CN115457088A - Method and system for fixing axle of train - Google Patents
Method and system for fixing axle of train Download PDFInfo
- Publication number
- CN115457088A CN115457088A CN202211346910.6A CN202211346910A CN115457088A CN 115457088 A CN115457088 A CN 115457088A CN 202211346910 A CN202211346910 A CN 202211346910A CN 115457088 A CN115457088 A CN 115457088A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- offset
- point cloud
- train
- cloud image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 64
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 abstract description 7
- 230000006872 improvement Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 230000036544 posture Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of train maintenance, and particularly relates to a method and a system for fixing a shaft of a train, wherein the method comprises the following steps: determining a train stopping range, and stopping a target axle of the train, which needs to be fixed, into the stopping range; shooting a 2D plane image and a 3D point cloud image I at the bottom of the train from an initial position I by using a shooting device according to a set shooting mode; defining a registration area by using the 2D plane image; registering the 3D point cloud image in the registration area with a standard template; calculating a starting position II by using the offset matrix; comparing the 3D point cloud image II with a standard template; the position of the target axle is calculated from the known positions of the axles in the standard templates and the offset matrix. The invention is not influenced by trench environment, new and old axles and other parts, so that the precision of the fixed axle is improved, and the precision of the positioning of the vehicle body is improved; the system overhead is small, the scanning time is short, and the axis fixing efficiency is high.
Description
Technical Field
The invention belongs to the technical field of train maintenance, and particularly relates to a method and a system for automatically fixing a shaft during train maintenance.
Background
In the automatic maintenance operation flow of the train in the parking garage, because the stop position of the train is not always at the same position but within a parking range, the positioning of the train directly influences whether the maintenance flow can smoothly run and the maintenance precision.
Because the train stopping position is not fixed, and the distance between the carriages is allowed to be changed elastically, the train position and the specific position of each carriage are mainly positioned in a mode of determining the axle position in the automatic train maintenance operation process. The existing point laser axle fixing method mainly utilizes the change of laser distance, and can detect the axle when vertical point laser and side point laser simultaneously detect the change of a similar axle (theoretically, a semicircular curve) and a wheel (appearing in the distance measuring range of the side point laser), the arrangement speed of the mode is high, but the method is easily influenced by a trench environment, new and old axles (the reflectivity of the new axle can seriously influence the effect of the laser) and other parts at the bottom of the car, particularly cables at the bottom of the car and other parts (such as an ATC antenna) which are coplanar with the wheel.
Disclosure of Invention
In view of this, the present invention provides a method and a system for train axle fixing, which are used to determine a stop position of a train and an accurate position of each carriage in an automatic train detection process through efficient and accurate axle fixing, so as to optimize the train detection process and improve the detection accuracy.
In order to solve the technical problems, the technical scheme of the invention is to adopt a train dead axle method, which comprises the following steps:
s1, determining a train parking range, and parking a target axle needing to be fixed into the parking range;
s2, shooting a 2D plane image and a 3D point cloud image I at the bottom of the train from the initial position I by using a shooting device according to a set shooting mode;
s3, defining a registration area by using the 2D plane image;
s4, registering the 3D point cloud image in the registration area with a standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template;
s5, calculating an initial position II by using the offset matrix, moving the shooting device to the initial position II, and shooting the 3D point cloud image II at the bottom of the train again according to a set shooting mode;
s6, comparing the 3D point cloud image II with a standard template, and if the two images are overlapped, determining that the offset matrix is accurate;
and S7, calculating the position of the target axle according to the known positions of the axles in the standard template and the offset matrix.
As an improvement, the shooting device comprises an AGV, and a mechanical arm is mounted on the AGV; and a camera is fixed at the tail end of the mechanical arm.
As a further improvement, an environment map in a train parking range is constructed before shooting, a shooting route and a parking point are planned, and the posture of the mechanical arm during shooting is determined through teaching.
As another further improvement, the method for calculating the starting position II by using the offset matrix is as follows:
s51, acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
s52, transferring the offset from the template coordinate system to the world coordinate system;
and S53, subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system.
As an improvement, the method for transferring the offset from the template coordinate system to the world coordinate system is as follows:
transferring the offset from the coordinate system of the standard template to the coordinate system of the tail end of the mechanical arm;
transferring the offset from the terminal coordinate system of the mechanical arm to the base coordinate system of the mechanical arm;
the offset is transferred from the robot base coordinate system to the world coordinate system.
As an improvement, the coordinate system of the standard template is a camera coordinate system at a first shooting point when the standard template is shot, and the standard template is formed by splicing point clouds shot at all shooting points by a camera to the coordinate system;
the coordinate system where the 3D point cloud image I is located is a camera coordinate system at a first shooting point when the 3D point cloud image I is shot, and the 3D point cloud image I is formed by splicing point clouds shot at all shooting points by a camera to the coordinate system.
As an improvement, the method of calculating the position of the target axle includes:
s71, acquiring the offset between the 3D point cloud image in the registration area and the standard template through the offset matrix;
s72, transferring the offset from the template coordinate system to the world coordinate system;
and S73, adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
The invention also provides a train dead axle system, comprising:
the image acquisition unit is used for shooting a 2D plane image and a 3D point cloud image I of the bottom of the train from the starting position I according to a set shooting mode and shooting a 3D point cloud image II of the bottom of the train from the starting position II according to a set shooting mode;
a registration region delineating unit for delineating a registration region using the 2D planar image;
the offset matrix acquisition unit is used for registering the 3D point cloud image in the registration area with the standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template;
a starting position II obtaining unit for calculating a starting position II by using the offset matrix;
the comparison unit is used for comparing the 3D point cloud image II with the standard template;
and the axle position calculating unit is used for calculating the position of the target axle through the known positions of the axles in the standard templates and the offset matrix.
As an improvement, the start position II acquisition unit includes:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system.
As an improvement, the axle position calculation unit includes:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
The invention has the advantages that:
1. the device is not influenced by a trench environment, old and new axles and other parts at the bottom of the vehicle, particularly a vehicle bottom cable and other parts (such as an ATC antenna) which are coplanar with wheels, so that the precision of the fixed axle is improved, and the precision of the positioning of the vehicle body is improved;
2. the system overhead is small, the scanning time is short, the axis fixing efficiency is high, and the efficiency of the whole detection process is improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a schematic diagram of the structure of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments in order to make those skilled in the art better understand the technical solutions of the present invention.
As shown in fig. 1, the present invention provides a method for fixing a train axle, which specifically comprises the following steps:
s1, determining a train parking range, and parking a target axle of the train, which needs to be fixed, into the parking range.
The function of determining the train stopping range is to ensure that only the target axle appears in the lens when the image of the train bottom is shot by the shooting device. In this embodiment, the range is 1 meter to 1.5 meters along the length of the rail.
And S2, shooting a 2D plane image and a 3D point cloud image I at the bottom of the train from the initial position I by utilizing a shooting device according to a set shooting mode.
In the present invention, the photographing device includes an AGV (Automated Guided Vehicle), and the AVG refers to a transport Vehicle equipped with an electromagnetic or optical automatic navigation device, which can travel along a predetermined navigation path, and has safety protection and various transfer functions. The industrial application does not need a driver's truck, and a rechargeable battery is used as a power source of the truck. Generally, the traveling path and behavior can be controlled by a computer, or the traveling path is set up by using an electromagnetic path (electromagnetic path-following system), the electromagnetic path is adhered to the floor, and the unmanned transport vehicle moves and operates according to the information brought by the electromagnetic path.
The AGV is provided with a mechanical arm, for example, a six-shaft mechanical arm, and the activity is large.
The tail end of the mechanical arm is fixed with a camera, and the camera can shoot 2D and 3D images.
Before shooting, an environment map in a train stopping range is constructed, a shooting route and a parking point are planned, and the posture of the mechanical arm during shooting is determined through teaching. The shooting route, the parking point and the shooting gesture of the mechanical arm are fixed, so that a set shooting mode is formed. The starting position I is the starting position of the AGV, and the starting position I is fixed.
Before the axis is fixed, the construction of a standard template is carried out. And similarly, starting the AGV from the initial position I, running according to a planned shooting route and a parking point, and then shooting and acquiring by the mechanical arm according to the taught posture. When the standard template is photographed, the position of the axle in the world coordinate system is known. The coordinate system of the standard template is a camera coordinate system at a first shooting point when the standard template is shot, and the standard template is formed by splicing point clouds shot at all shooting points by a camera to the coordinate system; the method of splicing is to convert point clouds obtained from other shooting points into a camera coordinate system of the first shooting point through a conversion matrix.
The first shooting in the shaft fixing process needs to shoot a 2D image and a 3D point cloud image of the bottom of the train. The 3D point cloud image is formed by splicing point clouds shot by a plurality of shooting positions. The coordinate system where the 3D point cloud image I is located is a camera coordinate system at the first shooting point when the 3D point cloud image I is shot, and the point cloud images shot by all the shooting points at the time of shooting are all spliced to the coordinate system to form a complete 3D point cloud image I. The splicing method is similar to the standard template, and is not described in detail here.
And S3, defining a registration area by using the 2D plane image.
In fact, the position of the axle can also be calculated by directly registering the 3D point cloud image I with the standard template, but because the 3D point cloud image I has more point clouds and the registration cost is huge, in the invention, a registration area is firstly defined by the 2D plane image, so that areas with more obvious characteristics can be selected for registration, and thus, redundant point clouds are removed and the system cost is reduced.
In some embodiments, the 2D image of the shooting area can be deeply learned, the area with many and obvious features and ensured to be near the axle can be found, and then the 3D point cloud of the area can be used for registration. Of course, the registration region may also be manually selected.
S4, registering the 3D point cloud image in the registration area with a standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template.
The parking point when the axis is fixed cannot be completely coincident with the parking point when the standard template is constructed, so that the 3D point cloud image I cannot be completely coincident with the standard template. The so-called offset matrix is actually a conversion matrix from the coordinate system of the 3D point cloud image I to the coordinate system of the standard template. Since the error of two stops can only be generally forward or backward along the rail, the offset matrix also has generally only a translation relationship and no roll-over relationship. The calculation of the shift matrix is a conventional technique in the field of 3D point cloud, and is not described in detail in the present invention.
S5, calculating an initial position II by using the offset matrix, moving the shooting device to the initial position II, and shooting the 3D point cloud image II at the bottom of the train again according to a set shooting mode, wherein the method specifically comprises the following steps:
s51, acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix; since the offset matrix contains the relative pose between the two coordinate systems, the offset between the 3D point cloud image I and the standard template is actually already well defined.
S52, transferring the offset from the template coordinate system to the world coordinate system; since the route of the AGV, including the start position, is in the world coordinate system, the offset needs to be transferred to the world coordinate system. And the transformation from the template coordinate system to the world coordinate system can be realized through a plurality of coordinate systems in the middle.
Firstly, transferring the offset from a coordinate system where a standard template is located to a coordinate system at the tail end of the mechanical arm; the coordinate system of the standard template is actually the camera coordinate system at the first shooting point when shooting the standard template. Transferring the coordinate system of the standard template to the coordinate system at the tail end of the mechanical arm through a conversion matrixTo realize the purpose of the method, the device is provided with a plurality of sensors,it is a fixed homogeneous transformation matrix that can be obtained by calibration.
Then, transferring the offset from the terminal coordinate system of the mechanical arm to a base coordinate system of the mechanical arm; transferring the coordinate system of the tail end of the mechanical arm to the coordinate system of the base of the mechanical arm through a conversion matrixTo realize the purpose of the method, the device is provided with a plurality of sensors,the pose of the tail end of the mechanical arm can be directly calculated.
And finally, transferring the offset from the mechanical arm base coordinate system to a world coordinate system. Transferring from the mechanical arm base coordinate system to the world coordinate system through a transformation matrixTo realize the purpose of the method, the device is provided with a plurality of sensors,may be obtained by calibration.
The whole process can be represented by formula
Is carried out, whereinIs the offset of the world coordinate system,the offset of the standard template in the coordinate system.
And S53, subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system. In short, if the amount of shift is positive, the shift is in a negative direction, and if the amount of shift is negative, the shift is in a positive direction, and the purpose is to cancel the shift.
And the AVG starts to shoot again from the initial position II, and the shooting mode is unchanged, namely the shooting postures of the relative route, the parking point and the mechanical arm are unchanged, so that a 3D point cloud image II is obtained.
And S6, comparing the 3D point cloud image II with the standard template, and if the two images are overlapped, determining that the offset matrix is accurate. Similarly, the point cloud in the 3D point cloud image II is transferred to the coordinate system of the standard template, and if the point cloud and the point cloud coincide, the offset matrix is accurate. If the overlapping can not be carried out, the steps S2 to S6 need to be carried out again until the overlapping is carried out.
S7, calculating the position of the target axle through the position of the axle in the known standard template and the offset matrix, and specifically comprising the following steps:
s71, acquiring the offset between the 3D point cloud image in the registration area and the standard template through the offset matrix;
s72, transferring the offset from the template coordinate system to the world coordinate system;
and S73, adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
In fact, steps S71 and S72 are already completed in step S5, and can be used directly after confirming the accuracy of the offset matrix through the verification in step S6. The position of the axle in the world coordinate system in the standard template is known, and the position coordinate of the target axle in the world coordinate system can be obtained by adding the offset to the position.
By circulating the steps, each axle of the train can be fixed, so that the stopping position of the train and the accurate position of each carriage can be determined.
As shown in fig. 2, the present invention further provides a train dead axle system, including:
the image acquisition unit is used for shooting a 2D plane image and a 3D point cloud image I of the bottom of the train from the starting position I according to a set shooting mode and shooting a 3D point cloud image II of the bottom of the train from the starting position II according to a set shooting mode;
a registration region delineating unit for delineating a registration region using the 2D planar image;
the offset matrix acquisition unit is used for registering the 3D point cloud image in the registration area with the standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template;
a starting position II obtaining unit for calculating a starting position II by using the offset matrix;
the comparison unit is used for comparing the 3D point cloud image II with the standard template;
and the axle position calculating unit is used for calculating the position of the target axle through the known positions of the axles in the standard templates and the offset matrix.
The start position II acquisition unit includes:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system.
The axle position calculation unit includes:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and these modifications and adaptations should be considered within the scope of the invention.
Claims (10)
1. A method for fixing a shaft of a train is characterized by comprising the following steps:
s1, determining a train parking range, and parking a target axle needing to be fixed into the parking range;
s2, shooting a 2D plane image and a 3D point cloud image I at the bottom of the train from the initial position I by utilizing a shooting device according to a set shooting mode;
s3, defining a registration area by using the 2D plane image;
s4, registering the 3D point cloud image in the registration area with a standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template;
s5, calculating an initial position II by using the offset matrix, moving the shooting device to the initial position II, and shooting the 3D point cloud image II at the bottom of the train again according to a set shooting mode;
s6, comparing the 3D point cloud image II with a standard template, and if the two images are overlapped, determining that the offset matrix is accurate;
and S7, calculating the position of the target axle according to the known positions of the axles in the standard template and the offset matrix.
2. The method for fixing the axle of the train as claimed in claim 1, wherein: the shooting device comprises an AGV, and a mechanical arm is mounted on the AGV; and a camera is fixed at the tail end of the mechanical arm.
3. The train axle fixing method according to claim 2, characterized in that: before shooting, an environment map in a train parking range is constructed, a shooting route and a parking point are planned, and the posture of the mechanical arm during shooting is determined through teaching.
4. The method for fixing the axle of the train as claimed in claim 2, wherein the method for calculating the starting position II by using the offset matrix comprises:
s51, acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
s52, transferring the offset from the template coordinate system to the world coordinate system;
and S53, subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system.
5. The method of claim 4, wherein the method of transferring the offset from the template coordinate system to the world coordinate system comprises:
transferring the offset from the coordinate system of the standard template to the coordinate system of the tail end of the mechanical arm;
transferring the offset from the terminal coordinate system of the mechanical arm to a base coordinate system of the mechanical arm;
the offset is transferred from the robot base coordinate system to the world coordinate system.
6. The train axle fixing method according to claim 2, characterized in that:
the coordinate system of the standard template is a camera coordinate system at a first shooting point when the standard template is shot, and the standard template is formed by splicing point clouds shot at all shooting points by a camera to the coordinate system;
the coordinate system of the 3D point cloud image I is a camera coordinate system at a first shooting point when the 3D point cloud image I is shot, and the 3D point cloud image I is formed by splicing point clouds shot at all shooting points by a camera to the coordinate system.
7. The train axle fixing method according to claim 2, wherein the method of calculating the position of the target axle comprises:
s71, acquiring the offset between the 3D point cloud image in the registration area and the standard template through the offset matrix;
s72, transferring the offset from the template coordinate system to the world coordinate system;
and S73, adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
8. A train dead axle system, comprising:
the image acquisition unit is used for shooting a 2D plane image and a 3D point cloud image I of the bottom of the train from the starting position I according to a set shooting mode and shooting a 3D point cloud image II of the bottom of the train from the starting position II according to a set shooting mode;
a registration region delineating unit for delineating a registration region using the 2D planar image;
the offset matrix acquisition unit is used for registering the 3D point cloud image in the registration area with the standard template to obtain an offset matrix between the 3D point cloud image in the registration area and the standard template; the offset matrix is a conversion matrix from a coordinate system of the 3D point cloud image I to a coordinate system of the standard template;
a starting position II obtaining unit for calculating a starting position II by using the offset matrix;
the comparison unit is used for comparing the 3D point cloud image II with the standard template;
and the axle position calculating unit is used for calculating the position of the target axle through the known positions of the axles in the standard templates and the offset matrix.
9. The train dead axle system according to claim 8, wherein said starting position II obtaining unit comprises:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for subtracting the offset from the coordinate of the starting position I in the world coordinate system to obtain the coordinate of the starting position II in the world coordinate system.
10. A train axle-fixing system as claimed in claim 8, wherein said axle position calculating unit comprises:
the offset acquisition unit is used for acquiring the offset between the 3D point cloud image in the registration area and the standard template through an offset matrix;
the offset transfer unit is used for transferring the offset from the template coordinate system to the world coordinate system;
and the calculating unit is used for adding the offset to the position coordinates of the axle in the standard template in the world coordinate system to obtain the position coordinates of the target axle in the world coordinate system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211346910.6A CN115457088B (en) | 2022-10-31 | 2022-10-31 | Method and system for fixing axle of train |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211346910.6A CN115457088B (en) | 2022-10-31 | 2022-10-31 | Method and system for fixing axle of train |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115457088A true CN115457088A (en) | 2022-12-09 |
CN115457088B CN115457088B (en) | 2023-03-24 |
Family
ID=84310658
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211346910.6A Active CN115457088B (en) | 2022-10-31 | 2022-10-31 | Method and system for fixing axle of train |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115457088B (en) |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070195285A1 (en) * | 2006-02-15 | 2007-08-23 | Mersive Technologies, Llc | Hybrid system for multi-projector geometry calibration |
US20130249901A1 (en) * | 2012-03-22 | 2013-09-26 | Christopher Richard Sweet | Systems and methods for geometrically mapping two-dimensional images to three-dimensional surfaces |
CN105426922A (en) * | 2015-12-08 | 2016-03-23 | 同方威视技术股份有限公司 | Train type recognition method and system as well as safety inspection method and system |
US20160187130A1 (en) * | 2014-12-19 | 2016-06-30 | Leica Geosystems Ag | Method for determining a position and orientation offset of a geodetic surveying device and such a surveying device |
CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
CN109816703A (en) * | 2017-11-21 | 2019-05-28 | 西安交通大学 | A kind of point cloud registration method based on camera calibration and ICP algorithm |
CN110986820A (en) * | 2019-12-16 | 2020-04-10 | 武汉汉宁轨道交通技术有限公司 | Track intrusion detection method and device and electronic equipment |
CN111080603A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Method for detecting breakage fault of shaft end bolt of railway wagon |
CN112198526A (en) * | 2020-09-30 | 2021-01-08 | 上海炬佑智能科技有限公司 | Reference plane adjustment and obstacle detection method, depth camera and navigation equipment |
CN112589791A (en) * | 2019-11-05 | 2021-04-02 | 牧今科技 | Robotic system with wall-based packaging mechanism and method of operation thereof |
CN112949478A (en) * | 2021-03-01 | 2021-06-11 | 浙江国自机器人技术股份有限公司 | Target detection method based on holder camera |
US20210195840A1 (en) * | 2019-12-31 | 2021-07-01 | Purdue Research Foundation | Vehicle automated unloading |
US20210271854A1 (en) * | 2020-02-25 | 2021-09-02 | Raytheon Company | Point cloud registration with error propagation |
CN113706621A (en) * | 2021-10-29 | 2021-11-26 | 上海景吾智能科技有限公司 | Mark point positioning and posture obtaining method and system based on marked image |
CN113902810A (en) * | 2021-09-16 | 2022-01-07 | 南京工业大学 | Robot gear chamfering processing method based on parallel binocular stereo vision |
CN114119757A (en) * | 2021-12-17 | 2022-03-01 | 腾讯科技(深圳)有限公司 | Image processing method, apparatus, device, medium, and computer program product |
CN114299104A (en) * | 2021-12-23 | 2022-04-08 | 中铭谷智能机器人(广东)有限公司 | Automobile spraying track generation method based on multiple 3D (three-dimensional) vision |
CN114627166A (en) * | 2022-02-17 | 2022-06-14 | 国网江西省电力有限公司超高压分公司 | Robot holder servo control method based on point cloud registration ICP algorithm |
CN114862964A (en) * | 2022-04-27 | 2022-08-05 | 武汉智行者科技有限公司 | Automatic calibration method for sensor, electronic device and storage medium |
CN115239776A (en) * | 2022-07-14 | 2022-10-25 | 阿波罗智能技术(北京)有限公司 | Point cloud registration method, device, equipment and medium |
-
2022
- 2022-10-31 CN CN202211346910.6A patent/CN115457088B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070195285A1 (en) * | 2006-02-15 | 2007-08-23 | Mersive Technologies, Llc | Hybrid system for multi-projector geometry calibration |
US20130249901A1 (en) * | 2012-03-22 | 2013-09-26 | Christopher Richard Sweet | Systems and methods for geometrically mapping two-dimensional images to three-dimensional surfaces |
US20160187130A1 (en) * | 2014-12-19 | 2016-06-30 | Leica Geosystems Ag | Method for determining a position and orientation offset of a geodetic surveying device and such a surveying device |
CN105426922A (en) * | 2015-12-08 | 2016-03-23 | 同方威视技术股份有限公司 | Train type recognition method and system as well as safety inspection method and system |
CN109816703A (en) * | 2017-11-21 | 2019-05-28 | 西安交通大学 | A kind of point cloud registration method based on camera calibration and ICP algorithm |
CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
CN112589791A (en) * | 2019-11-05 | 2021-04-02 | 牧今科技 | Robotic system with wall-based packaging mechanism and method of operation thereof |
CN111080603A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Method for detecting breakage fault of shaft end bolt of railway wagon |
CN110986820A (en) * | 2019-12-16 | 2020-04-10 | 武汉汉宁轨道交通技术有限公司 | Track intrusion detection method and device and electronic equipment |
US20210195840A1 (en) * | 2019-12-31 | 2021-07-01 | Purdue Research Foundation | Vehicle automated unloading |
US20210271854A1 (en) * | 2020-02-25 | 2021-09-02 | Raytheon Company | Point cloud registration with error propagation |
CN112198526A (en) * | 2020-09-30 | 2021-01-08 | 上海炬佑智能科技有限公司 | Reference plane adjustment and obstacle detection method, depth camera and navigation equipment |
CN112949478A (en) * | 2021-03-01 | 2021-06-11 | 浙江国自机器人技术股份有限公司 | Target detection method based on holder camera |
CN113902810A (en) * | 2021-09-16 | 2022-01-07 | 南京工业大学 | Robot gear chamfering processing method based on parallel binocular stereo vision |
CN113706621A (en) * | 2021-10-29 | 2021-11-26 | 上海景吾智能科技有限公司 | Mark point positioning and posture obtaining method and system based on marked image |
CN114119757A (en) * | 2021-12-17 | 2022-03-01 | 腾讯科技(深圳)有限公司 | Image processing method, apparatus, device, medium, and computer program product |
CN114299104A (en) * | 2021-12-23 | 2022-04-08 | 中铭谷智能机器人(广东)有限公司 | Automobile spraying track generation method based on multiple 3D (three-dimensional) vision |
CN114627166A (en) * | 2022-02-17 | 2022-06-14 | 国网江西省电力有限公司超高压分公司 | Robot holder servo control method based on point cloud registration ICP algorithm |
CN114862964A (en) * | 2022-04-27 | 2022-08-05 | 武汉智行者科技有限公司 | Automatic calibration method for sensor, electronic device and storage medium |
CN115239776A (en) * | 2022-07-14 | 2022-10-25 | 阿波罗智能技术(北京)有限公司 | Point cloud registration method, device, equipment and medium |
Non-Patent Citations (4)
Title |
---|
XIAOBO HU 等: "NrtNet: An Unsupervised Method for 3D Non-Rigid Point Cloud Registration Based on Transformer", 《SENSORS》 * |
何思婷: "轨道智能巡检小车动态基准测量系统", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
史红梅 等: "基于点集配准的非接触式地铁限界检测系统标定方法研究", 《铁道学报》 * |
聂良涛: "面向实体选线设计的铁路线路BIM与地理环境建模方法与应用", 《中国博士学位论文全文数据库 工程科技II辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115457088B (en) | 2023-03-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2720138C2 (en) | Method of automatic supply to loading-unloading platform for use in large-capacity trucks | |
CN106950964B (en) | Unmanned electric university student formula racing car and control method thereof | |
CN108196552B (en) | GPS visual navigation system of intelligent trolley | |
US10260889B2 (en) | Position estimation device and position estimation method | |
CN101842660B (en) | A device and a method for checking an attitude of a vehicle | |
CN112189225B (en) | Lane line information detection apparatus, method, and computer-readable recording medium storing computer program programmed to execute the method | |
CN110221623A (en) | A kind of air-ground coordination operating system and its localization method | |
CN107421518A (en) | A kind of trackless navigation AGV passes in and out lorry method automatically | |
CN112166059A (en) | Position estimation device for vehicle, position estimation method for vehicle, and computer-readable recording medium storing computer program programmed to execute the method | |
CN113791621B (en) | Automatic steering tractor and airplane docking method and system | |
CN111137298B (en) | Vehicle automatic driving method, device, system and storage medium | |
CN110766761B (en) | Method, apparatus, device and storage medium for camera calibration | |
CN110751693B (en) | Method, apparatus, device and storage medium for camera calibration | |
CN108459600A (en) | A kind of vision navigation system of AGV trolleies | |
CN111813114A (en) | Intelligent car visual navigation method | |
WO2023125754A1 (en) | Automatic platooning vehicle system and control method | |
CN110728720B (en) | Method, apparatus, device and storage medium for camera calibration | |
CN113605766B (en) | Detection system and position adjustment method of automobile carrying robot | |
CN113459852A (en) | Path planning method and device and mobile tool | |
CN115457088B (en) | Method and system for fixing axle of train | |
TW202120363A (en) | Automatic driving coordination system and control method capable of being applied in a fully automatic driving fleet to save manpower cost | |
CN115963510A (en) | Logistics park vehicle accurate parking method and system based on laser point cloud | |
WO2022252220A1 (en) | Precise stopping system and method for multi-axis flatbed vehicle | |
CN113581165A (en) | Method for operating a vehicle assistance or control system | |
CN114714360B (en) | Bogie wheel set positioning system and method based on distance value sequence constraint |
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 |