WO2016095328A1

WO2016095328A1 - Vehicle operation fault detection system and method

Info

Publication number: WO2016095328A1
Application number: PCT/CN2015/071850
Authority: WO
Inventors: 袁宁; 李骏; 郑煜; 宋野
Original assignee: 苏州华兴致远电子科技有限公司
Priority date: 2014-12-17
Filing date: 2015-01-29
Publication date: 2016-06-23
Also published as: CN104567725A

Abstract

A vehicle operation fault detection system and method. The system comprises: a three-dimensional information collection module (11) used for collecting three-dimensional image information of a vehicle, an identification module (12) used for identifying abnormal sites in the three-dimensional image information, and an alarm module (13) used for giving an alarm for the abnormal sites. The three-dimensional information collection module (11), the identification module (12) and the alarm module (13) are electrically connected. The system can collect three-dimensional image information of a vehicle in real time and given an alarm for abnormal sites during operation of the vehicle; in addition, the system does not give alarms for water stains, dust and other non-fault points, so as to improve alarm accuracy and avoid the problem that normal operation of the vehicle is affected due to false detection alarm.

Description

Vehicle operation fault detection system and method

The present application claims priority to Chinese Patent Application No. 201410789381.6, entitled "Vehicle Operation Fault Detection System and Method", filed on Dec. 17, 2014, the entire contents of which is incorporated herein by reference. .

Technical field

The present invention relates to the field of transportation technologies, and in particular, to a vehicle operation failure detection system and method.

Background technique

The traditional vehicle anomaly detection method is mainly based on the experience of the staff. This type of inspection requires the vehicle to enter or enter the warehouse. However, due to the complicated structure of the vehicle and the small number of small components, especially the EMU vehicles, the general length has More than 200 meters, there are thousands of bolts from the apron to the bogie and the bottom. At present, some vehicles usually run at the same time when the vehicle is running. Even if there are many stops in the middle, the stop time is very short. The detection time of the vehicle after entering the station is very short, so the manual detection method has the problems of low work efficiency and easy missed detection.

Summary of the invention

In order to overcome the problems in the related art, the present invention provides a vehicle operation failure detection system and method.

In a first aspect, the present invention provides a vehicle operating fault detection system comprising:

a three-dimensional information collecting module for collecting three-dimensional image information of the vehicle, the three-dimensional information collecting module being disposed at at least one of the bottom of the vehicle, the top of the vehicle, and the left and right sides of the vehicle and facing the The area to be inspected of the vehicle;

An identification module for identifying an abnormal portion in the three-dimensional image information; and

An alarm module for alerting the abnormal part;

The three-dimensional information collection module, the identification module, and the alarm module are electrically connected.

Optionally, the three-dimensional information collection module includes:

a structured light source for generating structured light projected onto the vehicle, the structured light source The illuminating light forms an illuminating area, and the area projected by the illuminating area on the vehicle covers the area to be detected;

An area array camera for collecting structural light image information projected in the area to be detected;

The imaging area of the area array camera on the vehicle covers all or part of the area to be detected, and an optical axis between the area camera and an optical axis of the structured light source is disposed at an angle.

Optionally, the three-dimensional information collection module further includes:

An image data collecting device for collecting vehicle image information of the area to be detected;

The image data collecting device covers all or part of the image forming area on the vehicle to the area to be detected.

Optionally, the structured light source is a line source, and the image data collecting device is a line camera;

The outgoing light of the line source forms an illumination plane, and the illumination plane forms a light strip on the vehicle;

The optical axis of the line camera is located in the illumination plane for collecting vehicle image information of the area to be detected;

The area array camera is located outside the illumination plane, and an angle is disposed between an optical axis of the area array camera and the illumination plane;

The area array camera covers the area to be detected in whole/part of the imaging area of the vehicle for collecting the structured light image information of the light strip.

a fill light source for supplementing light when the image data collecting device collects the image information of the vehicle;

The illumination source on the vehicle covers the image data acquisition device in an imaging region of the vehicle.

Optionally, the wavelength of the emitted light of the complementary light source is different from the wavelength of the emitted light of the structured light source.

Calibration piece

The calibration member is movable in an imaging region of the area array camera along an optical axis direction of the area array camera;

The area array camera captures a plurality of calibration image information included in the movement of the calibration piece.

Optionally, the three-dimensional information collection module includes:

At least two image data collection devices for acquiring two-dimensional image information including the same region to be detected from different locations;

Each of the image data collection devices is superimposed on an imaging area that is illuminated on the vehicle, wherein an area in which the imaging areas of the respective image data collection devices overlap is a to-be-detected area.

Optionally, the focal lengths of the respective image data collection devices are the same.

Optionally, an angle is disposed between optical axes of each of the image data collection devices;

The three-dimensional information collection module further includes: a structured light source for generating structured light projected on the vehicle, the structured light covering the area to be detected.

Optionally, the structured light source is at least one of a line source, a lattice source, a line array source, and a grid source.

Optionally, the image data collection device is at least one of a line camera, an area array camera, a line array camera, and an area array camera.

Optionally, it also includes:

a speed measuring device for measuring a vehicle speed when a vehicle passes on a track, and

a pulse generating circuit for generating a pulse control signal according to the vehicle speed measured by the speed measuring device and transmitting the signal to the three-dimensional information collecting module, so that the three-dimensional information collecting module can synchronously acquire the three-dimensional image information of the vehicle;

An input end of the pulse generating circuit is electrically connected to the speed measuring device, and an output end of the pulse generating circuit is electrically connected to the three-dimensional information collecting module.

Optionally, the identifying module includes:

a first memory for storing preset image information;

a first comparator for comparing the whole/partially described three-dimensional image information with the preset image information; and

A processor for extracting an abnormal portion in the three-dimensional image information according to a comparison result of the first comparator.

Optionally, the identifying module further includes:

a second memory for storing preset location information; and,

For comparing the three-dimensional image information with the preset position information to lock the preset position in the three-dimensional image information And a second comparator that intercepts the partial three-dimensional image information corresponding to the preset position;

The first comparator is further configured to compare the partial three-dimensional image information with preset image information; and

The processor is further configured to extract an abnormal part in the local three-dimensional image information according to the comparison result of the first comparator.

Optionally, the preset image information is image information of the fault-free vehicle, image information of the same vehicle passing through the nearest moment of the current sampling moment, and multiple sets of images of the same vehicle passing through the current sampling moment. At least one of statistical distribution information of information and image information of standard parts.

Optionally, the image information may be two-dimensional image information, or may be three-dimensional image information, where the three-dimensional image information may be composite information of the two-dimensional image information and the third-dimensional image information, or may be independent of each dimension image information. information.

In a second aspect, the present invention provides a vehicle operation failure detection method, including:

The three-dimensional information collecting module collects three-dimensional image information of a region to be detected of the vehicle;

The identification module identifies an abnormal part in the three-dimensional image information;

The alarm module alerts the abnormal part.

Optionally, the method further includes:

The speed measuring device measures the vehicle speed when the vehicle passes on the measuring track;

The pulse generating circuit generates a pulse control signal generated according to the vehicle speed measured by the speed measuring device and sends the pulse control signal to the three-dimensional information collecting module, so that the three-dimensional information collecting module can synchronously acquire the three-dimensional image information of the vehicle.

Optionally, the identifying module identifies an abnormal part in the three-dimensional image information, including:

Obtaining preset image information stored in the first memory;

The first comparator compares the whole/partially the three-dimensional image information with the preset image information;

The processor extracts an abnormal portion in the three-dimensional image information according to the comparison result of the first comparator.

Optionally, before the step of the first comparator comparing the whole/partial three-dimensional image information with the preset image information, the method further includes:

Obtaining preset location information stored in the second storage; and,

The second comparator compares the three-dimensional image information with the preset position information to lock the preset position in the three-dimensional image information, and intercepts the partial three-dimensional image information corresponding to the preset position;

among them,

The first comparator is configured to compare the partial three-dimensional image information with preset image information;

The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

The system provided by the embodiment of the invention can collect three-dimensional image information of the vehicle in real time during the running of the vehicle, and can perform image processing on the three-dimensional image information to identify an abnormality in the three-dimensional image information. The part, and the abnormal part is alarmed.

Compared with the prior art, since the three-dimensional image information of the vehicle is collected during the whole detection process, when the vehicle is fault-detected, the abnormal position of the three-dimensional structure on the vehicle can be detected in real time and accurately, and Because the water stains or dust on the vehicle will not affect the three-dimensional structure of the vehicle, the system will not alarm the non-fault points such as water stains and dust, which improves the accuracy of the alarm and avoids false alarms due to the detection of the vehicle. The problem affects normal operation. At the same time, the system also reduces the time for manual re-inspection and improves the detection efficiency.

The above general description and the following detailed description are intended to be illustrative and not restrictive.

DRAWINGS

The accompanying drawings, which are incorporated in the specification of FIG

1 is a schematic structural diagram of a vehicle running fault detection system according to an embodiment of the present invention;

2 is a schematic diagram of a scenario of a vehicle running fault detection system according to an embodiment of the present invention;

3 is a schematic diagram of a first structure of a three-dimensional information collection module according to an embodiment of the present invention;

4 is a schematic diagram of a second structure of a three-dimensional information collection module according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a third structure of a three-dimensional information collection module according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a third-dimensional information detection principle according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a fourth type of a three-dimensional information collection module according to an embodiment of the present disclosure;

FIG. 8 is a schematic structural diagram of a fifth type of a three-dimensional information collection module according to an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of a sixth type of a three-dimensional information collection module according to an embodiment of the present disclosure;

FIG. 10 is a schematic structural diagram of a seventh type of a three-dimensional information collection module according to an embodiment of the present disclosure;

Figure 11 is a schematic structural view of a specific embodiment of Figure 10;

FIG. 12 is a schematic structural diagram of an identification device according to an embodiment of the present invention;

FIG. 13 is a schematic structural diagram of another identification device according to an embodiment of the present disclosure;

FIG. 14 is a flowchart of a first method for detecting a running fault of a vehicle according to an embodiment of the present invention;

FIG. 15 is a flowchart of a second method for detecting a fault of a vehicle according to an embodiment of the present invention;

16 is a flowchart of a third method for detecting vehicle running faults according to an embodiment of the present invention;

FIG. 17 is a flowchart of a fourth method for detecting vehicle running fault according to an embodiment of the present invention.

detailed description

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. The following description refers to the same or similar elements in the different figures unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with aspects of the invention as detailed in the appended claims.

FIG. 1 is a schematic structural diagram of a vehicle running fault detection system according to an embodiment of the present invention. The vehicle motion fault detection system can be applied to a running vehicle, such as: an orbital train (including an EMU, a truck, a bus, a subway, or a city rail), and a vehicle that requires long-distance operation, such as a trackless train, or even some unmanned vehicles. . The vehicle operation fault detection system can detect the fault condition on the vehicle in operation, so that the vehicle can be easily non-contact detected when the vehicle is not parked or pitted.

As shown in FIG. 1 , the vehicle running fault system may include: a three-dimensional information collecting module 11 , an identifying module 12 and an alarm module 13 , wherein the three-dimensional information collecting module 11 , the identifying module 12 and the alarm module 13 are electrically connected.

The three-dimensional information collecting module 11 can be at least one, and at least one three-dimensional information collecting module 11 can be The three-dimensional information collecting module 11 can be located on the bottom of the vehicle, the top of the vehicle, and the two sides of the vehicle when the vehicle passes, so that each three-dimensional information collecting module 11 can collect the vehicle. Three-dimensional image information of the area to be detected.

The identification module 12 is connected to all the three-dimensional information collection modules 11 in a wireless/wired manner. The identification module 12 can be a microprocessor, a computer, or a server. The identification module 12 is used to collect three-dimensional images of all the three-dimensional information collection modules 11. The information is image processed to identify an abnormal portion in the three-dimensional image information.

The alarm module 13 is connected to the identification module 12 in a wireless/wired manner. The alarm module 13 is configured to alarm the identified abnormal portion when the identification module 12 recognizes the abnormal portion. The alarm module 13 can use at least one alarm mode, such as a text alarm, an image alarm, an audible alarm, and a light alarm light, in the embodiment of the present invention, the alarm module 13 can be a pop-up box on the display screen, and the sound is assisted. That is, combining the image and sound alarm modes.

Compared with the prior art, since the three-dimensional image information of the vehicle is collected during the whole detection process, when the vehicle is fault-detected, the abnormal position of the three-dimensional structure on the vehicle can be detected in real time and accurately. In addition, since the water stain or dust on the vehicle does not affect the three-dimensional structure of the vehicle, the system will not alarm the non-fault points such as water stains and dust, which improves the accuracy of the alarm and avoids the detection error of the vehicle. Alarms affect normal operation. At the same time, the system also reduces the traditional manual retest time, which improves the detection efficiency.

The vehicle running fault detection system provided by the embodiment of the present invention is described in detail below with reference to a specific scenario:

As shown in FIG. 2, the figure shows a schematic diagram of the vehicle running fault detecting system installed on the train track. The figure 2 includes: a track 100, a detecting point 200, a bottom box 101, a first side box 102 and a second. a side box 103, wherein a plurality of detecting points 200 may be disposed along the track 100, and a bottom box 101, a first side box 102 and a second side box 103 may be respectively disposed on each detecting point 200, and the bottom box The 101 is disposed between the pair of rails 100, and the first side box 102 and the second side box 103 are respectively disposed on both outer sides of the rail 100.

In the embodiment of the present invention, the positions of the first side box 102 and the second side box 103 may be in line with the position of the bottom box 101, and the bottom box 101, the first side box 102 and/or the second side box 103 Can be set It is placed on the base surface of the track and can also be placed under the base surface of the track by means of full or semi-buried.

One or more three-dimensional information collecting modules 11 are respectively disposed in the bottom box 101, the first side box 102, and the second side box 103, and one or more three-dimensional information collecting modules 11 can be simultaneously disposed in the bottom box 101. When a plurality of three-dimensional information collecting modules 11 are disposed in a box, the areas on the vehicle collected by the plurality of three-dimensional information collecting modules 11 are not completely identical, and may not overlap or partially overlap at all.

The three-dimensional information collecting module 11 in the bottom box 101 is used to collect three-dimensional image information on the track passing through the bottom of the vehicle, and the three-dimensional information collecting modules in the first side box 102 and the second side box 103 are respectively used to collect three-dimensional images on both sides of the vehicle. information.

In the embodiment of the present invention, the three-dimensional image information may be composite information of the two-dimensional image information of the to-be-detected area of the vehicle and the third-dimensional image information (usually image depth information), or may be independent information of the image information of each dimension.

In FIG. 2, 12 is an identification module, and the identification module is respectively connected to all three-dimensional information collection modules on the detection point 200. In the embodiment of the present invention, as shown in FIG. 2, the identification module 12 is connected to all three-dimensional information collection modules on the detection point 200 through the second side box 103.

The identification module 12 can calculate the three-dimensional structure information of the vehicle according to the three-dimensional image information collected by all the three-dimensional information collection modules on the detection point 200, and compare the three-dimensional structure information with the preset image information of the vehicle acquired in advance to determine the three-dimensional structure. A part of the information that differs from the preset image information and an alarm is issued.

The preset image information may be image information of the fault-free vehicle, image information of the same vehicle passing through the nearest moment of the current sampling time, and statistical distribution information of the plurality of sets of image information of the same vehicle passing through the current sampling moment. And at least one of the image information of the standard component, wherein the preset image information may be two-dimensional image information or three-dimensional image information.

As can be seen from FIG. 2, in a specific application, one or more three-dimensional information collecting devices may be disposed at a plurality of detecting points along the train track, and a plurality of three-dimensional information collecting devices on the same detecting point may be They are all connected to an identification module so that when the vehicle travels along the track, the three-dimensional fault condition of the vehicle can be detected along the track. Therefore, the system can complete the fault detection during the running of the vehicle and improve the fault detection efficiency.

When a plurality of three-dimensional information collecting devices are disposed on the same detecting point 200, as shown in FIG. 2, the system may further include: a speed measuring device 14 and a pulse generating circuit 15, wherein:

The speed measuring device may include: a speed measuring radar and/or a speed measuring magnet, and other speed measuring methods commonly used in the art. As shown in FIG. 2, the speed measuring device in the figure uses a speed measuring magnet. In FIG. 2, the speed measuring device 14 may include: a magnetic steel A1 and a magnetic steel A2, and the magnetic steel A1 and the magnetic steel A2 are located at the bottom in the direction of the track extension. One side of the box 101 is used to obtain vehicle information of the vehicle in the direction of the magnetic steel, and the vehicle speed of the vehicle can be calculated by the position between different magnetic steels and the time when different magnetic steels are in contact with the vehicle wheels;

The input of the pulse generating circuit 15 is connected to the speed measuring device 14, and the output of the pulse generating circuit 15 is connected to each of the three-dimensional information collecting modules 11 (not shown in Fig. 2).

The pulse generation circuit 15 is configured to generate a pulse control signal based on the measured vehicle speed, and the pulse generation circuit 15 transmits the generated pulse control signal to each of the three-dimensional information acquisition modules at the same detection point position. The pulse signal is used to control all three-dimensional information acquisition modules at the same detection point position to perform image information collection according to the same timing, that is, the three-dimensional information acquisition module at the same detection point position performs image information collection according to the synchronization timing.

According to the system provided by the embodiment of the present invention, each three-dimensional information collection module can perform image collection according to the same pulse signal, so that the three-dimensional image information does not appear in the three-dimensional image acquisition module when the fault detection is performed. Corresponding problems improve the accuracy of fault detection. In addition, when collecting three-dimensional image information of the vehicle, a plurality of three-dimensional information acquisition modules at the same detection point position may also perform image information collection according to the same pulse signal, so that the three-dimensional information acquisition module acquires synchronously according to the same acquisition timing. .

As shown in FIG. 3, the figure 300 is a detected vehicle. In the embodiment of the present invention, each of the three-dimensional information collection modules 11 includes: a structured light source 111 and an area array camera 112, wherein:

The structured light source 111 is configured to generate structured light projected on the vehicle, and the outgoing light of the structured light source 111 forms an illumination area, and the area projected by the illumination area on the vehicle can cover the area to be detected.

The structured light source 111 may be at least one of a line source, a lattice source, a line source, and a grid source. In the embodiment shown in FIG. 3, the structured light source 111 is preferably a line source.

The area array camera 112 is configured to collect structured light image information projected in the area to be detected;

In addition, the imaging area of the area array camera 112 on the vehicle covers all or part of the area to be detected, and an optical axis between the area array camera 112 and the optical axis of the structured light source 111 is provided with an angle.

Thus, when the structured light illuminated by the structured light source 111 is projected onto the vehicle, the area array camera 112 can The image information of the area to be detected in which the structured light is located on the vehicle is obtained from the side. Taking the shape of the structured light as a circle, for example, since the optical axis of the area array camera 112 and the optical axis of the structured light source 111 have a certain angle, The structured light in the acquired image information will become elliptical; correspondingly, when the surface of the vehicle in the area to be detected has a depth variation feature of the concave and convex, the structured light image information acquired by the area array camera 112 The shape also changes correspondingly. In FIG. 3, when the structured light source 111 is irradiated onto the groove on the detected vehicle, a polygonal line of light having groove depth information is formed. At this time, the area array camera 112 is collected. The structured light source 111 illuminates the image information on the groove, so that the depth information corresponding to the groove on the area to be detected can be acquired, and the image b is the structured light source 111 acquired by the area array camera 12 located in the area to be detected on the vehicle. Image information with depth information.

In addition, the above-mentioned area array camera 112 can acquire the two-dimensional image information of the area to be detected on the vehicle while acquiring the depth information of the image of the area to be detected where the structured light is located on the vehicle; through the area array camera 112 and the structured light source After the conversion processing of the position information between 111, the three-dimensional information collecting module can also acquire the three-dimensional image information of the area to be detected.

In another embodiment of the present invention, as shown in FIG. 4, the three-dimensional information collecting module 11 may further include: an image data collecting device 113, wherein the image data collecting device 113 covers all or part of the structured light on the imaging area on the vehicle. The area to be detected illuminated by the light source is used to collect vehicle image information of the area to be detected. Here, the image information acquired by the image data collecting device 113 is two-dimensional image information of the vehicle, which may be an area array camera, a line array camera, or a device such as an area array camera or a line array camera, depending on the operation of the vehicle. Speed and image detection accuracy standards, you can choose the area array camera, line array camera, area array camera or line array camera at the right time. In addition, the image data collecting device may be a visible light image data collecting device or a non-visible light image data collecting device, for example, a band pass image data collecting device processed by a filter, an infrared thermal image device or an ultraviolet device. Image data acquisition devices well known to those skilled in the art, such as thermal imaging devices.

In addition, in order to miniaturize the system structure, the structured light source 111 can also serve as a fill light source to fill the area of the vehicle to be detected.

In the preferred embodiment, the three-dimensional information collecting module may further include: a fill light source 114, as shown in FIG. 4, in the embodiment of the present invention, in consideration of the sharpness of the two-dimensional image collected by the image data collecting device 113.

The fill light source 114 is used to fill light when the image data collecting device collects the vehicle image information, and the illumination light source 114 covers the image data collecting device on the imaging area of the vehicle in the illumination area on the vehicle, the structured light source 111 and the complementary light source. 114 wavelengths can be the same, but to avoid between the two The image interference, the structured light source 111 and the fill light source 114 are preferably different wavelengths. For example, the line source may be a laser of 700 to 1000 nm, and the fill light source may be a laser of 600 to 900 nm. Moreover, the fill light source is no longer a line source, but may be a diffused light source, such as a common illumination lamp.

In a specific application embodiment, as shown in FIG. 5, the structured light source 111 is a line source, and the image data collecting device 113 is a line camera;

The area array camera 112 is located outside the illumination plane, and an angle is formed between the optical axis of the area array camera 112 and the illumination plane;

The area array camera 112 illuminates the imaging area of the vehicle in whole or in part covering the area to be detected for collecting structured light image information of the light strip formed by the line source on the vehicle. As can be seen from FIG. 5, when the line light source illuminates the formed linear light band on the detected vehicle 300, the shape of the light band in the image b collected by the area camera 112 appears tortuous with the groove on the detected vehicle 300. The shape of the light strip in the image a captured by the line camera is still linear, and the plurality of image information collected by the line camera can constitute the overall two-dimensional image information of the exterior of the vehicle.

In an embodiment of the present invention, as shown in FIG. 5, the device may further include: a calibration component 115,

The calibration component 115 is independent of the vehicle to be inspected, and may be a calibration component, a calibration plate, or the like, which is well known to those skilled in the art. Further, the calibration component 115 may be independent of the three-dimensional information acquisition module 11 shown in FIG. 4, and may also be The three-dimensional information acquisition module is disposed on the same bracket. As shown in FIG. 5, the calibration member 115 is disposed in the imaging area of the line camera and the area array camera, and the calibration member can be moved along the axis of the area array camera. When the calibration member 115 is moved, the area array camera 112 is also used for acquisition. A plurality of calibration image information during the movement of the calibration piece. The calibration member 115 is typically moved when the vehicle fails, and then a plurality of calibration image information can be acquired in advance.

In an embodiment of the present invention, the three-dimensional information collecting module may further include: a calibration information acquiring device, a depth information computing device, and an image information synthesizing device.

The calibration information acquiring device is configured to obtain calibration information according to image information of the calibration component in the plurality of calibration images, the calibration information includes: a distance between the calibration component and the area array camera, and an image of the calibration component is located in the image of the area array camera The number of rows on the sensor.

As shown in FIG. 6, it can be seen that when the calibration member 115 moves along the axial direction of the area array camera 112, since there will be image information of the calibration member 115 in the plurality of calibration images acquired by the area array camera 112, then When the calibration images are combined together, a coordinate system as shown in Fig. 6 is obtained. The x coordinate is the distance between the calibration member 115 and the area array camera, and the y coordinate is the optical band on the area array camera image sensor. The number of rows Li, when the calibration member 115 moves, is different from the distance between the area array cameras. Therefore, the corresponding number of rows Li is also different, and a curve can be fitted by using the corresponding relationship, as shown in FIG. 6. Through this fitting curve, in the actual detection process of the vehicle, the number of lines of the light on the image sensor of the area camera can be determined by the number of lines of light on the image sensor of the area to be detected in the area to be detected. The actual distance X.

The depth information calculating means is configured to determine depth information between the optical strips in each structured light image and the area array camera based on the calibration information and the information of the optical strips in the structured light image.

As shown in FIG. 6, by using the position of the light band corresponding to the light in the coordinate system, the depth information between the different points on the light strip to the area array camera can be calculated.

The image information synthesizing device is configured to synthesize the depth information between the different points on the optical strip calculated by the depth information computing device to the area array camera and the vehicle image information collected by the line camera, thereby obtaining three-dimensional image information of the vehicle.

In another embodiment of the present invention, the three-dimensional information collecting module may include: at least two image data collecting devices, configured to collect two-dimensional image information including the same to-be-detected region from different locations, and in the preferred embodiment, at least two images The data acquisition devices have the same focal length, and the optical axes can be parallel or set with a certain angle. In either case, the respective image data collecting devices overlap in the imaging regions that are illuminated on the vehicle, wherein the regions in which the imaging regions of the respective image data collecting devices overlap are covered by the regions to be detected. In a preferred embodiment, the three-dimensional information collecting module includes the above two image data collecting devices, and the image data collecting device may be an area array camera, a line array camera, or a camera or the like, depending on the running speed and image of the vehicle. Accuracy standards for detection, you can choose an area array camera, line array camera or line array camera or area array camera at the right time.

As shown in FIG. 7 , this embodiment discloses a structure of a three-dimensional information collecting module. The three-dimensional information collecting module 11 includes two image

data collecting devices

411A and 411B whose optical axes are parallel to each other, wherein the two images are The phase planes of the

data acquisition devices

411A, 411B are on the same plane, and the focal lengths are equal.

When the detected vehicle (or calibrator) 300 is in the Zi position in the area to be detected C, the image

data collecting devices

411A, 411B can simultaneously acquire the two-dimensional image of the detected vehicle 300, at this time, If the image center position of the detected vehicle 300 collected on the image data collecting device 411A is the reference position, the image center position of the detected vehicle 300 collected on the image data collecting device 411B may generate a horizontal offset ΔXi with respect to the reference position. .

When the detected vehicle 300 is sequentially moved from Z1 to Z3, the image

data collecting devices

411A, 411B can acquire a plurality of two-dimensional image groups of the detected vehicle 300, and at this time, between the horizontal offsets ΔXi and Zi The positional relationship can be fitted to obtain a fitting curve. In the process of actual vehicle detection, the positional relationship between the feature points between the two image

data collecting devices

411A and 411B can be obtained, and the vehicle surface in the area to be detected is obtained. The accurate depth information of the component and the corresponding relationship between the respective feature points and the two-dimensional image acquired on the image data collecting device 411A can construct a three-dimensional size model of the to-be-detected region C or the detected vehicle 300.

As shown in FIG. 8 and FIG. 9 , the embodiment discloses another two structures of the three-dimensional information collecting module 11 , including an image data collecting device with an angle of two optical axes, and the detecting mechanism and the detecting mechanism shown in FIG. 7 . the same.

The three-dimensional information collecting module 11 shown in FIG. 8 and FIG. 9 can be applied to different detection situations: wherein the structure shown in FIG. 8 is suitable for a case where the divergence angle of the detection range is large and the depth of field of the area to be detected is short; FIG. The structure shown is suitable for the case where the detection range is relatively concentrated and the depth of field of the area to be detected is long.

In addition, in order to improve the detection accuracy of the three-dimensional information, in the preferred embodiment, the three-dimensional information acquisition module 11 further includes a structured light source for generating structured light projected on the vehicle, and the projected structured light can be covered. Detection area.

FIG. 10 is a schematic diagram of another structure of a three-dimensional information collection module according to an embodiment of the present invention. The structured light source is 111. When the structured light illuminated by the structured light source 111 is located in the vehicle to be detected, the image data collection device 411A. 411B synchronously collects the two-dimensional image information of the structure light in the area to be detected, and performs the three-dimensional image information of the area to be detected through the stereo calibration, the correlation point correction and the matching operation of the image

data collection devices

411A and 411B.

The structured light source 111 may be located between the two image

data collecting devices

411A, 411B or on the outer side of the side where the image

data collecting device

411A or 411B is located. In this embodiment, in order to improve the detection accuracy of the three-dimensional information collecting module. And the data processing process for simplifying the image information, the two image

data collecting devices

411A, 411B are symmetrically disposed centering on the central axis of the structured light, and the

optical axes

411A, 411B of the two image data collecting devices and the optical axis of the structured light source 111 Coplanar. Among them, the knot The light source may be at least one of a line source, a lattice source, a line source, and a grid source or a source that is calibrated by size as known to those skilled in the art. In this embodiment, in order to facilitate parameter calibration during installation and debugging of the three-dimensional information acquisition module, the structured light source is preferably an array light source, for example, a lattice source, a line array source, a grid source, etc., and further, the array spacing can be reduced. In order to improve the accuracy of parameter calibration and detection, of course, this will also bring about a large amount of data calculation.

FIG. 11 is a schematic structural diagram of a specific embodiment of FIG. 10. FIG. 11 further includes: a storage device 5 and a remote communication interface 6. The embodiment is used for collecting vehicle wheel tread defect information, wherein the two image data collecting devices collect two-dimensional image information including the tread surface passing through the wheel of the vehicle from different positions, and the storage device disposed in the system The calibration information of the image data collecting device in each three-dimensional information collecting module is also stored in 5. In this way, when the vehicle passes the detection point on the track, the image data acquisition device in each three-dimensional information acquisition module can collect the two-dimensional image information including the structured light irradiated on the tread surface of the vehicle wheel, and send the two-dimensional image information. In the identification module (which may be an image processor), the identification module may also acquire calibration information from the storage device 5, and send all the received two-dimensional image information together with the calibration information to the remote communication module to pass the remote communication module. Sent to the backend server. In this way, the background server can perform image processing on all the two-dimensional image information by using the received calibration information, thereby obtaining the three-dimensional tread defect information of the final vehicle wheel.

In addition, the three-dimensional information acquisition module can also monitor the working state of a single contact line in the contact network and detect geometric parameters, such as contact line height, pull-out value, and contact line offset.

In the embodiment of the present invention, as shown in FIG. 12, the identification module 12 may further include: a first memory 121, a first comparator 122, and a processor 123, where

The first memory 121 (which may be the storage device 5 in FIG. 11) stores preset image information, where the preset image information may be: image information of the fault-free vehicle, and the same vehicle passing through the nearest moment of the current sampling moment. The image information of the vehicle, the statistical distribution information of the plurality of sets of image information of the same vehicle passing through the current sampling time, and the image information of the standard component, and the image information may be two-dimensional image information. The three-dimensional image information may be three-dimensional image information, which may be composite information of the two-dimensional image information and the third-dimensional image information, or may be independent information of the respective dimensional image information.

The first comparator 122 is configured to compare the whole/partial three-dimensional image information with the preset image information. When performing the comparison, the depth information included in the three-dimensional image information needs to be compared with the depth information in the preset image information. Yes, once the depth information is inconsistent, the position is determined as the abnormal part. Bit.

The processor 123 is configured to extract an abnormal part in the three-dimensional image information according to the comparison result of the first comparator.

When the running track of the vehicle is fixed, the first memory 121 may pre-store the image information of the same vehicle passing through the nearest moment of the current sampling time as the preset image information. At this time, the first comparator 122 collects the information collected by the three-dimensional information collecting module. The three-dimensional image information of each part of the vehicle is compared with the corresponding part of the preset image information one by one, and once the depth information is inconsistent, the abnormal part is alarmed. This method can effectively ensure the recognition accuracy of vehicle running faults, and avoid the phenomenon of vehicle fault false alarms caused by missed detection and false detection. However, at the same time, the detection method takes a long time to identify the abnormal part, and the real-time performance of the fault detection decreases.

In a preferred embodiment, the two-dimensional information part of the three-dimensional image information part of each part of the vehicle acquired by the three-dimensional information collection module may be used to retrieve the corresponding two-dimensional image information part of the preset image information, and the primary part of the abnormal part is performed. After locking, the depth information is compared with the locked abnormal part. When the depth information is inconsistent, the abnormal part is alarmed. This method can effectively improve the operation speed of the first comparator and the processor while ensuring the recognition accuracy of the vehicle running fault, and can save a large amount of transmission bandwidth, and can satisfy the limited bandwidth of the communication cable. Real-time transmission requirements.

In another preferred embodiment, as shown in FIG. 13, the identification module further includes a second memory 124 and a second comparator 125. The second memory 124 is configured to store preset position information of a preset component on the vehicle, and the preset position information may be at least one of axle position information, vehicle speed information, and fixed component position information of the to-be-detected area, or other capable Location information known to those skilled in the art for locating the area to be detected. The second comparator 125 is configured to compare the three-dimensional image information with the preset position information, thereby locking the preset position in the three-dimensional image information, and intercepting the partial three-dimensional image information corresponding to the preset position in the three-dimensional image information. The first comparator 122 also compares the captured partial three-dimensional image information with the preset image information, and the processor 123 may further extract the abnormal portion in the partial three-dimensional image information according to the comparison result of the first comparator.

In specific applications, some of the iconic features that may be pre-set on the vehicle, such as holes or rods, and the image information of the standard components in which the iconic features are located are known, and around the iconic features The location information of the components is also known. The second comparator can be a three-dimensional information acquisition module The collected three-dimensional image information is compared with the preset position information, thereby locking the preset position in the three-dimensional image information, and intercepting the partial three-dimensional image information corresponding to the preset position in the three-dimensional image information. Since the image information of the standard component around the iconic feature is known, when the comparison is performed, the captured partial 3D image information is compared with the image information of the standard component, and then the abnormal part extraction is performed in the processor. When the partial three-dimensional image information corresponding to the preset position is operated, if an abnormal part is found, for example, a bolt is lost, the specific position of the bolt loss can be determined.

In the embodiment shown in FIG. 13, since the identification module does not analyze the entire three-dimensional image information in turn, the partial three-dimensional image information around the preset component can be analyzed, and thus, in the application, the focus is on the preset position. Find faulty preset parts to improve fault detection and detection efficiency. In addition, this method is also suitable for fault detection of vehicles with uncertain vehicle running orbits.

Based on the foregoing device embodiment, the embodiment of the present application further provides a vehicle operation fault detection method. As shown in FIG. 14, the method may include the following steps:

Step S100: The three-dimensional information collection module collects three-dimensional image information of the to-be-detected area of the vehicle;

Step S200: the recognition module identifies an abnormal part in the three-dimensional image information;

Step S300: The alarm module alarms the abnormal part.

On the basis of the embodiment shown in FIG. 14, in another embodiment of the present application, as shown in FIG. 15, the method may further include the following steps:

Step: S400: The speed measuring device measures the vehicle speed when the vehicle passes on the measuring track;

Step: S500: The pulse generation circuit generates a pulse control signal generated according to the vehicle speed measured by the speed measuring device and sends the pulse control signal to the three-dimensional information collecting module, so that the three-dimensional information collecting module can synchronously collect the three-dimensional image information of the vehicle.

On the basis of the embodiment shown in FIG. 14, in another embodiment of the present application, as shown in FIG. 16, the method may further include the following steps:

Step S210: Acquire preset image information stored in the first memory;

Step S211: the first comparator compares the overall/partial three-dimensional image information with the preset image information;

Step S212: The processor extracts an abnormal part in the three-dimensional image information according to the comparison result of the first comparator.

On the basis of the embodiment shown in FIG. 14, in another embodiment of the present application, as shown in FIG. 17, before the step S211, the method may further include the following steps:

Step S220: Acquire preset location information stored in the second storage;

Step S221: The second comparator compares the three-dimensional image information with the preset position information to lock the preset position in the three-dimensional image information, and intercepts the partial three-dimensional image information corresponding to the preset position;

In addition, on the basis of step S220 to step S221, the first comparator is configured to compare the partial three-dimensional image information with the preset image information;

And the processor is further configured to extract an abnormal part in the partial three-dimensional image information according to the comparison result of the first comparator.

For a detailed description of the steps of the foregoing method embodiments, refer to the detailed description in the foregoing device embodiments, and details are not described herein.

Other embodiments of the invention will be apparent to those skilled in the <RTIgt; The present invention is intended to cover any variations, uses, or adaptations of the present invention, which are in accordance with the general principles of the invention and include common general knowledge or common technical means in the art that are not disclosed in the present disclosure. . The specification and examples are to be considered as illustrative only,

It is to be understood that the invention is not limited to the details of the details of The scope of the invention is limited only by the appended claims.

Claims

A vehicle operation fault detection system, comprising:

a three-dimensional information collecting module for collecting three-dimensional image information of the vehicle, the three-dimensional information collecting module being disposed at at least one of the bottom of the vehicle, the top of the vehicle, and the left and right sides of the vehicle and facing the The area to be inspected of the vehicle;

An identification module for identifying an abnormal portion in the three-dimensional image information; and

An alarm module for alerting the abnormal part;

The three-dimensional information collection module, the identification module, and the alarm module are electrically connected.
The vehicle operation fault detection system according to claim 1, wherein the three-dimensional information collection module comprises:

a structured light source for generating structured light projected on the vehicle, the outgoing light of the structured light source forming an illumination area, the area projected by the illumination area on the vehicle covering the area to be detected;

An area array camera for collecting structural light image information projected in the area to be detected;

The imaging area of the area array camera on the vehicle covers all or part of the area to be detected, and an optical axis between the area camera and an optical axis of the structured light source is disposed at an angle.
The vehicle operation fault detection system according to claim 2, wherein the three-dimensional information collection module further comprises:

An image data collecting device for collecting vehicle image information of the area to be detected;

The image data collecting device covers all or part of the image forming area on the vehicle to the area to be detected.
The vehicle operation fault detection system according to claim 3, wherein the structured light source is a line source, and the image data acquisition device is a line camera;

The outgoing light of the line source forms an illumination plane, and the illumination plane forms a light strip on the vehicle;

The optical axis of the line camera is located in the illumination plane for collecting vehicle image information of the area to be detected;

The area array camera is located outside the illumination plane, and an angle is disposed between an optical axis of the area array camera and the illumination plane;

The area array camera covers the area to be detected in whole/part of the imaging area of the vehicle for collecting structured light image information of the light strip.
The vehicle operation failure detecting system according to claim 3, wherein said three The dimension information collection module also includes:

a fill light source for supplementing light when the image data collecting device collects the image information of the vehicle;

The illumination source on the vehicle covers the image data acquisition device in an imaging region of the vehicle.
The vehicle operation fault detection system according to claim 2, wherein the three-dimensional information collection module further comprises:

Calibration piece

The calibration member is movable in an imaging region of the area array camera along an optical axis direction of the area array camera;

The area array camera captures a plurality of calibration image information included in the movement of the calibration piece.
The vehicle operation fault detection system according to claim 1, wherein the three-dimensional information collection module comprises:

At least two image data collection devices for acquiring two-dimensional image information including the same region to be detected from different locations;

Each of the image data collecting devices is located in an image forming area on the vehicle, wherein an area of each of the image data collecting devices that overlaps the image forming area covers the area to be detected.
The vehicle operation fault detection system according to claim 7, wherein the three-dimensional information acquisition module further comprises: a structured light source for generating structured light projected on the vehicle, the structured light covering the Area to be tested.
The vehicle operation fault detection system according to any one of claims 2-8, wherein the structured light source is at least one of a line source, a lattice source, a line array source, and a grid source.
The vehicle operation failure detecting system according to any one of claims 2-8, wherein the image data collecting device is at least one of a line camera, an area array camera, a line camera, and an area camera.
The vehicle operation fault detection system according to claim 1, further comprising:

a speed measuring device for measuring a vehicle speed when a vehicle passes on a track, and

a pulse generating circuit for generating a pulse control signal according to the vehicle speed measured by the speed measuring device and transmitting the signal to the three-dimensional information collecting module, so that the three-dimensional information collecting module can synchronously acquire the three-dimensional image information of the vehicle;

An input end of the pulse generating circuit is electrically connected to the speed measuring device, and an output end of the pulse generating circuit is electrically connected to the three-dimensional information collecting module.
The vehicle operation fault detection system according to claim 1, wherein the identification module comprises:

a first memory for storing preset image information;

a first comparator for comparing the whole/partially described three-dimensional image information with the preset image information; and

A processor for extracting an abnormal portion in the three-dimensional image information according to a comparison result of the first comparator.
The vehicle operating fault detection system according to claim 12, wherein the identification module further comprises:

a second memory for storing preset location information; and,

a second comparator for matching the three-dimensional image information with the preset position information to lock the preset position in the three-dimensional image information, and intercepting the partial three-dimensional image information corresponding to the preset position;

The first comparator is further configured to compare the partial three-dimensional image information with preset image information; and

The processor is further configured to extract an abnormal part in the local three-dimensional image information according to the comparison result of the first comparator.
A vehicle operation fault detection method, comprising:

The three-dimensional information collecting module collects three-dimensional image information of a region to be detected of the vehicle;

The identification module identifies an abnormal part in the three-dimensional image information;

The alarm module alerts the abnormal part.
The method of claim 14, wherein the method further comprises:

The speed measuring device measures the vehicle speed when the vehicle passes on the measuring track;

The pulse generating circuit generates a pulse control signal generated according to the vehicle speed measured by the speed measuring device and sends the pulse control signal to the three-dimensional information collecting module, so that the three-dimensional information collecting module can synchronously acquire the three-dimensional image information of the vehicle.
The method according to claim 14, wherein the identifying module identifies an abnormal part in the three-dimensional image information, including:

Obtaining preset image information stored in the first memory;

The first comparator compares the whole/partially the three-dimensional image information with the preset image information;

The processor extracts an abnormal portion in the three-dimensional image information according to the comparison result of the first comparator.
The method according to claim 16, wherein before the step of comparing the whole/partial three-dimensional image information with the preset image information by the first comparator, the method further comprises:

Obtaining preset location information stored in the second storage; and,

The second comparator compares the three-dimensional image information with the preset position information to lock the preset position in the three-dimensional image information, and intercepts the partial three-dimensional image information corresponding to the preset position;

among them,

The first comparator is configured to compare the partial three-dimensional image information with preset image information;

The processor is further configured to extract an abnormal part in the local three-dimensional image information according to the comparison result of the first comparator.