CN114662513A - Robust and efficient track visualization routing inspection starting point detection and alignment method - Google Patents
Robust and efficient track visualization routing inspection starting point detection and alignment method Download PDFInfo
- Publication number
- CN114662513A CN114662513A CN202210370454.2A CN202210370454A CN114662513A CN 114662513 A CN114662513 A CN 114662513A CN 202210370454 A CN202210370454 A CN 202210370454A CN 114662513 A CN114662513 A CN 114662513A
- Authority
- CN
- China
- Prior art keywords
- image
- starting point
- detection
- track
- electronic tag
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
- G06K7/10297—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves arrangements for handling protocols designed for non-contact record carriers such as RFIDs NFCs, e.g. ISO/IEC 14443 and 18092
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
- G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
- G06K19/067—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components
- G06K19/07—Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards also with resonating or responding marks without active components with integrated circuit chips
- G06K19/077—Constructional details, e.g. mounting of circuits in the carrier
- G06K19/07749—Constructional details, e.g. mounting of circuits in the carrier the record carrier being capable of non-contact communication, e.g. constructional details of the antenna of a non-contact smart card
- G06K19/07758—Constructional details, e.g. mounting of circuits in the carrier the record carrier being capable of non-contact communication, e.g. constructional details of the antenna of a non-contact smart card arrangements for adhering the record carrier to further objects or living beings, functioning as an identification tag
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Toxicology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a robust and efficient track visualization routing inspection starting point detection and alignment method, which aims to solve the problems of track visualization disease routing inspection starting point detection and background alignment based on data comparison.A detection starting point is selected on a track circuit, an RFID electronic tag and a visual identifier are arranged at the detection starting point, and an RFID reader is additionally arranged in a track visualization routing inspection system and is used for reading an electronic tag ID on the circuit and carrying out coarse positioning according to the electronic tag ID at the detection starting point; and performing visual identification detection in an orbit image acquired by an orbit visualization inspection system according to the coarse positioning result of the electronic tag, and performing pixel-level alignment on visual identifications in a current image and a background image by using an image matching method to realize high-precision background alignment of a detection starting point in the current image and a detection starting point in the background image.
Description
Technical Field
The invention relates to the technical field of visual track inspection, in particular to a robust and efficient method for detecting and aligning a track visual inspection starting point.
Background
The visual imaging technology is widely applied to the technical field of track inspection, the linear array camera and/or the 3D camera are/is installed at the bottom of a track inspection platform, 2D and/or 3D imaging is carried out on the surface of a track, 2D and/or 3D imaging data on the surface of the track are/is acquired, and data can be provided for track disease detection. And after the track visualized data is acquired, processing the acquired data through a pattern recognition technology so as to realize the visualized automatic detection of the track diseases.
According to different purposes, the track can be divided into an urban track (subway), a large iron (ballast low-speed railway) and a high-speed iron (ballastless high-speed railway). These rails have the following characteristics: the railway track with the visible image shooting function is characterized by comprising a large iron, a high iron, long mileage, large turning radius, good line straightness, fewer fastener types in a certain section of line, and simple shot visual image contents on the surface of the track; urban rail (subway), the mileage is short, turning radius is big, and the line state is complicated (construction mark section is many, leads to having multiple fastener, sleeper, railway roadbed type), makes the visual image content in track surface that obtains very complicated, brings huge challenge for the track disease detection method based on pattern recognition, consequently, current track surface visual inspection system towards big iron, high-speed railway development, when using widely in urban rail, because of the complicacy of the circuit condition, lead to track disease detection rate low, the false alarm rate is high.
Aiming at the problem, a simple and effective solution is explored, the method utilizes historical data to compare and judge the change information on the line, and the change information is utilized to detect the track diseases, so that the false alarm rate can be obviously reduced. The specific operation method comprises the following steps: the method comprises the steps of collecting a track reference image in advance as a background image, comparing the currently collected track image with the background image during detection, and finding a track change area, wherein the change area contains a large number of track diseases. The method is tested on 10 subway lines such as Chengdu, Beijing, Chongqing and the like, and the rail disease detection effect is good. In practical application, the problem of image alignment needs to be solved when a historical data comparison method is used for detecting track diseases. Because accurate comparison between the current image and the reference image can be ensured only after the images are aligned, if the images are not aligned, a large number of wrong comparison results are generated. Compared with a data comparison method in the field of video monitoring, the image acquired by the track disease detection system is the image of the whole line, and full-mileage image alignment is difficult to realize. We have solved this problem by cutting the full-range image into small images in units of fasteners or ties, aligning the current image and the background image on the small images in units of fasteners. But, because fasteners, ties have a high similarity, how to align the background image and the current image over the entire range? Is another key problem that we need to solve.
Aiming at the problem, the invention provides a robust and efficient track visualization routing inspection starting point detection and alignment method.
Disclosure of Invention
The invention provides a robust and efficient method for detecting and aligning a starting point of visual inspection of a track, aiming at the problem that a background image is difficult to align with a current image when the visual inspection of the track diseases is carried out by adopting a data comparison method.
The technical scheme of the invention is as follows: selecting a detection starting point on the track line, setting an RFID electronic tag and a visual identifier at the detection starting point, and additionally installing an RFID reader in the track visual inspection system for reading the ID of the electronic tag on the line and carrying out coarse positioning according to the ID of the electronic tag at the detection starting point; and in the track image acquired by the track visualization inspection system, visual identification detection is carried out according to the electronic tag coarse positioning result, and then pixel-level alignment is carried out on the visual identifications in the current image and the background image by using an image matching method, so that the high-precision alignment of the detection starting point in the current image and the detection starting point in the background image is realized.
The track visual inspection system consists of a carrying platform, an imaging module, a data acquisition and processing module, a system control module, an RFID reader, a power supply module, an RFID electronic tag and a visual identifier, wherein the RFID electronic tag and the visual identifier are arranged on a track bed;
the imaging module performs line scanning imaging on the track along the extension direction of the track to acquire a track image;
the track image includes: two-dimensional texture images or three-dimensional depth images or two-dimensional and three-dimensional fusion images;
the data acquisition and processing module is a computing platform, is connected with the imaging module and is used for acquiring and processing imaging data;
the system control module is an embedded computing platform, generates a line scanning imaging control pulse signal and outputs the signal to the imaging module, and is connected with an RFID reader to acquire an RFID electronic tag ID and signal intensity;
the power supply module is a battery pack or an external power supply interface, and is connected with the imaging module, the data acquisition and processing module, the system control module and the RFID reader and supplies power;
the RFID electronic tag has a unique ID, and the communication distance between the electronic tag and the RFID reader is more than 1 m;
the visual identification is a two-dimensional pattern or a three-dimensional shape with unique characteristics, and the specific form is represented by a bar code or a two-dimensional code or characters or numbers or a combination of the characters and the numbers;
the visual marker is mounted proximate to the RFID electronic tag and is located in the field of view of the imaging module.
The RFID reader is arranged on the carrying platform, an antenna of the RFID reader obliquely faces to the front of the carrying platform and forms an angle q with the plane of the track, and the value range of q is 10-60 degrees; the electronic tags and the visual identification are arranged in a collinear manner and are installed as a whole, and the installation positions are located on the connecting lines of the steel rail fastener areas on the left side and the right side.
The specific method for detecting the alignment between the starting point and the background is as follows: acquiring an electronic tag ID and a visual identification image at a detection starting point in advance, and taking the electronic tag ID and the visual identification image as a reference basis for starting point detection; when the track visual inspection system executes an inspection task, the carrying platform starts from the outside of the starting point and drives to the starting point, and after the RFID reader detects an electronic tag signal, whether the current area is the detection starting point or not is judged according to the ID; when the ID number is a detection starting point, performing visual identification detection in the collected image; and after the visual identification is detected, the current acquired image is aligned with the background image acquired in advance in a pixel level by using an image matching method.
Further, the visual identification is a combination of characters and numbers, wherein the characters are used for describing station information, the numbers are used for describing mileage, and hollow-out characters and digital patterns are manufactured in a flat-plate stamping mode; when the visual mark is installed, the visual mark is not less than h mm away from the surface of the track, and the value range of h is 50-100; the minimum width of lines forming the characters and the numbers is not less than w millimeters, and the value range of w is 5-10; and adopting a visual identification detection method based on threshold segmentation: firstly, according to the height prior of the visual identification, carrying out threshold segmentation on a depth image to find a candidate region of a visual identification region; then, training a visual identification classifier, and rejecting a false detection area; secondly, performing threshold segmentation on the visual identification area according to the height prior of the hollow characters and numbers to obtain character and number areas; finally, the OCR method is adopted to identify the characters and the numbers.
Furthermore, besides the additionally arranged visual marks, the RFID electronic tag can be installed nearby the visual marks as a detection starting point by using a safety door and a transponder on a line as the visual marks.
Further, the visual features of the electronic tag are directly used as visual identifiers, and the visual identifiers are not additionally added, so that the pixel level alignment is realized, and the specific method comprises the following steps: and constructing an electronic tag image detector based on pattern recognition, executing electronic tag image detection when the ID number is a detection starting point, and aligning the electronic tag image in the current image with the electronic tag image in the background image in the detected image by an image matching method. This mode can reduce and popularize use cost.
The visual identification or electronic tag image detection method comprises the following steps: image template matching, NCC or shape matching, or target detection; the target detection method comprises SVM + HOG or fasterncn or YOLOV3 or YOLOV5 or YOLOX; the image alignment method comprises image template matching or NCC or shape matching; the OCR methods include classification or CRNN or LSTM based string recognition methods.
The invention has the beneficial effects that:
1) the coarse positioning of the detection starting point is realized through the RFID, the pixel level alignment is realized through the visual identification, the efficiency and the precision are considered, and the method has the characteristics of robustness and high efficiency;
2) the RFID electronic tag with the unique ID is arranged on the line, starting point detection can be realized without depending on any third-party device, and the RFID electronic tag can be applied to scenes such as large railways, high-speed railways, subways and tunnels and has important significance for expanding the visual inspection application field of the track; the RFID is combined with the visual identification, the pixel level background alignment can be realized through the visual identification, and the method has important values for improving the data comparison result precision and reducing the false alarm caused by the image misalignment.
3) The positioning precision of the RFID is only 1m, the starting point detection cannot be accurately realized, and the background alignment is difficult to realize; the visual identification is used for detection and alignment, and the problems that the visual identification is easy to be polluted and the imaging quality is reduced exist; the combined application of RFID and visual identification information is more effective than the simple utilization of RFID or visual identification.
Drawings
None.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the present invention is further described in detail with reference to the following embodiments.
Example 1
The track visual inspection system consists of a carrying platform, an imaging module, a data acquisition and processing module, a system control module, an RFID reader, a power supply module, an RFID electronic tag and a visual identifier, wherein the RFID electronic tag and the visual identifier are arranged on a track bed;
the imaging module performs line scanning imaging on the track along the extension direction of the track to acquire a track image;
the track image includes: two-dimensional texture images or three-dimensional depth images or two-dimensional and three-dimensional fusion images;
the data acquisition and processing module is a computing platform, is connected with the imaging module and is used for acquiring and processing imaging data;
the system control module is an embedded computing platform, generates a line scanning imaging control pulse signal and outputs the signal to the imaging module, and is connected with an RFID reader to acquire an RFID electronic tag ID and signal intensity;
the power supply module is a battery pack or an external power supply interface, and is connected with the imaging module, the data acquisition and processing module, the system control module and the RFID reader and supplies power;
the RFID electronic tag has a unique ID, and the communication distance between the electronic tag and the RFID reader is more than 1 m;
the visual identification is a two-dimensional pattern or a three-dimensional shape with unique characteristics, and the specific form is represented by a bar code or a two-dimensional code or characters or numbers or a combination of the characters and the numbers;
the visual marker is mounted proximate to the RFID electronic tag and is located in the field of view of the imaging module.
The RFID reader is arranged on the carrying platform, an antenna of the RFID reader obliquely faces to the front of the carrying platform and forms an angle q with the plane of the track, and the value range of q is 10-60 degrees; the electronic tags and the visual identification are arranged in a collinear manner and are installed as a whole, and the installation positions are located on the connecting lines of the steel rail fastener areas on the left side and the right side.
The specific method for detecting the alignment between the starting point and the background is as follows: acquiring an electronic tag ID and a visual identification image at a detection starting point in advance, and taking the electronic tag ID and the visual identification image as a reference basis for starting point detection; when the track visual inspection system executes an inspection task, the carrying platform starts from the outside of the starting point and drives to the starting point, and after the RFID reader detects an electronic tag signal, whether the current area is the detection starting point or not is judged according to the ID; when the ID number is a detection starting point, performing visual identification detection in the collected image; and after the visual identification is detected, the current acquired image is aligned with the background image acquired in advance in a pixel level by using an image matching method. The visual identification detection method comprises the following steps: image template matching, NCC or shape matching, or target detection; the target detection method comprises SVM + HOG or fasterncn or YOLOV3 or YOLOV5 or YOLOX; the image alignment method includes image template matching or NCC or shape matching.
Example 2
The difference from the embodiment 1 is that the visual identification is a combination of characters and numbers, wherein the characters are used for describing station information, the numbers are used for describing mileage, and hollowed-out characters and digital patterns are manufactured in a flat-plate stamping mode; when the visual mark is installed, the visual mark is not less than h mm away from the surface of the track, and the value range of h is 50-100; the minimum width of lines forming the characters and the numbers is not less than w millimeters, and the value range of w is 5-10; and adopting a visual identification detection method based on threshold segmentation: firstly, according to the height prior of the visual identification, carrying out threshold segmentation on a depth image to find a candidate region of a visual identification region; then, training a visual identification classifier, and rejecting a false detection area; secondly, performing threshold segmentation on the visual identification area according to the height prior of the hollow characters and numbers to obtain character and number areas; finally, the OCR method is adopted to identify the characters and the numbers. The OCR methods include classification or CRNN or LSTM based string recognition methods.
Example 3
The difference from the embodiments 1 and 2 is that no additional visual mark is provided, the safety door and the transponder on the line are directly used as the visual marks, and the RFID electronic tag is installed nearby the visual marks as the detection starting point.
Example 4
The difference from the embodiments 1, 2 and 3 is that the visual characteristics of the electronic tag itself are directly used as the visual identifier, and the visual identifier is not additionally added, so as to realize the pixel level alignment, and the specific method is as follows: and constructing an electronic tag image detector based on pattern recognition, executing electronic tag image detection when the ID number is a detection starting point, and aligning the electronic tag image in the current image with the electronic tag image in the background image in the detected image by an image matching method. The electronic tag image detection method comprises the following steps: image template matching, NCC or shape matching, or target detection; the target detection method comprises SVM + HOG or fasterncn or YOLOV3 or YOLOV5 or YOLOX. This mode can reduce and popularize use cost.
The invention is not limited to the examples, and any equivalent changes to the technical solution of the invention by a person skilled in the art after reading the description of the invention are covered by the claims of the invention.
Claims (8)
1. A robust and efficient track visualization routing inspection starting point detection and alignment method is characterized in that a detection starting point is selected on a track line, an RFID electronic tag and a visual identification are arranged at the detection starting point, an RFID reader is additionally arranged in a track visualization routing inspection system and used for reading an electronic tag ID on the line, and rough positioning is carried out according to the electronic tag ID at the detection starting point; and in the track image acquired by the track visualization inspection system, visual identification detection is carried out according to the electronic tag coarse positioning result, and then pixel-level alignment is carried out on the visual identifications in the current image and the background image by using an image matching method, so that the alignment of the detection starting point in the current image and the high-precision background of the detection starting point in the background image is realized.
2. The robust and efficient track visualization inspection starting point detection and alignment method according to claim 1, wherein the track visualization inspection system is composed of a carrying platform, an imaging module, a data acquisition and processing module, a system control module, an RFID reader, a power supply module, and RFID electronic tags and visual marks arranged on a track bed;
the imaging module performs line scanning imaging on the track along the extension direction of the track to acquire a track image;
the track image includes: two-dimensional texture images or three-dimensional depth images or two-dimensional and three-dimensional fusion images;
the data acquisition and processing module is a computing platform, is connected with the imaging module and is used for acquiring and processing imaging data;
the system control module is an embedded computing platform, generates a line scanning imaging control pulse signal and outputs the signal to the imaging module, and is connected with an RFID reader to acquire an RFID electronic tag ID and signal intensity;
the power supply module is a battery pack or an external power supply interface, and is connected with the imaging module, the data acquisition and processing module, the system control module and the RFID reader and supplies power;
the RFID electronic tag has a unique ID, and the communication distance between the electronic tag and the RFID reader is more than 1 m;
the visual identification is a two-dimensional pattern or a three-dimensional shape with unique characteristics, and the specific form is represented by a bar code or a two-dimensional code or characters or numbers or a combination of the characters and the numbers;
the visual marker is mounted proximate to the RFID electronic tag and is located in the field of view of the imaging module.
3. The robust and efficient track visualization inspection starting point detecting and aligning method according to claim 1 or 2, characterized in that the RFID reader is mounted on the carrying platform, an antenna of the RFID reader is obliquely oriented to the front of the carrying platform and forms an angle q with a track plane, and the value range of q is 10-60 degrees; the electronic tags and the visual identification are arranged in a collinear manner and are installed as a whole, and the installation positions are located on the connecting lines of the steel rail fastener areas on the left side and the right side.
4. The robust and efficient track visualization inspection starting point detection and alignment method according to any one of claims 1 to 3, wherein the specific method for aligning the starting point detection with the background is as follows: acquiring an electronic tag ID and a visual identification image at a detection starting point in advance, and taking the electronic tag ID and the visual identification image as a reference basis for starting point detection; when the track visual inspection system executes an inspection task, the carrying platform starts from the outside of the starting point and drives to the starting point, and after the RFID reader detects an electronic tag signal, whether the current area is the detection starting point or not is judged according to the ID; when the ID number is a detection starting point, performing visual identification detection in the collected image; and after the visual identification is detected, the current acquired image is aligned with the background image acquired in advance in a pixel level by using an image matching method.
5. The robust and efficient track visualization inspection starting point detection and alignment method according to any one of claims 1 to 4, wherein the visual identification is a combination of letters and numbers, wherein the letters are used for describing site information, the numbers are used for describing mileage, and hollowed letter and number patterns are manufactured in a flat plate stamping manner; when the visual mark is installed, the visual mark is not less than h mm away from the surface of the track, and the value range of h is 50-100; the minimum width of lines forming the characters and the numbers is not less than w millimeters, and the value range of w is 5-10; and adopting a visual identification detection method based on threshold segmentation: firstly, according to the high prior of the visual identification, carrying out threshold segmentation on a depth image to find a candidate region of a visual identification region; then, training a visual identification classifier, and rejecting a false detection area; secondly, performing threshold segmentation on the visual identification area according to the height prior of the hollow characters and numbers to obtain character and number areas; finally, the OCR method is adopted to recognize the characters and the numbers.
6. The robust and efficient track visualization inspection starting point detecting and aligning method according to any one of claims 1 to 5, characterized in that besides the additionally arranged visual markers, a security gate and a transponder on a line can be used as the visual markers, and an RFID electronic tag is installed nearby the visual markers as a detection starting point.
7. The robust and efficient track visualization inspection starting point detection and alignment method according to any one of claims 1 to 5, wherein the visual features of the electronic tag are directly used as visual identifiers, and no additional visual identifiers are added, so as to realize pixel level alignment, and the specific method is as follows: and constructing an electronic tag image detector based on pattern recognition, executing electronic tag image detection when the ID number is a detection starting point, and aligning the electronic tag image in the current image with the electronic tag image in the background image in the detected image by an image matching method.
8. The robust and efficient rail visualization inspection tour start point detection and alignment method according to any one of claims 1 to 7, wherein the visual identification or electronic tag image detection method comprises: image template matching, NCC or shape matching, or target detection; the target detection method comprises SVM + HOG or fasterncn or YOLOV3 or YOLOV5 or YOLOX; the image alignment method comprises image template matching or NCC or shape matching; the OCR methods include classification or CRNN or LSTM based string recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210370454.2A CN114662513A (en) | 2022-04-09 | 2022-04-09 | Robust and efficient track visualization routing inspection starting point detection and alignment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210370454.2A CN114662513A (en) | 2022-04-09 | 2022-04-09 | Robust and efficient track visualization routing inspection starting point detection and alignment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114662513A true CN114662513A (en) | 2022-06-24 |
Family
ID=82034512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210370454.2A Pending CN114662513A (en) | 2022-04-09 | 2022-04-09 | Robust and efficient track visualization routing inspection starting point detection and alignment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114662513A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314921A (en) * | 2023-11-30 | 2023-12-29 | 山东道万电气有限公司 | RFID-based starting point detection and treatment method for track inspection equipment |
-
2022
- 2022-04-09 CN CN202210370454.2A patent/CN114662513A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314921A (en) * | 2023-11-30 | 2023-12-29 | 山东道万电气有限公司 | RFID-based starting point detection and treatment method for track inspection equipment |
| CN117314921B (en) * | 2023-11-30 | 2024-02-09 | 山东道万电气有限公司 | RFID-based starting point detection and treatment method for track inspection equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563419B (en) | Train positioning method combining image matching and two-dimensional code | |
| CN103324913B (en) | A kind of pedestrian event detection method of Shape-based interpolation characteristic sum trajectory analysis | |
| CN105550654B (en) | Bullet train image capturing system, real-time license number detection system and method | |
| CN102915433B (en) | Character combination-based license plate positioning and identifying method | |
| CN102508246B (en) | Method for detecting and tracking obstacles in front of vehicle | |
| CN109658397A (en) | A kind of rail polling method and system | |
| KR101339354B1 (en) | System for detecting position of the railway vehicle using images and the method of the same | |
| CN104616009A (en) | Character cutting and recognizing method | |
| CN105243381B (en) | Failure automatic identification detection system and method based on 3D information | |
| CN114581437A (en) | Visual inspection system for visual track guided by visual identification | |
| CN103824037B (en) | Vehicle anti-tracking alarm device | |
| CN102880863B (en) | Method for positioning license number and face of driver on basis of deformable part model | |
| CN106448189A (en) | Multilane speed measuring and block port triggering method and device based on microwaves | |
| CN105160884A (en) | Vehicle identification method and device fusing video monitoring and RFID | |
| CN103863357A (en) | Rail transit contact track measuring device and measuring method | |
| CN107437044A (en) | A kind of mine movable target following and localization method | |
| CN109242035A (en) | Vehicle bottom fault detection means and method | |
| CN114662513A (en) | Robust and efficient track visualization routing inspection starting point detection and alignment method | |
| CN112631307A (en) | Multi-sensor auxiliary positioning module and method for rail-mounted inspection robot | |
| CN103632376A (en) | Method for suppressing partial occlusion of vehicles by aid of double-level frames | |
| CN102706883B (en) | System and method for recognizing holes in paved waterproof board of tunnel | |
| CN111717244A (en) | Train automatic driving sensing method and system | |
| CN113256723B (en) | Automatic detection method for pantograph lifting time and pantograph head displacement curve | |
| Stein et al. | Model-based rail detection in mobile laser scanning data | |
| CN109977853A (en) | A kind of mine group overall view monitoring method based on more identifiers |
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 |