Train head detection device and method

Abstract

The present invention discloses a device and method for detecting the front of a train, comprising a speed measuring module collecting the timestamp of the wheel passing over two adjacent speed measuring positions and sending it to a signal processing module, which calculates the current vehicle speed; the signal processing module calculates the pulse frequency according to the current vehicle speed, sends a pulse signal to an image processing module, and calculates the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area; the image processing module collects the image of the roof detection area based on the received pulse signal, generates a first timestamp and sends it to the signal processing module when the image pixel changes, the signal processing module obtains the second timestamp of the vehicle arriving at the front detection area based on the first timestamp and the trigger delay and sends it to the image processing module, and the image processing module collects the image of the front according to the second timestamp. The present invention can accurately calculate the time when the front of the vehicle arrives at the detection area, can ignore the difference in vehicle wheelbase, and is more stable and reliable.

Description

Technical Field

[0001] The invention belongs to the technical field of railway line operation and maintenance detection equipment, and in particular relates to a device and method for detecting a train head. Background Art

[0002] With the advancement of technology, more and more high-precision unmanned intelligent safety detection and monitoring equipment are installed in railway monitoring stations. The harsh outdoor working environment has a great impact on the reliability of high-precision optical sensors. At present, the main methods for detecting the front of the train entering the detection area are wheel magnet detection and photoelectric sensor detection.

[0003] Traditional wheel magnet detection can effectively detect whether the train wheels have reached the detection area, but due to the different models of trains, their wheelbase information is also different, and it is impossible to correctly and effectively detect whether the train head has reached the detection area. Photoelectric sensors are sensors that use photoelectric elements as detection elements.

[0004] It first converts the measured changes into changes in light signals, and then further converts the light signals into electrical signals with the help of photoelectric elements. Photoelectric sensors generally consist of three parts: light source, optical path and photoelectric element. Therefore, when used in outdoor working conditions, it is easily interfered by dust, rain, fallen leaves and outdoor light. Traditional photoelectric detection sensors can detect whether the front of the train has reached the detection area, but due to the above factors, it is easy to generate false signals or omissions, resulting in the accuracy and reliability of the train head detection results not meeting the requirements in higher index application scenarios. Summary of the invention

[0005] In view of the above problems, the present invention proposes a device and method for detecting the front of a train, which can accurately calculate the time when the front of the train arrives at the detection area, ignore the difference in vehicle wheelbase, and is more stable and reliable.

[0006] In order to achieve the above technical objectives and the above technical effects, the present invention is implemented through the following technical solutions:

[0007] In a first aspect, the present invention provides a train head detection device, comprising:

[0008] The speed measurement module is used to collect the timestamps when the wheels pass through two adjacent speed measurement positions and send them to the signal processing module so that the signal processing module can calculate the current vehicle speed;

[0009] The signal processing module is further used to calculate the pulse frequency according to the current vehicle speed, send a pulse signal to the image processing module based on the pulse frequency, and calculate the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area;

[0010] The image processing module is used to collect images of the roof detection area based on the received pulse signal. When a change in the image pixels is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains a second timestamp when the vehicle arrives at the front detection area based on the first timestamp and the trigger delay and sends it to the image processing module, so that the image processing module collects the image of the front of the vehicle according to the second timestamp.

[0011] Optionally, the image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the roof image acquisition unit and the front image acquisition unit are arranged sequentially along the travel direction of the train;

[0012] The roof image acquisition unit is used to capture the image of the train roof detection area based on the received pulse signal and send it to the image processing unit. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to capture the image of the train head according to the second timestamp.

[0013] Optionally, the roof image acquisition unit is a line array camera, and the front image acquisition unit is an area array camera.

[0014] Optionally, the method for generating the first timestamp includes:

[0015] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0016]

[0017] Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame;

[0018] When i >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0019] Optionally, the method for generating the first timestamp includes:

[0020] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0021]

[0022] Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j I i+nj and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed, and the greater the speed, the smaller the n value; j is the pixel number in each frame, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows in the image frame;

[0023] When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0024] Optionally, the speed measuring module includes a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel;

[0025] The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area;

[0026] The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

[0027] In a second aspect, the present invention provides a method for detecting a train head, characterized by comprising:

[0028] The speed measurement module is used to collect the timestamps of the wheels passing through two adjacent speed measurement positions and send them to the signal processing module, so that the signal processing module calculates the current vehicle speed;

[0029] Calculate the pulse frequency using the signal processing module according to the current vehicle speed, send a pulse signal to the image processing module based on the pulse frequency, and calculate the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area;

[0030] The image processing module is used to collect images of the roof detection area based on the received pulse signal. When a change in the image pixels is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains a second timestamp when the vehicle arrives at the front detection area based on the first timestamp and the trigger delay, and sends it to the image processing module, so that the image processing module collects the image of the front of the vehicle according to the second timestamp.

[0031] Optionally, the image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the front image acquisition unit and the image processing unit are arranged in sequence along the travel direction of the train;

[0032] The roof image acquisition unit is used to capture the image of the train roof detection area based on the received pulse signal and send it to the image processing unit. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp when the vehicle arrives at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to capture the image of the train head according to the second timestamp.

[0033] Optionally, the method for generating the first timestamp includes:

[0034] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0035]

[0036] Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame;

[0037] When i >T g When T g is the image grayscale change threshold, it is determined that the train head reaches the train roof detection area, and the first timestamp is generated at the same time;

[0038] Alternatively, the method for generating the first timestamp includes:

[0039] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0040]

[0041] Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed, and the greater the speed, the smaller the n value; j is the pixel number in each frame, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows in the image frame;

[0042] When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0043] Optionally, the speed measuring module includes a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel;

[0044] The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area;

[0045] The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] Since the detection of the train head is difficult, the timing of the detection is more important than other detections. To this end, the present invention proposes to use a speed measurement module to collect the timestamp of the wheel passing through two adjacent speed measurement positions, and send it to a signal processing module, so that the signal processing module calculates the current vehicle speed; the signal processing module calculates the pulse frequency according to the current vehicle speed, and sends a pulse signal to the image processing module based on the pulse frequency, and calculates the trigger delay based on the current vehicle speed and the distance between the roof detection area and the head detection area; the image processing module collects the image of the roof detection area based on the received pulse signal, and when the image pixel changes, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the head detection area based on the first timestamp and the trigger delay and sends it to the image processing module, so that the image processing module collects the image of the head according to the second timestamp, realizing the linkage detection mode, and can accurately calculate the time when the train head arrives at the detection area. Compared with the magnetic steel detection method, the vehicle wheelbase difference can be ignored, and it is more stable and reliable than the photoelectric detection method.

[0048] The present invention can be implemented in hardware by directly utilizing the module components in the existing mature car body scanning and detection system based on linear array cameras. There is no need to install a separate on-track signal acquisition device, so the existing car body scanning and detection system can be functionally upgraded to realize the train head detection function, thereby reducing the installation cost, shortening the construction period, reducing the number of components in the detection station, and facilitating maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor, among which:

[0050] Figure 1 A schematic diagram of the principle of a train head detection device according to an embodiment of the present invention;

[0051] Figure 2 This is the imaging effect of the train roof in one embodiment of the present invention;

[0052] Figure 3 The figure is a schematic diagram of image changes when a vehicle passes through a detection area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0055] Example 1

[0056] In an embodiment of the present invention, a device for detecting a train head is provided, such as Figure 1 As shown, it includes a speed measurement module, a signal processing module and an image processing module; wherein:

[0057] The speed measurement module is used to collect the timestamps of the wheels passing through two adjacent speed measurement positions and send them to the signal processing module so that the signal processing module calculates the current vehicle speed;

[0058] The signal processing module is further used to calculate the pulse frequency according to the current vehicle speed, send a pulse signal to the image processing module based on the pulse frequency, and calculate the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area;

[0059] The image processing module is used to capture the image of the roof detection area based on the received pulse signal. When a change in the image pixels is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the front detection area based on the first timestamp and the trigger delay and sends it to the image processing module, so that the image processing module captures the image of the front of the vehicle according to the second timestamp.

[0060] The train locomotive detection device in the embodiment of the present invention can realize a linkage detection mode, accurately calculate the time when the train locomotive arrives at the detection area, ignore the difference in vehicle wheelbase compared to the magnetic steel detection method, and is more stable and reliable than the photoelectric detection method.

[0061] In a specific implementation of the embodiment of the present invention, the speed measuring module includes a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel;

[0062] The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area;

[0063] The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

[0064] In the specific implementation process, the first distance can be set to 80 meters, the second distance can be set to less than ten meters, such as 3 meters, and the interval between the first speed measuring magnet and the second speed measuring magnet can be set to several hundred millimeters. The specific distance can be adjusted according to the vehicle speed, and the optimal installation position is 270mm.

[0065] In a specific implementation of the embodiment of the present invention, the calculation formula of the current vehicle speed is:

[0066]

[0067] Wherein, s1 is the distance between the first speed measuring magnetic steel and the second speed measuring magnetic steel, which is a known parameter, and t=time stamp of the second speed measuring magnetic steel-time stamp of the first speed measuring magnetic steel.

[0068] In a specific implementation of the embodiment of the present invention, the calculation formula of the pulse frequency is:

[0069]

[0070] Among them, f is the pulse frequency, v is the current vehicle speed, and L is the number of pulses per kilometer.

[0071] In a specific implementation of the embodiment of the present invention, Figure 1 As shown, the image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the roof image acquisition unit and the front image acquisition unit are arranged in sequence along the travel direction of the train;

[0072] The roof image acquisition unit is used to acquire an image of the train roof detection area based on the received pulse signal and send it to the image processing unit. Figure 3As shown, when no vehicle passes, the image collected by the roof image acquisition unit is the background image of the detection area. When a vehicle passes, the image collected by the roof image acquisition unit is a 2048*1 train roof image frame. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to collect the image of the train head according to the second timestamp.

[0073] In the specific implementation process, the roof image acquisition unit generally uses a linear array camera, and the front image acquisition unit generally uses an area array camera. The resolution of the linear array camera is 2048*1. Every time the signal processing module sends a pulse signal, the linear array camera generates a frame of image. The image processing unit finally synthesizes a whole train roof image. The final imaging effect can be seen in Figure 2 .

[0074] In a specific implementation of the embodiment of the present invention, the calculation formula of the trigger delay is:

[0075]

[0076] Among them, Δt is the trigger delay, s2 is the distance between the roof image acquisition unit and the front image acquisition unit, and v is the current vehicle speed.

[0077] In a specific implementation of the embodiment of the present invention, the method for generating the first timestamp includes:

[0078] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0079]

[0080] Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame; where the image grayscale value I in the above formula is ij and I (i-1)j The average value when the change value is not large can be used instead to improve the image's resistance to interference from the method.

[0081] When i >T g When T gis the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0082] In another specific implementation of the embodiment of the present invention, it is known that the grayscale change values ​​of the subsequent n frames of images are set to be greater than a threshold value, and a first timestamp is obtained. The method for generating the first timestamp includes:

[0083] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0084]

[0085] Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed. The greater the speed, the smaller the n value is, to ensure the real-time detection; j is the pixel number in each frame, that is, the row number of a single-column image frame; J is the height of the image, that is, the total number of rows in the image frame;

[0086] When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0087] Example 2

[0088] An embodiment of the present invention provides a method for detecting a train head, comprising the following steps:

[0089] (1) Using the speed measurement module to collect the timestamps of the wheels passing through two adjacent speed measurement positions, and sending them to the signal processing module, so that the signal processing module calculates the current vehicle speed;

[0090] (2) using the signal processing module to calculate the pulse frequency according to the current vehicle speed, and sending a pulse signal to the image processing module based on the pulse frequency, and calculating the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area;

[0091] (3) An image processing module is used to collect an image of the roof detection area based on the received pulse signal. When a change in the image pixels is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains a second timestamp when the vehicle arrives at the front detection area based on the first timestamp and the trigger delay, and sends the second timestamp to the image processing module, so that the image processing module collects an image of the front of the vehicle according to the second timestamp.

[0092] Based on the train locomotive detection method in the embodiment of the present invention, a linkage detection mode can be realized, and the time when the train locomotive arrives at the detection area can be accurately calculated. Compared with the magnetic steel detection method, the vehicle wheelbase difference can be ignored, and it is more stable and reliable than the photoelectric detection method.

[0093] In a specific implementation of the embodiment of the present invention, the speed measuring module includes a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel;

[0094] The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area;

[0095] The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

[0096] In the specific implementation process, the first distance can be set to 80 meters, the second distance can be set to less than ten meters, such as 3 meters, and the interval between the first speed measuring magnet and the second speed measuring magnet can be set to several hundred millimeters. The specific distance can be adjusted according to the vehicle speed, and the optimal installation position is 270mm.

[0097] In a specific implementation of the embodiment of the present invention, the calculation formula of the current vehicle speed is:

[0098]

[0099] Wherein, s1 is the distance between the first speed measuring magnetic steel and the second speed measuring magnetic steel, which is a known parameter, and t=time stamp of the second speed measuring magnetic steel-time stamp of the first speed measuring magnetic steel.

[0100] In a specific implementation of the embodiment of the present invention, the calculation formula of the pulse frequency is:

[0101]

[0102] Among them, f is the pulse frequency, v is the current vehicle speed, and L is the number of pulses per kilometer.

[0103] In a specific implementation of the embodiment of the present invention, Figure 1 As shown, the image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the roof image acquisition unit and the front image acquisition unit are sequentially arranged along the travel direction of the train;

[0104] The roof image acquisition unit is used to acquire an image of the train roof detection area based on the received pulse signal and send it to the image processing unit. Figure 3 As shown, when no vehicle passes, the image collected by the roof image acquisition unit is the background image of the detection area. When a vehicle passes, the image collected by the roof image acquisition unit is a 2048*1 train roof image frame. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to collect the image of the train head according to the second timestamp.

[0105] In the specific implementation process, the roof image acquisition unit generally uses a linear array camera, and the front image acquisition unit generally uses an area array camera. The resolution of the linear array camera is 2048*1. Every time the signal processing module sends a pulse signal, the linear array camera generates a frame of image. The image processing unit finally synthesizes a whole train roof image. The final imaging effect can be seen in Figure 2 .

[0106] In a specific implementation of the embodiment of the present invention, the calculation formula of the trigger delay is:

[0107]

[0108] Among them, Δt is the trigger delay, s2 is the distance between the roof image acquisition unit and the front image acquisition unit, and v is the current vehicle speed.

[0109] In a specific implementation of the embodiment of the present invention, the method for generating the first timestamp includes:

[0110] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0111]

[0112] Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame; where the image grayscale value I in the above formula is ij and I (i-1)j The average value when the change value is not large can be used instead to improve the image's resistance to interference from the method.

[0113] When i >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0114] In another specific implementation of the embodiment of the present invention, it is known that the grayscale change values ​​of the subsequent n frames of images are set to be greater than a threshold value, and a first timestamp is obtained. The method for generating the first timestamp includes:

[0115] Calculate the image grayscale change value, the calculation formula of the image grayscale change value is:

[0116]

[0117] Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed. The greater the speed, the smaller the n value is, to ensure the real-time detection; j is the pixel number in each frame, that is, the row number of a single-column image frame; J is the height of the image, that is, the total number of rows in the image frame;

[0118] When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

[0124] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A train head detection device, characterized in that: include: The speed measurement module is used to collect the timestamps when the wheel passes through two adjacent speed measurement positions and send them to the signal processing module so that the signal processing module can calculate the current vehicle speed; The signal processing module is further used to calculate the pulse frequency according to the current vehicle speed, send a pulse signal to the image processing module based on the pulse frequency, and calculate the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area; An image processing module is used to collect an image of the roof detection area based on the received pulse signal, and when a change in the image pixel is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains a second timestamp when the vehicle arrives at the vehicle head detection area based on the first timestamp and the trigger delay, and sends the second timestamp to the image processing module, so that the image processing module collects the image of the vehicle head according to the second timestamp; The image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the roof image acquisition unit and the front image acquisition unit are arranged in sequence along the travel direction of the train; The roof image acquisition unit is used to capture the image of the train roof detection area based on the received pulse signal and send it to the image processing unit. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp of the vehicle arriving at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to capture the image of the train head according to the second timestamp.

2. A train head detection device according to claim 1, characterized in that: The roof image acquisition unit is a line array camera, and the front image acquisition unit is an area array camera.

3. The train head detection device according to claim 1, characterized in that: The method for generating the first timestamp includes: Calculate the image grayscale change value, the calculation formula of the image grayscale change value is: Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame; When i >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

4. The train head detection device according to claim 1, characterized in that: The method for generating the first timestamp includes: Calculate the image grayscale change value, the calculation formula of the image grayscale change value is: Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed, and the greater the speed, the smaller the n value; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame; When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

5. The train head detection device according to claim 1, characterized in that: The speed measuring module comprises a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel; The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area; The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

6. A method for detecting a train head, characterized in that: include: The speed measurement module is used to collect the timestamps of the wheels passing through two adjacent speed measurement positions and send them to the signal processing module, so that the signal processing module calculates the current vehicle speed; Calculate the pulse frequency using the signal processing module according to the current vehicle speed, send a pulse signal to the image processing module based on the pulse frequency, and calculate the trigger delay based on the current vehicle speed and the distance between the roof detection area and the front detection area; The image processing module is used to collect an image of the roof detection area based on the received pulse signal. When a change in the image pixel is detected, a first timestamp is generated and sent to the signal processing module, so that the signal processing module obtains a second timestamp when the vehicle arrives at the front detection area based on the first timestamp and the trigger delay, and sends the second timestamp to the image processing module, so that the image processing module collects an image of the front of the vehicle according to the second timestamp; The image processing module includes a roof image acquisition unit, a front image acquisition unit and an image processing unit; the front image acquisition unit and the image processing unit are arranged in sequence along the travel direction of the train; The roof image acquisition unit is used to capture the image of the train roof detection area based on the received pulse signal and send it to the image processing unit. When the image processing unit detects that the image pixels have changed, it generates a first timestamp and sends it to the signal processing module, so that the signal processing module obtains the second timestamp when the vehicle arrives at the train head detection area based on the first timestamp and the trigger delay, and sends it to the image processing unit. The image processing unit triggers the head image acquisition unit to capture the image of the train head according to the second timestamp.

7. A train head detection method according to claim 6, characterized in that: The method for generating the first timestamp includes: Calculate the image grayscale change value, the calculation formula of the image grayscale change value is: Among them, g i is the grayscale change value of the image in the i-th frame, I ij and I (i-1)j are the image grayscale values ​​of the jth pixel number of the i-th frame and the i-1-th frame collected by the roof image acquisition unit, i and i-1 are both image frame numbers; j is the pixel number in each frame image, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows of the image frame; When i >T g When T g is the image grayscale change threshold, it is determined that the train head reaches the train roof detection area, and the first timestamp is generated at the same time; Alternatively, the method for generating the first timestamp includes: Calculate the image grayscale change value, the calculation formula of the image grayscale change value is: Among them, g i+n is the grayscale change value of the image in the i+nth frame, I (i+n)j and I (i-1)j The image grayscale value of the jth pixel number in the i+nth frame and the i-1th frame collected by the roof image acquisition unit, i+n and i-1 are both image frame numbers, where n is set according to the train speed, and the greater the speed, the smaller the n value; j is the pixel number in each frame, that is, the row number of a single column image frame; J is the height of the image, that is, the total number of rows in the image frame; When i+n >T g When T g is the image grayscale change threshold, it is determined that the train head has arrived at the train roof detection area, and the first timestamp is generated at the same time.

8. A train head detection method according to claim 6, characterized in that: The speed measuring module comprises a first start-up magnetic steel, a second start-up magnetic steel, a first speed measuring magnetic steel and a second speed measuring magnetic steel; The first start-up magnet and the second start-up magnet are installed at a first distance set in front of the roof detection area, and signal logic is used to determine whether the train enters the speed detection area; The first speed measuring magnet and the second speed measuring magnet are sequentially installed at a second distance set in front of the roof detection area, and the timestamp of the wheel passing over the first speed measuring magnet and the second speed measuring magnet is obtained through signal transmission. The second distance is smaller than the first distance.

Images