CN114509089A - Non-contact rail transit train speed direction mileage detection method and system - Google Patents
Non-contact rail transit train speed direction mileage detection method and system Download PDFInfo
- Publication number
- CN114509089A CN114509089A CN202111671103.7A CN202111671103A CN114509089A CN 114509089 A CN114509089 A CN 114509089A CN 202111671103 A CN202111671103 A CN 202111671103A CN 114509089 A CN114509089 A CN 114509089A
- Authority
- CN
- China
- Prior art keywords
- train
- axle
- speed
- image
- running
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000005259 measurement Methods 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 7
- 239000013589 supplement Substances 0.000 claims description 7
- 230000001629 suppression Effects 0.000 claims description 5
- 230000036961 partial effect Effects 0.000 claims description 4
- 230000002829 reductive effect Effects 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000002441 reversible effect Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 6
- 238000000691 measurement method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 241001669679 Eleotris Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C23/00—Combined instruments indicating more than one navigational value, e.g. for aircraft; Combined measuring devices for measuring two or more variables of movement, e.g. distance, speed or acceleration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a non-contact rail transit train speed direction mileage detection method and a non-contact rail transit train speed direction mileage detection system, wherein a speed measurement pattern is arranged on a train axle in advance, and an image acquisition unit is arranged at the bottom of a train body and focuses on the speed measurement pattern; the method comprises the following steps of acquiring axle speed measurement pattern rotation image data of a train in operation at a high speed in real time by using an image acquisition unit, and transmitting the axle speed measurement pattern rotation image data to an image data processing unit through a network for image identification processing; and calculating the running direction of the train, the rotation angle and the number of turns of the axle of the train according to the difference of the recognition processing results of the two frames of images and the acquisition time difference of the two frames of images, and calculating the running mileage and the real-time running speed of the train by combining the wheel diameter of the wheels. The invention has wide application range, does not need to modify a train axle traveling part, has high speed measurement precision, timely speed updating and higher accumulated mileage calculation precision, and can accurately detect the running direction of the train.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a non-contact rail transit train running speed, running direction and running range measuring method and system based on machine vision.
Background
With the rapid development of urban rail transit and national electrified railways in China, the states of contact networks and rails are key factors influencing the running safety of electrified trains, so that a series of contact networks and rail detection devices installed on rail cars and operating trains are developed, and all detection devices need to acquire vehicle running speed information in real time to realize detection data positioning.
The running speed of the train is generally obtained by additionally arranging a speed sensor on an axle of the train; the operating train does not allow any change to the axle in consideration of safety, generally obtains speed information by analyzing the vehicle TCMS/MVB, but the refreshing frequency is slow and is generally 1 time/s, and accurate speed information cannot be provided for the detection device.
The patent application with the application number of CN201810365144.5 discloses a novel train speed and distance measuring device and a method, wherein the device comprises a high-frequency camera, an image recognition module, a logic processing module and a data interface; the high-frequency camera vertically shoots the pictures of the tracks downwards at regular intervals, and the displacement difference of adjacent pictures is calculated by utilizing the ground structure of periodic distribution between the tracks and the proportion of an actual picture object to the picture object by utilizing the image recognition module; the logic processing module calculates the running speed according to the high-frequency camera photographing frequency and the displacement difference calculated by the image recognition module, performs logic check according to the performance and the photographing period of the train, and the data interface is communicated with the vehicle-mounted equipment to output and input corresponding information. The scheme can quickly measure the speed of the train on the ground; however, the method is susceptible to the external environment during the image acquisition and identification process, and the error between the measurement result and the actual data is large, so that further improvement is needed.
For another example, patent application No. CN201010510191.8 discloses a vehicle speed measuring device based on track characteristics, which includes a measuring device for sensing changes of track characteristics and acquiring signals; the measuring device adjusting unit is used for adjusting the position of the measuring device and ensuring that the measuring device is within an effective measuring range; and the data acquisition and processing unit is used for receiving the signals acquired by the measuring device, and calculating the train operation parameters in real time after signal processing. The device of the scheme is based on a non-contact measuring probe, and the parameters such as the running distance, the movement speed, the acceleration and deceleration and the like of the train are obtained through the real-time acquisition and processing of the appearance or image characteristics such as a track sleeper, a fastener and the like, and are stored, communicated and displayed. Although the scheme can also realize non-contact measurement of the train speed, the train speed is obtained by processing based on the track characteristics, so the train speed measuring method is also easily influenced by the external environment, the error between the measurement result and actual data is large, and further improvement is needed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a system for detecting the mileage of a non-contact rail transit train in the speed direction.
The purpose of the invention is realized by the following technical scheme:
a non-contact rail transit train speed direction mileage detection method comprises the following steps:
the method comprises the following steps: setting a speed measurement pattern on a train axle in advance, installing an image acquisition unit at the bottom of a train body and focusing on the speed measurement pattern;
step two: the method comprises the following steps of acquiring axle speed measurement pattern rotation image data of a train in operation at a high speed in real time by using an image acquisition unit, and transmitting the axle speed measurement pattern rotation image data to an image data processing unit through a network for image identification processing;
step three: and calculating the running direction of the train, the rotation angle and the number of turns of the axle of the train according to the difference of the recognition processing results of the two frames of images and the acquisition time difference of the two frames of images, and calculating the running mileage and the real-time running speed of the train by combining the wheel diameter of the wheels.
The speed measuring pattern is a linear triangular or trapezoidal pattern with the height equal to the circumference of the train axle, and the number of the patterns is 1 or more than one same pattern.
Specifically, the second step specifically comprises:
s21: the method comprises the steps that an image acquisition unit is used for carrying out image acquisition on a speed measurement pattern on an axle when a train runs in real time to form a rotating axle high-definition image;
s22: filtering the axle high-definition image by adopting Gaussian filtering to remove image noise and obtain the noise-reduced axle high-definition image;
s23: calculating the amplitude and the direction of the gradient of the speed measurement pattern in the high-definition image of the axle by using the finite difference of the first-order partial derivatives, and performing non-maximum suppression on the gradient amplitude;
s24: and detecting and connecting edges by using a dual-threshold algorithm to identify the edges at two sides of the speed measurement pattern in the axle high-definition image after the non-maximum value is inhibited, and calculating the distance between the edges at the left side and the right side at the two sides of the speed measurement pattern.
Specifically, step S24 specifically includes: carrying out identification processing on the axle high-definition image subjected to non-maximum suppression by using a double-threshold algorithm detection and connection edge; setting an image fixed height y in the axle high-definition image, and selecting edge points on the image fixed height y to obtain a left edge point P1(x1, y) and a right edge point P2(x2, y); the lateral distance X between the two points P1 and P2 is calculated.
Specifically, the third step specifically comprises:
s31: the image acquisition unit acquires the speed measurement pattern on the axle at a high speed according to the preset acquisition frequency to obtain an axle high-definition image stream, and the axle high-definition image stream is processed according to the image identification processing process in the step two to obtain n transverse distances X1，X2，…，Xn；
S32: by usingThe axle high-definition image is transmitted to the image data processing unit through the timestamp or the system time of the axle high-definition image, and the corresponding image acquisition time T of the n transverse distances X is obtained1，T2，…，Tn；
S33: then passes through the wheel diameter d of the wheel and the transverse distance XmaxAnd XminCalculating X from the difference ofmaxTo XminCalculating the total running mileage of the train by accumulating the running distance L within the running time of the train;
s34: according to the corresponding transverse distance X of the front and back two frames of images of the current trainn、Xn-1Running time TnAnd Tn-1Calculating the current train speed S, wherein the calculation formula of the train speed S is as follows:
s35: simultaneously passing this XnAnd last Xn-1Obtaining the running direction of the vehicle, namely, the vehicle runs in a forward direction when X is increased, and runs in a reverse direction when X is decreased;
s36: when the speed measurement pattern in the axle high-definition image is collected to be at the maximum and minimum critical points, the fact that the wheel rotates to a complete circle is shown, the accumulated distance error in the wheel rotating to the circle is corrected, and meanwhile, X is measured at the momentn-Xn-1The calculation of (2) requires the use of XmaxI.e. the axle transverse distance X varies by Xn+Xmax-Xn-1。
A non-contact rail transit train speed direction mileage detection system is used for realizing the non-contact rail transit train speed direction mileage detection method, and comprises the following steps: the image acquisition unit and the image data processing unit are connected; the image acquisition unit is used for acquiring train axle speed measurement pattern rotation image data when the train runs at a high speed and uploading the train axle speed measurement pattern rotation image data to the image data processing unit; the image data processing unit is used for receiving, analyzing and processing the axle rotation image data and calculating the running speed, the running direction and the running mileage of the train in real time.
The image acquisition unit comprises a high-definition camera and a light supplement device; the high-definition camera and the light supplementing equipment are arranged at the bottom of the train through a C-shaped groove of the train body; the image data processing unit is connected with the high-definition camera.
Furthermore, a circle of linear triangle or trapezoid (1 or more) speed measurement patterns with the height equal to the circumference of the train axle are adhered on the train axle.
The invention has the beneficial effects that:
1. the method realizes the detection of the running speed of the train by adopting a non-contact method based on machine vision, only needs to install equipment at the existing C-shaped groove interface at the bottom of the train body of the train, does not need to modify a train axle running part, and greatly ensures the running safety of the rail train.
2. The measuring method and the measuring device have wide application range, and can be suitable for engineering vehicles such as contact network detection vehicles, contact network operation vehicles, rail detection vehicles and rail operation vehicles, and vehicle types such as urban rail transit operation trains, large railway operation trains and high-speed motor train unit trains.
3. The non-contact speed measurement method has the advantages of high acquisition frequency, namely high speed measurement precision, timely speed updating, higher accumulated calculation precision of mileage and capability of accurately detecting the running direction of the vehicle.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a system component architecture diagram of the present invention.
Fig. 3 is a schematic diagram of the measurement principle of the system of the present invention.
In fig. 3: 1-high definition camera, 2-speed measurement pattern, and 3-train axle.
Detailed Description
The following detailed description will be selected to more clearly understand the technical features, objects and advantages of the present invention. It should be understood that the embodiments described are illustrative of some, but not all embodiments of the invention, and are not to be construed as limiting the scope of the invention. All other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present invention without any inventive step are within the scope of the present invention.
The existing method generally includes that a speed sensor is additionally arranged on a vehicle axle to acquire the running speed of a vehicle; the operating train does not allow any change to the axle in consideration of safety, generally obtains speed information by analyzing the vehicle TCMS/MVB, but the refreshing frequency is slow and is generally 1 time/s, and accurate speed information cannot be provided for the detection device. The invention aims at the defects, designs a non-contact type rail transit train speed direction mileage detection method and a non-contact type rail transit train speed direction mileage detection system, automatically identifies train axle pattern edges by utilizing an image edge detection algorithm, calculates train axle rotation angles and turns according to the variation of the distance between the front frame image axle pattern edge and the rear frame image axle pattern edge, and can calculate information such as real-time running speed of a train by combining wheel diameter and time difference.
The first embodiment is as follows:
in this embodiment, as shown in fig. 1, since the axle of the rail transit train rotates synchronously with the wheels during operation, a non-contact train operation speed measurement method based on machine vision, that is, a non-contact rail transit train attitude measurement method, is designed according to the characteristics, and includes the following steps:
the method comprises the following steps: setting a speed measurement pattern on a train axle in advance, installing an image acquisition unit at the bottom of the train and focusing on the speed measurement pattern;
step two: the method comprises the following steps of acquiring axle speed measurement pattern rotation image data of a train in operation at a high speed in real time by using an image acquisition unit, and transmitting the axle speed measurement pattern rotation image data to an image data processing unit through a network for image identification processing;
step three: and calculating the running direction of the train, the rotation angle and the number of turns of the axle of the train according to the difference of the recognition processing results of the two frames of images and the acquisition time difference of the two frames of images, and calculating the running mileage and the real-time running speed of the train by combining the wheel diameter of the wheels.
In this embodiment, the pattern setting process of the train axle includes that a circle of clearly black and white linear triangular or trapezoidal (1 or more) patterns is pasted (or coated) on the rail transit train axle, so that the rotation distance of the train wheels can be calculated conveniently.
In this embodiment, the second step specifically includes:
s21: and the image acquisition unit is used for carrying out image acquisition on the speed measurement pattern on the axle when the train runs in real time to form a rotating axle high-definition image.
S22: and filtering the axle high-definition image by adopting Gaussian filtering to remove image noise and obtain the noise-reduced axle high-definition image.
Gaussian smoothing filtering is a linear filtering for eliminating gaussian noise, and is widely used for noise reduction in image processing. The gaussian filtering is to perform weighted average on the whole image, and the value of each pixel is obtained by performing weighted average on the value of each pixel and other pixels in the neighborhood.
S23: and calculating the amplitude and the direction of the gradient of the speed measurement pattern in the high-definition image of the axle by using the finite difference of the first-order partial derivatives, and performing non-maximum suppression on the gradient amplitude.
After the image is subjected to Gaussian smooth filtering, part of Gaussian noise of the image is reduced, and the sharpness is weakened, but the edge decomposition of the image is not obvious at the moment, and the changed gray level is not strong and is not easy to capture. Therefore, in order to define the size of the edge gray level change, image gradient is proposed, and the size of the gradient is used to represent the size of the edge gray level change.
The gradient is a vector (vector) indicating that the directional derivative of a certain function at the point takes the maximum value along the direction, i.e. the function changes the fastest (the direction of the gradient) and the change rate is the maximum (the mode of the gradient) along the direction at the point. I.e., derivative (gradient), the rate of change of the image is expressed as a differential for the image as the function f (x, y) f (x, y) f (x, y). Since the image is a two-dimensional function, the partial derivatives are calculated. The gradient (amplitude and direction) at any point is calculated, namely convolution is carried out on the gradient (amplitude and direction) at any point and the corresponding pixel point by using a cable convolution operator (with optional size, generally 3 multiplied by 3). For the gradient of the edge point, if the edge supplement is not carried out, the surrounding pixel points are defaulted to be 0.
Since the image edges calculated from the gradients are blurred, there are many phenomena where the gradients of the edges respond. We strive to find a local maximum in a gradient direction to represent the gradient response in that gradient direction. This has the advantage of facilitating calculations, facilitating understanding, that the gradient directions in each region are all approximated to one gradient direction, and that maxima are sought after and after this approximated one gradient direction.
S24: and detecting and connecting edges by using a dual-threshold algorithm to identify the edges at two sides of the speed measurement pattern in the axle high-definition image after the non-maximum value is inhibited, and calculating the distance between the edges at the left side and the right side at the two sides of the speed measurement pattern.
In step S24, the specific implementation process of dual-threshold detection and edge connection includes:
(1) selecting a proper high threshold value and a proper low threshold value according to the image, wherein the high threshold value is 2 to 3 times of the low threshold value generally;
(2) if the gradient value of a certain pixel is higher than the high threshold value, keeping;
(3) discarding if the gradient value of a pixel is below a low threshold;
(4) if the gradient value of a certain pixel is between the high threshold and the low threshold, the gradient values of the pixels are searched from the 8 neighborhoods of the pixel, if the gradient values of the pixels are higher than the high threshold, the gradient values are kept, and if the gradient values of the pixels are not higher than the high threshold, the gradient values of the pixels are discarded.
Then, setting an image fixed height y in the axle high-definition image, and selecting edge points on the image fixed height y to obtain a left edge point P1(x1, y) and a right edge point P2(x2, y); the lateral distance X between the two points P1 and P2 is calculated.
In this embodiment, the third step specifically includes:
s31: the image acquisition unit acquires the speed measurement pattern on the axle at a high speed according to the preset acquisition frequency to obtain an axle high-definition image stream, the axle high-definition image stream is processed according to the image identification processing process in the step two, and a large amount of high-speed acquisition (200Hz and above) can be carried out in 1 secondX, i.e. n transverse distances X1，X2，…，Xn；
S32: acquiring corresponding image acquisition time T of n transverse distances X by utilizing a timestamp carried by the axle high-definition image or system time for transmitting the axle high-definition image to the image data processing unit1，T2，…，Tn；
S33: then passes through the wheel diameter d of the wheel and the transverse distance XmaxAnd XminCalculating X from the difference ofmaxTo XminCalculating the total running mileage of the train by accumulating the running distance L within the running time of the train;
s34: according to the corresponding transverse distance X of the front and back two frames of images of the current trainn、Xn-1Running time TnAnd Tn-1Calculating the current train speed S, wherein the calculation formula of the train speed S is as follows:
s35: simultaneously passing this XnAnd last Xn-1Obtaining the running direction of the vehicle, namely, when X is increased, the vehicle runs in a forward direction (the difference is positive), and when X is decreased, the vehicle runs in a reverse direction (the difference is negative);
s36: when the speed measurement pattern in the axle high-definition image is collected to be at the maximum and minimum critical points, the fact that the wheel rotates to a complete circle is shown, the accumulated distance error in the wheel rotating to the circle is corrected, and meanwhile, X is measured at the momentn-Xn-1The calculation of (2) requires the use of XmaxI.e. the axle transverse distance X varies by Xn+Xmax-Xn-1。
Example two:
in this embodiment, to implement the non-contact rail transit train attitude measurement method in the first embodiment, a non-contact rail transit train speed direction mileage detection system is designed, and as shown in fig. 2, the system includes: the image acquisition unit and the image data processing unit are connected; the image acquisition unit is used for acquiring the rotating image data of the train axle 3 when the train runs at a high speed and uploading the rotating image data to the image data processing unit; the image data processing unit is used for receiving, analyzing and processing the axle rotation image data and calculating the running speed, the running direction and the running mileage of the train in real time.
The image acquisition unit comprises a high-definition camera 1 and a light supplementing device; high definition camera 1 installs through C type groove and is connected with high definition camera 1 and light filling equipment at image data processing unit.
Further, a circle of linear triangle or trapezoid (1 or more) speed measurement patterns with the height equal to the circumference of the train axle 3 are adhered on the train axle 3.
In this embodiment, the image data processing unit is an industrial personal computer, and image processing software may be provided in the industrial personal computer to implement the train attitude measurement method according to the first embodiment.
In the embodiment, the speed measurement pattern 2 (a black and white linear triangle or a trapezoid (1 or more) pattern) is focused on the train axle 3 through the image acquisition unit (the high-definition camera 1 and the light supplement device) installed on the train body, the high-definition camera 1 synchronously triggers the light supplement device to acquire a high-definition image during train running at a high speed, the image data processing unit (the industrial personal computer) receives, analyzes and processes axle rotation image data, the train running speed is calculated in real time, and the schematic diagram of the measuring system is shown in fig. 3.
The detailed measurement principle and method of the embodiment are as follows:
1. pattern of train axles: a circle of clearly black and white linear triangular or trapezoidal (1 or more) patterns is stuck (or coated) on the axle of the rail transit train.
2. An image acquisition unit: the image acquisition unit consists of a high-definition camera 1 and a light supplement device, and the high-definition camera 1 triggers the light supplement device to synchronously work and acquire images; the image acquisition unit is arranged at the bottom of the train body and focuses on the train axle pattern, and acquires a high-definition image formed by the pattern on the train axle in real time.
3. Image data processing unit (industrial personal computer): the acquired train axle high-definition images are transmitted to an image data processing host (industrial personal computer) through a gigabit network, edges on two sides of the pattern are identified by using an edge detection algorithm, and the distance between the edges on the left side and the edges on the right side are calculated.
4. Mileage, direction and speed calculation: on the basis of the steps, the rotation angle and the number of turns of the axle of the train can be calculated according to the difference value of the edge distances of the axle pattern recognized by the front frame image and the rear frame image and the time difference of the front frame image and the rear frame image, the running mileage and the real-time running speed of the train can be calculated by combining the wheel diameters of the wheels, and the running direction of the train can be obtained by the positive and negative of the difference value of the edge distances of the front frame image and the rear frame image. And providing accurate mileage positioning information for the detection device.
The present embodiment has the following technical advantages:
1. the method realizes the detection of the running speed of the train by adopting a non-contact method based on machine vision, only equipment needs to be installed on the existing C-shaped groove interface at the bottom of the train body, and a train axle running part does not need to be modified, so that the running safety of the rail train is greatly ensured.
2. The measuring method and the measuring device have wide application range, and can be suitable for engineering vehicles such as contact network detection vehicles, contact network operation vehicles, rail detection vehicles and rail operation vehicles, and vehicle types such as urban rail transit operation trains, large railway operation trains and high-speed motor train unit trains.
3. The non-contact speed measurement method realized by the embodiment has the advantages of high acquisition frequency, namely high speed measurement precision, timely speed updating, higher accumulated calculation precision of mileage and capability of accurately detecting the running direction of the vehicle.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A non-contact rail transit train speed direction mileage detection method is characterized by comprising the following steps:
the method comprises the following steps: setting a speed measurement pattern on a train axle in advance, installing an image acquisition unit at the bottom of a train body and focusing on the speed measurement pattern;
step two: the method comprises the following steps of acquiring axle speed measurement pattern rotation image data of a train in operation at a high speed in real time by using an image acquisition unit, and transmitting the axle speed measurement pattern rotation image data to an image data processing unit through a network for image identification processing;
step three: and calculating the running direction of the train, the rotation angle and the number of turns of the axle of the train according to the difference of the recognition processing results of the two frames of images and the acquisition time difference of the two frames of images, and calculating the running mileage and the real-time running speed of the train by combining the wheel diameter of the wheels.
2. The method as claimed in claim 1, wherein the velocity measurement pattern is a linear triangle or trapezoid pattern with a height equal to the circumference of the axle of the train.
3. The non-contact rail transit train speed and direction mileage detection method according to claim 1, wherein the second step specifically comprises:
s21: the method comprises the steps that an image acquisition unit is used for carrying out image acquisition on a speed measurement pattern on an axle when a train runs in real time to form a rotating axle high-definition image;
s22: filtering the axle high-definition image by adopting Gaussian filtering to remove image noise and obtain the noise-reduced axle high-definition image;
s23: calculating the amplitude and the direction of the gradient of the speed measurement pattern in the high-definition image of the axle by using the finite difference of the first-order partial derivatives, and performing non-maximum suppression on the gradient amplitude;
s24: and detecting and connecting edges by using a dual-threshold algorithm to identify the edges at two sides of the speed measurement pattern in the axle high-definition image after the non-maximum value is inhibited, and calculating the distance between the edges at the left side and the right side at the two sides of the speed measurement pattern.
4. The method for detecting the speed and direction mileage of a non-contact rail transit train as claimed in claim 3, wherein the step S24 specifically comprises: carrying out identification processing on the axle high-definition image subjected to non-maximum suppression by using a double-threshold algorithm detection and connection edge; setting an image fixed height y in the axle high-definition image, and selecting edge points on the image fixed height y to obtain a left edge point P1(x1, y) and a right edge point P2(x2, y); the lateral distance X between the two points P1 and P2 is calculated.
5. The non-contact rail transit train speed and direction mileage detection method according to claim 1, wherein the third step specifically comprises:
s31: the image acquisition unit acquires the speed measurement pattern on the axle at a high speed according to the preset acquisition frequency to obtain an axle high-definition image stream, and the axle high-definition image stream is processed according to the image identification processing process in the step two to obtain n transverse distances X1，X2，…，Xn；
S32: acquiring corresponding image acquisition time T of n transverse distances X by utilizing a timestamp carried by the axle high-definition image or system time for transmitting the axle high-definition image to the image data processing unit1，T2，…，Tn；
S33: then passes through the wheel diameter d of the wheel and the transverse distance XmaxAnd XminCalculating X from the difference ofmaxTo XminCalculating the total running mileage of the train by accumulating the running distance L within the running time of the train;
s34: according to the corresponding transverse distance X of the front and back two frames of images of the current trainn、Xn-1Running time TnAnd Tn-1Calculating the current train speed S, wherein the calculation formula of the train speed S is as follows:
s35: simultaneously passing this XnAnd last Xn-1Obtaining the running direction of the vehicle, namely, the vehicle runs in a forward direction when X is increased, and runs in a reverse direction when X is decreased;
s36: when the speed measurement pattern in the axle high-definition image is collected to be at the maximum and minimum critical points, the fact that the wheel rotates to a complete circle is shown, the accumulated distance error in the wheel rotating to the circle is corrected, and meanwhile, X is measured at the momentn-Xn-1The calculation of (2) requires the use of XmaxI.e. the axle transverse distance X varies by Xn+Xmax-Xn-1。
6. A non-contact rail transit train speed direction mileage detection system is used for realizing the non-contact rail transit train speed direction mileage detection method of any one of claims 1 to 5, and is characterized by comprising the following steps: the image acquisition unit and the image data processing unit are connected; the image acquisition unit is used for acquiring train axle speed measurement pattern rotation image data when the train runs at a high speed and uploading the train axle speed measurement pattern rotation image data to the image data processing unit; the image data processing unit is used for receiving, analyzing and processing the axle rotation image data and calculating the running speed, the running direction and the running mileage of the train in real time.
7. The system for detecting the speed and direction mileage of the non-contact rail transit train according to claim 6, wherein the image acquisition unit comprises a high definition camera and a light supplement device; the high-definition camera and the light supplementing equipment are arranged at the bottom of the train through a C-shaped groove of the train body; the image data processing unit is connected with the high-definition camera.
8. The system for detecting the mileage of a non-contact type rail transit train as claimed in claim 6, wherein a circle of linear triangular or trapezoidal velocity pattern with a height equal to the circumference of the train axle is adhered on the train axle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671103.7A CN114509089A (en) | 2021-12-31 | 2021-12-31 | Non-contact rail transit train speed direction mileage detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671103.7A CN114509089A (en) | 2021-12-31 | 2021-12-31 | Non-contact rail transit train speed direction mileage detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114509089A true CN114509089A (en) | 2022-05-17 |
Family
ID=81547407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111671103.7A Pending CN114509089A (en) | 2021-12-31 | 2021-12-31 | Non-contact rail transit train speed direction mileage detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114509089A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876363A (en) * | 2024-03-11 | 2024-04-12 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000097968A (en) * | 1998-09-25 | 2000-04-07 | Japan Aviation Electronics Industry Ltd | Speedometer and method for measuring speed |
| CN201247072Y (en) * | 2008-05-30 | 2009-05-27 | 安徽宏实光机电高科有限公司 | Rotary encoder based on linear array CCD relevant speed-measuring technology |
| CN102944689A (en) * | 2012-11-13 | 2013-02-27 | 江苏科技大学 | Brushless direct-current motor rotation speed detection device adopting charge coupled device (CCD) camera and method |
| CN103528568A (en) * | 2013-10-08 | 2014-01-22 | 北京理工大学 | Wireless channel based target pose image measuring method |
| CN106443046A (en) * | 2016-11-23 | 2017-02-22 | 福州大学 | Device and method for measuring rotating speed of rotating shaft based on variable density sine fringe |
| CN110163916A (en) * | 2019-05-23 | 2019-08-23 | 西华大学 | The matching process of circulating type circular markers based on rolling target |
| CN111798449A (en) * | 2020-09-09 | 2020-10-20 | 江苏恒力化纤股份有限公司 | Spinneret plate residual impurity detection method based on image technology |
| CN111855693A (en) * | 2020-08-25 | 2020-10-30 | 成都精工华耀科技有限公司 | Track inspection line scanning imaging control signal generation device and signal generation method |
| CN113447670A (en) * | 2021-06-25 | 2021-09-28 | 福州大学 | Rotation speed measuring method and system for monocular linear array visual tracking stripe coding mark |
| CN217385548U (en) * | 2021-12-31 | 2022-09-06 | 成都弓网科技有限责任公司 | Non-contact rail transit train speed direction mileage detection device |
-
2021
- 2021-12-31 CN CN202111671103.7A patent/CN114509089A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000097968A (en) * | 1998-09-25 | 2000-04-07 | Japan Aviation Electronics Industry Ltd | Speedometer and method for measuring speed |
| CN201247072Y (en) * | 2008-05-30 | 2009-05-27 | 安徽宏实光机电高科有限公司 | Rotary encoder based on linear array CCD relevant speed-measuring technology |
| CN102944689A (en) * | 2012-11-13 | 2013-02-27 | 江苏科技大学 | Brushless direct-current motor rotation speed detection device adopting charge coupled device (CCD) camera and method |
| CN103528568A (en) * | 2013-10-08 | 2014-01-22 | 北京理工大学 | Wireless channel based target pose image measuring method |
| CN106443046A (en) * | 2016-11-23 | 2017-02-22 | 福州大学 | Device and method for measuring rotating speed of rotating shaft based on variable density sine fringe |
| CN110163916A (en) * | 2019-05-23 | 2019-08-23 | 西华大学 | The matching process of circulating type circular markers based on rolling target |
| CN111855693A (en) * | 2020-08-25 | 2020-10-30 | 成都精工华耀科技有限公司 | Track inspection line scanning imaging control signal generation device and signal generation method |
| CN111798449A (en) * | 2020-09-09 | 2020-10-20 | 江苏恒力化纤股份有限公司 | Spinneret plate residual impurity detection method based on image technology |
| CN113447670A (en) * | 2021-06-25 | 2021-09-28 | 福州大学 | Rotation speed measuring method and system for monocular linear array visual tracking stripe coding mark |
| CN217385548U (en) * | 2021-12-31 | 2022-09-06 | 成都弓网科技有限责任公司 | Non-contact rail transit train speed direction mileage detection device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876363A (en) * | 2024-03-11 | 2024-04-12 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
| CN117876363B (en) * | 2024-03-11 | 2024-06-07 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103217111B (en) | A kind of non-contact contact line geometric parameter detection method | |
| CN106575473B (en) | Method and device for non-contact axle counting of vehicle and axle counting system | |
| CA2837314C (en) | Method for measuring a height profile of a vehicle passing on a road | |
| CN104129389A (en) | Method for effectively judging and recognizing vehicle travelling conditions and device thereof | |
| CN103686083B (en) | Real-time speed measurement method based on vehicle-mounted sensor video streaming matching | |
| CN102999759A (en) | Light stream based vehicle motion state estimating method | |
| CN107462223A (en) | Driving sight distance self-operated measuring unit and measuring method before a kind of highway is turned | |
| CN106503636A (en) | A kind of road sighting distance detection method of view-based access control model image and device | |
| CN112866673B (en) | Image acquisition equipment, camera control method and device and train image acquisition system | |
| CN103413325B (en) | A kind of speed of a motor vehicle authentication method based on vehicle body positioning feature point | |
| CN115035000B (en) | Road dust image identification method and system | |
| CN113063361A (en) | Symmetrical rail contact net detection device and detection method | |
| WO2018149539A1 (en) | A method and apparatus for estimating a range of a moving object | |
| CN114509089A (en) | Non-contact rail transit train speed direction mileage detection method and system | |
| CN109229206A (en) | The detection method and system of a kind of vehicle and its steering angle | |
| CN115219251A (en) | Railway vehicle dynamic performance monitoring system based on wheel pair operation posture | |
| CN217385548U (en) | Non-contact rail transit train speed direction mileage detection device | |
| CN116409325A (en) | Vehicle chassis control method and device, vehicle and computer storage medium | |
| JP5957182B2 (en) | Road surface pattern recognition method and vehicle information recording apparatus | |
| CN106875427B (en) | Method for monitoring snaking motion of locomotive | |
| CN111539279B (en) | Road height limit detection method, device, equipment and storage medium | |
| JP3958566B2 (en) | Measuring equipment for railway vehicles | |
| CN114332453A (en) | Front vehicle detection method suitable for automatic emergency braking system | |
| CN114659457A (en) | Track gauge dynamic measurement method based on structured light | |
| CN105242060B (en) | A kind of train wheel idle running and the method for real-time slided |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |