JP4818747B2 - Railway vehicle inspection method and apparatus using long images - Google Patents

Description

  The present invention relates to a railway vehicle inspection method and apparatus using a long image of an entire moving railway vehicle, and in particular, bearing temperature of the railway vehicle, underfloor equipment temperature, noise, vehicle vibration, and electric / magnetic field from the vehicle. The present invention relates to a strength inspection method and apparatus.

Conventionally, a system for converting a video image into a continuous seamless and low distortion panoramic image and making it into a database has been proposed. Inspecting the appearance of roads and power transmission lines is disclosed (Patent Document 1 below).
On the other hand, in the field of railways, the use of railway vehicle images is being examined for inspection of railway vehicles.
JP 2003-9144 A WO 01/15081 A2 Publication

However, in the above-described conventional system, inspection objects that cannot be viewed at a time because of the wide range are simply converted into a panoramic image having no continuous joints and less distortion, and the database is created.
Therefore, in the field of railways, research for inspecting the state of railway vehicles by combining long images of railway vehicles with other types of data is being promoted for maintenance.

  In view of the above situation, the present invention acquires a long image of the entire railway vehicle, and can inspect the railway vehicle using the image, and a railway vehicle inspection method and apparatus using the long image. The purpose is to provide.

In order to achieve the above object, the present invention provides
[1] In a railway vehicle inspection method using a long image, a moving railway vehicle is photographed using a camera, and long image data of the entire railway vehicle is generated from the photographed image using a processing device. , by determining the difference compared to features extracted the features extracted from the long image data from the previously stored reference long image data, and performs inspection of the entire rail vehicle.

[2] In the railway vehicle inspection method using the long image according to the above [1], the long image data of the entire moving railway vehicle selects a partial image from the center of each image frame of the camera. It generates by combining partial images.
[3] In the railway vehicle inspection method using the long image according to [2], the partial image width of the image frame is selected on the basis of the movement amount of the railway vehicle.

[4] In railway vehicle inspection method using a long image described in [3], when the amount of movement of the rail vehicle is large takes broadly the partial image width, taking narrow when the amount of movement is small It is characterized by.
[5] The railway car inspection method using a long image according to any one of [1] to [4], the long image data is the railcar is created using the camera and processing unit It is obtained from the image which image | photographed the side surface, bottom face, or upper surface of this.

[6] In a railway vehicle inspection method using a long image, long image data of the entire moving rail vehicle is acquired by using a camera and a processing device, and another type of sensor is used with a sensor different from the camera. to obtain information, it performs the long image data and synchronize, and acquires the time series data combined with the long image data.
[7] The railway vehicle inspection method using the long image according to [6], wherein the sensor measures an underfloor equipment temperature, an on-roof equipment temperature, or a vehicle side surface temperature of the railway vehicle.

[8] In the railway vehicle inspection method using the long image according to [7], the underfloor equipment temperature is a wheel bearing temperature.
[9] In the railway vehicle inspection method using the long image according to [6], the abnormal sound of the railway vehicle is measured by the sensor.
[10] In the railway vehicle inspection method using the long image according to [6], vibration of the railway vehicle is measured by the sensor.

[11] In the railway vehicle inspection method using the long image according to [6], the electric field intensity or magnetic field intensity from the railway vehicle is measured by the sensor.
[12] In a railway vehicle inspection apparatus using a long image, a camera that acquires an image of a moving railway vehicle that is disposed on or in a railroad track and generates long image data of the entire railway vehicle from the image as well as, by determining the difference by comparing the features extracted from the reference long image data previously stored features extracted from the long image data, and a processing device for examination of the rail vehicle It is characterized by doing.

In railway vehicle inspection apparatus using the [13] elongated image, arranged in wayside or in line, and a camera for acquiring an image of a moving railway vehicle, it is arranged fixedly before Symbol line Michiwaki or in line Acquiring information of a different type from the image of the railway vehicle, synchronizing a sensor of a different type from the camera, and the long image data generated from the image, And a processing device that acquires time-series data combined with the scale image data .

[14] In the railway vehicle inspection apparatus using the long image according to [13], the sensor is a thermo camera that measures an underfloor equipment temperature, an on-roof equipment temperature, or a vehicle side surface temperature of the railway vehicle. And
[15] In the railway vehicle inspection apparatus using the long image according to [14], the sensor is a non-contact thermometer that measures a wheel bearing temperature of the railway vehicle.

[16] In the railway vehicle inspection apparatus using the long image according to [13], the sensor is an abnormal sound measurement microphone that measures noise of the railway vehicle.
[17] The railway vehicle inspection apparatus using the long image according to [13], wherein the sensor is a vibration sensor that measures vibration of the railway vehicle.
[18] The railway vehicle inspection apparatus using the long image according to [13], wherein the sensor is an electric field / magnetic field sensor that measures an electric field / magnetic field intensity from the railway vehicle.

  ADVANTAGE OF THE INVENTION According to this invention, while acquiring the long image of the whole railway vehicle as a moving body, a rail vehicle can be test | inspected quickly and exactly using the image.

The railway vehicle inspection apparatus using a long image of the present invention images a moving railway vehicle using a camera, and generates long image data of the entire railway vehicle from the captured image using a processing device. , by determining the difference compared to features extracted the features extracted from the long image data from the previously stored reference long image data, performs the inspection of the entire rail vehicle.

Hereinafter, embodiments of the present invention will be described in detail.
FIG. 1 is a schematic diagram of a railway vehicle inspection apparatus using a long image (SLIm: Super Long Imaging) showing an embodiment of the present invention. FIG. 2 is a diagram showing the principle of acquiring a long image of a rail vehicle. FIG. 4 is a view showing a long image obtained as a result, and FIG. 4 is a block diagram of the railway vehicle inspection apparatus.

First, in FIG. 4, 1 is a moving railway vehicle, 2 is a camera, 3 is a processing device, 4 is an editing unit for a long image of the entire railway vehicle using an image of the moving railway vehicle 1 photographed by the camera 2. 5 is a long image data of the edited railway vehicle as a whole, 5A is a feature extraction unit for extracting features from the long image data 5 , 6 is a reference long image data of the railway vehicle stored in advance, and 6A is feature extracting unit for extracting a feature from the reference long image data 6, 7 comparison unit for comparing the characteristic features and the reference long image data 6 of the feature extraction unit 5A, elongated image data 5 which has been extracted with 6A , 8 is a determination unit for the comparison result, and 9 is an output unit for the determination result.

The acquisition of long image data of the entire railway vehicle will be described with reference to FIGS. 2 and 4.
In order to photograph the side surface of the moving railway vehicle 1, a camera 2 is arranged beside the track. At this time, the focus, aperture, and angle of view of the camera 2 are adjusted while looking through the viewfinder of the camera 2.
Here, an image of the railway vehicle 1 is taken by the camera 2, captured by the processing device 3, and edited by the editing unit 4 to obtain the long image data 5 of the entire railway vehicle. Adjustment is made so that the image frame 2A is always parallel to the edge of the image frame 2A. In particular, in order to make the present invention function efficiently, a fixing device, an angle, and the like of the camera 2 are set so that an imaging target can be captured from the normal direction.

Therefore, first, the traveling railway vehicle 1 is photographed to obtain a frame image as shown in FIG. The moving amount of the vehicle between the frame images is calculated, the partial image 2B is cut out from the image frame 2A, and the partial images 2B are combined to create the long image data 5 of the entire railway vehicle 1 as shown in FIG. The
The long image data 5 of the entire railway vehicle 1 generated in this way is an overall image of the railway vehicle as shown in FIG. In FIG. 3, FIG. 3A is an entire image of the railway vehicle, FIG. 3B is a first enlarged image, and FIG. 3C is a second enlarged image.

Therefore, as shown in FIG. 4, the long image (overall image) data 5 of the entire railway vehicle 1 and the reference long image data 6 stored in advance are compared via their feature extraction units 5A and 6A. Compared by the unit 7, the output is determined by the determination unit 8, and is output from the output unit 9 as inspection information of the railway vehicle 1.
In this way, the present invention provides, for example, (1) an inspection device for the state of the railway vehicle 1, (2) a snow accretion monitoring device that monitors snow accretion on the rail vehicle 1, and (3) a degree of congestion for each vehicle. It can be used as a congestion degree monitoring device in the railway vehicle 1 for monitoring.

FIG. 5 is a schematic diagram of a railway vehicle inspection apparatus in which information of another type of sensor is combined with long image data according to an embodiment of the present invention.
In this embodiment, in addition to the above-described long image data of the entire railway vehicle, as shown in FIG. 5, in order to obtain other types of information corresponding to the long image data of the entire rail vehicle, Alternatively, the sensor 14 is arranged at a fixed position in the track. Naturally, when the sensor 14 is arranged at a position shifted from the photographing position of the camera 12, correction processing is performed to match the two. However, when the sensor 14 is arranged at a position that matches the shooting position of the camera 12, the shooting image data of the railway vehicle 11 and other types of information are matched without being corrected in position. Can be remembered.

That is, depending on the purpose of inspection of the railway vehicle 11, analog or digital data such as abnormal noise, vibration, electric field / magnetic field strength of the railway vehicle can be recorded in synchronization with the frame image of the railway vehicle. The long image of the entire railway train 11 is processed by the processing device 13, and the partial image of the image frame is selected based on the amount of train movement. The partial image width changes such that the partial image width is wide when the movement amount is large and narrow when the movement amount is small. To display such long image data and other types of sensor data together, normalize the data from that sensor by synchronizing it with the long image data as described above.

When the data of other types of sensors is intensity data, normalization is easy because the data does not change by normalization. However, when normalizing data having a characteristic in frequency, the quality of the data may change due to normalization. Therefore, normalization is performed in consideration of this.
In this way, if the long image technology is used, the entire image of the railway vehicle can be captured, and the long image data and other types of data can be combined to accurately inspect the railway vehicle. it can.

Hereinafter, application examples of inspection of railway vehicles will be described.
(1) Railway vehicle underfloor equipment temperature inspection device FIG. 6 is a schematic diagram of a railcar underfloor equipment temperature inspection device showing an embodiment of the present invention, and FIG. 7 is a diagram showing the railcar underfloor equipment temperature information.
In this embodiment, as shown in FIG. 6, the camera 22 arranged in the track generates long image data 28 of the lower surface of the floor of the railway vehicle 21 as shown in FIG. (b), to obtain the temperature information of the equipment floor 29 by thermo camera 27 placed in line, by a Turkey synchronize these data, it is possible to inspect the floor equipment temperature railcar 21 . For example, the heat generation 29 </ b> A is detected by the underfloor device 29. That is, the captured image from the camera 22 is captured by the processing device 23 and edited by the editing unit 24 to obtain long image data of the entire railway vehicle, and the temperature information from the thermo camera 27 is converted into the long image data. Acquired as time-series data synchronized with image data . Such information is determined by the determination unit 25, and the determination result is output from the output unit 26. Thereby, it is possible to accurately detect abnormalities in temperature and abnormal parts of railway vehicle underfloor equipment.

In the above-described embodiment, the underfloor equipment temperature of the railway vehicle is measured by the thermo camera. However, the equipment temperature on the roof of the railway car or the vehicle side surface temperature may be measured by the thermo camera.
(2) Railway Vehicle Wheel Bearing Temperature Inspection Device FIG. 8 is a schematic diagram of a railway vehicle wheel bearing temperature inspection device showing an embodiment of the present invention.

In FIG. 8, 31 is a railway vehicle, 32 is a camera, 33 is a processing device, 34 is an editing unit, 35 is a determination unit, 36 is an output unit, and 37 is a non-contact thermometer.
In this embodiment, the captured image from the camera 32 arranged on the side of the track or in the track is taken into the processing device 33 and edited by the editing unit 34 to generate long image data of the entire railway vehicle. Temperature information is obtained from the contact-type thermometer 37 and acquired as time-series data synchronized with the long image data . Such information is determined by the determination unit 35, and the determination result is output from the output unit 36. Thereby, the abnormality of a wheel bearing temperature and the detection of an abnormal part can be performed exactly.

(3) Railway Vehicle Abnormal Sound Inspection Device FIG. 9 is a schematic diagram of a railway vehicle abnormal sound inspection device showing an embodiment of the present invention.
In FIG. 9, 41 is a railway vehicle, 42 is a camera, 43 is a processing device, 44 is an editing unit, 45 is a determination unit, 46 is an output unit, and 47 is an abnormal sound measurement microphone.
In this embodiment, the captured image from the camera 42 arranged on the side of the track or in the track is taken into the processing device 43 and edited by the editing unit 44 to generate long image data of the entire railway vehicle. Abnormal sound information is obtained from the sound measuring microphone 47 and obtained as time-series data synchronized with the long image data . The These information determined by the determination unit 45, the determination result is output from the output unit 46. Thereby, the detection of the abnormal sound of a railway vehicle and the detection of the abnormal sound generation | occurrence | production site | part can be performed exactly.

(4) Railway vehicle vibration inspection apparatus FIG. 10 is a schematic diagram of a railway vehicle vibration inspection apparatus showing an embodiment of the present invention.
In FIG. 10, 51 is a railway vehicle, 52 is a camera, 53 is a processing device, 54 is an editing unit, 55 is a determination unit, 56 is an output unit, and 57 is a vibration sensor.
In this embodiment, a captured image from a camera 52 arranged beside or on the track is taken into the processing device 53 and edited by the editing unit 54 to generate long image data of the entire railway vehicle. Vibration information is obtained from the sensor 57 and acquired as time series data synchronized with the long image data . The These information determined by the determination unit 55, the determination result is output from the output unit 56. Thereby, the detection of the vibration of the railway vehicle and the detection of the vibration part can be accurately performed.

(5) Electric field / magnetic field strength inspection apparatus from railway vehicle FIG. 11 is a schematic diagram of an electric field / magnetic field intensity inspection apparatus from a railway vehicle showing an embodiment of the present invention.
In FIG. 11, 61 is a railway vehicle, 62 is a camera, 63 is a processing device, 64 is an editing unit, 65 is a determination unit, 66 is an output unit, and 67 is an electric field / magnetic field sensor.

In this embodiment, a captured image from a camera 62 arranged beside or in the track is captured by the processing device 63 and edited by the editing unit 64 to generate long image data of the entire railway vehicle. The electric field / magnetic field strength information of the railway vehicle is obtained from the magnetic field sensor 67 and obtained as time series data synchronized with the long image data . The These information determined by the determination unit 65, the determination result is output from the output unit 66. As a result, it is possible to accurately detect the electric field / magnetic field strength of the railway vehicle and to detect a portion where the electric field / magnetic field strength is high.

  In addition, this invention is not limited to the said Example, A various deformation | transformation is possible based on the meaning of this invention, and these are not excluded from the scope of the present invention.

  The railway vehicle inspection method and apparatus using a long image of the present invention can be used as various inspection apparatuses for railway vehicles.

It is a schematic diagram of the inspection apparatus of a railway vehicle using the long image (SLIm: Super Long Imaging) which shows the Example of this invention. It is a figure which shows the acquisition principle of the elongate image of the railway vehicle concerning this invention. It is a figure which shows the elongate image obtained using this invention. 1 is a block diagram of a railway vehicle inspection apparatus using a long image showing an embodiment of the present invention. It is a schematic diagram of the inspection apparatus of a railway vehicle which combined the information of another kind of sensor with the long image information which shows the Example of this invention. It is a schematic diagram of the underfloor equipment temperature test | inspection apparatus of the railway vehicle which shows the Example of this invention. It is a figure which shows the railway vehicle underfloor apparatus temperature information which shows the Example of this invention. 1 is a schematic diagram of a wheel bearing temperature inspection device for a railway vehicle showing an embodiment of the present invention. 1 is a schematic diagram of an abnormal sound inspection apparatus for a railway vehicle showing an embodiment of the present invention. It is a schematic view of a railway vehicle both vibration testing apparatus according to an embodiment of the present invention. 1 is a schematic diagram of an apparatus for inspecting electric field / magnetic field strength from a railway vehicle according to an embodiment of the present invention.

DESCRIPTION OF SYMBOLS 1 Rail vehicle 2, 12, 22, 32, 42, 52, 62 Camera 2A Image frame 2B Partial image 3, 13, 23, 33, 43, 53, 63 Processing apparatus 4 Long image editing part 5 of the entire rail vehicle characteristic extraction unit 7 comparing unit 8,25,35,45,55 that extracts features from long image data 5A length extracting features from scale image data characteristic extraction section 6 referring elongated image data 6A see elongated image data, 65 Judgment part 9, 26, 36, 46, 56, 66 Output part 11, 21, 31, 41, 51, 61 Railway vehicle 14 Sensor 24, 34, 44, 54, 64 Editing part 27 Thermo camera 28 Length of floor under surface Measured image data 29 Underfloor equipment 29A Heat generated from underfloor equipment 37 Non-contact thermometer 47 Microphone for measuring abnormal sound 57 Vibration sensor 67 Electric field / magnetic field sensor

Claims (18)

A moving railway vehicle is photographed using a camera, a long image data of the entire railway vehicle is generated from the photographed image using a processing device, and features extracted from the long image data are stored in advance. A rail vehicle inspection method using a long image, wherein the entire rail vehicle is inspected by determining a difference with a feature extracted from reference long image data. The railway vehicle inspection method using a long image according to claim 1, wherein for the long image data of the entire moving railway vehicle, a partial image is selected from the center of each image frame of the camera, and the partial images are combined. A railway vehicle inspection method using a long image characterized by being generated by the above.   3. The railway vehicle inspection method using a long image according to claim 2, wherein the partial image width of the image frame is selected based on a moving amount of the rail vehicle. Inspection method. 4. The railway vehicle inspection method using a long image according to claim 3, wherein the partial image width is wide when the movement amount of the railway vehicle is large, and is narrow when the movement amount is small. Railway vehicle inspection method using long images. The railway vehicle inspection method using the long image according to any one of claims 1 to 4, wherein the long image data created using the camera and the processing device is a side surface, a bottom surface, or an upper surface of the rail vehicle. A railway vehicle inspection method using a long image obtained from an image obtained by photographing Get the elongated image data of the whole railway vehicle moving with the camera and processing unit, to obtain different types of information in different types of sensors and the camera, the elongated image data and synchronize A railway vehicle inspection method using a long image, which is obtained as time-series data combined with the long image data .   7. The railway vehicle inspection method using a long image according to claim 6, wherein the sensor is used to measure an underfloor equipment temperature, a roof equipment temperature or a vehicle side surface temperature of the railway vehicle. Railway vehicle inspection method.   The railway vehicle inspection method using a long image according to claim 7, wherein the underfloor equipment temperature is a wheel bearing temperature.   7. The railway vehicle inspection method using a long image according to claim 6, wherein an abnormal sound of the railway vehicle is measured by the sensor.   7. The railway vehicle inspection method using a long image according to claim 6, wherein vibration of the railway vehicle is measured by the sensor.   The railway vehicle inspection method using a long image according to claim 6, wherein the electric field intensity or magnetic field intensity from the railway vehicle is measured by the sensor. (A) a camera that is placed beside or within a track and acquires an image of a moving railway vehicle;
With (b) from the image to produce a long image data of the entire rail vehicle, the difference by comparing the features extracted from the reference long image data previously stored extracted feature from the long continuous image data A railcar inspection device using a long image, comprising: a processing device that inspects the railcar by determining . (A) a camera that is placed beside or within a track and acquires an image of a moving railway vehicle;
(B) fixedly disposed in front Symbol line Michiwaki or in line, get another type of information from the image of the rail vehicle, and another type of sensor and the camera,
(C) a processing device that synchronizes the other type of information with the long image data generated from the image and acquires the information as time-series data combined with the long image data. Railway vehicle inspection device using a scale image.   14. The railway vehicle inspection apparatus using a long image according to claim 13, wherein the sensor is a thermo camera that measures an underfloor equipment temperature, an on-roof equipment temperature, or a vehicle side surface temperature of the railway vehicle. Railway vehicle inspection device using images.   15. The railway vehicle inspection apparatus using a long image according to claim 14, wherein the sensor is a non-contact type thermometer that measures a wheel bearing temperature of the railway vehicle. Inspection device.   14. The railway vehicle inspection apparatus using a long image according to claim 13, wherein the sensor is an abnormal sound measuring microphone for measuring noise of the railway vehicle. .   The railway vehicle inspection apparatus using a long image according to claim 13, wherein the sensor is a vibration sensor that measures vibration of the railway vehicle.   14. The railway vehicle inspection apparatus using a long image according to claim 13, wherein the sensor is an electric field / magnetic field sensor for measuring an electric field / magnetic field intensity from the railway vehicle. Vehicle inspection device.

Images