CN114670899A - Image acquisition device for track detection system - Google Patents
Image acquisition device for track detection system Download PDFInfo
- Publication number
- CN114670899A CN114670899A CN202210419324.3A CN202210419324A CN114670899A CN 114670899 A CN114670899 A CN 114670899A CN 202210419324 A CN202210419324 A CN 202210419324A CN 114670899 A CN114670899 A CN 114670899A
- Authority
- CN
- China
- Prior art keywords
- track
- linear array
- array camera
- image
- control unit
- 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 16
- 238000012545 processing Methods 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 22
- 230000002265 prevention Effects 0.000 claims description 20
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000013500 data storage Methods 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 15
- 230000003287 optical effect Effects 0.000 claims description 13
- 239000000428 dust Substances 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 10
- 238000007726 management method Methods 0.000 claims description 10
- 241001669679 Eleotris Species 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009792 diffusion process Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000005855 radiation Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 230000000630 rising effect Effects 0.000 claims description 5
- 239000004576 sand Substances 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000007547 defect Effects 0.000 description 10
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 238000006748 scratching Methods 0.000 description 1
- 230000002393 scratching effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/042—Track changes detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses an image acquisition device for a track detection system, which comprises: the system comprises a linear array camera control unit, a plurality of independent linear array camera units and a mileage recording unit; the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track; the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit; the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit. The environmental adaptability of the system is enhanced, the system can adapt to the area with insufficient light, and the interference of the ambient stray light can be effectively reduced.
Description
Technical Field
The invention relates to the field of image acquisition, in particular to an image acquisition device for a track detection system.
Background
The running speed of the railway is continuously improved, the back and forth of the train are more frequent, and the load of the track is heavier and heavier. In order to ensure the running safety of the train and the smooth line, the track must be monitored in real time. In daily inspection, except that detecting the geometric status of track through using the track detector, still need in time to know rail surface and fastener whether have the defect to discover defect and position as early as possible, correctly guide the staff to maintain the track in real time, guarantee railway transportation safety.
At present, a visual method, namely visual inspection of track patrolling workers, is mainly adopted for detecting the defects of the track. This method has a number of disadvantages: the time consumption is long, the efficiency is not high, and the influence of weather factors and the responsibility of patrol workers is easy to influence. Meanwhile, the personal safety of the patrol workers is greatly threatened due to the high-speed running of the train. Therefore, there is an urgent need for an image acquisition device for a track inspection system, which can rapidly, safely and completely acquire track images, acquire track information, and ensure the normal transportation of a line.
Disclosure of Invention
The invention provides an image acquisition device for a track detection system, which aims to solve the problems that the running speed of a railway is continuously improved, the train is more frequently reciprocated, and the load of a track is heavier and heavier in the prior art. In order to ensure the running safety of the train and the smooth line, the track must be monitored in real time. In daily inspection, except that detecting the geometric status of track through using the track detector, still need in time to know rail surface and fastener whether have the defect to discover defect and position as early as possible, correctly guide the staff to maintain the track in real time, guarantee railway transportation safety. At present, a visual method, namely visual inspection of track patrolling workers, is mainly adopted for detecting the defects of the track. This method has a number of disadvantages: the time consumption is long, the efficiency is not high, and the influence of weather factors and the responsibility of patrol workers is easy to influence. Meanwhile, the personal safety of the patrol workers is greatly threatened due to the high-speed running of the train. Therefore, there is a need for an image collecting device for a track inspection system, which can collect track images quickly, safely and completely, acquire track information, and ensure the normal transportation of the line.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention provides an image acquisition device for a track detection system, which comprises: the system comprises a linear array camera control unit, a plurality of independent linear array camera units and a mileage recording unit;
the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track;
the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit;
the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit.
Wherein the plurality of independent line camera units comprise: the system comprises a linear array camera, a laser and an external adjusting device;
the linear array camera is used for dynamically adjusting scanning line frequency according to train speed on a track, and acquiring high-definition image data of key components of the track in a track picture shooting mode, wherein the key components comprise: two sides of a track rail, a fastener, a sleeper and a track bed;
the laser is used for obtaining uniform beam distribution through diffusion of the configured cylindrical lens;
the external adjusting device is used for preventing direct light radiation through dust prevention, fog prevention, water prevention and light prevention, and the linear array camera normally collects image data in rainy days, sunshine, ultraviolet rays, dust and sand storm.
Wherein, the linear array camera management and control unit includes: a data storage module;
in the image acquisition process, the acquired track image is stored through the data storage module, wherein the data storage module adopts a multithreading technology to increase the response speed of image storage.
Wherein, the line camera includes: the device comprises an optical encoder, a singlechip, a driving device and a camera;
the linear array camera automatically calibrates according to the train speed on the current track and the position of a shooting object, and acquires a track image after automatic calibration;
the optical encoder generates a pulse signal, the single chip microcomputer converts pulse information into a TTL level trigger signal which can be recognized by the linear array camera, the TTL level trigger signal triggers a driving device to drive a camera to shoot a track picture, and track image data are obtained by shooting the track picture;
through an external trigger mode, pulse signals generated by the optical encoder according to different track running speeds are different, and the linear array camera scans at fixed intervals to ensure clear images.
The linear array camera control unit sets a preset shooting angle range according to the track movement condition, acquires an adjustment mode corresponding to the linear array camera, and controls the camera to focus;
the track movement situation includes: the linear array camera management and control unit converts the angular velocity information and the acceleration information into the same coordinate system to calculate the movement value.
The mileage recording unit acquires the mileage of the train on the track through a square wave signal in the photoelectric encoder and a counter in the singlechip;
the photoelectric encoder outputs pulse signals by rotating a preset angle, obtains the rotating angle by calculating the total amount of the sent pulse signals, converts the rotating angle into pulse electric signals to be output, sends a fixed pulse number every time the photoelectric encoder rotates for one circle, transmits the pulse number to the single chip microcomputer, captures input effective edges by using a programmable counter array module in the single chip microcomputer, generates interruption on both the rising edge and the falling edge of the input signals, obtains the counting work of the output pulses, and obtains the actual mileage by using a calculation principle through the number of high-low level pulses and the wheel circumference of a train on a track.
The linear array camera control unit adopts a neural network technology to carry out deep learning on a target image, automatically identifies the abnormal state of a target part through the deep learning and carries out alarm prompt on the identified abnormal state;
the linear array camera collects track images and then positions key structure parts on the images, the linear array camera control unit classifies positioning areas by using a classifier algorithm, and judges whether classification results are abnormal or not;
the linear array camera control unit positions a track key structure in an algorithm comprehensive evaluation mode, a depth neural network positioning algorithm is adopted to identify and position a first frame of image acquired by the linear array camera, a fuzzy algorithm is adopted to track and position subsequent images acquired by the linear array camera, and positioning of track key components is obtained by combining two positioning algorithms.
Wherein, still include: high-definition high-speed infrared thermal image acquisition unit, high-definition high-speed infrared thermal image acquisition unit includes: the system comprises a thermal infrared imager and a thermal infrared image processing module;
the system comprises an infrared thermal imager, an infrared thermal image processing module, a thermal infrared image acquisition module, a thermal infrared image processing module and a thermal infrared image processing module, wherein the thermal infrared thermal imager acquires the thermal infrared image of a rail current-receiving temperature field of a traveling crane in the rail running process and high-temperature points and distribution maps in the thermal image in a high-definition shooting mode, the collected thermal infrared image is uploaded to the thermal infrared thermal image processing module, and the thermal infrared thermal image processing module analyzes the thermal infrared image in real time to acquire the temperature and frequency distribution curves of the thermal infrared thermal image.
The linear array camera control unit measures track profile and track gauge through track images;
the linear array camera and the laser are combined, and a laser triangulation method is utilized to measure a pull-out value and a lead height value of a contact line;
when a train runs along a track, a laser emits linear laser to irradiate on a contact line to form a light spot, and the linear array camera takes an upward shooting light spot area from the side surface to acquire an image;
along with the difference of the space position of the contact line, the position of a laser spot in the image correspondingly changes, and the height conducting value and the pull-out value of the contact line are measured and calculated through the positioning of the spot;
and acquiring a height guiding value through the distance between the light spot and the bottom end of the image, and acquiring the variation of the pulling value through the distance between the light spot and the center of the image.
The linear array camera control unit removes Gaussian noise from the track images acquired by the independent linear array camera units through a Gaussian filtering technology, divides the track images without the Gaussian noise into A, B, C three image data, performs median filtering and sharpening on the three image data respectively, and merges the three image data channels after the median filtering and sharpening are performed.
Compared with the prior art, the invention has the following advantages:
an image capture device for a rail inspection system, comprising: the system comprises a linear array camera control unit, a plurality of independent linear array camera units and a mileage recording unit; the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track; the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit; the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit. The method has the advantages of high acquisition speed and low mining leakage rate, and ensures the running safety of the train through efficient detection of the track.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an image capture device for a rail inspection system according to an embodiment of the present invention;
FIG. 2 is a flow chart of an image capture device for a rail inspection system according to an embodiment of the present invention;
fig. 3 is a structural diagram of a plurality of independent line camera units in an image acquisition device for a track inspection system according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
An embodiment of the present invention provides an image capturing device for a track detection system, referring to fig. 1 to 3, the image capturing device for a track detection system includes: the system comprises a linear array camera control unit, a plurality of independent linear array camera units and a mileage recording unit;
the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track;
the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit;
the mileage recording unit is used for recording the driving distance of a train on the track, determining the shooting position of each track picture according to the driving distance, and feeding the position of the track picture back to the linear array camera control unit.
The working principle of the technical scheme is as follows: the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track; the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit; the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit.
The beneficial effects of the above technical scheme are: the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track; the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit; the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit. The method has the advantages of high acquisition speed and low mining leakage rate, and ensures the running safety of the train through efficient detection of the track.
In another embodiment, the number of independent line camera units comprises: the system comprises a linear array camera, a laser and an external adjusting device;
the linear array camera is used for dynamically adjusting scanning line frequency according to train speed on a track, and acquiring high-definition image data of key components of the track in a track picture shooting mode, wherein the key components comprise: two sides of a track rail, a fastener, a sleeper and a track bed;
the laser is used for obtaining uniform beam distribution through diffusion of the configured cylindrical lens;
the external adjusting device is used for preventing direct light radiation through dust prevention, fog prevention, water prevention and light prevention, and the linear array camera normally collects image data in rainy days, sunshine, ultraviolet rays, dust and sand storm.
The working principle of the technical scheme is as follows: the plurality of independent line camera units comprise: the system comprises a linear array camera, a laser and an external adjusting device; the linear array camera is used for dynamically adjusting scanning line frequency according to train speed on a track, and acquiring high-definition image data of key components of the track in a track picture shooting mode, wherein the key components comprise: two sides of a track rail, a fastener, a sleeper and a track bed; the laser is used for obtaining uniform beam distribution through diffusion of the configured cylindrical lens; the external adjusting device is used for preventing direct light radiation through dust prevention, fog prevention, water prevention and light prevention, and the linear array camera normally collects image data in rainy days, sunshine, ultraviolet rays, dust and sand storm. The laser adopts the light intensity self-adaptive technology, and the quality stability of the collected image in the rail environment is ensured. The linear array camera dynamically adjusts scanning line frequency according to the driving speed, and high-definition images of key positions such as steel rails, fasteners, dust pillows and track beds under non-uniform motion are acquired. The driving speed can be acquired through a TCMS network, or a speed sensor is added to detect in real time.
The beneficial effects of the above technical scheme are: the plurality of independent line camera units comprise: the system comprises a linear array camera, a laser and an external adjusting device; the linear array camera is used for dynamically adjusting scanning line frequency according to train speed on a track, and acquiring high-definition image data of key components of the track in a track picture shooting mode, wherein the key components comprise: two sides of a track rail, a fastener, a sleeper and a track bed; the laser is used for obtaining uniform beam distribution through diffusion of the configured cylindrical lens; the external adjusting device is used for preventing direct light radiation through dust prevention, fog prevention, water prevention and light prevention, and the linear array camera normally collects image data in rainy days, sunshine, ultraviolet rays, dust and sand storm. The rail defect detection device has the characteristics of high efficiency, high speed, high maneuverability, all-weather and full-automatic operation, can automatically judge the rail defect condition, record the mileage information of the rail defect condition, and can automatically identify the defects of falling blocks, scratching, fastener dislocation, falling and the like of the steel rail.
In another embodiment, the line camera mastering unit includes: a data storage module;
in the image acquisition process, the acquired track image is stored through the data storage module, wherein the data storage module adopts a multithreading technology to increase the response speed of image storage.
The working principle of the technical scheme is as follows: in the image acquisition process, the acquired track image is stored through the data storage module, wherein the data storage module adopts a multithreading technology to increase the response speed of image storage. The image storage speed is kept up with the picture shooting speed, and the image data storage speed and the real-time display are facilitated.
The beneficial effects of the above technical scheme are: in the image acquisition process, the acquired track image is stored through the data storage module, wherein the data storage module adopts a multithreading technology to increase the response speed of image storage. The image storage speed is kept up with the picture shooting speed, and the image data storage speed and the real-time display are facilitated.
In another embodiment, the line camera comprises: the device comprises an optical encoder, a singlechip, a driving device and a camera;
the linear array camera automatically calibrates according to the train speed on the current track and the position of a shooting object, and acquires a track image after automatic calibration;
the optical encoder generates a pulse signal, the single chip microcomputer converts pulse information into a TTL level trigger signal which can be recognized by the linear array camera, the TTL level trigger signal triggers a driving device to drive a camera to shoot a track picture, and track image data are obtained by shooting the track picture;
through an external trigger mode, pulse signals generated by the optical encoder according to different track running speeds are different, and the linear array camera scans at fixed intervals to ensure clear images.
The working principle of the technical scheme is as follows: the linear array camera automatically calibrates according to the train speed on the current track and the position of a shooting object, and acquires a track image after automatic calibration; the optical encoder generates a pulse signal, the single chip microcomputer converts pulse information into a TTL level trigger signal which can be recognized by the linear array camera, the TTL level trigger signal triggers a driving device to drive a camera to shoot a track picture, and track image data are obtained by shooting the track picture; through an external trigger mode, pulse signals generated by the optical encoder according to different track running speeds are different, and the linear array camera scans at fixed intervals to ensure clear images.
The beneficial effects of the above technical scheme are: the linear array camera carries out automatic calibration according to the train speed on the current track and the position of a shooting object, and acquires a track image after the automatic calibration; the optical encoder generates a pulse signal, the single chip microcomputer converts pulse information into a TTL level trigger signal which can be recognized by the linear array camera, the TTL level trigger signal triggers the driving device to drive the camera to shoot a track picture, and track image data are obtained by shooting the track picture; through an external trigger mode, pulse signals generated by the optical encoder according to different track running speeds are different, and the linear array camera scans at fixed intervals to ensure clear images.
In another embodiment, the linear array camera control unit sets a preset shooting angle range according to a track movement condition, acquires an adjustment mode corresponding to the linear array camera, and controls the camera to perform focusing processing;
the track movement situation includes: the linear array camera management and control unit converts the angular velocity information and the acceleration information into the same coordinate system to calculate the movement value.
The working principle of the technical scheme is as follows: the linear array camera control unit sets a preset shooting angle range according to the track movement condition, acquires an adjustment mode corresponding to the linear array camera, and controls the camera to focus; the track movement situation includes: the linear array camera control unit converts the angular velocity information and the acceleration information into the same coordinate system to calculate the movement value.
The beneficial effects of the above technical scheme are: the linear array camera control unit sets a preset shooting angle range according to the track movement condition, acquires an adjustment mode corresponding to the linear array camera, and controls the camera to focus; the track movement situation includes: the linear array camera management and control unit converts the angular velocity information and the acceleration information into the same coordinate system to calculate the movement value.
In another embodiment, the mileage recording unit acquires the mileage of the train on the track through a square wave signal in the photoelectric encoder and a counter in the singlechip;
the photoelectric encoder outputs pulse signals by rotating a preset angle, obtains the rotating angle by calculating the total amount of the sent pulse signals, converts the rotating angle into pulse electric signals to be output, sends a fixed pulse number every time the photoelectric encoder rotates for one circle, transmits the pulse number to the single chip microcomputer, captures input effective edges by using a programmable counter array module in the single chip microcomputer, generates interruption on both the rising edge and the falling edge of the input signals, obtains the counting work of the output pulses, and obtains the actual mileage by using a calculation principle through the number of high-low level pulses and the wheel circumference of a train on a track.
The working principle of the technical scheme is as follows: the mileage recording unit acquires the mileage of the train on the track through a square wave signal in the photoelectric encoder and a counter in the singlechip; the photoelectric encoder outputs pulse signals by rotating a preset angle, obtains the rotating angle by calculating the total amount of the sent pulse signals, converts the rotating angle into pulse electric signals to be output, sends a fixed pulse number every time the photoelectric encoder rotates for one circle, transmits the pulse number to the single chip microcomputer, captures input effective edges by using a programmable counter array module in the single chip microcomputer, generates interruption on both the rising edge and the falling edge of the input signals, obtains the counting work of the output pulses, and obtains the actual mileage by using a calculation principle through the number of high-low level pulses and the wheel circumference of a train on a track.
The beneficial effects of the above technical scheme are: the mileage recording unit acquires the mileage of the train on the track through a square wave signal in the photoelectric encoder and a counter in the singlechip; the photoelectric encoder outputs pulse signals by rotating a preset angle, obtains the rotating angle by calculating the total amount of the sent pulse signals, converts the rotating angle into pulse electric signals to be output, sends a fixed pulse number every time the photoelectric encoder rotates for one circle, transmits the pulse number to the single chip microcomputer, captures input effective edges by using a programmable counter array module in the single chip microcomputer, generates interruption on both the rising edge and the falling edge of the input signals, obtains the counting work of the output pulses, and obtains the actual mileage by using a calculation principle through the number of high-low level pulses and the wheel circumference of a train on a track.
In another embodiment, the linear array camera control unit adopts a neural network technology to carry out deep learning on a target image, automatically identifies the abnormal state of a target part through the deep learning, and carries out alarm prompt on the identified abnormal state;
the linear array camera collects track images and then positions key structure parts on the images, the linear array camera control unit classifies positioning areas by using a classifier algorithm, and judges whether classification results are abnormal or not;
the linear array camera control unit positions a track key structure in an algorithm comprehensive evaluation mode, a depth neural network positioning algorithm is adopted to identify and position a first frame of image acquired by the linear array camera, a fuzzy algorithm is adopted to track and position subsequent images acquired by the linear array camera, and positioning of track key components is obtained by combining two positioning algorithms.
The working principle of the technical scheme is as follows: the linear array camera control unit adopts a neural network technology to carry out deep learning on a target image, automatically identifies the abnormal state of a target part through the deep learning and carries out alarm prompt on the identified abnormal state; the linear array camera collects track images and then positions key structure parts on the images, the linear array camera control unit classifies positioning areas by using a classifier algorithm, and judges whether classification results are abnormal or not; the linear array camera control unit positions a track key structure in an algorithm comprehensive evaluation mode, a depth neural network positioning algorithm is adopted to identify and position a first frame of image acquired by the linear array camera, a fuzzy algorithm is adopted to track and position subsequent images acquired by the linear array camera, and positioning of track key components is obtained by combining two positioning algorithms.
The beneficial effects of the above technical scheme are: the linear array camera control unit adopts a neural network technology to carry out deep learning on a target image, automatically identifies the abnormal state of a target part through the deep learning and carries out alarm prompt on the identified abnormal state; the linear array camera collects track images and then positions key structure parts on the images, the linear array camera control unit classifies positioning areas by using a classifier algorithm, and judges whether the classification result is abnormal or not; the linear array camera control unit positions a key structure of the track in an algorithm comprehensive evaluation mode, a depth neural network positioning algorithm is adopted to identify and position a first frame of image acquired by the linear array camera, a fuzzy algorithm is adopted to track and position subsequent images acquired by the linear array camera, and positioning of key components of the track is obtained by combining two positioning algorithms.
In another embodiment, further comprising: high-definition high-speed infrared thermal image acquisition unit, high-definition high-speed infrared thermal image acquisition unit includes: the system comprises a thermal infrared imager and a thermal infrared image processing module;
the system comprises an infrared thermal imager, an infrared thermal image processing module, a thermal infrared image acquisition module, a thermal infrared image processing module and a thermal infrared image processing module, wherein the thermal infrared thermal imager acquires the thermal infrared image of a rail current-receiving temperature field of a traveling crane in the rail running process and high-temperature points and distribution maps in the thermal image in a high-definition shooting mode, the collected thermal infrared image is uploaded to the thermal infrared thermal image processing module, and the thermal infrared thermal image processing module analyzes the thermal infrared image in real time to acquire the temperature and frequency distribution curves of the thermal infrared thermal image.
The working principle of the technical scheme is as follows: the system comprises an infrared thermal imager, an infrared thermal image processing module, a rail current receiving temperature field thermal image, a thermal image distribution curve and high temperature points and distribution maps, wherein the infrared thermal imager collects infrared thermal images of targets in a set range in a high-definition shooting mode, the infrared thermal imager uploads the collected infrared thermal images to the infrared thermal image processing module, the infrared thermal image processing module analyzes the infrared thermal images in real time, the temperature and frequency distribution curve of the infrared thermal images are obtained, and the rail current receiving temperature field thermal image and the high temperature points and the distribution maps in the thermal image of a traveling crane in the rail running process are obtained according to the temperature and frequency distribution curve of the infrared thermal images.
The beneficial effects of the above technical scheme are: the system comprises an infrared thermal imager, an infrared thermal image processing module, a thermal infrared image acquisition module, a thermal infrared image processing module and a thermal infrared image processing module, wherein the thermal infrared thermal imager acquires the thermal infrared image of a rail current-receiving temperature field of a traveling crane in the rail running process and high-temperature points and distribution maps in the thermal image in a high-definition shooting mode, the collected thermal infrared image is uploaded to the thermal infrared thermal image processing module, and the thermal infrared thermal image processing module analyzes the thermal infrared image in real time to acquire the temperature and frequency distribution curves of the thermal infrared thermal image.
In another embodiment, the line camera management and control unit measures track profile and track gauge through track images;
the linear array camera and the laser are combined, and a laser triangulation method is utilized to measure a pull-out value and a lead height value of a contact line;
when a train runs along a track, a laser emits linear laser to irradiate on a contact line to form a light spot, and the linear array camera takes an upward shooting light spot area from the side surface to acquire an image;
along with the difference of the space position of the contact line, the position of a laser spot in the image correspondingly changes, and the height conducting value and the pull-out value of the contact line are measured and calculated through the positioning of the spot;
and acquiring a height guiding value through the distance between the light spot and the bottom end of the image, and acquiring the variation of the pulling value through the distance between the light spot and the center of the image.
The working principle of the technical scheme is as follows: the linear array camera control unit measures track profile and track gauge through track images; the linear array camera and the laser are combined, and a laser triangulation method is utilized to measure a pull-out value and a lead height value of a contact line; when a train runs along a track, a laser emits linear laser to irradiate on a contact line to form a light spot, and the linear array camera takes an upward shooting light spot area from the side surface to acquire an image; along with the difference of the space position of the contact line, the position of a laser spot in the image correspondingly changes, and the height conducting value and the pull-out value of the contact line are measured and calculated through the positioning of the spot; and acquiring a height guiding value through the distance between the light spot and the bottom end of the image, and acquiring the variation of the pulling value through the distance between the light spot and the center of the image.
The beneficial effects of the above technical scheme are: the linear array camera control unit measures track profile and track gauge through track images; the linear array camera and the laser are combined, and a laser triangulation method is utilized to measure a pull-out value and a lead height value of a contact line; when a train runs along a track, a laser emits linear laser to irradiate on a contact line to form a light spot, and the linear array camera takes an upward shooting light spot area from the side surface to acquire an image; along with the difference of the space position of the contact line, the position of a laser spot in the image correspondingly changes, and the height conducting value and the pull-out value of the contact line are measured and calculated through the positioning of the spot; and acquiring a height guiding value through the distance between the light spot and the bottom end of the image, and acquiring the variation of the pulling value through the distance between the light spot and the center of the image.
In another embodiment, the linear array camera management and control unit removes gaussian noise from the track image acquired by the independent linear array camera units through a gaussian filtering technology, divides the track image without gaussian noise into A, B, C three image data, performs median filtering and sharpening on the three image data, and merges the three image data channels after median filtering and sharpening.
The working principle of the technical scheme is as follows: the linear array camera control unit removes Gaussian noise from the track images acquired by the independent linear array camera units through a Gaussian filtering technology, divides the track images without the Gaussian noise into A, B, C three image data, performs median filtering and sharpening on the three image data respectively, and merges the three image data channels after the median filtering and sharpening are performed.
The depth of field limit value can be calculated according to parameters such as the shooting distance, the aperture value, the lens focal length, the pixel resolution, the angle between the linear array camera and the shot object, and the like, and the depth of field limit value formula is as follows:
wherein Δ represents the depth of field limit; ω represents the pixel resolution; h represents an f-number; l represents a shooting distance; f represents the focal length of a lens of the high-definition video monitoring camera; theta is an included angle between the high-definition video monitoring camera and a shot object.
By acquiring the depth of field limit value, the finally acquired image can be clearly imaged, and the later image processing task is facilitated.
The beneficial effects of the above technical scheme are: the linear array camera control unit removes Gaussian noise from the track images acquired by the independent linear array camera units through a Gaussian filtering technology, divides the track images without the Gaussian noise into A, B, C three image data, performs median filtering and sharpening on the three image data respectively, and merges the three image data channels after the median filtering and sharpening are performed. The image distortion or blurring caused by the difference of the train running speed is eliminated.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. An image capture device for a rail inspection system, comprising: the system comprises a linear array camera control unit, a plurality of independent linear array camera units and a mileage recording unit;
the linear array camera control unit is used for transmitting control instructions to the plurality of independent linear array camera units according to the speed of trains on the track;
the plurality of independent linear array camera units are used for acquiring track image data according to the received control instruction, and the acquired track image data are transmitted to the linear array camera control unit;
the mileage recording unit is used for recording the distance traveled by a train on the track, determining the shooting position of each track picture according to the distance traveled, and feeding the position of the track picture back to the linear array camera control unit.
2. The image capturing device of claim 1, wherein said plurality of individual line camera units comprises: the system comprises a linear array camera, a laser and an external adjusting device;
the linear array camera is used for dynamically adjusting scanning line frequency according to train speed on a track, and acquiring high-definition image data of key components of the track in a track picture shooting mode, wherein the key components comprise: two sides of a track rail, a fastener, a sleeper and a track bed;
the laser is used for obtaining uniform beam distribution through diffusion of the configured cylindrical lens;
the external adjusting device is used for preventing direct light radiation through dust prevention, fog prevention, water prevention and light prevention, and the linear array camera normally collects image data in rainy days, sunshine, ultraviolet rays, dust and sand storm.
3. The image capturing device for track inspection system as claimed in claim 1, wherein the line camera management and control unit comprises: a data storage module;
in the image acquisition process, the acquired track image is stored through the data storage module, wherein the data storage module adopts a multithreading technology to increase the response speed of image storage.
4. The image capturing device of claim 2, wherein the line camera comprises: the device comprises an optical encoder, a singlechip, a driving device and a camera;
the linear array camera automatically calibrates according to the train speed on the current track and the position of a shooting object, and acquires a track image after automatic calibration;
the optical encoder generates a pulse signal, the single chip microcomputer converts pulse information into a TTL level trigger signal which can be recognized by the linear array camera, the TTL level trigger signal triggers a driving device to drive a camera to shoot a track picture, and track image data are obtained by shooting the track picture;
through an external trigger mode, pulse signals generated by the optical encoder according to different track running speeds are different, and the linear array camera scans at fixed intervals to ensure clear images.
5. The image acquisition device for the track detection system according to claim 4, wherein the linear array camera control unit sets a preset shooting angle range according to the track movement condition to obtain an adjustment mode corresponding to the linear array camera, and controls the camera to perform focusing processing;
the track movement situation includes: the linear array camera management and control unit converts the angular velocity information and the acceleration information into the same coordinate system to calculate the movement value.
6. The image acquisition device for the track detection system according to claim 4, wherein the mileage recording unit acquires the mileage of the train on the track through a square wave signal in the photoelectric encoder and a counter in the single chip microcomputer;
the photoelectric encoder outputs pulse signals by rotating a preset angle, obtains the rotating angle by calculating the total amount of the sent pulse signals, converts the rotating angle into pulse electric signals to be output, sends a fixed pulse number every time the photoelectric encoder rotates for one circle, transmits the pulse number to the single chip microcomputer, captures input effective edges by using a programmable counter array module in the single chip microcomputer, generates interruption on both the rising edge and the falling edge of the input signals, obtains the counting work of the output pulses, and obtains the actual mileage by using a calculation principle through the number of high-low level pulses and the wheel circumference of a train on a track.
7. The image acquisition device for the track detection system according to claim 2, wherein the linear array camera control unit adopts a neural network technology to perform deep learning on the target image, automatically identifies the abnormal state of the target part through the deep learning, and performs alarm prompt on the identified abnormal state;
the linear array camera collects track images and then positions key structure parts on the images, the linear array camera control unit classifies positioning areas by using a classifier algorithm, and judges whether classification results are abnormal or not;
the linear array camera control unit positions a track key structure in an algorithm comprehensive evaluation mode, a depth neural network positioning algorithm is adopted to identify and position a first frame of image acquired by the linear array camera, a fuzzy algorithm is adopted to track and position subsequent images acquired by the linear array camera, and positioning of track key components is obtained by combining two positioning algorithms.
8. The image capturing device of claim 1, further comprising: high-definition high-speed infrared thermal image acquisition unit, high-definition high-speed infrared thermal image acquisition unit includes: the system comprises a thermal infrared imager and a thermal infrared image processing module;
the system comprises an infrared thermal imager, an infrared thermal image processing module, a rail current receiving temperature field thermal image, a thermal image distribution curve and high temperature points and distribution maps, wherein the infrared thermal imager collects infrared thermal images of targets in a set range in a high-definition shooting mode, the infrared thermal imager uploads the collected infrared thermal images to the infrared thermal image processing module, the infrared thermal image processing module analyzes the infrared thermal images in real time, the temperature and frequency distribution curve of the infrared thermal images are obtained, and the rail current receiving temperature field thermal image and the high temperature points and the distribution maps in the thermal image of a traveling crane in the rail running process are obtained according to the temperature and frequency distribution curve of the infrared thermal images.
9. The image acquisition device for the track detection system according to claim 2, wherein the linear array camera management and control unit measures track profile and track gauge through track images;
the linear array camera and the laser are combined, and a pulling value and a leading height value of a contact wire are measured by using a laser triangulation method;
when a train runs along a track, a laser emits linear laser to irradiate on a contact line to form a light spot, and the linear array camera takes an upward shooting light spot area from the side surface to acquire an image;
along with the difference of the space position of the contact line, the position of a laser spot in the image correspondingly changes, and the height conducting value and the pull-out value of the contact line are measured and calculated through the positioning of the spot;
and acquiring a height guiding value through the distance between the light spot and the bottom end of the image, and acquiring the variation of the pulling value through the distance between the light spot and the center of the image.
10. The image acquisition device for the track detection system according to claim 1, wherein the line camera management and control unit removes gaussian noise from the track images acquired by the plurality of independent line camera units through a gaussian filtering technique, divides the track images without gaussian noise into A, B, C three image data, performs median filtering and sharpening on the three image data, and merges the three image data channels after median filtering and sharpening.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210419324.3A CN114670899A (en) | 2022-04-20 | 2022-04-20 | Image acquisition device for track detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210419324.3A CN114670899A (en) | 2022-04-20 | 2022-04-20 | Image acquisition device for track detection system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114670899A true CN114670899A (en) | 2022-06-28 |
Family
ID=82078790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210419324.3A Pending CN114670899A (en) | 2022-04-20 | 2022-04-20 | Image acquisition device for track detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114670899A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116320791A (en) * | 2023-03-16 | 2023-06-23 | 北京运达华开科技有限公司 | Image acquisition system and method based on track detection |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120137974A (en) * | 2011-06-14 | 2012-12-24 | 한국철도기술연구원 | Detection apparatus and method of train outside fault |
CN106080661A (en) * | 2016-05-27 | 2016-11-09 | 电子科技大学 | Train guide rail profile undulatory wear measuring method |
CN107014294A (en) * | 2017-05-09 | 2017-08-04 | 中国铁道科学研究院 | A kind of contact net geometric parameter detection method and system based on infrared image |
CN108248634A (en) * | 2018-01-24 | 2018-07-06 | 西南交通大学 | Track switch and track full-sized abrasion vision measurer and its measuring method |
CN110254468A (en) * | 2019-06-20 | 2019-09-20 | 吉林大学 | A kind of raceway surface defect intelligent online detection device and detection method |
CN110261436A (en) * | 2019-06-13 | 2019-09-20 | 暨南大学 | Rail deformation detection method and system based on infrared thermal imaging and computer vision |
CN112590868A (en) * | 2020-12-24 | 2021-04-02 | 上海海事大学 | System for detecting abrasion through shooting track by machine vision technology |
CN113554618A (en) * | 2021-07-22 | 2021-10-26 | 上海工程技术大学 | Railway track state monitoring method and device based on infrared image |
CN113705412A (en) * | 2021-08-23 | 2021-11-26 | 中国铁道科学研究院集团有限公司 | Deep learning-based multi-source data fusion track state detection method and device |
-
2022
- 2022-04-20 CN CN202210419324.3A patent/CN114670899A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120137974A (en) * | 2011-06-14 | 2012-12-24 | 한국철도기술연구원 | Detection apparatus and method of train outside fault |
CN106080661A (en) * | 2016-05-27 | 2016-11-09 | 电子科技大学 | Train guide rail profile undulatory wear measuring method |
CN107014294A (en) * | 2017-05-09 | 2017-08-04 | 中国铁道科学研究院 | A kind of contact net geometric parameter detection method and system based on infrared image |
CN108248634A (en) * | 2018-01-24 | 2018-07-06 | 西南交通大学 | Track switch and track full-sized abrasion vision measurer and its measuring method |
CN110261436A (en) * | 2019-06-13 | 2019-09-20 | 暨南大学 | Rail deformation detection method and system based on infrared thermal imaging and computer vision |
CN110254468A (en) * | 2019-06-20 | 2019-09-20 | 吉林大学 | A kind of raceway surface defect intelligent online detection device and detection method |
CN112590868A (en) * | 2020-12-24 | 2021-04-02 | 上海海事大学 | System for detecting abrasion through shooting track by machine vision technology |
CN113554618A (en) * | 2021-07-22 | 2021-10-26 | 上海工程技术大学 | Railway track state monitoring method and device based on infrared image |
CN113705412A (en) * | 2021-08-23 | 2021-11-26 | 中国铁道科学研究院集团有限公司 | Deep learning-based multi-source data fusion track state detection method and device |
Non-Patent Citations (2)
Title |
---|
吴禄慎 等: "基于线阵CCD相机的轨道图像采集***设计", 《铁道标准设计》 * |
程雨 等: "基于FPGA和DSP的高速实时轨道巡检图像采集处理***", 《中国铁道科学》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116320791A (en) * | 2023-03-16 | 2023-06-23 | 北京运达华开科技有限公司 | Image acquisition system and method based on track detection |
CN116320791B (en) * | 2023-03-16 | 2023-10-17 | 北京运达华开科技有限公司 | Image acquisition system and method based on track detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102818538B (en) | Detection system based on modulated glass thread structure laser image | |
CN106226157B (en) | Concrete structure member crevices automatic detection device and method | |
CN100574376C (en) | Camera head, camera system and image capture method | |
KR101111569B1 (en) | Monitering System of Railroad Facilities using Railway Vehicle | |
CN101769877B (en) | Track surface scratch detection system | |
CN109242035B (en) | Vehicle bottom fault detection device and method | |
CN101789177B (en) | Device and method for detecting and tracking vehicles crossing and pressing the yellow line and for capturing vehicle information | |
CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
CN206563560U (en) | A kind of phone housing quality on-line detecting device based on line laser structured light | |
CN112172862A (en) | Multifunctional track detection system | |
KR101280243B1 (en) | Measuring system for height and stagger and wear of catenary using machine vision | |
CN109238756A (en) | Lorry operation troubles motion image detection equipment and detection method | |
CN114670899A (en) | Image acquisition device for track detection system | |
CN108827982B (en) | Straddle type monorail track beam finger-shaped plate defect detection method and system based on deep learning | |
CN116989881A (en) | Contact line vibration measurement system and method based on line laser target identification | |
CN205991785U (en) | A kind of railway tunnel gauge dynamic detection system | |
CN207248769U (en) | A kind of railway rail clip abnormal detector based on monocular vision and laser speckle | |
CN111208146A (en) | Tunnel cable detection system and detection method | |
CN107621229B (en) | Real-time railway track width measurement system and method based on area array black-and-white camera | |
CN207725421U (en) | Vehicle wheel is to dynamic detection system | |
CN100421456C (en) | All-weather two camera shooting laser speed measuring testification apparatus | |
CN207809418U (en) | A kind of Railway wheelset dynamic detection system | |
CN113222907B (en) | Detection robot based on curved rail | |
JP5576050B2 (en) | Linear levitation type high-speed rail guideway travel path inspection device and inspection method | |
RU2268183C1 (en) | Method of noncontact dynamic monitoring of rolling stock wheels parameters |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220628 |