CN115236628B - Method for detecting residual cargoes in carriage based on laser radar - Google Patents
Method for detecting residual cargoes in carriage based on laser radar Download PDFInfo
- Publication number
- CN115236628B CN115236628B CN202210886142.7A CN202210886142A CN115236628B CN 115236628 B CN115236628 B CN 115236628B CN 202210886142 A CN202210886142 A CN 202210886142A CN 115236628 B CN115236628 B CN 115236628B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- carriage
- data
- cloud data
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012937 correction Methods 0.000 claims abstract description 11
- 238000009499 grossing Methods 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 230000001788 irregular Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 claims description 2
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to a method for detecting carriage residual cargoes based on a laser radar, which is used for extracting carriage data in single-frame original data; extracting a carriage target point cloud, and performing inclination correction on the acquired single-frame point cloud contour; acquiring a current vehicle speed, converting a coordinate system taking a radar as an origin into a coordinate system taking the bottom of a carriage as a center, and splicing single-frame point clouds to form a carriage integral point cloud image; noise reduction and simplification of carriage point cloud data; smoothing the spliced carriage point cloud data; slicing the carriage point cloud data; projecting point clouds between two adjacent slices, and extracting a cross section profile; for the extracted section profile, obtaining the section area, and multiplying the section area by the section spacing to obtain the section-to-point cloud volume; and accumulating and calculating the volume of the residual cargoes in the carriage. The invention can automatically detect the goods residue condition in the train carriage without stopping, does not need the worker to climb into the carriage for observation, reduces the labor intensity of the worker, improves the working safety, and has high automatic detection efficiency and good accuracy.
Description
Technical Field
The invention relates to a method for detecting residual cargos in a carriage, in particular to a method for detecting residual cargos in a carriage based on a laser radar.
Background
The residual freight in the railway carriage is a common phenomenon for railway freight vehicles, and the carriage loading articles cannot be completely unloaded during unloading operation due to the shape and characteristics of the carriage loading articles or due to weather and the like. For residual cargoes, workers often need to climb to the upper surface of the carriage by means of tools to observe the residual condition of the cargoes in the box body, and then the corresponding number of workers are arranged to enter the carriage for cleaning according to the residual quantity, so that the phenomenon of ton shortage is avoided. The manual detection method has the potential safety hazard problem, influences the normal operation of the train, increases the labor intensity of workers and has low working efficiency.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for detecting the residual cargoes in a carriage based on a laser radar, which has the advantages of no influence on the running of a train, convenient residue detection, no need of checking by workers when boarding, high safety and high efficiency.
In order to achieve the above purpose, the present invention provides the following technical solutions: a method for detecting carriage residual cargoes based on a laser radar is characterized by comprising the following steps:
S10, extracting carriage data in single-frame original data by adopting a cluster analysis method based on Euclidean distance, judging the front and rear boundaries of the carriage by utilizing a three-dimensional coordinate relationship, and acquiring the data information of a first frame and a last frame;
S20, extracting a carriage target point cloud by adopting a conditional filtering method, and performing inclination correction on the acquired single-frame point cloud contour;
S30, acquiring a current vehicle speed by using a preset radar, converting a coordinate system taking the radar as an origin into a coordinate system taking the bottom of a carriage as a center, and splicing single-frame point clouds by using a displacement fusion algorithm to form a carriage integral point cloud image;
s40, adopting a statistical filtering and voxelized grid method to reduce noise and simplify the carriage point cloud data;
s50, smoothing the spliced carriage point cloud data by using a mobile least square method;
S60, slicing the carriage point cloud data along the running direction of the vehicle;
S70, projecting point clouds between two adjacent slices, and extracting a section profile by using an alpha algorithm and a ray 360-degree algorithm;
s80, for the extracted cross section outline, obtaining the cross section area by utilizing shoelace theorem, and multiplying the cross section area by the slice spacing to obtain the volume from the segment to the point cloud; and accumulating and calculating the volume of the residual cargoes in the carriage.
Further, the performing conditional filtering and contour correction on the point cloud in step S20 includes: and selecting a stationary point cloud of the frame scanning according to the frame data obtained by scanning, searching the same column of point cloud data, analyzing coordinate values of the same column of point cloud data, fitting and calculating a deflection angle, and carrying out rotation correction on the whole point cloud data.
Further, the step S30 of converting the coordinate system and splicing the point cloud includes: based on the coordinate system with the radar as the origin, converting the coordinate system into the coordinate system with the carriage as the origin, determining a coordinate value conversion relation according to the radar installation position relation, and completing the coordinate system conversion; according to the point cloud splicing method based on the mobile displacement fusion, all frames of point cloud data are corrected to the same frame of coordinate system in a unified mode through giving new Z-axis coordinate values to the point cloud, and point cloud splicing is completed.
Further, the method for statistically filtering and voxelizing the grid in step S40 includes: the average interval distribution relation from the sampling point to the neighborhood point accords with a Gaussian distribution function, and outlier point cloud data are removed through a set reasonable threshold value; and downsampling the point cloud data by using a voxelized grid method, and dropping the point cloud data into grids with a specified size, wherein each grid only retains the point cloud nearest to the center of the grid, and the rest point clouds in the grid are deleted, so that the effect of simplifying the point clouds is achieved.
Further, the slicing the point cloud data in the step S60 includes: and intercepting the carriage point cloud data by using a tangent plane parallel to the section of the carriage along the running direction of the vehicle at certain interval intervals to form a section of scattered point cloud data. The larger the spacing, the more the number of point cloud segments cut, and vice versa.
Further, the extracting the point cloud contour in step S70 includes: projecting point clouds between adjacent slices, and determining a rough boundary contour by using an alpha algorithm; and then adopting a ray 360-degree scanning algorithm to carry out secondary discrimination on the boundary contour, and eliminating the boundary point cloud data which do not meet the conditions. The accuracy of the boundary contour is improved.
Further, the calculating the point cloud volume in step S80 includes: the shoelace theorem is adopted to calculate the cross-sectional area of the point cloud of the irregular polygon, the cross-sectional area is multiplied by the slicing interval to obtain the volume of the point cloud data of the section, and the integral point cloud volume of the carriage is obtained through accumulation; and obtaining the volume of the residual cargoes of the carriage by using the difference between the volume of the point cloud of the empty carriage and the volume of the carriage when the residual cargoes exist.
Compared with the prior art, the invention can automatically detect the goods residue condition in the train carriage without stopping, does not need a worker to climb into the carriage for observation, reduces the labor intensity of the worker, improves the working safety, and has high automatic detection efficiency and good accuracy; the invention can not only identify the area and the volume of the residual cargoes in the railway carriage, but also detect the loading of materials such as scattered sand, scattered stone and the like on the highway truck, and can calculate the mass of the transfer load according to the density of the loaded materials so as to judge the overload condition of the truck.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of car data according to an embodiment of the present invention;
FIG. 3 is a diagram showing a judgment of a boundary of a vehicle compartment according to an embodiment of the present invention;
FIG. 4 is a diagram of the cause of the inclination of the point cloud profile of the carriage according to the embodiment of the invention;
FIG. 5 is a single frame point cloud data correction chart according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of coordinate system conversion according to an embodiment of the present invention;
FIG. 7 is a graph of a point cloud of an original carriage spliced based on movement displacement according to an embodiment of the invention;
FIG. 8 is a diagram of a voxel grid method and a point cloud smoothing result according to an embodiment of the present invention;
FIG. 9 is a cross-sectional view of an empty car outline according to an embodiment of the present invention;
FIG. 10 is a cross-sectional view of a car outline with residue in accordance with an embodiment of the present invention;
Fig. 11 is a schematic diagram of irregular polygon area calculation according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides a technical scheme, a method for detecting residual cargoes in a carriage based on a laser radar, which comprises the following steps:
S10, extracting carriage data in single-frame original data by adopting a cluster analysis method based on Euclidean distance, judging the front and rear boundaries of the carriage by utilizing a three-dimensional coordinate relationship, and acquiring the data information of a first frame and a last frame;
Preprocessing point cloud initial data by adopting a cluster analysis algorithm based on Euclidean distance, and clustering the conditions: the search radius of the neighbor search is 0.2 meter, the minimum clustering point number is 1000, and the maximum clustering point number is 5000; the specific implementation steps are as follows:
(1) A point P 10 in space is found, the n closest points to him are found kdTree, and the distances of these n points to P 10 are determined. Point P at which the distance is less than the threshold r 12,P13,P14..placing in class Q;
(2) Finding a point P 12 in Q (P 10), repeating (1);
(3) Find one point at Q (P 10,P12), repeat (1), find P 22,P23,P24.
(4) When Q can not be added with new points any more, the search is completed.
As shown in fig. 2 and 3, if the radar XOY plane is completely perpendicular to the running direction of the train, assuming that the width of a car is 3.3 meters and the height is 2.8 meters, in the car boundary determination, the point M is the highest point of the car, the point M coordinates are (X m,ymax,zm), the point N is the lowest point of the car, the point N coordinates are (X n,ymin,zn), and it is known from the three-dimensional coordinate relationship:
ymax-ymin＝2.8，
Wherein y max is the highest point M point y coordinate, y min is the lowest point N point y coordinate, the carriage height is 2.8 meters, carriage point cloud data are processed, the left side wall and the right side wall of the carriage are respectively hidden by 0.5 meter, if the change amplitude of y max and y min of the hidden point cloud data is smaller, namely the difference between y max and y min is larger than a certain threshold t, the current carriage data are judged to be carriage boundary data, otherwise, the current carriage data are judged to be non-carriage boundary data. When the carriage boundary information appears for the first time, starting to record data information; when the carriage data appears last time, stopping recording the data information to obtain a complete carriage data information.
S20, extracting a carriage target point cloud by adopting a conditional filtering method, and performing contour inclination correction on the acquired single-frame point cloud data;
If the radar XOY plane is completely perpendicular to the running direction of the train, the laser points scanned by the same column should be on the same horizontal line, as shown in fig. 4 (a); if the radar XOY plane is not perpendicular to the running direction of the train, an inclined included angle appears, and then the points of the same column of data also show an inclined state, as shown in fig. 4 (b); the static point cloud correction-based method comprises the following steps:
(1) Selecting a frame of point cloud data of measurement scanning, selecting stationary objects around the scanned objects as a reference system (the invention selects a wall beside a track), and extracting the whole data of the point cloud of the reference system;
(2) Performing inverse operation according to the three-dimensional coordinates of the point cloud data to obtain the number of columns of radar scanning of the point cloud;
(3) Extracting data Q= { P 0,P1......P15 }, wherein the X and Y coordinate values of the data are approximately the same, and the Z-axis data are gradually changed according to a certain trend;
(4) Fitting a straight line according to the scatter images of the Z-axis coordinates, calculating a fitting straight line equation, and obtaining an included angle theta z relative to the Z axis by using atan;
(5) And determining a rotation matrix and a rotation direction through the angle theta, and realizing rotation transformation on the frame point cloud.
As shown in fig. 5, the white point cloud is corrected data, and the gray point cloud is data before correction.
S30, acquiring a current vehicle speed by using a preset radar, converting a coordinate system taking the radar as an origin into a coordinate system taking the bottom of a carriage as a center, and splicing single-frame point clouds by using a displacement fusion algorithm to form a carriage integral point cloud image;
As shown in fig. 6, a point a is a scanning point in the carriage, h is a vertical distance from the laser radar to the vehicle bottom, under the radar coordinate system, the coordinates of the point a are output as (x, y, z) through internal processing of the laser radar, after the coordinate system is converted, O 1 is used as an origin of coordinates, OO 1 is located on the same straight line, the coordinates of the point a are (x 1,y1,z1), according to the positional geometry relationship,
As shown in fig. 7, the method of the present application is based on the method of mobile displacement fusion compensation, and a new Z value is given to the scanned point cloud Z axis coordinate. And respectively translating the point cloud data of each frame in the forward direction of the train according to the total frame number of the scanning point cloud and the scanning sequence to obtain a complete point cloud image based on a carriage coordinate system. Assuming that the speed of the train moving forward at a constant speed is V, the working frequency of the laser radar is 10Hz, the distance length of the train moving along the Z-axis direction within 0.1 second is V/10, and the displacement compensation is carried out on the point cloud data:
Zij′＝Zij±(n-i)*v/10
wherein Z ij' represents the Z coordinate value of the j point in the i-th frame point cloud data after displacement compensation, Z i represents the Z coordinate value of the j point in the i-th frame point cloud data under the original coordinate system, n is the recorded point cloud frame number, and i is the current frame number. When the Z-axis direction of the laser radar is the same as the running direction of the train, the sign of "+" is given to the above formula, and otherwise the sign of "-" is given to the above formula.
S40, adopting a statistical filtering and voxelized grid method to reduce noise and simplify the carriage point cloud data;
as shown in fig. 8, the statistical filtering steps are as follows:
(1) Establishing a point cloud topological structure relationship for the target point cloud through the KD-tree;
(2) Searching a neighborhood of the sampling points through indexes, and calculating the average Euclidean distance from each sampling point to a neighborhood range point;
(3) Calculating the average distance from all points in the point cloud data set to the neighborhood;
(4) The obtained distance distribution accords with a Gaussian function, so that a mean value mu and a standard deviation sigma are calculated;
(5) And setting a threshold value and eliminating noise data. As can be seen from gaussian distribution characteristics, points in the range of (μ - σstd, μ+σstd), where std is called standard deviation multiple, belong to the effective point cloud, and are used to adjust the set threshold range. If the value of a certain sampling point d i is greater than μ+σstd or less than μ - σstd, the noise point is determined, and filtering is performed.
Voxel grid selection the grid with the size of 0.1m realizes the compaction of the point cloud data.
S50, smoothing the spliced carriage point cloud data by using a mobile least square method; the basic steps of the mobile least squares method are as follows:
(1) Inputting a fitting data point region, and performing gridding operation on the input region;
(2) Determining the range of the influence area of the grid point x, and determining the number of nodes influenced in the range; calculating node values of the grid points according to a formula;
(4) Traversing all grid points, and repeating the steps (2) and (3);
(5) The values calculated at the grid points are connected to form a smooth curve.
S60, slicing the carriage point cloud data along the running direction of the vehicle;
As the advancing direction of the train is a positive half axis of the Z axis, the Z axis is selected as the cutting direction, and the carriage model point cloud is divided into a plurality of sections. The density of the point cloud is limited, and it is difficult to form the shape outline of the point cloud simply by means of a single thin plane, so that it is required that this plane has a certain "thickness". The equidistant point cloud segments are just formed between two adjacent slices, so that the outline of the point cloud segments can be obtained by directly projecting the point cloud between two slice planes:
Where i is the serial number of the slice, Z i is the position of the tangent plane, l is the spacing distance of the slice, Z min and Z max represent the minimum and maximum values of the point cloud coordinates in the Z-axis direction, respectively, and n is the number of the tangent planes.
S70, projecting point clouds between two adjacent slices, and extracting a section profile by using an alpha algorithm and a ray 360-degree algorithm;
the generated point cloud is projected on an XOY plane, the rough point cloud outline is extracted by using an alpha algorithm, and then the outline is screened by a ray 360 degree algorithm, as shown in fig. 9 and 10, the ray 360 degree algorithm comprises the following steps:
(1) Gravity center O point mark of calculation request point cloud
(2) Any point P 0(x0,y0) is taken as an initial scanning point, an OP 0 is connected as a reference scanning ray, and the rest data points are scanned in the anticlockwise direction of the scanning line;
(3) Calculating included angles theta i between the rest scanning points and the datum line;
(4) And sorting according to the calculated included angles theta i, and sequentially connecting the point clouds according to the sequence, so as to form the outline of the point cloud.
S80, for the extracted cross section outline, obtaining the cross section area by utilizing shoelace theorem, and multiplying the cross section area by the slice spacing to obtain the volume from the segment to the point cloud; and calculating the volume of the residual cargoes in the carriage through accumulation.
As shown in fig. 11, the shoelace theorem is that the area of the closed image is calculated by determinant calculation in the case where the vertex coordinates of the polygon are known. The specified irregular section is composed of n vertexes P 1,P2...Pn, the ordered points are connected end to end according to a counterclockwise sequence according to a ray scanning method, a closed polygon is formed and is marked as P i, and the calculated section area A i is as follows in the deduction process:
Where a i is the area of the ith polygonal cross section, and the polygon vertex P i coordinates (x i,yi),xn＝x1,yn＝y1).
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the invention, but any minor modifications, equivalents, and improvements made to the above embodiments according to the technical principles of the present invention should be included in the scope of the technical solutions of the present invention.
Claims (6)
1. The method for detecting the residual cargoes in the carriage based on the laser radar is characterized by comprising the following steps of:
S10, extracting carriage data in single-frame original data by adopting a cluster analysis method based on Euclidean distance, judging the front and rear boundaries of the carriage by utilizing a three-dimensional coordinate relationship, and acquiring the data information of a first frame and a last frame;
S20, extracting a carriage target point cloud by adopting a conditional filtering method, and performing inclination correction on the acquired single-frame point cloud contour;
S30, acquiring a current vehicle speed by using a preset radar, converting a coordinate system taking the radar as an origin into a coordinate system taking the bottom of a carriage as a center, and splicing single-frame point clouds by using a displacement fusion algorithm to form a carriage integral point cloud image;
s40, adopting a statistical filtering and voxelized grid method to reduce noise and simplify the carriage point cloud data;
s50, smoothing the spliced carriage point cloud data by using a mobile least square method;
S60, slicing the carriage point cloud data along the running direction of the vehicle;
S70, projecting point clouds between two adjacent slices, and extracting a section profile by using an alpha algorithm and a ray 360-degree algorithm;
S80, for the extracted cross section outline, obtaining the cross section area by utilizing shoelace theorem, and multiplying the cross section area by the slice spacing to obtain the volume from the segment to the point cloud; accumulating and calculating the volume of the residual cargoes in the carriage;
The calculating the point cloud volume in step S80 includes: the shoelace theorem is adopted to calculate the cross-sectional area of the point cloud of the irregular polygon, the cross-sectional area is multiplied by the slicing interval to obtain the volume of the point cloud data of the section, and the integral point cloud volume of the carriage is obtained through accumulation; and obtaining the volume of the residual cargoes of the carriage by using the difference between the volume of the point cloud of the empty carriage and the volume of the carriage when the residual cargoes exist.
2. The method for detecting residual cargo in a vehicle cabin based on a lidar as defined in claim 1, wherein the performing conditional filtering and contour correction on the point cloud in step S20 comprises: and selecting a stationary point cloud of the frame scanning according to the frame data obtained by scanning, searching the same column of point cloud data, analyzing coordinate values of the same column of point cloud data, fitting and calculating a deflection angle, and carrying out rotation correction on the whole point cloud data.
3. The method for detecting residual cargoes in a car based on the lidar according to claim 1, wherein the converting the coordinate system and the stitching the point cloud in step S30 comprises: based on the coordinate system with the radar as the origin, converting the coordinate system into the coordinate system with the carriage as the origin, determining a coordinate value conversion relation according to the radar installation position relation, and completing the coordinate system conversion; according to the point cloud splicing method based on the mobile displacement fusion, all frames of point cloud data are corrected to the same frame of coordinate system in a unified mode through giving new Z-axis coordinate values to the point cloud, and point cloud splicing is completed.
4. A method for detecting residual cargo in a vehicle cabin based on a lidar as defined in claim 1, wherein the method for statistically filtering and voxel-forming the grid in step S40 comprises: the average interval distribution relation from the sampling point to the neighborhood point accords with a Gaussian distribution function, and outlier point cloud data are removed through setting a threshold value; and downsampling the point cloud data by using a voxelized grid method, and dropping the point cloud data into grids with a specified size, wherein each grid only retains the point cloud nearest to the center of the grid, and the rest point clouds in the grid are deleted.
5. The method for detecting residual cargo in a vehicle cabin based on a lidar as defined in claim 1, wherein the slicing of the point cloud data in step S60 comprises: and intercepting the carriage point cloud data by using a tangent plane parallel to the section of the carriage along the running direction of the vehicle at intervals to form a section of scattered point cloud data.
6. The method for detecting residual cargo in a vehicle cabin based on a lidar as defined in claim 1, wherein the extracting the point cloud profile in step S70 comprises: projecting point clouds between adjacent slices, and determining a rough boundary contour by using an alpha algorithm; and then adopting a ray 360-degree scanning algorithm to carry out secondary discrimination on the boundary contour, and eliminating the boundary point cloud data which do not meet the conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210886142.7A CN115236628B (en) | 2022-07-26 | 2022-07-26 | Method for detecting residual cargoes in carriage based on laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210886142.7A CN115236628B (en) | 2022-07-26 | 2022-07-26 | Method for detecting residual cargoes in carriage based on laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115236628A CN115236628A (en) | 2022-10-25 |
| CN115236628B true CN115236628B (en) | 2024-05-31 |
Family
ID=83675499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210886142.7A Active CN115236628B (en) | 2022-07-26 | 2022-07-26 | Method for detecting residual cargoes in carriage based on laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115236628B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115423835B (en) * | 2022-11-02 | 2023-03-24 | 中汽创智科技有限公司 | Rod-shaped object point cloud data processing method and device, electronic equipment and storage medium |
| CN115724221A (en) * | 2022-11-15 | 2023-03-03 | 大连科润重工起重机有限公司 | Intelligent bulk material feeding system |
| CN115984195B (en) * | 2022-12-16 | 2023-09-29 | 秦皇岛燕大滨沅科技发展有限公司 | Carriage contour detection method and system based on three-dimensional point cloud |
| CN115856923B (en) * | 2023-02-27 | 2023-06-16 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Method, device, equipment and storage medium for measuring ore card unloading time |
| CN115862001A (en) * | 2023-03-02 | 2023-03-28 | 青岛慧拓智能机器有限公司 | Surface mine carriage residue detection method and system based on volume measurement |
| CN116148809B (en) * | 2023-04-04 | 2023-06-20 | 中储粮成都储藏研究院有限公司 | Automatic generation method and system for grain vehicle sampling point based on laser radar scanning and positioning |
| CN117314903B (en) * | 2023-11-28 | 2024-03-15 | 四川港投云港科技有限公司 | 3D point cloud data processing method for bulk commodity indoor warehouse laser radar |
| CN117492026B (en) * | 2023-12-29 | 2024-03-15 | 天津华铁科为科技有限公司 | Railway wagon loading state detection method and system combined with laser radar scanning |
| CN118392191B (en) * | 2024-06-28 | 2024-08-23 | 睿羿科技(山东)有限公司 | Method for covering operation of unmanned sweeper in indoor unknown environment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113280733A (en) * | 2021-04-07 | 2021-08-20 | 深圳市异方科技有限公司 | Truck carriage volume measurement method and system based on laser radar |
| CN113554689A (en) * | 2021-07-19 | 2021-10-26 | 广州市杜格科技有限公司 | Method and device for measuring carriage cargo volume, equipment and storage medium |
| WO2022141914A1 (en) * | 2021-01-01 | 2022-07-07 | 杜豫川 | Multi-target vehicle detection and re-identification method based on radar and video fusion |
-
2022
- 2022-07-26 CN CN202210886142.7A patent/CN115236628B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022141914A1 (en) * | 2021-01-01 | 2022-07-07 | 杜豫川 | Multi-target vehicle detection and re-identification method based on radar and video fusion |
| CN113280733A (en) * | 2021-04-07 | 2021-08-20 | 深圳市异方科技有限公司 | Truck carriage volume measurement method and system based on laser radar |
| CN113554689A (en) * | 2021-07-19 | 2021-10-26 | 广州市杜格科技有限公司 | Method and device for measuring carriage cargo volume, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 基于切片方法截面数据处理;龚友平;陈国金;陈立平;;计算机辅助设计与图形学学报;20080315(第03期);全文 * |
| 基于地面激光雷达的洞库容量计量;程效军;熊鑫鑫;杨泽鑫;杨荣淇;;激光与光电子学进展;20191210(第23期);全文 * |
| 基于激光雷达探测技术的列车车厢载货体积测量方法研究;孔德明;张娜;黄紫双;陈晓玉;沈阅;;燕山大学学报;20190331(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115236628A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115236628B (en) | Method for detecting residual cargoes in carriage based on laser radar | |
| CN112465948B (en) | Vehicle-mounted laser pavement point cloud rarefying method capable of retaining spatial features | |
| CN110969624B (en) | Laser radar three-dimensional point cloud segmentation method | |
| CN106780524B (en) | Automatic extraction method for three-dimensional point cloud road boundary | |
| CN108074232B (en) | Voxel segmentation-based airborne LIDAR building detection method | |
| CN111325138B (en) | Road boundary real-time detection method based on point cloud local concave-convex characteristics | |
| CN110390683A (en) | A kind of Old City Wall three-dimensional cracking detection method based on point off density cloud | |
| CN107644452A (en) | Airborne LiDAR point cloud roof dough sheet dividing method and system | |
| CN113487479B (en) | Method and system for detecting and identifying high-precision map boundary at vehicle end in real time | |
| CN112099046B (en) | Airborne LIDAR three-dimensional plane detection method based on multi-value voxel model | |
| CN115423824A (en) | Train carriage positioning and segmenting method based on point cloud voxel rectangular grid | |
| CN112465991B (en) | Method for denoising tunnel point cloud and generating visual model | |
| CN117011309B (en) | Automatic coal-coiling system based on artificial intelligence and depth data | |
| CN113936215A (en) | Mining area road surface pit identification method and system and unmanned truck | |
| CN116843742B (en) | Calculation method and system for stacking volume after point cloud registration for black coal loading vehicle | |
| CN117760342A (en) | Laser point cloud-based outer wall flatness detection method | |
| CN113077473B (en) | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium | |
| CN115856923A (en) | Measuring method, device, equipment and storage medium for unloading of mine truck | |
| CN116012613B (en) | Method and system for measuring and calculating earthwork variation of strip mine based on laser point cloud | |
| CN116379956A (en) | Method and system for detecting tunnel super-undermining state | |
| CN116934832A (en) | Real-time calibration method of three-dimensional point cloud based on field reference object | |
| CN111723797B (en) | Method and system for determining bounding box of three-dimensional target | |
| CN114202631A (en) | Method for determining rock working face and working point in secondary rock crushing operation | |
| CN112862844A (en) | Road boundary interactive extraction method based on vehicle-mounted point cloud data | |
| CN115824070B (en) | Rail part size measurement method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |