CN111238365B - Subway train distance measurement and positioning method and system based on stereoscopic vision - Google Patents
Subway train distance measurement and positioning method and system based on stereoscopic vision Download PDFInfo
- Publication number
- CN111238365B CN111238365B CN201911308746.8A CN201911308746A CN111238365B CN 111238365 B CN111238365 B CN 111238365B CN 201911308746 A CN201911308746 A CN 201911308746A CN 111238365 B CN111238365 B CN 111238365B
- Authority
- CN
- China
- Prior art keywords
- image
- dimensional code
- train
- subway
- distance
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
-
- 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
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10792—Special measures in relation to the object to be scanned
- G06K7/10801—Multidistance reading
Abstract
The invention relates to a subway train distance measurement and positioning method and system based on stereoscopic vision, which belong to the technical field of positioning and solve the problem of distance measurement and positioning of a subway train; processing the image shot by the binocular camera to determine the position of the two-dimensional code in the image; decoding and ranging the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code; and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code. The invention ensures the accuracy of the output result, greatly reduces the operation time of the system, does not need to deploy trackside equipment, and can greatly reduce the deployment cost and the operation cost.
Description
Technical Field
The invention relates to the technical field of positioning, in particular to a subway train distance measuring and positioning method and system based on stereoscopic vision.
Background
At present, a positioning system of a subway train mainly depends on vehicle-mounted equipment and trackside equipment, and position calibration is carried out in a response mode. The positioning mode which depends on the trackside equipment seriously causes great construction difficulty and complex construction process of the subway train. After the train is delivered for operation, the failure rate is high, the maintenance difficulty is high, and meanwhile, due to the fact that the response principle, the message and the like are different, the interchange of subway trains among different lines in the same city cannot be achieved.
Binocular Stereo bsv (binocular Stereo vision) may be used for target detection and ranging. Usually, a binocular stereo BSV searches for a target position in a global traversal mode, performs target detection based on machine learning, and measures distance information from the target through a stereo matching BM (stereo match).
However, when the current binocular stereo vision BSV is applied to subway train positioning, the following problems still exist:
1. the adopted global traversal method needs to traverse the image and carry out hierarchical screening, the time and space complexity is quite large, the required computing resources are many, and correspondingly, the execution time of the algorithm is long. In addition, in the subway environment, due to the reasons of light rays, shooting positions and the like of images, pixel characteristics and ideal conditions can change, and therefore the accuracy of identification is not high.
2. The recognition accuracy of the adopted machine learning method depends on the number of training data sets and the structure of the network to a great extent, and a huge data set is not easy to collect for a specific application scene. Although the identification accuracy of some networks is high at present, the networks are large in scale and complicated in calculation process, and are not suitable for being applied to equipment with limited calculation resources, such as embedded systems. Therefore, the development cost and the operation process are slow when the scheme is used.
3. The adopted stereo matching algorithm is used for matching the overall situation of the binocular image, time-consuming whole image traversal operation is required, time is consumed, and the requirement on measurement time cannot be met under the condition that the requirement on measurement precision is met.
Disclosure of Invention
In view of the above analysis, the present invention aims to provide a subway train distance measurement and positioning method and system based on stereoscopic vision, which solves the problem of distance measurement and positioning of subway trains.
The purpose of the invention is mainly realized by the following technical scheme:
the invention discloses a subway train distance measurement and positioning method based on stereoscopic vision, which comprises the following steps:
the method comprises the following steps that a binocular camera is installed on a subway train and used for shooting images beside a subway rail, and two-dimensional codes are paved beside the subway rail;
processing the image shot by the binocular camera to determine the position of the two-dimensional code in the image;
decoding and ranging the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code;
and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code.
Furthermore, a plurality of two-dimensional codes are paved on two sides of the subway rail, the paved position coordinates correspond to the ID numbers of the two-dimensional codes one by one, and the patterns of the two-dimensional codes adopt a certain characteristic color;
the binocular camera is installed at the unilateral of train, and the shooting visual angle homoenergetic of two cameras covers the two-dimensional code that sets up in the other, train the place ahead of homonymy rail.
Furthermore, the binocular cameras face the advancing direction of the train, and the connecting line of the two cameras and the vertical plane of the advancing direction of the train form an angle of 30 +/-5 degrees.
Further, the image processing process includes:
preprocessing the image containing the two-dimensional code picture;
intercepting the preprocessed image to obtain an effective range of the image;
carrying out binarization on the intercepted image to obtain a binary image, so that an image area with the same characteristic color is one color value, and other areas are the other color values;
and segmenting and reducing the area of the binary image, searching the area of the two-dimensional code image in the binary image, and determining the position of the two-dimensional code image in the binary image.
Furthermore, the two-dimensional code is laid beside the track and forms a fixed shooting relation with a subway track and a binocular camera on the train, so that the two-dimensional code only appears on one side of a shooting view field when entering an effective shooting range; the effective range of the image is a half image of the side in the shot image.
Further, the binarizing includes:
converting the intercepted image into an HSV map;
according to the characteristic color of the two-dimensional code pattern, carrying out threshold segmentation on the HSV image to obtain a threshold image;
carrying out binarization on the threshold value map; and enabling the threshold image to only have black and white color values, wherein the image area with the same characteristic color is black, and the other areas are white.
Further, the image processing process further comprises performing an opening operation on the binarized image.
Further, the dividing and reducing the area of the binary image adopts a sliding window method, which includes:
1) dividing the binary image by a set window size, initializing a global counter to record iteration times, and setting an initial value to be 0;
2) traversing the segmented image blocks, calculating the area of a black area in each image block, and judging whether the area of the black area of a certain image block is larger than a preset maximum value; if yes, go to 3); if not, entering 4);
3) judging iteration times, if the iteration times are more than 2, indicating that the binary image does not contain a two-dimensional code picture, ending the search of the binary image, otherwise, adding 1 to an iteration counter, increasing the size specification of a window, re-dividing the binary image, and returning to 2);
4) obtaining a block with the largest black area, and judging whether the area ratio of the black area in the block is smaller than a preset minimum value; if the iteration frequency is judged, if the iteration frequency is more than 2, the binary image does not contain the two-dimensional code image, and the search of the binary image is finished; otherwise, the iteration counter is increased by 1, the size of the window is reduced, and the process returns to 2); and if not, stopping adjusting the size of the window, and storing the coordinate of the block with the largest black area as the position of the two-dimensional code picture in the binary image.
Further, the decoding and ranging method includes;
carrying out gray level processing on the preprocessed image to obtain a gray level image;
finding the two-dimensional code in the gray-scale image according to the position of the two-dimensional code in the binary image;
decoding the two-dimensional code in the gray-scale image to obtain the ID number of the two-dimensional code;
and accurately positioning four corner points of the two-dimensional code in the gray-scale image successfully decoded, and obtaining distance information from the binocular camera to the two-dimensional code by using the parallax of the corner points of the two-dimensional code in the binocular image.
The invention also discloses a subway train distance measurement positioning system based on stereoscopic vision, which comprises a two-dimensional code, a binocular camera, an image processing module and a distance measurement positioning module;
the two-dimensional code is laid on two sides of a ground rail, the laid position coordinates correspond to the ID numbers of the two-dimensional code one by one, and the pattern of the two-dimensional code adopts a certain characteristic color;
the binocular camera is installed on a subway train and used for shooting the two-dimensional code paved beside the subway track and acquiring an image containing the two-dimensional code picture;
the image processing module is used for processing the image shot by the binocular camera and determining the position of the two-dimensional code in the image;
the distance measurement positioning module is used for decoding and measuring the distance of the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code; and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code.
The invention has the following beneficial effects:
1. the invention solves the problem that the trackside equipment needs to be deployed in the traditional subway rail train distance measuring system, and can greatly reduce the deployment cost and the operation cost;
2. the binocular vision technology is utilized to carry out rapid detection and distance measurement on the two-dimensional code area arranged beside the track, so that the complicated target detection and three-dimensional matching process is omitted, the operation time of the system is greatly reduced, and the accuracy of the output result is ensured;
3. the embedded board card equipment with slightly poor carrying performance is used for ranging and positioning, the calculation time of each frame of image can still be guaranteed within 75ms, about 13 output results can be given in each second, and the embedded board card equipment has practical application value.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a flowchart of a subway train distance measuring and positioning method in the first embodiment;
fig. 2 is a position relationship diagram of a binocular camera and a two-dimensional code in the first embodiment;
fig. 3 is a flowchart of a method for determining a position of a two-dimensional code in an image according to a first embodiment;
FIG. 4 is a flowchart illustrating a sliding window algorithm according to an embodiment of the present invention;
fig. 5 is a flowchart of a two-dimensional code decoding and ranging method for determining a position in the first embodiment.
Detailed Description
The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and which together with the embodiments of the invention serve to explain the principles of the invention.
The first embodiment,
The embodiment discloses a subway train distance measuring and positioning method based on stereoscopic vision, which comprises the following steps of:
step S1, mounting a binocular camera on the subway train, and shooting images beside the subway rail, wherein two-dimensional codes are laid beside the subway rail;
specifically, a plurality of two-dimensional codes are paved on two sides of a subway rail, the paved position coordinates correspond to the ID numbers of the two-dimensional codes one by one, and the patterns of the two-dimensional codes adopt a certain characteristic color, such as blue.
Specifically, the unilateral at the train is installed to the binocular camera, and the two-dimensional code that sets up beside the homonymy rail, train the place ahead can be covered to the shooting visual angle homoenergetic of its two cameras.
Preferably, in order to enable the better two-dimensional code that covers of shooting visual angle scope, place binocular camera level forward, binocular camera places on the train, apart from about 1.5m of platform. The size of the two-dimensional code mark is fixed, and the size and the width of the two-dimensional code mark are 21cm by adopting A4 paper; the minimum value of the range of the binocular camera is about 1.5 m.
In order to make the two-dimensional code that shoots that binocular camera can be better, can let the whole perpendicular angle setting that becomes 30 degrees angles towards automobile body direction of advance and with direction of advance of binocular camera, make the distance be 12 cm's the left eye and the overlapping portion of right purpose visual angle can cover the two-dimensional code region.
The setting angle and the position relation between the visual angle coverage range of the binocular camera and the two-dimensional code are shown in fig. 2, and the view can be regarded as a top view for placing the binocular camera. According to the visual angle of the binocular camera being 50 degrees, the inclination angle is 30 degrees, and the left visual angle line of the left eye camera forms an angle of 35 degrees with the vertical plane of the advancing direction.
Step S2, processing the image shot by the binocular camera, and determining the position of the two-dimensional code in the image;
as shown in fig. 3, the image processing process includes the following sub-steps:
step S2-1, preprocessing the image;
because the binocular camera can produce tiny displacement in the manufacturing process, the left and right eyes of the binocular camera are not parallel coplane under theoretical analysis, and the shot image can produce tiny distortion and is not beneficial to calculating the distance. Therefore, the image is preprocessed, and stereo correction is carried out according to the distortion parameters, the rotation matrix and the translation matrix of the binocular camera, so that distortion generated by the image is eliminated.
S2-2, intercepting the preprocessed image to obtain an effective range of the image;
in the embodiment, the two-dimensional code is laid beside the track and is fixed with the position relation between the two-dimensional code and the subway track and the position relation between the two-dimensional code and the binocular camera, so that the two-dimensional code only appears on one side of a shooting view field when entering an effective shooting range in the formed shooting relation; only the half image of the side in the shot image needs to be intercepted, and the two-dimensional code image can be used for subsequent processing of the two-dimensional code image, so that the post-processing can reduce half of the operation amount.
For example, the binocular camera is located on the left side of the train, and is used for shooting the two-dimensional code picture beside the same side rail, so that the two-dimensional code picture only appears on the left side of the shot image, the left side of the image is the effective range of the image, and the left side of the image is intercepted.
Step S2-3, converting the intercepted preprocessed image into an HSV (hue, saturation and value) image;
in the HSV color space in computer vision, the identification of an object with a specific color is easier to realize, and therefore, the intercepted effective range is converted into an HSV map.
Step S2-4, performing threshold segmentation on the HSV image to obtain a threshold image;
in the embodiment, the characteristic color adopted by the two-dimensional code pattern is blue; therefore, the original image in the HSV color space is reduced with blue as a characteristic color, and the reduced image is subjected to a threshold segmentation operation to brighten the blue portion and darken the other color portions in the original image. And then, reversing the color to lighten the dark part and darken the bright part.
Therefore, it is considered here that the image is reduced to further concentrate the blue region of the two-dimensional code and further reduce the calculation time.
Step S2-5, binarizing the threshold value map; the threshold value image only has black and white colors.
The region containing the characteristic color is made black, and the other regions are made white.
Preferably, the opening operation is carried out on the binarized image; through the opening operation, the burrs of the bright part and the small bright points in the image are eliminated, and the black area is more concentrated and smooth. It is more favorable for finding the position of the characteristic color.
S2-6, reducing the area of the binary image through a set sliding window to determine the position of the two-dimensional code;
in this embodiment, the area of the binary image is divided and reduced by a sliding window method, and an area most likely to be a two-dimensional code in the binary image is searched and determined.
Specifically, as shown in fig. 4, the method includes:
1) dividing the binary image by a set window size, according to experimental tests, in a range to be tested, enabling the size of the two-dimensional code with the size of A4 paper to be about 24 pixels in the image, using an initial value of 24 pixels for stable identification, and initializing a global counter to record iteration times, wherein the initial value is 0;
2) traversing the segmented image blocks, calculating the area of a black area in each image block, and judging whether the area of the black area of a certain image block is larger than a preset maximum value; if yes, go to 3); if not, entering 4);
3) judging iteration times, if the iteration times are more than 2, indicating that the binary image does not contain a two-dimensional code picture, ending the search of the binary image, otherwise, adding 1 to an iteration counter, increasing the size specification of a window, increasing 2 pixels in length and width, re-dividing the binary image, and returning to 2);
4) obtaining a block with the largest black area, and judging whether the area ratio of the black area in the block is smaller than a preset minimum value; if so, judging the iteration times, if the iteration times are more than 2, indicating that the binary image does not contain the two-dimensional code picture, ending the search of the binary image, otherwise, adding 1 to an iteration counter, reducing the size of a window, reducing the length and the width by 2 pixels respectively, and returning to 2); and if not, stopping adjusting the size of the window, and storing the coordinate containing the block with the largest black area as the position of the two-dimensional code picture in the binary image.
Preferably, the maximum value may be set to 80%; the minimum value may be set to 20%.
S3, decoding and ranging the two-dimensional code with the determined position to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code;
as shown in fig. 5, the following sub-steps are included:
step S3-1, carrying out gray processing on the preprocessed image to obtain a gray image;
s3-2, finding the two-dimensional code in the gray-scale image according to the position of the two-dimensional code determined in the step S2;
s3-3, decoding the two-dimensional code in the gray-scale image to obtain the ID number of the two-dimensional code;
s3-4, accurately positioning four corner points of the two-dimensional code in the successfully decoded image, and obtaining distance information from a binocular camera to the two-dimensional code, namely distance information from a train to the two-dimensional code by using parallax of the corner points of the two-dimensional code in the binocular image;
and step S4, determining the train position coordinate according to the position coordinate corresponding to the two-dimensional code ID number and the distance between the train and the two-dimensional code.
Because the ID number of the two-dimensional code corresponds to the laying position one by one, the position coordinate corresponding to the two-dimensional code can be obtained through the ID number of the two-dimensional code, the distance information from the train to the two-dimensional code is the distance from the train to the position coordinate, and the current position coordinate of the train is determined through a conventional conversion rule.
Compared with the prior art, the subway train distance measurement and positioning method based on stereoscopic vision solves the problem that trackside equipment needs to be deployed in the traditional subway rail train distance measurement system, and can greatly reduce deployment cost and operation cost; the binocular vision technology is utilized to carry out rapid detection and distance measurement on the two-dimensional code area arranged beside the track, so that the complicated target detection and three-dimensional matching process is omitted, the operation time of the system is greatly reduced, and the accuracy of the output result is ensured;
in the test, the embedded board card equipment with slightly poor performance is carried for ranging and positioning, the calculation time of each frame of image can still be guaranteed within 75ms, about 13 output results can be given in each second, and the method has practical application value.
Example II,
The embodiment discloses a subway train distance measuring and positioning system based on stereoscopic vision, which comprises a two-dimensional code, a binocular camera, an image processing module and a distance measuring and positioning module;
the two-dimensional code is laid on two sides of a ground rail, the laid position coordinates correspond to the ID numbers of the two-dimensional code one by one, and the pattern of the two-dimensional code adopts a certain characteristic color;
the binocular camera is installed on a subway train and used for shooting the two-dimensional code paved beside the subway track and acquiring an image containing the two-dimensional code picture;
the image processing module is used for processing the image shot by the binocular camera and determining the position of the two-dimensional code in the image;
the distance measurement positioning module is used for decoding and measuring the distance of the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code; and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code.
Compared with the prior art, the beneficial effects of the subway train distance measurement and positioning system based on stereoscopic vision provided by the embodiment are basically the same as those provided by the first embodiment, and are not repeated herein.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (7)
1. A subway train distance measurement and positioning method based on stereoscopic vision is characterized by comprising the following steps:
the method comprises the following steps that a binocular camera is installed on a subway train and used for shooting images beside a subway rail, and two-dimensional codes are paved beside the subway rail;
processing the image shot by the binocular camera to determine the position of the two-dimensional code in the image;
the image processing process includes:
preprocessing an image containing a two-dimensional code picture;
intercepting the preprocessed image to obtain an effective range of the image;
the two-dimensional code is laid beside the track and forms a fixed shooting relation with the subway track and a binocular camera on the train, so that the two-dimensional code only appears on one side of a shooting view field when entering an effective shooting range; the effective range of the image is a half image of the side in the shot image;
carrying out binarization on the intercepted image to obtain a binary image, so that an image area with the same characteristic color as the two-dimensional code pattern is one color value, and other areas are the other color values;
the area of the binary image is segmented and reduced, the area of the two-dimensional code image in the binary image is searched, and the position of the two-dimensional code image in the binary image is determined;
the area of the binary image is divided and reduced by adopting a sliding window method, which comprises the following steps:
1) dividing the binary image by a set window size, initializing a global counter to record iteration times, and setting an initial value to be 0;
2) traversing the segmented image blocks, calculating the area of a black area in each image block, and judging whether the area of the black area of a certain image block is larger than a preset maximum value; if yes, go to 3); if not, entering 4);
3) judging iteration times, if the iteration times are more than 2, indicating that the binary image does not contain a two-dimensional code picture, ending the search of the binary image, otherwise, adding 1 to an iteration counter, increasing the size specification of a window, re-dividing the binary image, and returning to 2);
4) obtaining a block with the largest black area, and judging whether the area ratio of the black area in the block is smaller than a preset minimum value; if the iteration frequency is judged, if the iteration frequency is more than 2, the binary image does not contain the two-dimensional code image, and the search of the binary image is finished; otherwise, the iteration counter is increased by 1, the size of the window is reduced, and the process returns to 2); if not, stopping adjusting the size of the window, and storing the coordinate of the block with the largest black area as the position of the two-dimensional code picture in the binary image;
decoding and ranging the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code;
and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code.
2. A subway train distance measuring and positioning method as claimed in claim 1, wherein a plurality of said two-dimensional codes are laid on both sides of a subway rail, the position coordinates of the laying are in one-to-one correspondence with ID numbers of said two-dimensional codes, and the patterns of said two-dimensional codes adopt a certain characteristic color;
the binocular camera is installed at the unilateral of train, and the shooting visual angle homoenergetic of two cameras covers the two-dimensional code that sets up in the other, train the place ahead of homonymy rail.
3. A subway train ranging and positioning method as claimed in claim 2, wherein said binocular cameras are directed to the train advancing direction, and the line connecting the two cameras makes an angle of 30 ± 5 degrees with the vertical plane of the train advancing direction.
4. The subway train distance measuring and positioning method as claimed in claim 1, wherein said binarizing comprises:
converting the intercepted image into an HSV map;
according to the characteristic color of the two-dimensional code pattern, carrying out threshold segmentation on the HSV image to obtain a threshold image;
carrying out binarization on the threshold value map; and enabling the threshold image to only have black and white color values, wherein the image area with the same characteristic color is black, and the other areas are white.
5. A subway train distance measuring and positioning method as claimed in claim 4, wherein said image processing process further includes performing opening operation on the binarized image.
6. A subway train ranging and positioning method as claimed in claim 1,
the decoding and ranging method comprises;
carrying out gray level processing on the preprocessed image to obtain a gray level image;
finding the two-dimensional code in the gray-scale image according to the position of the two-dimensional code in the binary image;
decoding the two-dimensional code in the gray-scale image to obtain the ID number of the two-dimensional code;
and accurately positioning four corner points of the two-dimensional code in the gray-scale image successfully decoded, and obtaining distance information from the binocular camera to the two-dimensional code by using the parallax of the corner points of the two-dimensional code in the binocular image.
7. A subway train distance measurement positioning system based on the subway train distance measurement and positioning method of any one of claims 1-6, comprising two-dimensional code, binocular camera, image processing module and distance measurement positioning module;
the two-dimensional code is laid on two sides of a ground rail, the laid position coordinates correspond to the ID numbers of the two-dimensional code one by one, and the pattern of the two-dimensional code adopts a certain characteristic color; in a fixed shooting relation formed by the two-dimensional code pavements, the subway rails and binocular cameras on the trains, the two-dimensional codes only appear on one side of a shooting view field when entering an effective shooting range; the effective range of the image is a half image of the side in the shot image;
the binocular camera is installed on a subway train and used for shooting the two-dimensional code paved beside the subway track and acquiring an image containing the two-dimensional code picture;
the image processing module is used for processing the image shot by the binocular camera and determining the position of the two-dimensional code in the image;
the distance measurement positioning module is used for decoding and measuring the distance of the two-dimensional code with the determined position in the image to obtain the ID number of the two-dimensional code and the distance between the train and the two-dimensional code; and determining the position coordinate of the train according to the position coordinate corresponding to the ID number of the two-dimensional code and the distance between the train and the two-dimensional code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911308746.8A CN111238365B (en) | 2019-12-18 | 2019-12-18 | Subway train distance measurement and positioning method and system based on stereoscopic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911308746.8A CN111238365B (en) | 2019-12-18 | 2019-12-18 | Subway train distance measurement and positioning method and system based on stereoscopic vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111238365A CN111238365A (en) | 2020-06-05 |
| CN111238365B true CN111238365B (en) | 2021-01-15 |
Family
ID=70874133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911308746.8A Active CN111238365B (en) | 2019-12-18 | 2019-12-18 | Subway train distance measurement and positioning method and system based on stereoscopic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111238365B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112622987A (en) * | 2020-12-04 | 2021-04-09 | 中国铁道科学研究院集团有限公司通信信号研究所 | Train autonomous positioning speed measurement and integrity check system and method |
| CN113895481B (en) * | 2021-10-26 | 2024-01-23 | 卡斯柯信号有限公司 | Train positioning and tracking management method, device and medium based on pattern recognition |
| CN115465333B (en) * | 2022-09-01 | 2023-10-31 | 卡斯柯信号有限公司 | Safety coding method for trackside train positioning information |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014104062A1 (en) * | 2012-12-27 | 2014-07-03 | 株式会社オプトエレクトロニクス | Optical information reading apparatus |
| CN106780495A (en) * | 2017-02-15 | 2017-05-31 | 深圳市中科微光医疗器械技术有限公司 | Cardiovascular implantation support automatic detection and appraisal procedure and system based on OCT |
| CN106802144A (en) * | 2016-12-28 | 2017-06-06 | 深圳市美好幸福生活安全系统有限公司 | A kind of vehicle distance measurement method based on monocular vision and car plate |
| CN107563419A (en) * | 2017-08-22 | 2018-01-09 | 交控科技股份有限公司 | The train locating method that images match and Quick Response Code are combined |
| CN110163025A (en) * | 2019-04-29 | 2019-08-23 | 达泊(东莞)智能科技有限公司 | Two dimensional code localization method and device |
| CN110264521A (en) * | 2019-06-21 | 2019-09-20 | 北京邮电大学 | A kind of localization method and system based on binocular camera |
| CN110334692A (en) * | 2019-07-17 | 2019-10-15 | 河南科技大学 | A kind of blind way recognition methods based on image procossing |
-
2019
- 2019-12-18 CN CN201911308746.8A patent/CN111238365B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014104062A1 (en) * | 2012-12-27 | 2014-07-03 | 株式会社オプトエレクトロニクス | Optical information reading apparatus |
| CN106802144A (en) * | 2016-12-28 | 2017-06-06 | 深圳市美好幸福生活安全系统有限公司 | A kind of vehicle distance measurement method based on monocular vision and car plate |
| CN106780495A (en) * | 2017-02-15 | 2017-05-31 | 深圳市中科微光医疗器械技术有限公司 | Cardiovascular implantation support automatic detection and appraisal procedure and system based on OCT |
| CN107563419A (en) * | 2017-08-22 | 2018-01-09 | 交控科技股份有限公司 | The train locating method that images match and Quick Response Code are combined |
| CN110163025A (en) * | 2019-04-29 | 2019-08-23 | 达泊(东莞)智能科技有限公司 | Two dimensional code localization method and device |
| CN110264521A (en) * | 2019-06-21 | 2019-09-20 | 北京邮电大学 | A kind of localization method and system based on binocular camera |
| CN110334692A (en) * | 2019-07-17 | 2019-10-15 | 河南科技大学 | A kind of blind way recognition methods based on image procossing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111238365A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970566B2 (en) | Lane line detection method and apparatus | |
| CN111238365B (en) | Subway train distance measurement and positioning method and system based on stereoscopic vision | |
| CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
| Shin et al. | Vision-based navigation of an unmanned surface vehicle with object detection and tracking abilities | |
| CN107014294B (en) | Contact net geometric parameter detection method and system based on infrared image | |
| CN101853528B (en) | Hand-held three-dimensional surface information extraction method and extractor thereof | |
| JP6904614B2 (en) | Object detection device, prediction model creation device, object detection method and program | |
| CN110569704A (en) | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision | |
| CN103814306A (en) | Depth measurement quality enhancement | |
| CN105809149A (en) | Lane line detection method based on straight lines with maximum length | |
| CN108319920A (en) | A kind of pavement strip detection and calculation method of parameters scanning three-dimensional point cloud based on line | |
| US20080319704A1 (en) | Device and Method for Determining Spatial Co-Ordinates of an Object | |
| CN111899288A (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
| CN112991369B (en) | Method for detecting outline size of running vehicle based on binocular vision | |
| CN111832410B (en) | Forward train detection method based on fusion of vision and laser radar | |
| CN103632376A (en) | Method for suppressing partial occlusion of vehicles by aid of double-level frames | |
| CN110660094A (en) | Subway tunnel mobile scanning point cloud fine division method based on image recognition | |
| Schiopu et al. | Pothole detection and tracking in car video sequence | |
| Zheng et al. | Rail detection based on LSD and the least square curve fitting | |
| Hernández et al. | Lane marking detection using image features and line fitting model | |
| CN108846363A (en) | A kind of subregion vehicle bottom shadow detection method based on divergence expression scanning | |
| CN105096314A (en) | Binary grid template-based method for obtaining structured light dynamic scene depth | |
| CN110516527B (en) | Visual SLAM loop detection improvement method based on instance segmentation | |
| CN116901089A (en) | Multi-angle vision distance robot control method and system | |
| EP4250245A1 (en) | System and method for determining a viewpoint of a traffic camera |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |