CN116934832A - Real-time calibration method of three-dimensional point cloud based on field reference object - Google Patents
Real-time calibration method of three-dimensional point cloud based on field reference object Download PDFInfo
- Publication number
- CN116934832A CN116934832A CN202310886117.3A CN202310886117A CN116934832A CN 116934832 A CN116934832 A CN 116934832A CN 202310886117 A CN202310886117 A CN 202310886117A CN 116934832 A CN116934832 A CN 116934832A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- mine car
- real
- reference object
- cloud data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000005477 standard model Effects 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000005065 mining Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241000238097 Callinectes sapidus Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005303 weighing Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a real-time calibration method of a three-dimensional point cloud based on a field reference object, which is characterized by comprising the following steps of: s1: accurately measuring the position of a fixed reference object, and calibrating external parameters for later mine car measurement; s2: the laser radars at the two sides extract building point clouds to finish calibration; s3: and driving into the mine car to enter a mine car charging channel, acquiring point clouds at two sides of the mine car by the laser radars at two sides, preprocessing the acquired point cloud image to filter background redundant point cloud data, completing point cloud downsampling, removing the background by the point clouds, fusing the point clouds at two sides, and obtaining processed point cloud data information. The invention relates to the technical field of machine vision data processing, in particular to a real-time calibration method of a three-dimensional point cloud based on a field reference object. The technical problem to be solved by the invention is to provide a real-time calibration method of three-dimensional point cloud based on a site reference object, which is convenient for mine car loading.
Description
Technical Field
The invention relates to the technical field of machine vision data processing, in particular to a real-time calibration method of a three-dimensional point cloud based on a field reference object.
Background
Along with the continuous progress of mining technology, modern mine collection is developed towards digital intelligence, material loading is an important link of an ore production process, a truck transportation system is basically configured at the current stage of the mine, but due to the fact that trucks are various and still in a manual dispatching state, a few automatic loading and delivering systems also have the problems of complex flow, unbalanced loading of material loading, weighing cheating and the like, vehicles are slow to pass, and efficiency is low.
The mine car size detection is an important link of mine digital development, at present, a portal frame type infrared light curtain combined laser radar measuring method and a portal frame type laser radar combined computer vision measuring method are commonly adopted for measuring the external dimensions of the vehicles in China, the frequency of sampling is limited by the existing products, an infrared light curtain receiver is required to be installed on the ground during width measurement, maintenance is not facilitated, and higher measuring precision is difficult to achieve. Therefore, how to detect the size of the mine car rapidly and accurately becomes a problem to be solved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a real-time calibration method of three-dimensional point cloud based on a site reference object, which is convenient for mine car loading.
The invention adopts the following technical scheme to realize the aim of the invention:
the real-time calibration method of the three-dimensional point cloud based on the field reference object is characterized by comprising the following steps of:
s1: accurately measuring the position of a fixed reference object, and calibrating external parameters for later mine car measurement;
s2: the laser radars at the two sides extract building point clouds to finish calibration;
s3: the mine car enters a mine car charging channel, the laser radars at two sides acquire point clouds at two sides of the mine car, and pre-process the acquired point cloud images to filter background redundant point cloud data, so as to finish point cloud downsampling, removing the background of the point cloud, and fusing the point clouds at two sides to obtain processed point cloud data information;
s4: according to the mine car point cloud data, carrying out feature recognition on carriages of different types of mine cars;
s5: calculating the length, width and height of the carriage according to the calibration result of the step S2;
s6: detecting a cross beam or an in-car obstacle on the carriage, and guiding a feed opening;
s7: and monitoring the state of charge of the mine car in real time, predicting and guiding the action of the feed opening until the completion of the charging.
As a further limitation of the technical scheme, the mine car charging channel comprises a ground and two side walls, symmetrical upright posts are fixedly connected to the walls on the two sides respectively, the laser radars are fixedly connected to the walls on the two sides respectively, and the upright posts are fixed reference objects;
s21: firstly, selecting a calibration object in the real world, selecting four fixed upright posts as the calibration object, manufacturing a standard model of the upright posts by using solidworks according to the position relation between the actual upright posts, and dispersing the standard model into point cloud data;
s22: and constructing a standard point cloud model of the upright in the solidworks, taking the XOY surface as the bottom surface, taking one upright as the origin, and constructing a coordinate system of a known model to finish the calibration of the upright.
As a further limitation of the present solution, each of the lidars is located at a symmetrical center position of the upright.
As a further limitation of the present technical solution, the S3 includes:
s31: downsampling is carried out on mine car point cloud data, downsampling simplification is carried out on the point cloud data by adopting a voxel filter, the shape characteristics of the point cloud data can be maintained while the point density is reduced, the smallest cubic voxel grid is found according to the characteristics of the input point cloud data, and the cubic grid is selectedAccording to the length of the side of the cube gridThe three-dimensional voxel grid consists of a plurality of small three-dimensional cubes, the point clouds are divided into corresponding small grids, the centroid of each small cube grid is used for representing other point clouds in the cube, and the point cloud density is reduced by a centroid substitution method without establishing a topological structure between the points;
s32: filtering background information point cloud through a filter, reserving mine car point cloud data, filtering out points with values not in a self-defined threshold range in a specified direction through the filter, and achieving the purposes of filtering and extracting a region of interest;
s33: the laser radars on two sides collect point cloud data of the mine car, the point cloud data obtained by scanning the two laser radars have respective coordinate systems, and the point cloud coordinate systems are unified through point cloud registration.
As a further limitation of the technical scheme, the S4 is mainly used for identifying and dividing the carriage aiming at the mine cars of different types, and dividing the carriage and the mine cars, so that later dimension measurement is facilitated.
As a further limitation of the technical scheme, when executing the step S4, the processed mine car point cloud and the stand column standard point cloud are fused, and the process is as follows:
s41: importing the processed mine car point cloud data into a standard point cloud of an upright post to obtain a relative position relationship between a standard point cloud model of the upright post and the mine car point cloud;
s42: in the mine car point cloud, the distance between the stand column and the laser radar is fixed, so that the point cloud data of the stand column is segmented from the mine car point cloud according to a known position relationship, and the scanning point cloud is registered to the standard point cloud of the stand column by using an ICP algorithm.
As a further limitation of the technical scheme, the position of the obstacle in the car influences the position of the feeding hole of the mine car, point cloud data of the mine car are acquired through the laser radar, point clouds of obstacle point clouds are closely adjacent, a certain distance exists between different obstacle point clouds, according to the rule, the obstacle is clustered and segmented based on the Euclidean distance, so that the position of the obstacle is determined, and the feeding hole is not influenced by the obstacle during feeding.
As a further limitation of the technical scheme, the S5 calculates the relative offset angle of the mine car, the length, width and height of the carriage and the position of the obstacle in the car according to the calibration result of the S2, and the ICP algorithm is specific to measurement of each parameter.
The specific steps of the S5 are as follows:
s51: applying the transformation matrix calculated by ICP to mine car point cloud, and transforming mine car point cloud;
s52: the position of the stand column is known, a certain point on the mine car is arbitrarily selected, the displacement relation of the point relative to the known position can be obtained, and based on the relation, various parameters of the length, width and height of the mine car and the position of the obstacle in the car can be obtained.
Compared with the prior art, the invention has the advantages and positive effects that:
1. the invention provides a real-time calibration method of three-dimensional point cloud based on a site reference object, which effectively solves the problems of measurement of mine car size and real-time loading of mineral aggregates in the automatic mine car loading process, obtains the corresponding mine car size according to an algorithm processing result, monitors the mine car loading process in real time, realizes unmanned loading environment, and timely reacts to conditions such as no-load, full-load unbalanced loading and the like in the mine car loading.
2. The research result of the invention can be widely applied to bulk cargo automatic loading systems in related fields, and the system body of the bulk cargo automatic loading system can catalyze a new mine equipment growing point while improving the mine operation efficiency. A set of efficient real-time supply chain system is established, and powerful guarantee is provided for safe production of mines, energy conservation and consumption reduction. And the transportation vehicles are screened, so that the problems of overload, misloading and the like are completely eradicated from the source, vehicles which do not meet the displacement are refused to be on the road, and green transportation is promoted.
Drawings
Fig. 1 is a block diagram of a point cloud data processing flow of the present invention.
Fig. 2 is a schematic structural view of the present invention.
FIG. 3 is a standard point cloud coordinate system of the column of the present invention.
FIG. 4 is a diagram of the location relationship between the point cloud and standard point cloud of the column of the present invention.
FIG. 5 is a standard point cloud and a scanning point cloud of the present invention.
Fig. 6 is an ICP conversion matrix algorithm of the invention.
FIG. 7 is a photograph of the mine car point cloud converted according to the present invention.
FIG. 8 is a point cloud of the mine car after registration of the present invention.
FIG. 9 is a mine car point cloud position estimation of the present invention.
In the figure: 1. mine car, 2, wall, 3, ground, 4, carriage, 5, crossbeam, 6, laser radar, 7, stand.
Detailed Description
One embodiment of the present invention will be described in detail below with reference to the attached drawings, but it should be understood that the scope of the present invention is not limited by the embodiment.
The invention is characterized by comprising the following steps:
s1: and accurately measuring the position of a fixed reference object, and performing external parameter calibration for later mine car 1 measurement.
The mine car charging channel comprises a ground 3 and two side walls 2, symmetrical stand columns 7 are fixedly connected to the two side walls 2 respectively, the laser radars 6 are fixedly connected to the two side walls 2 respectively, and the stand columns 7 are fixed reference objects.
Each of the lidars 6 is located in a symmetrical middle position of the upright 7.
In order to increase the accuracy and speed of calibrating the mine car 1 by the lidar 6, the external parameters of the lidar 6 are measured with a reference object having a special shape provided in the environment, which requires manual measurement of the actual size and position information of the reference object. First, several fixed references, such as four posts 7 in fig. 2, are set, and two lidars 6 are fixed on the two side walls 2, respectively.
S2: and the laser radars 6 on the two sides extract building point clouds to finish calibration.
After the reference points are selected, in order to avoid the influence of other interferents in the environment on the external parameter calibration of the laser radar 6, the laser radars 6 at the two sides shoot the point cloud of the site which does not drive into the mine car 1, extract the point cloud of the building, and perform identification and prediction on the point Yun Zhong stand column 7 to finish the external parameter calibration.
S21: firstly, selecting a calibration object in the real world, selecting four fixed upright posts 7 as the calibration object, manufacturing a standard model of the upright posts by using solidworks according to the position relation between the actual upright posts, and dispersing the standard model into point cloud data;
s22: and constructing a standard point cloud model of the upright column in the solidworks, taking the XOY surface as the bottom surface, taking one upright column 7 as the origin, and constructing a coordinate system of a known model as shown in figure 3 to finish the calibration of the upright column 7.
S3: and the laser radars 6 at two sides acquire point clouds at two sides of the mine car 1, and preprocess the acquired point cloud images so as to filter background redundant point cloud data, finish point cloud downsampling, remove the background of the point clouds, and fuse the point clouds at two sides to obtain processed point cloud data information.
In a specific implementation, as the number of the point cloud output points of the laser radar 6 per second is too large, the calculation is directly carried out on the original point cloud data of the mine car 1 acquired by the laser radar 6, the speed is very slow, and the requirement of rapid processing cannot be met.
Thus, the S3 includes:
s31: downsampling mine car point cloud data, simplifying downsampling of the point cloud data by adopting a voxel filter, reducing the point density, simultaneously maintaining the shape characteristics of the point cloud data, finding out the smallest cubic voxel grid according to the characteristics of the input point cloud data, selecting the side length of the cubic grid, and changing the basis of the cubic grid into a division basisA small grid consisting of a collection of small three-dimensional cubes, the point cloud being divided into respective small grids, with each small cubeThe centroid of the grid body represents other point clouds in the cube, and the point cloud density is reduced by a centroid substitution method without establishing a topological structure between points;
s32: in order to better measure mine car point cloud data, the background information point cloud is filtered through a filter, mine car point cloud data is reserved, and points with values not in the self-defined threshold range in the designated direction are filtered through the filter, so that the purposes of filtering and extracting the region of interest are achieved;
s33: the laser radars 6 on two sides collect point cloud data of the mine car 1, the point cloud data obtained by scanning the two laser radars 6 have respective coordinate systems, and the point cloud coordinate systems are required to be unified through point cloud registration. And unifying the acquired two pieces of point cloud data under different coordinate systems into the same coordinate system through rotation and translation, and solving a rotation matrix and a translation matrix. Coarse registration is the basis of a point cloud registration process, and the main purpose is to obtain more corresponding points, so that two point clouds of a source can be overlapped as much as possible. The fine registration is to register again on the basis of the previous step, so as to improve the coincidence ratio of the two point clouds.
S4: and carrying out feature recognition on compartments 4 of different types of mining vehicles 1 according to the point cloud data of the mining vehicles 1.
The required point cloud data of the mine car 1 is obtained through the point cloud data preprocessing, and the S4 is mainly used for identifying and dividing the carriage 4 aiming at different types of mine cars 1, and dividing the carriage 4 and the mine car 1, so that later dimension measurement is facilitated.
And (4) fusing the processed mine car point cloud with the stand column standard point cloud when executing the step (S4), wherein the process is as follows:
s41: importing the processed mine car point cloud data into a standard point cloud of an upright post, and obtaining the relative position relationship between a standard point cloud model of the upright post and the mine car point cloud as shown in fig. 4;
s42: in the mine car point cloud, the distance between the stand column 7 and the laser radar 6 is fixed, so that the point cloud data of the stand column 7 is segmented from the mine car point cloud according to a known position relationship, and the scanning point cloud is registered to the standard stand column point cloud by using an ICP algorithm. As shown in fig. 5, the red point cloud is a standard point cloud of the column, and the blue point cloud is a scanning point cloud of the column. The conversion matrix calculated by the ICP algorithm is shown in fig. 6.
The position of the obstacle in the car influences the position of the feeding hole of the mine car 1, as shown in fig. 2, a cross beam 5 exists in a carriage 4 of the mine car 1, point cloud data of the mine car 1 acquired by the laser radar 6 are closely adjacent to point cloud of the obstacle point cloud clusters, a certain distance exists between different obstacle point cloud clusters, and according to the rule, the obstacle is clustered and segmented based on the Euclidean distance, so that the position of the obstacle is determined, and the feeding hole is not influenced by the obstacle during feeding.
S5: and calculating the length, width and height of the carriage 4 according to the calibration result of the step S2.
And S5, calculating the relative offset angle of the mine car 1, the length, width and height of the carriage 4 and the position of the obstacle in the car according to the calibration result of the S2, wherein an ICP algorithm is specific to measurement of each parameter.
The specific steps of the S5 are as follows:
s51: applying the transformation matrix calculated by ICP to mine car point cloud, and transforming mine car point cloud; as shown in fig. 7.
S52: the converted point cloud is shown in fig. 8, wherein the position of the upright post 7 is known, a certain point on the mine car 1 is arbitrarily selected to obtain the displacement relation of the point relative to the known position, and based on the relation, various parameters of the length, width and height of the mine car and the position of the obstacle in the car can be obtained as shown in fig. 9.
S6: and detecting a cross beam 5 or an in-car obstacle on the carriage 4, and guiding a feed opening.
And according to the detection of the carriage upper cross beam 5, the in-car obstacle and the like in S4 and S5, the specific position and the specific size are sent to the upper computer, and the upper computer guides the feed opening to move, so that automatic loading is realized.
S7: and monitoring the loading state of the mine car 1 in real time, predicting and guiding the action of the feed opening until the loading is completed.
The laser radar 6 monitors the loading state of the mine car 1 in real time, predicts and guides the action of the feed opening until the loading is completed.
The above disclosure is merely illustrative of specific embodiments of the present invention, but the present invention is not limited thereto, and any variations that can be considered by those skilled in the art should fall within the scope of the present invention.
Claims (9)
1. The real-time calibration method of the three-dimensional point cloud based on the field reference object is characterized by comprising the following steps of:
s1: accurately measuring the position of a fixed reference object, and calibrating an external parameter for the measurement of a later mine car (1);
s2: the laser radars (6) at the two sides extract building point clouds to finish calibration;
s3: the mine car (1) is driven into a mine car charging channel, the laser radars (6) at two sides acquire point clouds at two sides of the mine car (1), and the acquired point cloud images are preprocessed to filter background redundant point cloud data, so that point cloud downsampling is completed, point clouds are removed from the background, point clouds at two sides are fused, and processed point cloud data information is obtained;
s4: according to the point cloud data of the mine car (1), carrying out feature recognition on carriages (4) of different types of mine cars (1);
s5: calculating the length, width and height of the carriage (4) according to the calibration result of the step S2;
s6: detecting a cross beam (5) or an in-car obstacle on the carriage (4), and guiding a feed opening;
s7: and monitoring the loading state of the mine car (1) in real time, predicting and guiding the action of the feed opening until the loading is completed.
2. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 1, wherein the method comprises the following steps of: the mine car charging channel comprises a ground (3) and two side walls (2), symmetrical stand columns (7) are fixedly connected to the two side walls (2) respectively, the two side walls (2) are fixedly connected to the laser radar (6) respectively, and the stand columns (7) are fixed reference objects;
s21: firstly, selecting a calibration object in the real world, selecting four fixed upright posts (7) as the calibration object, manufacturing a standard model of the upright posts by using solidworks according to the position relation between the actual upright posts, and dispersing the standard model into point cloud data;
s22: and constructing a standard point cloud model of the upright column in the solidworks, taking the XOY surface as the bottom surface, taking one upright column (7) as the origin, and constructing a coordinate system of a known model to finish the calibration of the upright column (7).
3. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 2, wherein the method comprises the following steps of: each laser radar (6) is positioned in the middle of the symmetrical upright post (7).
4. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 1, wherein the method comprises the following steps of: the step S3 comprises the following steps:
s31: the method comprises the steps of performing downsampling processing on mine car point cloud data, performing downsampling simplification on the point cloud data by adopting a voxel filter, reducing the point density, simultaneously keeping the shape characteristics of the point cloud data, finding out the smallest cubic voxel grid according to the characteristics of the input point cloud data, selecting the side length of the cubic grid, changing the basis of the cubic grid into a plurality of small grids, dividing the point cloud into corresponding small grids, using the mass center of each small cube grid to represent other point clouds in the cube, and reducing the point cloud density by a mass center substitution method without establishing a topological structure between points;
s32: filtering background information point cloud through a filter, reserving mine car point cloud data, filtering out points with values not in a self-defined threshold range in a specified direction through the filter, and achieving the purposes of filtering and extracting a region of interest;
s33: the laser radars (6) on two sides collect point cloud data of the mine car (1), the point cloud data obtained by scanning the two laser radars (6) have respective coordinate systems, and the point cloud coordinate systems are required to be unified through point cloud registration.
5. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 4, wherein the method comprises the following steps of: s4 is mainly used for identifying and dividing the carriage (4) aiming at different types of mine cars (1), and dividing the carriage (4) and the mine cars (1) so as to facilitate later dimension measurement.
6. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 5, wherein the method comprises the following steps of: and (4) fusing the processed mine car point cloud with the stand column standard point cloud when executing the step (S4), wherein the process is as follows:
s41: importing the processed mine car point cloud data into a standard point cloud of an upright post to obtain a relative position relationship between a standard point cloud model of the upright post and the mine car point cloud;
s42: in the mine car point cloud, the distance between the stand column (7) and the laser radar (6) is fixed, so that the point cloud data of the stand column (7) are segmented from the mine car point cloud according to a known position relationship, and the scanning point cloud is registered to the standard point cloud of the stand column by using an ICP algorithm.
7. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 6, wherein the method comprises the following steps of: the position of the obstacle in the car influences the position of a feeding hole of the mine car (1) for feeding, point cloud data of the mine car (1) are acquired through the laser radar (6), point clouds of obstacle point cloud clusters are closely adjacent, a certain distance exists between different obstacle point cloud clusters, and according to the rule, the obstacle is clustered and segmented based on Euclidean distance, so that the position of the obstacle is determined, and the feeding hole is not influenced by the obstacle during feeding.
8. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 6, wherein the method comprises the following steps of: and S5, calculating the relative offset angle of the mine car (1), the length, width and height of the carriage (4) and the position of the obstacle in the car according to the calibration result of the S2, wherein an ICP algorithm is specific to measurement of each parameter.
9. The real-time calibration method of the three-dimensional point cloud based on the field reference object according to claim 8, wherein the method comprises the following steps of: the specific steps of the S5 are as follows:
s51: applying the transformation matrix calculated by ICP to mine car point cloud, and transforming mine car point cloud;
s52: the position of the upright post (7) is known, a certain point on the mine car (1) is arbitrarily selected to obtain the displacement relation of the point relative to the known position, and based on the relation, various parameters of the length, the width and the height of the mine car and the position of the obstacle in the car can be obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310886117.3A CN116934832A (en) | 2023-07-19 | 2023-07-19 | Real-time calibration method of three-dimensional point cloud based on field reference object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310886117.3A CN116934832A (en) | 2023-07-19 | 2023-07-19 | Real-time calibration method of three-dimensional point cloud based on field reference object |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116934832A true CN116934832A (en) | 2023-10-24 |
Family
ID=88378486
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310886117.3A Pending CN116934832A (en) | 2023-07-19 | 2023-07-19 | Real-time calibration method of three-dimensional point cloud based on field reference object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116934832A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117553686A (en) * | 2024-01-12 | 2024-02-13 | 成都航空职业技术学院 | Laser radar point cloud-based carriage bulk cargo overrun detection method |
-
2023
- 2023-07-19 CN CN202310886117.3A patent/CN116934832A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117553686A (en) * | 2024-01-12 | 2024-02-13 | 成都航空职业技术学院 | Laser radar point cloud-based carriage bulk cargo overrun detection method |
CN117553686B (en) * | 2024-01-12 | 2024-05-07 | 成都航空职业技术学院 | Laser radar point cloud-based carriage bulk cargo overrun detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110320504B (en) | Unstructured road detection method based on laser radar point cloud statistical geometric model | |
CN110780305A (en) | Track cone bucket detection and target point tracking method based on multi-line laser radar | |
CN106290388A (en) | A kind of insulator breakdown automatic testing method | |
CN114049294B (en) | Road surface technical condition detection method and equipment based on three-dimensional contour | |
CN115236628B (en) | Method for detecting residual cargoes in carriage based on laser radar | |
CN112698303A (en) | Method and system for measuring point cloud tower inclination parameters based on unmanned aerial vehicle laser radar | |
CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
CN116934832A (en) | Real-time calibration method of three-dimensional point cloud based on field reference object | |
CN115049700A (en) | Target detection method and device | |
CN113640821B (en) | Mine car loading capacity metering method based on single-line laser radar scanner scanning | |
CN115423824A (en) | Train carriage positioning and segmenting method based on point cloud voxel rectangular grid | |
CN113936215A (en) | Mining area road surface pit identification method and system and unmanned truck | |
CN115187964A (en) | Automatic driving decision-making method based on multi-sensor data fusion and SoC chip | |
CN117492026B (en) | Railway wagon loading state detection method and system combined with laser radar scanning | |
CN113362385A (en) | Cargo volume measuring method and device based on depth image | |
CN111768417A (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
Ma et al. | An intelligent object detection and measurement system based on trinocular vision | |
CN115761682A (en) | Method and device for identifying travelable area based on laser perception and intelligent mine card | |
CN114545877A (en) | Bulk cargo-oriented multi-engineering mechanical digital twin online monitoring system and method | |
CN102044155B (en) | Vehicle configuration dimension image detection and analysis device based on field programmable gate array (FPGA) | |
CN116524017B (en) | Underground detection, identification and positioning system for mine | |
CN113267124A (en) | Caving coal caving amount measuring system and caving coal control method based on laser radar | |
CN111275753B (en) | Method for measuring volume of sand and stone in carriage | |
CN113240682A (en) | Overturn-preventing construction driving map generation method and system for crawler crane | |
Giosan et al. | Superpixel-based obstacle segmentation from dense stereo urban traffic scenarios using intensity, depth and optical flow information |
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 |