. The appearance inspection apparatus 1 includes two sets of imaging apparatuses 12 arranged on one side and the other side of the railroad track so that the left and right sides of the railway vehicle can be captured.

  The vehicle proximity detection device 11 detects, for example, an optical sensor or an electrical sensor using a track circuit, and the railcar enters the shooting section, and outputs a detection signal to the shooting device 12. Further, the vehicle proximity detection device 11 has a radio frequency identifier (RFID) receiver, communicates with the RFID mounted on the rail vehicle, reads out the vehicle name information of the rail vehicle, and uses this information as the inspection processing device 20. Send to. The inspection processing device 20 can specify the vehicle type from the vehicle number information. The RFID receiver corresponds to an example of an information acquisition unit according to the present invention.

  The photographing device 12 has a line scan camera 13 as photographing means, and photographs a railway vehicle traveling on the track from the side by a line scan method. The line scan camera 13 is a line scan type photographing apparatus that repeatedly performs scanning in one direction, that is, line-shaped imaging at a constant frequency. The line scan camera 13 repeatedly performs line-shaped imaging in a direction that intersects the moving direction on an imaging target that moves in a predetermined direction, and sequentially outputs line-shaped imaging data. A plurality of line-shaped imaging data that are sequentially output are arranged in a two-dimensional direction to obtain a captured image spread in a planar shape. Line-shaped imaging means imaging with a large number of pixels in the vertical direction and a single number of pixels in the horizontal direction, such as imaging of 2000 pixels in the vertical direction × 1 pixel in the horizontal direction. Hereinafter, the line-shaped imaging is referred to as “line scanning”, and the direction of the pixel column imaged by the line scanning is referred to as “line scanning direction”.

  The line scan camera 13 is set so that the line scan direction is in a direction crossing the track, such as the vertical direction. The imaging device 12 automatically starts imaging based on the proximity signal from the vehicle proximity detection device 11. The imaging device 12 continuously captures line-shaped imaging data and transmits it to the image processing device 15. In line-scan imaging, a high-resolution captured image without distortion can be obtained when an imaging target moves at a constant speed in a direction orthogonal to the line scanning direction. On the other hand, if there is a variation in speed or displacement in the line scan direction on the object to be imaged, these appear as distorted shapes in the captured image.

  The background plate 14 is a structure having a single color and single brightness background display surface. The background plate 14 is disposed at a position facing the image capturing device 12 with the track interposed therebetween so that the background display surface overlaps the portion where the line scan camera 13 performs line scanning. The background plate 14 is an area in which the opposite side of the vehicle, such as the lower part of the vehicle body or the vicinity of the carriage, is reflected when the railway vehicle enters the track, and is reflected in the photographed image of the line scan camera 13 as a background.

  The image processing device 15 expands the line-shaped imaging data continuously captured by the line scan camera 13 in the frame memory 16 to generate the image data of the entire railway vehicle that is long in the track direction, and this is used as the inspection processing device. 20 is transmitted. The photographed image of the railway vehicle includes a luminance variation due to ambient brightness as a variation factor of the photographing environment. Also, in the captured image of the railway vehicle, the fluctuation factors of the railway vehicle include the speed variation of the railway vehicle, the vertical vibration of the railway vehicle due to the rail sinking, and the vertical vibration of the vehicle body due to the action of the air spring (suspension) of the railway vehicle. A plurality of geometric distortions resulting from each are included.

  The inspection processing device 20 includes a CPU (central processing unit) 21 that executes a control program, a RAM (random access memory) 22 that provides a working memory space for the CPU 21, and an interface 23 that exchanges signals with external devices. And a storage device 24 storing a control program and control data. The storage device 24 stores, as a control program, an appearance inspection program 24A that performs an appearance inspection of a railway vehicle based on a captured image. In addition, the storage device 24 has a normal image database (corresponding to normal image storage means) 24B in which appearance images of normal railway vehicles serving as a comparison reference at the time of appearance inspection are stored, and photographing indicating abnormal appearance of the railway vehicles. An abnormal image database (corresponding to an abnormal image storage means) 24C for storing images is provided.

Next, the inspection process executed by the inspection processing device 20 according to the appearance inspection program 24A will be described.
FIG. 3 is a flowchart showing a procedure of inspection processing executed by the inspection processing apparatus. FIG. 4 is a flowchart showing a detailed procedure of the distortion correction process in step S2 of FIG.
The inspection process is started when a captured image of the railway vehicle is received from the image processing device 15 to the inspection processing device 20. When the inspection processing is started, first, the inspection processing device 20 inputs a captured image of the railway vehicle from the image processing device 15 (step S1).

  When the captured image is input, the inspection processing device 20 performs distortion correction (step S2) of the captured image. In distortion correction, correction to correct distortion caused by rail car vertical movement, correction of brightness variation due to shooting environment, and aspect ratio of shot image caused by railway vehicle movement speed. The correction for removing the variation and the correction for correcting the distortion caused by the vertical movement of the carriage and the vehicle body relative to each other by the action of the suspension in the railway vehicle are performed. A configuration including hardware and software that realizes the processes of step S2 and step S2 corresponds to an example of a correction unit according to the present invention.

Subsequently, a specific example of the distortion correction processing will be described with reference to FIG. 4, but the distortion correction processing according to the present invention is not limited to this content.
When the process proceeds to the distortion correction process, first, the inspection processing apparatus 20 extracts a rail edge from the photographed image (step S21). Next, the inspection processing apparatus 20 shifts these pixel columns in the line scan direction for each vertically long pixel column having a width of one pixel so that the rail edge is linear (step S22). As a result, the rail is corrected so as to be linear, and the distortion of the shape caused by the vertical movement of the railway vehicle due to the sinking of the rail is corrected.

  In addition, you may perform the process of step S21, S22 using an additional structure. That is, as an additional configuration, the calibrator is rigidly connected to the rail so as to overlap the line to be scanned. A calibrator is a panel that displays a reference line. In this case, the line scan camera 13 repeats the line scan with a line that overlaps the calibrator while the railway vehicle is running, so the position of the reference line of the calibrator is linked to the captured image from the front end to the rear end and is copied as a correction line. Is done. In the processing of steps S21 and S22, if the inspection processing device 20 uses a correction line of the calibrator instead of extracting the rail edge, and performs a correction process of shifting the pixel column so that it is linear. Good.

  Next, the inspection processing device 20 corrects the luminance of the entire image so that the luminance of the captured image becomes the same as that of the reference image (step S23). This brightness correction processing may also be performed using the following additional configuration. In other words, as an additional configuration, a luminance display panel displaying a plurality of luminances is fixed to a part of a portion where the line scan is performed by the line scan camera 13. In step S23, the inspection processing device 20 calculates the difference between the brightness of the captured image and the brightness of the reference image from the image portion of the brightness display panel, and corrects the brightness of the entire captured image so as to eliminate this difference. Good. For example, the luminance display panel may be provided in the calibrator described above.

  Next, the inspection processing device 20 performs edge extraction of the characteristic part of the railway vehicle (step S24), and compares the reference profile showing the characteristic part of the same vehicle type with the extracted edge (step S25). In the comparison process, the deviation of the aspect ratio of the captured image is calculated for each part in the front-rear direction of the railway vehicle. When the deviation of the aspect ratio is calculated, the inspection processing device 20 performs a horizontal expansion / contraction correction process on the captured image (step S26). In the expansion / contraction correction process, the shot image is divided into strip-shaped image elements that are long in the line scan direction, and all the divided strip-shaped image elements are expanded and contracted in the horizontal direction to eliminate the aspect ratio deviation. All the strip-shaped images are pasted together to generate a corrected captured image. Thereby, the distortion of the shape resulting from the variation in the moving speed of the railway vehicle is corrected from the captured image.

  Subsequently, in order to correct the shape distortion caused by the vertical vibration of the vehicle body due to the action of the suspension of the railway vehicle, the inspection processing device 20 first performs a process of masking the rail and carriage portions in the captured image (step S27). ). Next, the inspection processing apparatus 20 performs a process of extracting a straight edge (for example, a lower edge of the vehicle body) at an unmasked portion (step S28). Then, the inspection processing device 20 has a vertically long image element with a width of several pixels only in a portion that is not masked (such as various parts fixedly connected to the vehicle body and the lower part of the vehicle body) so that the extracted edge is linear. Is shifted in the line scan direction, and processing for shifting such image elements is performed from the beginning to the end of the captured image (step S29). Thereafter, the inspection processing apparatus 20 restores the masked portion to the original image (step S30). Thereby, the shape distortion resulting from the vertical vibration of the vehicle body due to the action of the suspension of the railway vehicle is corrected.

  Each correction process described above can be variously changed. For example, in step S22, the vertical image correction is performed using the rail edge as a reference, but the vertical image correction may be performed using another part as a reference. In steps S27 to S30, the vertical image correction of the vehicle body and the portion fixedly connected to the vehicle body is performed with reference to the lower edge of the vehicle body, but the other characteristic portions are compared with the reference image and shifted. By detecting this, the image correction in the vertical direction may be performed.

When the distortion correction processing in FIG. 4 is completed, the inspection processing device 20 executes loop processing (steps S3 to S8 in FIG. 3) for inspecting whether there is an abnormality based on the captured image. When the process shifts to the loop process, the inspection processing apparatus 20 first selects each inspection target area from a plurality of inspection target areas set in advance (step S3).
FIG. 5 is an explanatory diagram illustrating an example of the inspection target area. FIG. 5A is an image diagram showing an example of a railway vehicle to be inspected, and FIGS. 5B to 5D are partial enlarged views showing a plurality of inspection target regions set in each part of the railway vehicle. FIG. 5 (a) shows one and two railway vehicles, but in actuality, a formation in which a plurality of railway vehicles are connected is an inspection target.

The inspection target area E can be arbitrarily set. For example, the inspection area E may be a large area such as the whole of the carriage 81 or the whole of the brake device 85, or the air passage cock 82 for opening / closing the door or the lever 86 of the brake device 85. It is good also as a small area | region surrounding the component of the part. Or you may set the small test | inspection area | region E in large test | inspection area | regions E, such as some components 83 and 84 in a trolley | bogie.
The coordinate information indicating the position of the inspection target region E is stored in, for example, a coordinate information database 24D (see FIG. 3) provided in the storage device 24. In step S3 of FIG. 3, the inspection processing apparatus 20 reads information from the coordinate information database 24D and selects the inspection target region E one by one. Note that the coordinate information of the inspection target region E may be information on absolute coordinates of the captured image, or information on relative coordinates from a reference point set on the railway vehicle, for example.

  When one inspection target area is selected, the inspection processing apparatus 20 extracts an image of this inspection target area from the captured image (step S4: equivalent to target area extracting means), and the normal image stored in the normal image database 24B. The image is compared with an image of a railway vehicle (hereinafter referred to as “normal image”) (step S5). The normal image database 24B stores one or a plurality of normal railcar images for each vehicle type, and the inspection processing device 20 in step S5, one normal image of the same vehicle type as the railcar to be inspected. Is read out from the normal image database 24B and used as a reference for comparison. In the comparison process, for example, the difference in hue and brightness of each pixel between the captured image and the normal image is digitized, and the sum of differences in all pixels in the comparison target region is calculated as a distance value. In addition, when digitizing the difference of each pixel, a specific calculation such as squaring the difference in brightness or hue to obtain a difference value, or calculating the difference value by weighting according to the brightness or hue, etc. The method can be changed as appropriate. In addition, before the comparison, the comparison process may be performed after the process of eliminating the small positional deviation between the two, or the comparison position is shifted little by little and the comparison is performed a plurality of times to obtain the minimum distance value. You may make it employ | adopt as a comparison result.

  Subsequently, the inspection processing device 20 determines whether or not the comparison with all normal images of the same vehicle type stored in the normal image database 24B has been completed (step S6). The loop process of reading out and comparing the normal images is repeated. On the other hand, if it is completed, the inspection processing apparatus 20 exits the loop process and proceeds to the next step. By the loop processing of steps S5 and S6, the captured image of one inspection target area is compared with all normal images of the same vehicle type stored in the normal image database 24B.

When the comparison with all the normal images is completed, the inspection processing device 20 compares the distance value obtained by the plurality of image comparisons with the threshold value to determine whether there is an abnormality in the inspection target region (step S7). ).
FIG. 6 is an explanatory diagram illustrating the comparison process of the inspection target region and the determination threshold value.
When many images of normal railway vehicles are compared, the distance value calculated in step S5 appears in a frequency distribution as shown in FIG. The frequency may be rephrased as the appearance frequency. In FIG. 6, normalization is performed so that the maximum distance value is “1”. Therefore, as shown in FIG. 6, the determination threshold value used in step S7 is set to be a distance value that is larger than the distance value at which the frequency reaches a peak and that does not occur much in comparison between normal images. Is done. Such a threshold value is appropriately set for each inspection target region, and is stored in a determination threshold value database 24E (see FIG. 3) provided in the storage device 24. The inspection processing device 20 performs the determination process in step S7 using this threshold value.

  In the determination process in step S7, it is preferable that the smallest distance value is used among a plurality of distance values respectively obtained by a plurality of image comparisons to be compared with a threshold value. By such a determination process, a comparison is made between the normal image that is closest to the image in the inspection target region among the plurality of normal images accumulated in the normal image database, and an abnormal condition is determined based on this comparison. Presence / absence is determined.

Even if the railway vehicle is the same vehicle type, for example, the arrangement of parts such as cables is slightly different, or normal discoloration due to aging occurs. Therefore, even when comparing the areas to be inspected, as described above, comparison is performed using normal images of a plurality of the same models, and it is determined whether or not there is an abnormality, thereby excluding small differences in the normal range. Thus, the presence or absence of an abnormality to be inspected can be determined with high accuracy. In addition, if the part that determines the presence or absence of an abnormality is fine and the difference in the image is relatively small, by setting a small comparison target area, even if there is a difference in the normal range It is possible to determine with high accuracy without missing any abnormality.
The configuration for realizing the processes of steps S5 to S7 corresponds to an example of the abnormality detection unit according to the present invention.

  As a result of the determination process in step S7, if it is determined that the distance value is smaller than the threshold value and normal, the inspection processing apparatus 20 advances the process to step S9. On the other hand, if the distance value is greater than or equal to the threshold value and it is determined that there is an abnormality, the inspection processing device 20 registers the photographed image of the railway vehicle determined to be abnormal in the abnormality image database 24C (step S8). When registering, data indicating a corresponding inspection target area may be added so that the inspection target area determined to be abnormal can be known. In addition, when a plurality of inspection target areas of the same captured image are determined to be abnormal, a single captured image and a plurality of inspection target areas determined to be abnormal are determined so that the same captured image is not registered twice. It is preferable that information to be stored is accumulated.

By accumulating captured images that are determined to be abnormal, analysis of these captured images is followed by analyzing deterioration over time, analyzing trends in abnormalities for each vehicle model, and analyzing various abnormalities. be able to. An efficient maintenance system can be realized according to these analysis results.
In the abnormality registration process in step S8, the inspection processing apparatus 20 may perform a notification process for notifying the staff of the abnormality. In the notification process, it is preferable that the inspection target area determined to be abnormal is displayed on the captured image of the railway vehicle in an identifiable manner and notified.

  If the determination is normal or abnormal, the inspection processing apparatus 20 determines whether the processing for all the inspection target regions has been completed (step S9), and if not, returns to step S3 and continues the loop processing. On the other hand, if it is completed, the loop process is exited and the process proceeds to the next step. By the loop process of step S3 to step S9 described above, the presence / absence of abnormality of the railway vehicle is determined for a plurality of inspection target areas in the captured image.

  After exiting the loop process, the inspection processing device 20 determines whether the image comparison results of all the inspection target areas are normal (step S10), and if not, ends the inspection process. On the other hand, if all are normal, the inspection processing device 20 determines whether the captured image satisfies the registration condition in the normal image database 24B (step S11), and if satisfied, the captured image is displayed together with the vehicle type information in the normal image database. 24B is registered (step S12). The captured image to be registered may be only the image after the correction process or may be an image both before and after the correction process. By accumulating the photographed images determined to be normal, normal images in the normal image database 24B are increased by increasing the number of inspections. As a result, various methods for determining the presence or absence of an abnormality can be introduced, and an inspection with higher accuracy can be performed.

The registration condition of the captured image is, for example, a condition that the maximum value or average value of the distance values calculated in the image comparison in step S5 is in a normal range, or a captured image of the same vehicle type stored in the normal image database 24B. Various conditions such as a condition that the number does not reach the upper limit may be applied.
When the normal image is registered, the inspection processing apparatus 20 ends the inspection processing of FIG. If it is determined in step S11 that the registration condition is not satisfied, the inspection process of FIG.

  As described above, according to the railway vehicle appearance inspection apparatus 1 of this embodiment, there is no irregular distortion due to photographing by the line scan camera 13 and correction processing by the inspection processing apparatus 20, and a certain direction in any part. It is possible to obtain a high-resolution captured image of a railway vehicle that shows the shape when viewed from above. Therefore, by individually extracting the images of the region to be inspected from such a photographed image and comparing it with a normal image, it is possible to perform an appearance inspection with the same or higher accuracy than a conventional visual inspection.

  Further, according to the railway vehicle appearance inspection apparatus 1 of this embodiment, the correction processing of the inspection processing apparatus 20 includes correction of variation in the aspect ratio of each part caused by variation in the moving speed of the railway vehicle, It includes correction of shape distortion caused by vertical movement and correction of luminance variations caused by brightness variations during shooting. Therefore, for example, even if the railway vehicle is photographed during normal travel, such as when the railway vehicle enters a depot, the correction process causes variations in the speed of the railway vehicle, vertical movement, and variations due to environmental brightness. A photographed image that eliminates the above is obtained. Therefore, the appearance inspection with higher accuracy can be performed by these.

  Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. For example, in the above-described embodiment, the left and right side surfaces of the railway vehicle are photographed and the appearance inspection in which the portion below the vehicle body is the inspection target region has been mainly described. May be used. Furthermore, it is good also as a structure which image | photographs from the upper direction or the downward direction of a rail vehicle, and performs the external appearance inspection of a vehicle body upper part or a vehicle body lower part using this picked-up image.

Moreover, in the said embodiment, the example which provided the normal image database 24B and the abnormal image database 24C in the memory | storage device 24 in the test | inspection processing apparatus 20 was shown. However, the normal image database 24B and the abnormal image database 24C may be provided in separate storage devices and connected to the inspection processing device 20 (computer) via, for example, a LAN.
In the above-described embodiment, an example in which the inspection processing apparatus that performs image correction processing and abnormality detection is arranged away from the imaging unit has been described. However, the inspection processing apparatus may be arranged beside the track like the photographing means, and in that case, the function of the image processing apparatus (15) is incorporated in the inspection processing apparatus (20), and both are integrally configured. May be.

DESCRIPTION OF SYMBOLS 1 Appearance inspection apparatus 11 Vehicle proximity detection apparatus (information acquisition means)
13 Line scan camera (photographing means)
14 Background board (background structure)
20 Inspection processing device (correction means, target area extraction means, abnormality detection means)
21 CPU
22 RAM
23 Interface 24 Storage Device 24A Appearance Inspection Program 24B Normal Image Database (Normal Image Storage Means)
24C abnormal image database (abnormal image storage means)
E Inspection target area

Claims (5)

Normal image storage means for accumulating images of normal railway vehicles;
A line scan type photographing means for obtaining a photographed image by scanning a railway vehicle moving on the rail in a direction crossing the rail;
Correction means for correcting variations in the captured image caused by a fluctuating factor of the railway vehicle or the imaging environment;
Target area extraction means for extracting an image of the inspection target area from the photographed image corrected by the correction means;
An abnormality detection means for detecting an abnormality by comparing the image of the inspection target region with the image stored in the normal image storage means;
An apparatus for inspecting the appearance of a railway vehicle, comprising:   The correction means corrects at least the variation in the aspect ratio of each part of the captured image due to the moving speed of the railway vehicle at the time of shooting, and the vertical direction of the captured image due to the vertical movement of the railway vehicle at the time of shooting. The railroad vehicle visual inspection apparatus according to claim 1, wherein distortion correction and luminance correction of the captured image due to brightness at the time of shooting are performed. A background structure having a surface serving as a background of the photographed image in an arrangement facing the photographing means across a track;
The target area extracting means extracts, as the inspection target area, at least a region where a part attached to a lower part of a railcar body and a region where a railcar bogie is arranged are individually extracted. The appearance inspection apparatus for a railway vehicle according to claim 1 or 2, characterized in that It further comprises an abnormal image storage means for storing a photographed image indicating an abnormal appearance,
2. The photographed image determined to be normal by the abnormality detection unit is stored in the normal image storage unit, and the captured image determined to be abnormal by the abnormality detection unit is stored in the abnormal image storage unit. The visual inspection apparatus for a railway vehicle according to any one of claims 1 to 3. It further comprises information acquisition means for acquiring vehicle type information of the railway vehicle to be inspected,
The normal image storage means stores a plurality of images of the same vehicle type,
The abnormality detection means compares the images of the inspection target region using a captured image of the railway vehicle to be inspected and a plurality of images of the same vehicle type as the railway vehicle to be inspected, and the plurality of images The rail vehicle appearance inspection apparatus according to any one of claims 1 to 4, wherein a determination is made as to whether or not there is an abnormality based on a comparison result with an image having a smaller difference among the images. .

Images