CN117420562A - Top-open carriage identification measurement system based on three-dimensional data of cradle head - Google Patents
Top-open carriage identification measurement system based on three-dimensional data of cradle head Download PDFInfo
- Publication number
- CN117420562A CN117420562A CN202311367342.2A CN202311367342A CN117420562A CN 117420562 A CN117420562 A CN 117420562A CN 202311367342 A CN202311367342 A CN 202311367342A CN 117420562 A CN117420562 A CN 117420562A
- Authority
- CN
- China
- Prior art keywords
- carriage
- point
- cradle head
- point cloud
- bottom plate
- 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
- 238000005259 measurement Methods 0.000 title claims abstract description 37
- 230000007246 mechanism Effects 0.000 claims abstract description 36
- 238000004891 communication Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 29
- 239000013598 vector Substances 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 22
- 238000013519 translation Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 210000000481 breast Anatomy 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000012946 outsourcing Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims 1
- 238000003860 storage Methods 0.000 description 8
- 230000004888 barrier function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/495—Counter-measures or counter-counter-measures using electronic or electro-optical means
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Abstract
The application discloses a top-open carriage recognition measurement system based on cloud deck three-dimensional data relates to the technical field of top-open carriage recognition. The top-open carriage identification measurement system based on the three-dimensional data of the cradle head comprises the cradle head, a travelling mechanism and an identification measurement module; the cradle head comprises a laser radar and a rotary platform, wherein the laser radar is used for scanning one section of a carriage at equal angle intervals, the laser radar is arranged on the rotary platform, the rotary platform is used for driving the laser radar to rotate and accurately controlling the rotation angle, the speed and the movement mode of the laser radar, and the laser radar scanning plane is parallel to the rotation axis of the rotary platform; the cradle head is in communication connection with the identification measurement module; the cradle head is arranged right above a carriage of the travelling mechanism after the truck is stopped, and the carriage of the truck falls into the spherical scanning range of the cradle head. By adopting the system, the accuracy and the reliability of carriage identification measurement can be improved.
Description
Technical Field
The application relates to the technical field of jack-up carriage identification, in particular to a jack-up carriage identification measurement system based on three-dimensional data of a cradle head.
Background
In the logistics industry, the loading demand of the top-open carriage is large. As aging increases and population numbers decrease in people in the country, fewer and fewer people engage in traditional manual loading/traditional mechanical loading. Wherein, mainly influence the factor of loading and have: the labor intensity is high, the working dust concentration is high, the outdoor winter and summer heat is high, the labor cost is high, and the labor is difficult to carry out. Therefore, the street mechanism loading system is combined with the industrial sensor to realize automatic loading, so that the cost of a company can be saved, the labor condition of workers can be improved, the loading efficiency is improved, and the street mechanism loading system is a necessary trend of industrial automation development. Wherein, definition of top-open carriage is a truck with carriage, and this truck has characterized by: a planar floor, a roof-less, roof-exposed cabin, cabin side panels having different heights, and a pull cord may be present between the side panels.
The vehicle identification and measurement system of the top-open carriage provides accurate vehicle model data for automatic loading of vehicles and provides a prepared loading point data source for subsequent travelling mechanisms and loading mechanisms.
The technical disadvantages of the non-contact detection device and the non-contact detection method for the state of the carriage of the railway vehicle disclosed in China patent application number CN201710294600.7 are as follows: the three-dimensional scanning scheme is a scanner fixed scheme, namely, the scanner is fixed and the vehicle moves, so that the scheme can only scan the external characteristics of the carriage and can not identify the internal characteristics of the carriage, such as whether foreign matters exist in the carriage or not and whether a pull rope exists in the carriage or not; the scanning device is fixed, the scanning beat is limited by the running speed of the vehicle, and therefore, the scanning beat of the scheme is slow, namely the scanning time is long; the carriage recognition measurement adopts a deep learning scheme, and the scheme requires huge training samples for each vehicle model to train, so that the robustness to various vehicle models is poor.
The visual system based on depth camera overlook recognition and positioning of carriage as disclosed in chinese patent application No. cn202111349914. X, and the carriage pose measurement system and method facing automated loading as disclosed in chinese patent application No. CN202010361420.8 have the following technical disadvantages: by adopting a binocular structured light depth camera, effective data measurement is difficult to be carried out on a vehicle with the depth of 4 meters; the binocular structure light is detected to have a detection blind area because the smaller the detectable plane area is as the horizontal open angle is limited and the closer the binocular structure light is to the camera, the more the binocular structure light is detected to have a detection blind area; the carriage identification and measurement system uses a threshold value division method to carry out driving measurement, so that the type of the vehicle can only be roughly identified, the prepared vehicle characteristic dimension data can not be provided, and the requirement of carriage automatic material loading operation can not be met.
The method and the device for measuring the interior of the carriage disclosed in China patent application No. CN202210277297.0 have the following technical defects: the laser scanner is arranged on the bridge type super-heavy machine (in the travelling mechanism), and the cross section data of the laser radar and the angle position data of the bridge type super-heavy machine are fused through the movement of the bridge type super-heavy machine to form a three-dimensional point cloud; the three-dimensional modeling mode of the bridge type overweight machine matched with the scanner has the advantages that the precision of the movement direction of the bridge type overweight machine can be directly superposed on the precision of the three-dimensional point cloud, normally, a reinforcing device such as a pull rope can be arranged on a vehicle, and the pull rope is about 10-50mm, so that the mode is easy to ignore the characteristics, and meanwhile, the bridge type overweight machine is easy to cause error accumulation in the back and forth walking process, so that the precision is poor; in the carriage segmentation algorithm, a clustering mode is adopted to segment the carriage, the aspect needs to have good continuity on carriage point clouds, and has general effects on discontinuous data, such as data loss in the carriage caused by water or smooth surfaces, and the data loss is caused, so that the continuity of the point clouds is influenced, and the clustering method adopting a 'prior model and then identifying vehicles' has limitation, so that the point clouds are unevenly distributed and are obviously disturbed, and the final identification effect is influenced; in general vehicle types, it is common that the floor of the carriage is one flat plate and two flat plates, and the scheme aims at the recognition measurement of the saddle of the carriage and does not effectively recognize the two flat plates, so that important result data is not provided for the number recognition of the floors of the carriage in the scheme applied to the recognition of the carriage of the general vehicle.
In summary, the vehicle identification and measurement system of the top-open type carriage in the prior art has more or less technical defects. There is a need for a more reliable jack-up car identification measurement system.
Disclosure of Invention
The purpose of the application is to provide a top-open carriage recognition measurement system based on three-dimensional data of a cradle head, so as to solve at least one technical problem in the background technology.
In order to achieve the above purpose, the present application discloses the following technical solutions: a top-open carriage recognition measurement system based on three-dimensional data of a cradle head comprises the cradle head, a traveling mechanism and a recognition measurement module; the cloud platform comprises a laser radar and a rotating platform, wherein the laser radar is used for scanning one section of a carriage at equal angle intervals, the laser radar is arranged on the rotating platform, the rotating platform is used for driving the laser radar to rotate and accurately controlling the rotation angle, the speed and the movement mode of the laser radar, and the laser radar scanning plane is parallel to the rotation axis of the rotating platform; the cradle head is in communication connection with the identification measurement module;
the cradle head is arranged right above a carriage of the travelling mechanism after the truck is stopped, and the carriage of the truck falls into the spherical scanning range of the cradle head;
the identification measurement module converts the three-dimensional field point cloud data of the holder into Cartesian coordinate data through a formula I, wherein the formula I is as follows:wherein r is the radius of the spherical coordinate model corresponding to the spherical scanning range of the cradle head, delta is the pitch angle of the spherical coordinate model, and phi is the rotation angle of the spherical coordinate model.
Preferably, the processing algorithm for identifying and positioning the wagon box by the identification and measurement module comprises the following steps:
s0-calibrating a holder coordinate system of the holder and a coordinate system of the travelling mechanism, wherein the method comprises the following steps: recording unit vectors of each direction axis of the travelling mechanism under a holder coordinate system to obtain a rotation matrix M Rotating And calculating a translation matrix T by point-to-point pairs Translation of Finally, the matrix M is rotated Rotating And a translation matrix T Translation of After synthesis, a conversion matrix M is obtained, and the obtained conversion is performedMatrix arrayFinally, a Cartesian coordinate system Oxyz is obtained, wherein in the Cartesian coordinate system Oxyz, the x direction is the direction that the head points to the tail of the vehicle, the y direction is the direction that the left side of the vehicle body points to the right side of the vehicle body, the z direction is the direction that the bottom points to the roof, and the origin of coordinates is positioned at the upper left side of the head of the vehicle;
s1, carrying out rotary transformation on the transformation matrix M to obtain the coordinates of the travelling mechanism, and filtering to remove the unnecessary points according to the area range of the travelling coordinate system; comprising the following steps: in the loading site, a parking area omega is drawn,most of unnecessary points are removed by limiting the region omega;
s2, clustering the point cloud with the useless points removed based on density, wherein the dimension of the clustering is the clustering of the XZ plane; comprising the following steps: defining p point to belong to N by setting maximum radius Eps of the field and minimum point MinPts in the point field Eps (q) and the P-dot density satisfies |N Eps (q) is not less than MinPts, and point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof are realized;
S3-European clustering is carried out on point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof, and the European clustering method comprises the following steps: setting a fixed threshold value to divide different point clusters into different point cloud blocks, wherein the point cloud clusters with average height less than 2000mm are marked as P 1 ～P n ；
S4-Peer-to-Peer cloud Cluster P 1 ～P n Respectively carrying out least square plane fitting to obtain normal vectors (i, j, k) of fitting planes of each point cloud cluster and standard deviation (delta) i ,δ j ,δ k ) Calculating the Z-axis included angle between the normal vector and the Cartesian coordinate system Oxyz to be within the range of 5 DEG of the threshold value delta k At a threshold of 2500mm 2 Points within range are listed in a floor alternate point Plane 1 ～Plane k ；
S5-alternative point Plane 1 ～Plane k Plane combination is carried out to lead the included angle to be within 2 DEGPlanes with adjacent boundary points smaller than 300mm and plane height difference within 50mm in the surrounding area are combined on the same plane to obtain a plurality of combined planes Pcmb 1 ～Pcmb k ；
S6-involution plane Pcmb 1 ～Pcmb k Positioning and identifying a carriage bottom plate, and judging the type of the carriage bottom plate as a boss car when the normal vector included angle between two planes is within a range of 2 degrees and the height difference of the planes is within 150-250 mm, wherein the boss car is a carriage bottom plate formed by two flat plates; otherwise, searching a merging plane which meets the conditions that the X direction is larger than 4000mm and the Z direction is larger than 1800mm, selecting the longest merging plane in the X direction as a carriage bottom plate, and judging the type of the carriage bottom plate as a flat car, wherein the flat car is a carriage bottom plate formed by a flat plate;
s7, performing least square rectangular fitting on the point cloud clusters of the carriage bottom plate to obtain carriage angular point coordinates, carriage horizontal deflection angles, carriage length and carriage width, and measuring the carriage bottom plate;
s8, extracting the height average value of 4 sides of the rectangle corresponding to the carriage bottom plate, obtaining the height average value of each side, and taking the height average value as the height of the corresponding carriage breast board;
s9, removing points of a carriage breast board from the calibrated point cloud by adopting regional range filtering, obtaining a point cloud Pstiffer of a carriage pull rope, carrying out European clustering on the Pstiffer in XYZ direction, and dividing different points with a distance larger than a preset threshold into different point cloud clusters PT 1 ～PT k The direction variance (δT) of each group of point cloud clusters is calculated i ,δT j ,δT k ) Satisfy δT i <4*10 2 And δT k >2.5*10 3 The point cloud of (1) is determined as the point cloud PT corresponding to the pull rope 1 ～PT k Point-to-point cloud PT 1 ～PT k And carrying out minimum outsourcing rectangular processing to obtain the position information of the pull rope, and realizing the identification and positioning of the pull rope.
Preferably, in S0, the step of obtaining the conversion matrix M specifically includes:
(1) Under the condition that the coordinates of Y and Z of the travelling mechanism are unchanged, the points A1-An are marked;
(2) Under the condition that the X and Z coordinates of the travelling mechanism are unchanged, the points B1 to Bn are marked;
(3) The least square method is adopted to calculate the direction vector (alpha) of A1-An 1 ,α 2 ,α 3 ) And direction vectors (. Beta.) of B1 to Bn 1 ,β 2 ,β 3 )；
(4) Vector cross-multiplication is used to obtain a Z-direction vector (gamma) 1 ,γ 2 ,γ 3 )，(γ 1 ,γ 2 ,γ 3 )＝(α 1 ,α 2 ,α 3 )×(β 1 ,β 2 ,β 3 )；
(5) According to (alpha) 1 ,α 2 ,α 3 )、(β 1 ,β 2 ,β 3 ) And (gamma) 1 ,γ 2 ,γ 3 ) Coordinate-derived rotation matrix
(6) According to the coordinates of a preset fixed point in the holder coordinate system and the corresponding coordinates in the running mechanism coordinate system, a translation vector T is obtained Translation of ＝[t1 t2 t3] T ；
(7) Obtaining a conversion matrixAnd the calibration between the cradle head and the walking coordinate system is realized.
The application discloses a top-open carriage discernment measurement system based on cloud platform three-dimensional data compares with prior art, has following beneficial effect:
1. the system is developed based on the cradle head, is an independent system, and does not depend on a travelling mechanism to realize independent autonomous scanning, control and installation;
2. the calculation result of the system is based on the point cloud under the global coordinate system of the holder without depending on external walking machinery, so that the system has independent and stable error without being interfered by other mechanisms, and has high stability;
3. the system has simple and clear calibration mode, is easy to understand, can well correlate the running mechanism coordinate system with the cradle head coordinate system, and is convenient for personnel to understand and maintain;
4. the system acquires the three-dimensional point cloud by adopting a holder mode, has the advantage of short scanning time, and is beneficial to the production working condition of high beats on site;
5. the carriage identification measurement method has the advantages of high calculation speed, no need of pre-training, short time consumption and fast beat, and is favorable for the production working condition of high beat on site;
6. the carriage identifying and measuring method has excellent adaptability to various overhead empty carriages, can automatically identify the type of the overhead empty carriage, can identify and position high barrier plates, low barrier plates and no barrier plates, can identify and position whether a carriage bottom plate is a flat plate or a boss, and can identify and position whether a pull rope exists. The complex pre-training is not needed, and meanwhile, the external input is not needed for the vehicle type;
7. the carriage identification and measurement method does not require the vehicle head, and increases the robustness of carriage identification.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a layout schematic diagram of a top-open carriage recognition measurement system based on three-dimensional data of a cradle head in an embodiment of the application;
FIG. 2 is a schematic diagram of a spherical coordinate model corresponding to a spherical scanning range in an embodiment of the present application;
FIG. 3 is a schematic diagram of a pan/tilt coordinate system according to an embodiment of the present application;
fig. 4 is a schematic diagram of point cloud data of a spherical coordinate model according to an embodiment of the present application;
FIG. 5 is a schematic view of point cloud density-based clustering in an embodiment of the present application;
fig. 6 is a schematic diagram of an operation flow of a top-open carriage recognition measurement system based on three-dimensional data of a cradle head in an embodiment of the present application;
fig. 7 is a schematic flow chart of an algorithm in a top-open carriage recognition measurement system based on three-dimensional data of a cradle head in an embodiment of the application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
In this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
Referring to fig. 1, a top-open carriage recognition measurement system based on three-dimensional data of a cradle head comprises the cradle head, a travelling mechanism and a recognition measurement module. In the figure, the installation height parking range is R, and the vehicle width direction horizontal parking range W. Meanwhile, the vehicle length parking range (R, W) is related to the vehicle width, the rotation speed of the cradle head, the mounting height of the cradle head and the equipment type. The cloud platform comprises a laser radar and a rotating platform, wherein the laser radar is used for scanning one section of a carriage at equal angle intervals, the laser radar is arranged on the rotating platform, the rotating platform is used for driving the laser radar to rotate and accurately controlling the rotation angle, the speed and the movement mode of the laser radar, and the laser radar scanning plane is parallel to the rotation axis of the rotating platform; and the cradle head is in communication connection with the identification measurement module. The cradle head is fixedly arranged right above the wagon carriage, and the wagon carriage falls into the spherical scanning range of the cradle head. The fixed installation of the cradle head has the advantages that: the cradle head is an independent closed-loop system, has a set of complete hardware, and is not limited by other field systems; the scanning direction of the cradle head is from one side of the carriage width to the other side of the carriage width, so that the minimum scanning range is realized, and the scanning beat of carriage scanning is more beneficial to shortening; the cradle head adopts a polar coordinate scanning model to effectively control the accuracy error of the cradle head without being interfered by other external system errors.
Referring to fig. 2 and fig. 3, the identification measurement module converts the three-dimensional field point cloud data of the pan-tilt into cartesian coordinate data according to a formula one, where the formula one is:wherein r is the radius of the spherical coordinate model corresponding to the spherical scanning range of the cradle head, delta is the pitch angle of the spherical coordinate model, and phi is the rotation angle of the spherical coordinate model.
Further, referring to fig. 3-7, the processing algorithm for identifying and positioning the wagon box by the identification measurement module includes:
s0-calibrating a holder coordinate system of the holder and a coordinate system of the travelling mechanism, wherein the method comprises the following steps: recording unit vectors of each direction axis of the travelling mechanism under a holder coordinate system to obtain a rotation matrix M Rotating And calculating a translation matrix T by point-to-point pairs Translation of Finally, the matrix M is rotated Rotating And a translation matrix T Translation of After synthesis, a conversion matrix M is obtained, and the obtained conversion matrixFinally, a Cartesian coordinate system Oxyz is obtained, wherein in the Cartesian coordinate system Oxyz, the x direction is the direction of the head to the tail, the y direction is the direction of the left side of the vehicle body to the right side of the vehicle body, the z direction is the direction of the bottom to the roof, and the origin of coordinates is positionedThe left upper part of the vehicle head;
s1, carrying out rotary transformation on the transformation matrix M to obtain the coordinates of the travelling mechanism, and filtering to remove the unnecessary points according to the area range of the travelling coordinate system; comprising the following steps: in the loading site, a parking area omega is drawn,most of unnecessary points are removed by limiting the region omega;
s2, clustering the point cloud with the useless points removed based on density, wherein the dimension of the clustering is the clustering of the XZ plane; comprising the following steps: defining p point to belong to N by setting maximum radius Eps of the field and minimum point MinPts in the point field Eps (q) and the P-dot density satisfies |N Eps (q) is not less than MinPts, and point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof are realized;
S3-European clustering is carried out on point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof, and the European clustering method comprises the following steps: setting a fixed threshold value to divide different point clusters into different point cloud blocks, wherein the point cloud clusters with average height less than 2000mm are marked as P 1 ～P n ；
S4-Peer-to-Peer cloud Cluster P 1 ～P n Respectively carrying out least square plane fitting to obtain normal vectors (i, j, k) of fitting planes of each point cloud cluster and standard deviation (delta) i ,δ j ,δ k ) Calculating the Z-axis included angle between the normal vector and the Cartesian coordinate system Oxyz to be within the range of 5 DEG of the threshold value delta k At a threshold of 2500mm 2 Points within range are listed in a floor alternate point Plane 1 ～Plane k ；
S5-alternative point Plane 1 ～Plane k Combining planes with an included angle within 2 degrees, adjacent boundary points being less than 300mm and planes with a height difference within 50mm on the same plane to obtain a plurality of combined planes Pcmb 1 ～Pcmb k ；
S6-involution plane Pcmb 1 ～Pcmb k Positioning and identifying the carriage bottom plate, when the normal vector included angle between two planes is within 2 DEG and the height of the planeJudging the type of the carriage bottom plate as a boss car when the height difference is within 150-250 mm, wherein the boss car is a carriage bottom plate formed by two flat plates; otherwise, searching a merging plane which meets the conditions that the X direction is larger than 4000mm and the Z direction is larger than 1800mm, selecting the longest merging plane in the X direction as a carriage bottom plate, and judging the type of the carriage bottom plate as a flat car, wherein the flat car is a carriage bottom plate formed by a flat plate;
s7, performing least square rectangular fitting on the point cloud clusters of the carriage bottom plate to obtain carriage angular point coordinates, carriage horizontal deflection angles, carriage length and carriage width, and measuring the carriage bottom plate;
s8, extracting the height average value of 4 sides of the rectangle corresponding to the carriage bottom plate, obtaining the height average value of each side, and taking the height average value as the height of the corresponding carriage breast board;
s9, removing points of a carriage breast board from the calibrated point cloud by adopting regional range filtering, obtaining a point cloud Pstiffer of a carriage pull rope, carrying out European clustering on the Pstiffer in XYZ direction, and dividing different points with a distance larger than a preset threshold into different point cloud clusters PT 1 ～PT k The direction variance (δT) of each group of point cloud clusters is calculated i ,δT j ,δT k ) Satisfy δT i <4*10 2 And δT k >2.5*10 3 The point cloud of (1) is determined as the point cloud PT corresponding to the pull rope 1 ～PT k Point-to-point cloud PT 1 ～PT k And carrying out minimum outsourcing rectangular processing to obtain the position information of the pull rope, and realizing the identification and positioning of the pull rope.
In S0, the step of obtaining the conversion matrix M specifically includes:
(1) Under the condition that the coordinates of Y and Z of the travelling mechanism are unchanged, the points A1-An are marked;
(2) Under the condition that the X and Z coordinates of the travelling mechanism are unchanged, the points B1 to Bn are marked;
(3) The least square method is adopted to calculate the direction vector (alpha) of A1-An 1 ,α 2 ,α 3 ) And direction vectors (. Beta.) of B1 to Bn 1 ,β 2 ,β 3 )；
(4) Vector cross-multiplication is used to obtain a Z-direction vector (gamma) 1 ,γ 2 ,γ 3 )，(γ 1 ,γ 2 ,γ 3 )＝(α 1 ,α 2 ,α 3 )×(β 1 ,β 2 ,β 3 )；
(5) According to (alpha) 1 ,α 2 ,α 3 )、(β 1 ,β 2 ,β 3 ) And (gamma) 1 ,γ 2 ,γ 3 ) Coordinate-derived rotation matrix
(6) According to the coordinates of a preset fixed point in the holder coordinate system and the corresponding coordinates in the running mechanism coordinate system, a translation vector T is obtained Translation of ＝[t1 t2 t3] T ；
(7) Obtaining a conversion matrixAnd the calibration between the cradle head and the walking coordinate system is realized.
In the embodiments provided herein, it should be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For a hardware implementation, the processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the flow of an embodiment may be accomplished by a computer program to instruct the associated hardware. When implemented, the above-described programs may be stored in or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. The computer-readable storage media may include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
To sum up, the jacking type carriage identification measurement system based on the three-dimensional data of the cradle head has the following characteristics:
1. the system is developed based on the cradle head, is an independent system, and does not depend on a travelling mechanism to realize independent autonomous scanning, control and installation;
2. the calculation result of the system is based on the point cloud under the global coordinate system of the holder without depending on external walking machinery, so that the system has independent and stable error without being interfered by other mechanisms, and has high stability;
3. the system has simple and clear calibration mode, is easy to understand, can well correlate the running mechanism coordinate system with the cradle head coordinate system, and is convenient for personnel to understand and maintain;
4. the system acquires the three-dimensional point cloud by adopting a holder mode, has the advantage of short scanning time, and is beneficial to the production working condition of high beats on site;
5. the carriage identification measurement method has the advantages of high calculation speed, no need of pre-training, short time consumption and fast beat, and is favorable for the production working condition of high beat on site;
6. the carriage identifying and measuring method has excellent adaptability to various overhead empty carriages, can automatically identify the type of the overhead empty carriage, can identify and position high barrier plates, low barrier plates and no barrier plates, can identify and position whether a carriage bottom plate is a flat plate or a boss, and can identify and position whether a pull rope exists. The complex pre-training is not needed, and meanwhile, the external input is not needed for the vehicle type;
7. the carriage identification and measurement method does not require the vehicle head, and increases the robustness of carriage identification.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present application, and although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof, and any modifications, equivalents, improvements or changes that fall within the spirit and principles of the present application are intended to be included in the scope of protection of the present application.
Claims (3)
1. A top-open carriage recognition measurement system based on three-dimensional data of a cradle head is characterized by comprising the cradle head, a travelling mechanism and a recognition measurement module; the cloud platform comprises a laser radar and a rotating platform, wherein the laser radar is used for scanning one section of a carriage at equal angle intervals, the laser radar is arranged on the rotating platform, the rotating platform is used for driving the laser radar to rotate and accurately controlling the rotation angle, the speed and the movement mode of the laser radar, and the laser radar scanning plane is parallel to the rotation axis of the rotating platform; the cradle head is in communication connection with the identification measurement module;
the cradle head is arranged right above a carriage of the travelling mechanism after the truck is stopped, and the carriage of the truck falls into the spherical scanning range of the cradle head;
the identification measurement module converts the three-dimensional field point cloud data of the holder into Cartesian coordinate data through a formula I, wherein the formula I is as follows:wherein r is the radius of the spherical coordinate model corresponding to the spherical scanning range of the cradle head, delta is the pitch angle of the spherical coordinate model, and phi is the rotation angle of the spherical coordinate model.
2. The system for identifying and measuring a top-open type carriage based on three-dimensional data of a cradle head according to claim 1, wherein the processing algorithm for identifying and positioning the carriage of the truck by the identifying and measuring module comprises:
s0-calibrating a holder coordinate system of the holder and a coordinate system of the travelling mechanism, wherein the method comprises the following steps: recording unit vectors of each direction axis of the travelling mechanism under a holder coordinate system to obtain a rotation matrix M Rotating And calculating a translation matrix T by point-to-point pairs Translation of Finally, the matrix M is rotated Rotating And a translation matrix T Translation of After synthesis, a conversion matrix M is obtained, and the obtained conversion matrixFinally, a Cartesian coordinate system Oxyz is obtained, wherein in the Cartesian coordinate system Oxyz, the x direction is the direction that the head points to the tail of the vehicle, the y direction is the direction that the left side of the vehicle body points to the right side of the vehicle body, the z direction is the direction that the bottom points to the roof, and the origin of coordinates is positioned at the upper left side of the head of the vehicle;
s1, carrying out rotary transformation on the transformation matrix M to obtain the coordinates of the travelling mechanism, and filtering to remove the unnecessary points according to the area range of the travelling coordinate system; comprising the following steps: in the loading site, a parking area omega is drawn, most of unnecessary points are removed by limiting the region omega;
s2, clustering the point cloud with the useless points removed based on density, wherein the dimension of the clustering is the clustering of the XZ plane; comprising the following steps: defining p point to belong to N by setting maximum radius Eps of the field and minimum point MinPts in the point field Eps (q 0, and P-dot density satisfying |N Eps (q) is not less than MinPts, and point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof are realized;
S3-European clustering is carried out on point clouds of a carriage bottom plate, front and rear breast plates and a vehicle roof, and the European clustering method comprises the following steps: setting a fixed threshold value to divide different point clusters into different point cloud blocks, wherein the point cloud clusters with average height less than 2000mm are marked as P 1 ～P n ；
S4-Peer-to-Peer cloud Cluster P 1 ～P n Respectively carrying out least square plane fitting to obtain normal vectors (i, j, k) of fitting planes of each point cloud cluster and standard deviation (delta) i ,δ j ,δ k ) Calculating the Z-axis included angle between the normal vector and the Cartesian coordinate system Oxyz to be within the range of 5 DEG of the threshold value delta k At a threshold of 2500mm 2 Points within range are listed in a floor alternate point Plane 1 ～Plane k ；
S5-alternative point Plane 1 ～Plane k Combining planes with an included angle within 2 degrees, adjacent boundary points being less than 300mm and planes with a height difference within 50mm on the same plane to obtain a plurality of combined planes Pcmb 1 ～Pcmb k ；
S6-involution plane Pcmb 1 ～Pcmb k Positioning and identifying a carriage bottom plate, and judging the type of the carriage bottom plate as a boss car when the normal vector included angle between two planes is within a range of 2 degrees and the height difference of the planes is within 150-250 mm, wherein the boss car is a carriage bottom plate formed by two flat plates; otherwise, searching a merging plane which meets the conditions that the X direction is larger than 4000mm and the Z direction is larger than 1800mm, selecting the longest merging plane in the X direction as a carriage bottom plate, and judging the type of the carriage bottom plate as a flat car, wherein the flat car is a carriage bottom plate formed by a flat plate;
s7, performing least square rectangular fitting on the point cloud clusters of the carriage bottom plate to obtain carriage angular point coordinates, carriage horizontal deflection angles, carriage length and carriage width, and measuring the carriage bottom plate;
s8, extracting the height average value of 4 sides of the rectangle corresponding to the carriage bottom plate, obtaining the height average value of each side, and taking the height average value as the height of the corresponding carriage breast board;
s9, removing points of carriage sideboards from the calibrated point cloud by adopting regional range filtering, removing points of carriage sideboards from the point cloud which does not restrict the Z direction in the whole carriage bottom plate range to obtain a point cloud Pstiffer of a carriage pull rope, carrying out European clustering on the Pstiffer in the XYZ direction, and obtaining the distance larger than the preset distanceDifferent points with threshold values are divided into different point cloud clusters PT 1 ～PT k The direction variance (δT) of each group of point cloud clusters is calculated i ,δT j ,δT k ) Satisfy δT i <4*10 2 And δT k >2.5*10 3 The point cloud of (1) is determined as the point cloud PT corresponding to the pull rope 1 ～PT k Point-to-point cloud PT 1 ～PT k And carrying out minimum outsourcing rectangular processing to obtain the position information of the pull rope, and realizing the identification and positioning of the pull rope.
3. The system for measuring the identification of a top-open type car based on three-dimensional data of a pan-tilt as set forth in claim 2, wherein in S0, the step of obtaining the conversion matrix M specifically includes:
(1) Under the condition that the coordinates of Y and Z of the travelling mechanism are unchanged, the points A1-An are marked;
(2) Under the condition that the X and Z coordinates of the travelling mechanism are unchanged, the points B1 to Bn are marked;
(3) The least square method is adopted to calculate the direction vector (alpha) of A1-An 1 ,α 2 ,α 3 ) And direction vectors (. Beta.) of B1 to Bn 1 ,β 2 ,β 3 )；
(4) Vector cross-multiplication is used to obtain a Z-direction vector (gamma) 1 ,γ 2 ,γ 3 )，(γ 1 ,γ 2 ,γ 3 )＝(α 1 ,α 2 ,α 3 )×(β 1 ,β 2 ,β 3 )；
(5) According to (alpha) 1 ,α 2 ,α 3 )、(β 1 ,β 2 ,β 3 ) And (gamma) 1 ,γ 2 ，γ 3 ) Coordinate-derived rotation matrix
(6) According to the coordinates of a preset fixed point in the holder coordinate system and the corresponding coordinates in the running mechanism coordinate system, a translation vector T is obtained Translation of ＝[t1 t2 t3] T ；
(7) Obtaining a conversion matrixAnd the calibration between the cradle head and the walking coordinate system is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311367342.2A CN117420562B (en) | 2023-10-21 | 2023-10-21 | Top-open carriage identification measurement system based on three-dimensional data of cradle head |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311367342.2A CN117420562B (en) | 2023-10-21 | 2023-10-21 | Top-open carriage identification measurement system based on three-dimensional data of cradle head |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117420562A true CN117420562A (en) | 2024-01-19 |
| CN117420562B CN117420562B (en) | 2024-09-03 |
Family
ID=89525833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311367342.2A Active CN117420562B (en) | 2023-10-21 | 2023-10-21 | Top-open carriage identification measurement system based on three-dimensional data of cradle head |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117420562B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192328A (en) * | 2019-12-31 | 2020-05-22 | 芜湖哈特机器人产业技术研究院有限公司 | Two-dimensional laser radar-based point cloud processing method for three-dimensional scanning system of compartment container |
| CN112417591A (en) * | 2020-11-16 | 2021-02-26 | 上海交通大学 | Vehicle modeling method, system, medium and equipment based on holder and scanner |
| CN215728846U (en) * | 2021-06-16 | 2022-02-01 | 泉州装备制造研究所 | Modeling device of transport vehicle without baffle at top of carriage |
| CN114061446A (en) * | 2021-10-20 | 2022-02-18 | 成都利君环际智能装备科技有限公司 | Carriage size measuring system and method based on multiple three-dimensional scanning devices |
| CN114241475A (en) * | 2021-11-22 | 2022-03-25 | 中冶赛迪重庆信息技术有限公司 | Self-adaptive automobile type identification method and system based on three-dimensional laser scanning |
| CN116263320A (en) * | 2021-12-15 | 2023-06-16 | 武汉万集光电技术有限公司 | Vehicle measurement method, device, system and storage medium |
| CN116385516A (en) * | 2023-05-31 | 2023-07-04 | 广州市杜格科技有限公司 | Static vehicle contour detection method, system, device and storage medium |
-
2023
- 2023-10-21 CN CN202311367342.2A patent/CN117420562B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192328A (en) * | 2019-12-31 | 2020-05-22 | 芜湖哈特机器人产业技术研究院有限公司 | Two-dimensional laser radar-based point cloud processing method for three-dimensional scanning system of compartment container |
| CN112417591A (en) * | 2020-11-16 | 2021-02-26 | 上海交通大学 | Vehicle modeling method, system, medium and equipment based on holder and scanner |
| CN215728846U (en) * | 2021-06-16 | 2022-02-01 | 泉州装备制造研究所 | Modeling device of transport vehicle without baffle at top of carriage |
| CN114061446A (en) * | 2021-10-20 | 2022-02-18 | 成都利君环际智能装备科技有限公司 | Carriage size measuring system and method based on multiple three-dimensional scanning devices |
| CN114241475A (en) * | 2021-11-22 | 2022-03-25 | 中冶赛迪重庆信息技术有限公司 | Self-adaptive automobile type identification method and system based on three-dimensional laser scanning |
| CN116263320A (en) * | 2021-12-15 | 2023-06-16 | 武汉万集光电技术有限公司 | Vehicle measurement method, device, system and storage medium |
| CN116385516A (en) * | 2023-05-31 | 2023-07-04 | 广州市杜格科技有限公司 | Static vehicle contour detection method, system, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117420562B (en) | 2024-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114049294B (en) | Road surface technical condition detection method and equipment based on three-dimensional contour | |
| CN110320506B (en) | Automatic calibration device and method for automotive laser radar | |
| CN105300469A (en) | Moving gantry type measuring system and method for vehicle-mounted material volume | |
| CN113448333B (en) | Bottom inspection positioning method and device based on sensor combination and electronic equipment | |
| CN111796258B (en) | Construction method and construction device of radar parameter calibration field and readable storage medium | |
| CN111522345B (en) | Wheel position control method for docking cabin door of boarding bridge | |
| CN111578893A (en) | Method for identifying included angle between tractor and trailer | |
| CN206177947U (en) | Road and bridge concrete inspection device | |
| CN104005324B (en) | A kind of detection system of pavement structure information | |
| CN113917479A (en) | Vehicle included angle calculation method and device, computer equipment and storage medium | |
| CN117420562B (en) | Top-open carriage identification measurement system based on three-dimensional data of cradle head | |
| CN116128834A (en) | Rail transit platform limit rapid detection method based on three-dimensional laser scanning | |
| CN206479299U (en) | A kind of photo-electric deflection of bridge span instrument calibrating installation | |
| CN115793656B (en) | Track inspection robot positioning method, device and system based on line mark | |
| CN201951492U (en) | Railway transportation overrunning detector | |
| CN210514611U (en) | Automatic calibration device for automotive laser radar | |
| CN111551122A (en) | Train wagon number and length measuring system and method based on laser radar | |
| CN114279452B (en) | Unmanned integrated card trailer posture detection method and detection system | |
| CN217561347U (en) | Container body damage detection system | |
| CN115959170A (en) | Track detection method based on track surface detection system | |
| CN115205397A (en) | Vehicle space-time information identification method based on computer vision and pose estimation | |
| CN114269676B (en) | Container positioning method, system and storage medium | |
| CN112731431A (en) | Positioning detection device and method for van truck | |
| CN217399343U (en) | Race road surface flatness detection device based on BIM model | |
| CN114179851B (en) | Railway equipment limit detection device and method |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Unit 01-05, 08, Floor 18, No. 15, the Pearl River West Road, Tianhe District, Guangzhou, Guangdong 510000 (for office use only) Applicant after: Guangdong Xike Intelligent Technology Co.,Ltd. Address before: Unit 01-05, 08, Floor 18, No. 15, the Pearl River West Road, Tianhe District, Guangzhou, Guangdong 510000 (for office use only) Applicant before: GUANGZHOU SICK SENSOR Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |