CN111591321A - Continuous recognition and correction device and method for contents of track pole number plate - Google Patents
Continuous recognition and correction device and method for contents of track pole number plate Download PDFInfo
- Publication number
- CN111591321A CN111591321A CN202010727484.5A CN202010727484A CN111591321A CN 111591321 A CN111591321 A CN 111591321A CN 202010727484 A CN202010727484 A CN 202010727484A CN 111591321 A CN111591321 A CN 111591321A
- Authority
- CN
- China
- Prior art keywords
- pole
- image
- controller
- rod
- pole number
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 50
- 230000005540 biological transmission Effects 0.000 claims description 26
- 230000003287 optical effect Effects 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 16
- 239000013589 supplement Substances 0.000 claims description 9
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012805 post-processing Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L25/00—Recording or indicating positions or identities of vehicles or trains or setting of track apparatus
- B61L25/02—Indicating or recording positions or identities of vehicles or trains
- B61L25/026—Relative localisation, e.g. using odometer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a continuous recognition and correction device and method for contents of a track pole number plate, which relate to the technical field of train positioning and comprise a carriage, an image acquisition device, an image processing device and a display device, wherein the image acquisition device is connected with the image processing device, the image processing device is connected with the display device, and by judging the number of poles in an image, when a plurality of poles exist, the optimal pole is selected for recognition, so that the pole number on the optimal pole is recognized, and then the continuous pole number is corrected, so that the accurate pole number is obtained.
Description
Technical Field
The invention relates to the technical field of train positioning, in particular to a continuous identification and correction device and method for contents of a track pole number plate.
Background
Train positioning is a key technology for train operation control and plays an important role in a rail transit signal system. The method can accurately acquire the train position information in real time, is a guarantee for high-efficiency and safe operation of rail transit, and is a premise for improving efficiency and exerting transportation performance. The train tracking interval is reduced by train positioning, and the development of rail transit to the direction of high density and large transportation volume is facilitated.
The current common train positioning technology comprises: train positioning based on track circuits, train positioning based on transponders, train positioning based on satellite positioning systems, etc. The train positioning technology based on the track circuit is a coarse-precision positioning method, and the positioning precision completely depends on the length of a track section; the train positioning based on the transponder is a point type positioning, which has the characteristics of strong anti-interference performance, no positioning blind area, stable work and the like, but in order to realize the continuous and accurate positioning of the train, a large number of transponders need to be laid in the track, so the investment is huge; the train adopting the satellite positioning system has high positioning precision and convenient maintenance, but has positioning blind areas in places with many barriers around, such as mountain forests, cities, tunnels and the like.
The train uses the odometer as the main basis of positioning, and adopts the high-precision odometer to obtain millimeter-scale continuous position information, but in practice, the odometer has accumulated errors due to wheel slip, idle running or wheel wear and the like. In train control systems, track circuit demarcation points or transponders with fixed precise locations are often used to eliminate this error. High-density placement of transponders is expensive, and some lines have no track circuit and cannot be populated with transponders.
The prior art carries out identification analysis through the identification image to the trackside, discerns the data message of pole number tablet to and the opportunity that the train passed through the pole number tablet, and with this carry out train position location and correction, but because the speed of a motor train is fast to need carry out continuous discernment to pole number tablet content, probably neglect to gather certain pole number tablet so that the identification error, finally lead to the problem that the location appears the mistake.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a continuous identification and correction device and method for the number plate content of a track rod.
The purpose of the invention is realized by the following technical scheme:
a continuous recognition and correction device for the contents of track pole number plates comprises a carriage, an image acquisition device, an image processing device and a display device, wherein the image acquisition device is connected with the image processing device;
the image acquisition device comprises a high-definition camera, a first optical sensor, a light supplement lamp, a controller, a first transmission unit and a second transmission unit, wherein the high-definition camera is connected with the first transmission unit, and the first transmission unit, the first optical sensor, the light supplement lamp and the second transmission unit are connected with the controller;
the image processing device comprises a second receiving unit, an image processing unit, a calculation correction unit and a processor, wherein the second receiving unit is connected with the image processing unit, the image processing unit is connected with the calculation correction unit, the calculation correction unit is connected with the processor, and the processor is connected with the display device;
the output end of the second transmission unit is connected with the input end of the second receiving unit;
preferably, the vehicle-mounted road traffic monitoring system further comprises a mileage encoder connected with the processor, wherein the mileage encoder is fixedly mounted at the wheel axle end of the carriage and used for measuring mileage data of the carriage.
By adopting the technical scheme, the railway positioning is realized by fusing the image data and the data of the mileage encoder.
Preferably, the image acquisition device further comprises a second optical sensor, the second optical sensor is connected with the controller, a normal optical signal threshold range is arranged in the controller, and when the optical signal transmitted to the controller by the first optical sensor does not belong to the normal optical signal threshold range, the controller starts the second optical sensor to detect the external light signal.
By adopting the technical scheme, when the first light sensor breaks down, the second light sensor can be started to continue to detect light.
Preferably, the top end of the carriage is also provided with a wireless router, and the router is internally provided with a 4G SIM card and is positioned by connecting the SIM card to a telecommunication, mobile or Unicom communication base station.
Preferably, at the bottom of the train installation Doppler radar sensor, make it to the track fastener transmission electromagnetic wave, Doppler radar makes the electromagnetic wave that the radar received with there is Doppler effect between the electromagnetic wave of launching along with the vehicle constantly marchs, calculates the functioning speed on the relative ground of vehicle, and then realizes the location of vehicle running position.
A continuous recognition and correction method for the contents of track pole number plates comprises the following steps:
step 1, a first optical sensor detects an external light signal and transmits the external light signal to a controller, and if the external light signal is larger than or equal to a threshold value set in the controller, the controller controls a high-definition camera arranged at the top end of a carriage to continuously shoot images along a railway; if the external light signal is smaller than a threshold value set in the controller, the controller controls the light supplement lamp to be turned on and simultaneously controls the high-definition camera to continuously shoot images along the railway;
step 2, the high-definition camera transmits the shot image to the controller through the first transmission unit, the controller transmits the image to the second receiving unit through the second transmission unit, the second receiving unit transmits the image to the image processing unit for processing, then the image processing unit corrects the single bar number after processing and recognition through the calculation correction unit, the calculation correction unit transmits the corrected result to the controller, and the controller displays the result through the display device;
the steps of processing and correcting the image are as follows:
step 1; acquiring images continuously shot by a high-definition camera arranged at the top end of a carriage along a railway;
step 2: marking the line pole in the image;
and step 3: judging whether the number of the line rods in the graph is zero, if so, executing the step 1, and if not, executing the step 4;
step 4; judging the number of the line rods in the graph, executing the step 5 when the number of the line rods is single, and executing the step 6 when the number of the line rods is more than 1;
and 5: identifying the pole number plate on the line pole, if the identification is successful, executing the step 7, and if the identification is failed, executing the step 8;
step 6: identifying the pole number plate of the pole closest to the high-definition camera, if the pole number plate is successfully identified, executing a step 7, and if the pole number plate is unsuccessfully identified, executing a step 8;
and 7: processing and identifying the content of the pole number plate to obtain a pole number; executing the step 9;
and 8: replacing other images shot at the same time for identification; executing the step 2;
and step 9: and putting the continuous rod number data identified in batches into a continuous rod number correction algorithm, correcting the rod numbers which are misjudged and missed in judgment through a series of judgment conditions preset by the algorithm, and finally outputting a continuous rod number detection result.
The steps of marking the line pole in the image are as follows:
step 1, enhancing the vertical edge of an outlet pole by utilizing a Sobel operator;
step 2, performing binarization processing on a result of enhancing the vertical edge of the outlet pole by using a Sobel operator;
step 3, detecting a straight line by using hough transformation; marking lines on two sides of a suspected line pole;
the identification of the line pole closest to the high-definition camera refers to the selection of the thickest line pole for pole number identification;
inputting the batch of continuous pole numbers into a continuous pole number correction algorithm, artificially correcting misjudged and missed pole numbers, and then matching the pole numbers with corresponding line pole images, wherein the specific process is as follows:
step 1, searching an initial pole number index for an input pole number through a judgment condition;
step 2, calculating and comparing the difference between the current index rod number and the front and rear rod numbers, and judging the relative position of the current rod;
step 3, if the difference value between the front and rear rods is 0, comparing the last digit of the current rod number with the last digit of the front and rear rod numbers, and judging whether the current rod image belongs to the front item or the rear item; if the difference value between the front and rear rods is 4, the current rod number is the middle value of the front and rear rod numbers;
step 4, if the situations are not met, the current pole number is corrected bit by bit; similarly, each position of the current pole number is compared with the previous and next items in sequence, and the pole number is modified according to the equality relationship, and finally the pole number is modified;
and 5, outputting the modified rod numbers in sequence, corresponding the rod numbers to the paths of the image files, and finally outputting complete continuous rod number information.
Preferably, the process of identifying the content of the pole number plate comprises the following steps;
step 1, quickly positioning a pole number approximate area to be identified according to the distribution condition of an image HSV;
step 2, accurately extracting a rod number ROI through an image processing algorithm, carrying out binarization processing on an ROI area, and segmenting each character;
step 3, training and recognizing each character by using an SVM algorithm;
and 4, post-processing the result according to the characteristics of each character, and further eliminating false recognition.
By adopting the technical scheme, as the character recognition may have error recognition, post-processing needs to be carried out on the recognized character. The post-processing is mainly based on the characteristics of each character, whether the recognized result is correct or not is determined by sampling and comparing each character area, and whether the recognized result is correct or not is determined by utilizing cached historical data for comparison and analysis.
The invention has the beneficial effects that:
1. judging whether the train is outside or inside the tunnel through the first optical sensor, and transmitting a light signal to the controller; the controller is through deciding whether to start the light filling lamp for the image that high definition digtal camera shot is more clear.
2. By arranging the second light sensor, when the controller judges that the first light sensor has a fault, the second light sensor can be started to continue to detect.
3. The number of the line poles in the image is identified, the line poles with optimal identification are selected, the success rate of identification of the pole number plate on the line poles is further improved, then the pole numbers are identified one by one through identification of the content on the pole number plate, and continuous and correct pole numbers are obtained through calculation and correction processing.
4. The invention also comprises base station positioning and Kepler positioning, and aims to ensure that the positioning effect is more accurate, part of positioning errors or inaccurate positioning can be caused by singly using any positioning method, and when the existing base station can not completely cover all lines, the positioning loss of part of lines can be caused; the Doppler radar is used for positioning only, and the Doppler radar can only calculate the running speed and the running kilometers of the train, but cannot acquire the position of the starting point of the train.
Drawings
FIG. 1 is a flow chart of the present invention for image processing and correction;
FIG. 2 is a flow chart of the present invention for continuous pole number correction.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to the accompanying drawings, but the scope of the present invention is not limited to the following.
The prior art carries out identification analysis through the identification image to the trackside, discerns the data message of pole number tablet to and the opportunity that the train passed through the pole number tablet, and with this carry out train position location and correction, but because the speed of a motor train is fast to need carry out continuous discernment to pole number tablet content, probably neglect to gather certain pole number tablet so that the identification error, finally lead to the problem that the location appears the mistake.
A continuous recognition and correction device for the contents of track pole number plates comprises a carriage, an image acquisition device, an image processing device and a display device, wherein the image acquisition device is connected with the image processing device;
the image acquisition device comprises a high-definition camera, a first optical sensor, a light supplement lamp, a controller, a first transmission unit and a second transmission unit, wherein the high-definition camera is connected with the first transmission unit, and the first transmission unit, the first optical sensor, the light supplement lamp and the second transmission unit are connected with the controller;
the image processing device comprises a second receiving unit, an image processing unit, a calculation correction unit and a processor, wherein the second receiving unit is connected with the image processing unit, the image processing unit is connected with the calculation correction unit, the calculation correction unit is connected with the processor, and the processor is connected with the display device;
the output end of the second transmission unit is connected with the input end of the second receiving unit;
the mileage encoder is connected with the processor, and is fixedly installed at the wheel axle end of the carriage for measuring the mileage data of the carriage.
Further, the image acquisition device still includes the second light sensor, the second light sensor with the controller is connected, be provided with normal light signal threshold value scope in the controller, when the light signal that first light sensor transmitted the controller does not belong to normal light signal threshold value scope, the controller starts the second light sensor and carries out outside light signal detection.
It should be noted that, the top end of the carriage is also provided with a wireless router, and the router is equipped with a 4G SIM card and is positioned by connecting the SIM card to a telecommunication, mobile or connected communication base station.
Wherein, at the bottom of the train installation Doppler radar sensor, make it to the track fastener transmission electromagnetic wave, Doppler radar makes the electromagnetic wave that the radar received constantly march along with the vehicle and has Doppler effect with between the electromagnetic wave of launching away, calculates the functioning speed on the relative ground of vehicle, and then realizes the location of vehicle running position.
A continuous identification and correction method for the contents of track pole number plates comprises the following steps;
step 1, a first optical sensor detects an external light signal and transmits the external light signal to a controller, and if the external light signal is larger than or equal to a threshold value set in the controller, the controller controls a high-definition camera arranged at the top end of a carriage to continuously shoot images along a railway; if the external light signal is smaller than a threshold value set in the controller, the controller controls the light supplement lamp to be turned on and simultaneously controls the high-definition camera to continuously shoot images along the railway;
step 2, the high-definition camera transmits the shot image to the controller through the first transmission unit, the controller transmits the image to the second receiving unit through the second transmission unit, the second receiving unit transmits the image to the image processing unit for processing, then the image processing unit corrects the single bar number after processing and recognition through the calculation correction unit, the calculation correction unit transmits the corrected result to the controller, and the controller displays the result through the display device;
the steps of processing and correcting the image are as follows: as shown in figure 1 of the drawings, in which,
step 1; acquiring images continuously shot by a high-definition camera arranged at the top end of a carriage along a railway;
step 2: marking the line pole in the image;
and step 3: judging whether the number of the line rods in the graph is zero, if so, executing the step 1, and if not, executing the step 4;
step 4; judging the number of the line rods in the graph, executing the step 5 when the number of the line rods is single, and executing the step 6 when the number of the line rods is more than 1;
and 5: identifying the pole number plate on the line pole, if the identification is successful, executing the step 7, and if the identification is failed, executing the step 8;
step 6: identifying the pole number plate of the pole closest to the high-definition camera, if the pole number plate is successfully identified, executing a step 7, and if the pole number plate is unsuccessfully identified, executing a step 8;
and 7: processing and identifying the content of the pole number plate to obtain a pole number; executing the step 9;
and 8: replacing other images shot at the same time for identification; executing the step 2;
and step 9: and putting the continuous rod number data identified in batches into a continuous rod number correction algorithm, correcting the rod numbers which are misjudged and missed in judgment through a series of judgment conditions preset by the algorithm, and finally outputting a continuous rod number detection result.
The steps of marking the line pole in the image are as follows:
step 1, enhancing the vertical edge of an outlet pole by utilizing a Sobel operator;
step 2, performing binarization processing on a result of enhancing the vertical edge of the outlet pole by using a Sobel operator;
step 3, detecting a straight line by using hough transformation; marking lines on two sides of a suspected line pole;
the identification of the line pole closest to the high-definition camera refers to the selection of the thickest line pole for pole number identification;
inputting the batch of continuous pole numbers into a continuous pole number correction algorithm, artificially correcting misjudged and missed pole numbers, and then matching the pole numbers with corresponding line pole images, as shown in fig. 2, the specific process is as follows:
step 1, searching an initial pole number index for an input pole number through a judgment condition;
step 2, calculating and comparing the difference between the current index rod number and the front and rear rod numbers, and judging the relative position of the current rod;
step 3, if the difference value between the front and rear rods is 0, comparing the last digit of the current rod number with the last digit of the front and rear rod numbers, and judging whether the current rod image belongs to the front item or the rear item; if the difference value between the front and rear rods is 4, the current rod number is the middle value of the front and rear rod numbers;
step 4, if the situations are not met, the current pole number is corrected bit by bit; similarly, each position of the current pole number is compared with the previous and next items in sequence, and the pole number is modified according to the equality relationship, and finally the pole number is modified;
and 5, outputting the modified rod numbers in sequence, corresponding the rod numbers to the paths of the image files, and finally outputting complete continuous rod number information.
Wherein, the process of identifying the content of the pole number plate comprises the following steps;
step 1, quickly positioning a pole number approximate area to be identified according to the distribution condition of an image HSV;
step 2, accurately extracting a rod number ROI through an image processing algorithm, carrying out binarization processing on an ROI area, and segmenting each character;
step 3, training and recognizing each character by using an SVM algorithm;
and 4, post-processing the result according to the characteristics of each character, and further eliminating false recognition.
The foregoing is merely a preferred embodiment of the invention, it being understood that the embodiments described are part of the invention, and not all of it. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. The invention is not intended to be limited to the forms disclosed herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A continuous recognition and correction device for the contents of track pole number plates is characterized by comprising a carriage, an image acquisition device, an image processing device and a display device, wherein the image acquisition device is connected with the image processing device;
the image acquisition device comprises a high-definition camera, a first optical sensor, a light supplement lamp, a controller, a first transmission unit and a second transmission unit, wherein the high-definition camera is connected with the first transmission unit, and the first transmission unit, the first optical sensor, the light supplement lamp and the second transmission unit are connected with the controller;
the image processing device comprises a second receiving unit, an image processing unit, a calculation correction unit and a processor, wherein the second receiving unit is connected with the image processing unit, the image processing unit is connected with the calculation correction unit, the calculation correction unit is connected with the processor, and the processor is connected with the display device;
and the output end of the second transmission unit is connected with the input end of the second receiving unit.
2. The continuous identification correction device for contents of track rod number plate according to claim 1, further comprising a mileage encoder connected with the processor, the mileage encoder being fixedly installed at the wheel axle end of the car for measuring mileage data of the car.
3. The apparatus as claimed in claim 1, wherein the image capturing device further comprises a second optical sensor, the second optical sensor is connected to the controller, a normal optical signal threshold range is set in the controller, and when the optical signal transmitted from the first optical sensor to the controller does not fall within the normal optical signal threshold range, the controller activates the second optical sensor to perform the external light signal detection.
4. The apparatus of claim 1, wherein a wireless router is installed at the top of the car, and the router is equipped with a 4G SIM card, and is located by connecting to a telecommunication, mobile or internet communication base station by using the SIM card.
5. The continuous recognition and correction device for the contents of the track rod number plate according to claim 1, wherein a doppler radar sensor is installed at the bottom of the train to emit electromagnetic waves toward the track fastener, and the doppler radar continuously advances with the vehicle to cause doppler effect between the electromagnetic waves received by the radar and the emitted electromagnetic waves, so as to calculate the running speed of the vehicle relative to the ground, thereby realizing the positioning of the running position of the vehicle.
6. A continuous identification and correction method for the contents of track pole number plates is characterized by comprising the following steps;
step 1, a first optical sensor detects an external light signal and transmits the external light signal to a controller, and if the external light signal is larger than or equal to a threshold value set in the controller, the controller controls a high-definition camera arranged at the top end of a carriage to continuously shoot images along a railway; if the external light signal is smaller than a threshold value set in the controller, the controller controls the light supplement lamp to be turned on and simultaneously controls the high-definition camera to continuously shoot images along the railway;
step 2, the high-definition camera transmits the shot image to the controller through the first transmission unit, the controller transmits the image to the second receiving unit through the second transmission unit, the second receiving unit transmits the image to the image processing unit for processing, then the image processing unit corrects the single bar number after processing and recognition through the calculation correction unit, the calculation correction unit transmits the corrected result to the controller, and the controller displays the result through the display device;
the steps of processing and correcting the image are as follows:
step 1; acquiring images continuously shot by a high-definition camera arranged at the top end of a carriage along a railway;
step 2: marking the line pole in the image;
and step 3: judging whether the number of the line rods in the graph is zero, if so, executing the step 1, and if not, executing the step 4;
step 4; judging the number of the line rods in the graph, executing the step 5 when the number of the line rods is single, and executing the step 6 when the number of the line rods is more than 1;
and 5: identifying the pole number plate on the line pole, if the identification is successful, executing the step 7, and if the identification is failed, executing the step 8;
step 6: identifying the pole number plate of the pole closest to the high-definition camera, if the pole number plate is successfully identified, executing a step 7, and if the pole number plate is unsuccessfully identified, executing a step 8;
and 7: processing and identifying the content of the pole number plate to obtain a pole number; executing the step 9;
and 8: replacing other images shot at the same time for identification; executing the step 2;
and step 9: putting the continuous rod number data identified in batches into a continuous rod number correction algorithm, correcting the rod numbers which are misjudged and missed in judgment through a series of judgment conditions preset by the algorithm, and finally outputting a continuous rod number detection result;
the steps of marking the line pole in the image are as follows:
step 1, enhancing the vertical edge of an outlet pole by utilizing a Sobel operator;
step 2, performing binarization processing on a result of enhancing the vertical edge of the outlet pole by using a Sobel operator;
step 3, detecting a straight line by using hough transformation; marking lines on two sides of a suspected line pole;
the identification of the line pole closest to the high-definition camera refers to the selection of the thickest line pole for pole number identification;
inputting the batch of continuous pole numbers into a continuous pole number correction algorithm, artificially correcting misjudged and missed pole numbers, and then matching the pole numbers with corresponding line pole images, wherein the specific process is as follows:
step 1, searching an initial pole number index for an input pole number through a judgment condition;
step 2, calculating and comparing the difference between the current index rod number and the front and rear rod numbers, and judging the relative position of the current rod;
step 3, if the difference value between the front and rear rods is 0, comparing the last digit of the current rod number with the last digit of the front and rear rod numbers, and judging whether the current rod image belongs to the front item or the rear item; if the difference value between the front and rear rods is 4, the current rod number is the middle value of the front and rear rod numbers;
step 4, if the situations are not met, the current pole number is corrected bit by bit; similarly, each position of the current pole number is compared with the previous and next items in sequence, and the pole number is modified according to the equality relationship, and finally the pole number is modified;
and 5, outputting the modified rod numbers in sequence, corresponding the rod numbers to the paths of the image files, and finally outputting complete continuous rod number information.
7. The continuous recognition correction method for contents of track pole number plate according to claim 6, wherein the process of recognizing contents of pole number plate comprises the steps of;
step 1, quickly positioning a pole number approximate area to be identified according to the distribution condition of an image HSV;
step 2, accurately extracting a rod number ROI through an image processing algorithm, carrying out binarization processing on an ROI area, and segmenting each character;
step 3, training and recognizing each character by using an SVM algorithm;
and 4, post-processing the result according to the characteristics of each character, and further eliminating false recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010727484.5A CN111591321A (en) | 2020-07-27 | 2020-07-27 | Continuous recognition and correction device and method for contents of track pole number plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010727484.5A CN111591321A (en) | 2020-07-27 | 2020-07-27 | Continuous recognition and correction device and method for contents of track pole number plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111591321A true CN111591321A (en) | 2020-08-28 |
Family
ID=72191814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010727484.5A Pending CN111591321A (en) | 2020-07-27 | 2020-07-27 | Continuous recognition and correction device and method for contents of track pole number plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111591321A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112009529A (en) * | 2020-09-03 | 2020-12-01 | 西南交通大学 | Train positioning method based on contact net support pole number image recognition |
| CN112009528A (en) * | 2020-09-03 | 2020-12-01 | 西南交通大学 | Train positioning method based on contact net and accessory thereof |
| CN112990132A (en) * | 2021-04-27 | 2021-06-18 | 成都中轨轨道设备有限公司 | Positioning and identifying method for track number plate |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203528510U (en) * | 2013-09-17 | 2014-04-09 | 苏州华兴致远电子科技有限公司 | Image collection device of railway overhead line system |
| KR20150034860A (en) * | 2013-09-25 | 2015-04-06 | 한국철도공사 | Pole position detection system through number recognition |
| CN107403180A (en) * | 2017-06-30 | 2017-11-28 | 广州广电物业管理有限公司 | A kind of numeric type equipment detection recognition method and system |
| CN107786673A (en) * | 2017-11-17 | 2018-03-09 | 成都正光恒电子科技有限责任公司 | A kind of Internet of things system |
| CN109664919A (en) * | 2017-10-17 | 2019-04-23 | 株洲中车时代电气股份有限公司 | A kind of train locating method and positioning system |
| CN110728269A (en) * | 2019-12-17 | 2020-01-24 | 西南交通大学 | High-speed rail contact net support pole number plate identification method |
-
2020
- 2020-07-27 CN CN202010727484.5A patent/CN111591321A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203528510U (en) * | 2013-09-17 | 2014-04-09 | 苏州华兴致远电子科技有限公司 | Image collection device of railway overhead line system |
| KR20150034860A (en) * | 2013-09-25 | 2015-04-06 | 한국철도공사 | Pole position detection system through number recognition |
| CN107403180A (en) * | 2017-06-30 | 2017-11-28 | 广州广电物业管理有限公司 | A kind of numeric type equipment detection recognition method and system |
| CN109664919A (en) * | 2017-10-17 | 2019-04-23 | 株洲中车时代电气股份有限公司 | A kind of train locating method and positioning system |
| CN107786673A (en) * | 2017-11-17 | 2018-03-09 | 成都正光恒电子科技有限责任公司 | A kind of Internet of things system |
| CN110728269A (en) * | 2019-12-17 | 2020-01-24 | 西南交通大学 | High-speed rail contact net support pole number plate identification method |
Non-Patent Citations (1)
| Title |
|---|
| FSHMENG: ""一个高铁线杆杆号自动识别分类系统"", 《CSDN（HTTPS://BLOG.CSDN.NET/FSHMENG/ARTICLE/DETAILS/50893734?LOCATIONNUM=5&FPS=1）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112009529A (en) * | 2020-09-03 | 2020-12-01 | 西南交通大学 | Train positioning method based on contact net support pole number image recognition |
| CN112009528A (en) * | 2020-09-03 | 2020-12-01 | 西南交通大学 | Train positioning method based on contact net and accessory thereof |
| CN112990132A (en) * | 2021-04-27 | 2021-06-18 | 成都中轨轨道设备有限公司 | Positioning and identifying method for track number plate |
| CN112990132B (en) * | 2021-04-27 | 2023-01-03 | 成都中轨轨道设备有限公司 | Positioning and identifying method for track number plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111591321A (en) | Continuous recognition and correction device and method for contents of track pole number plate | |
| CN110189424B (en) | Multi-lane free flow vehicle detection method and system based on multi-target radar | |
| CN104851295B (en) | Obtain the method and system of traffic information | |
| KR101446546B1 (en) | Display system of vehicle information based on the position | |
| CN110751788A (en) | System and method for identifying whether vehicle direction and angle and distance of road are correct | |
| CN1949292A (en) | Real-time testing system and method for speed and relative position of vehicle on expressway | |
| CN106652063A (en) | Free-flow electronic charging method and system for bidirectional lane | |
| CN112085950B (en) | Method and system for estimating traffic state discrimination index, storage medium and application | |
| CN109085177B (en) | Leaky cable appearance detection method and device based on RFID positioning | |
| CN105551307A (en) | Lane recognition system and method based on vehicle highway communication | |
| CN106599894A (en) | Method for identifying pole number of overhead line system based on image identification | |
| CN113591643A (en) | Underground vehicle station entering and exiting detection system and method based on computer vision | |
| CN207115750U (en) | A kind of radar traffic event automatic detection system | |
| CN110796869A (en) | Method and device for detecting illegal car following | |
| CN111243022A (en) | Bottom layer absolute positioning method and positioning system based on track path | |
| CN207097233U (en) | A kind of information of vehicles intelligent acquisition system for prompting | |
| CN117037305A (en) | Road parking inspection evidence collection charging system based on edge calculation | |
| CN107831789A (en) | A kind of unmanned automatic driving mechanical transport signal lamp synchronisation control means | |
| CN112085034A (en) | Rail transit train positioning method and system based on machine vision | |
| CN116092305A (en) | Site information broadcasting method, server, vehicle, road side equipment and system | |
| CN211075861U (en) | Road state detection system | |
| CN116429123A (en) | Vehicle positioning method based on multi-source information fusion | |
| CN110363982B (en) | Vehicle type identification method based on roadside wireless unit, terminal equipment and storage medium | |
| CN115782969A (en) | Data acquisition system applied to environmental monitoring of railway system | |
| CN209776454U (en) | Train positioning device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |
|
| RJ01 | Rejection of invention patent application after publication |