CN112529958A - Single laser radar bulk cargo ship hatch position identification method - Google Patents
Single laser radar bulk cargo ship hatch position identification method Download PDFInfo
- Publication number
- CN112529958A CN112529958A CN202011434857.6A CN202011434857A CN112529958A CN 112529958 A CN112529958 A CN 112529958A CN 202011434857 A CN202011434857 A CN 202011434857A CN 112529958 A CN112529958 A CN 112529958A
- Authority
- CN
- China
- Prior art keywords
- hatch
- point cloud
- point
- contour
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013507 mapping Methods 0.000 claims abstract description 13
- 238000002310 reflectometry Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 10
- 238000003672 processing method Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 7
- 239000003245 coal Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method 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
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G06T3/06—
-
- G06T3/08—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
A single laser radar bulk cargo ship hatch position identification method belongs to the technical field of cabin opening position identification. The method solves the problems that errors exist when the prior method is adopted to identify the bulk cargo ship hatch and the spatial information of the four side planes of the cabin cannot be identified. The method is based on point cloud spherical mapping, the point cloud is converted into an image, the image processing method is used for identifying and positioning the hatch, and then the position of the hatch in the three-dimensional space is calculated by using point cloud inverse mapping. The advantage that the point cloud can store three-dimensional space information is combined with the advantage that the image processing operation amount is relatively small, the identification of the cargo ship hatch position is achieved, and meanwhile the space information of the hatch four-wall plane is identified. The invention can be applied to the position identification of the cabin opening.
Description
Technical Field
The invention belongs to the technical field of position identification of a hold opening, and particularly relates to a method for identifying the position of a hatch opening of a bulk cargo ship by using a single laser radar.
Background
Along with the development of economy in China, the freight volume of bulk cargos in bulk cargo wharfs, particularly bulk cargos, is continuously increased, the unmanned ship loading operation is realized, the efficiency of the bulk cargo ship transferring operation can be improved, the operation reliability is enhanced, the working risk of personnel is reduced, and the identification of the position of a hatch is realized, so that the method is a key step in the unmanned ship loading operation. The use of lidar to acquire point cloud data has long and stable applications in the fields of industrial production, unmanned driving, and the like. Compared with a common camera, the laser radar has strong penetrating power and low requirement on illumination conditions, and is particularly suitable for a working environment with large dust at a coal wharf.
There have been many research achievements in directly processing point cloud data, and an open source algorithm library pcl (point closed library) and MeshLab may be used for point cloud processing, including down-sampling point cloud, filtering and denoising, geometric feature extraction, and the like. But the amount of calculation for directly processing the point cloud is large, and the difficulty of algorithm design is high. Compared with the point cloud processing technology, the image processing technology is more mature, and the computation amount is small when the geometric features are extracted.
Most of the existing published hatch identification technologies convert point clouds collected by a laser radar into a cargo ship deck plane coordinate system, or consider that a deck plane is parallel to a world reference coordinate system coordinate axis, and then project the point clouds on the deck plane to generate a depth map, and consider that a cabin is a rectangle in the projection depth map by default, and then identify a rectangular frame by using an image processing technology. Problems with such methods are: (1) in the actual shipping operation, a cargo ship can have certain shaking, namely the conversion relation between a deck plane and a world reference coordinate system is changed, and a depth map generated by directly projecting on the deck plane can have errors, so that identification errors are brought; (2) only the edge lines of the hatches can be identified, while the actual shipping workspace lacks spatial information on the four-sided plane of the hold in three-dimensional space.
Disclosure of Invention
The invention aims to solve the problems that an error exists when the prior method is adopted to identify the hatch of a bulk cargo ship and the spatial information of the four side planes of a cabin cannot be identified, and provides a method for identifying the position of the hatch of the bulk cargo ship by using a single laser radar.
The technical scheme adopted by the invention for solving the technical problems is as follows: a single laser radar bulk cargo ship hatch position identification method specifically comprises the following steps:
arranging and installing a laser radar on a ship loader, and ensuring that point cloud data acquired by the laser radar comprises a cargo ship hatch through adjusting a visual angle, wherein the acquired point cloud data takes the cargo ship as a main body;
secondly, preprocessing the collected point cloud data to obtain preprocessed point cloud data;
performing cluster analysis on the preprocessed point cloud data to obtain a plurality of groups of point cloud sets, wherein the set containing the most point cloud data is used as a ship body point cloud data set;
step four, setting a point cloud reflectivity intensity threshold value IthFor step three, obtainScreening the point cloud data in the obtained ship body point cloud data set, and enabling the point cloud data to be more than or equal to a reflectivity intensity threshold value IthScreening out point cloud data;
step five: acquiring an angular range of point cloud data acquired by the laser radar, performing spherical mapping on the point cloud data screened in the fourth step, and converting the point cloud data into a single-channel image;
step six: performing morphological 'closing' operation on the single-channel image obtained in the step five to form a connected domain image;
step seven: carrying out contour extraction on the connected domain graph generated in the step six to obtain a plurality of contour point sets; and screening the obtained Contour point set to obtain Contour point set Contour of the hatchhatch;
Step eight, carrying out Contour on the Contour point set obtained in the step sevenhatchSolving the bounding box with the minimum area to obtain four vertexes P of the bounding boxminBox1、PminBox2、PminBox3、PminBox4The four vertexes are sequentially connected end to form four edges of the hatch outline;
step nine, respectively calculating the distance from any point in the contour point set of the hatch to four edges, if the distance from the point to a certain edge is smaller than a threshold value corresponding to the edge, the point belongs to the edge, and after traversing all points in the contour point set of the hatch, respectively extracting a data point set of each edge of the contour of the hatch;
step ten, carrying out point cloud spherical surface inverse mapping on the data point set of each edge of the hatch outline extracted in the step nine to obtain four groups of three-dimensional point cloud sets hashpart1、hatchpart2、hatchpart3、hatchpart4;
Step eleven, performing plane fitting on each group of three-dimensional point cloud sets obtained in the step eleven to obtain four fitting planes, and taking the four fitting planes as the four-wall plane of the hatch;
step twelve: and respectively calculating the distances of the four walls of the hatch relative to the plane to obtain the space size of the hatch.
The invention has the beneficial effects that: the invention provides a single laser radar bulk cargo ship hatch position identification method. The advantage that the point cloud can store three-dimensional space information is combined with the advantage that the image processing operation amount is relatively small, the identification of the cargo ship hatch position is achieved, and meanwhile the space information of the hatch four-wall plane is identified. The method solves the problem that the hatch identification error exists due to the shaking of the cargo ship in the prior art.
Drawings
FIG. 1 is a diagram of raw point cloud data collected by the present invention;
FIG. 2 is a point cloud data diagram after downsampling by using a voxel grid method;
FIG. 3 is a ship body point cloud data diagram extracted after Euclidean clustering segmentation;
FIG. 4 is a graph of the results of filtering coal point cloud data within a bay;
FIG. 5 is a diagram of the result of spherical mapping of point cloud data;
FIG. 6 is a graph of the results of the image morphological "close" processing;
FIG. 7 is a graph of the recognition result of a contour point set of hatches;
FIG. 8 is a graph of the results of calculation of minimum area bounding boxes for a cabin profile;
FIG. 9 is a diagram of the segmentation result of the four-sided pixel point set of the hatch contour;
fig. 10 is a diagram showing the results of recognition of the four-wall plane of the hatch.
Detailed Description
The first embodiment is as follows: the method for identifying the hatch position of the single laser radar bulk cargo ship specifically comprises the following steps:
arranging and installing a laser radar on a ship loader, and ensuring that point cloud data acquired by the laser radar comprises a cargo ship hatch through adjusting a visual angle, wherein the acquired point cloud data takes the cargo ship as a main body;
the acquired original point cloud data is shown in fig. 1;
secondly, preprocessing the collected point cloud data to obtain preprocessed point cloud data;
performing cluster analysis on the preprocessed point cloud data to obtain a plurality of groups of point cloud sets, wherein the set containing the most point cloud data is used as a ship body point cloud data set;
step four, setting a point cloud reflectivity intensity threshold value IthScreening the point cloud data in the ship body point cloud data set obtained in the step three, and enabling the point cloud data to be larger than or equal to a reflectivity intensity threshold value IthScreening out point cloud data;
reflectance intensity threshold IthThe value of the point cloud is determined according to data obtained by actual field testing, and the point cloud of the ship body obtained by the segmentation in the step three possibly contains coal in the hatch, which can cause certain interference on hatch identification. The coal is pure black, and the infrared reflectivity of the coal is obviously lower than that of the hatch, so the filtering is carried out according to the point cloud data point reflectivity intensity, the coal point cloud is filtered, and the filtering result is shown in figure 4;
step five: acquiring an angular range of point cloud data acquired by the laser radar, performing spherical mapping on the point cloud data screened in the fourth step, and converting the point cloud data into a single-channel image;
step six: performing morphological 'closing' operation on the single-channel image obtained in the step five to form a connected domain image; as shown in fig. 6;
step seven: carrying out contour extraction on the connected domain graph generated in the step six to obtain a plurality of contour point sets; and screening the obtained Contour point set to obtain Contour point set Contour of the hatchhatch;
Step eight, carrying out Contour on the Contour point set obtained in the step sevenhatchSolving the bounding box with the minimum area to obtain four vertexes P of the bounding boxminBox1、PminBox2、PminBox3、PminBox4The four vertexes are sequentially connected end to form four edges of the hatch outline; as shown in fig. 8;
step nine, respectively calculating the distance from any point in the contour point set of the hatch to four edges, if the distance from the point to a certain edge is smaller than a threshold value corresponding to the edge, the point belongs to the edge, and after traversing all points in the contour point set of the hatch, respectively extracting a data point set of each edge of the contour of the hatch; as shown in fig. 9;
step ten, carrying out point cloud spherical surface inverse mapping on the data point set of each edge of the hatch outline extracted in the step nine, converting the data point set into a three-dimensional space, and obtaining four groups of three-dimensional point cloud sets hashpart1、hatchpart2、hatchpart3、hatchpart4;
Step eleven, performing plane fitting on each group of three-dimensional point cloud sets obtained in the step eleven to obtain four fitting planes, and taking the four fitting planes as the four-wall plane of the hatch;
fitting the planes to obtain an equation Ax + By + Cz (D) of the four spatial planes, and obtaining the positions of the four-wall planes of the hatch in the space;
step twelve: and respectively calculating the distances of the four walls of the hatch relative to the plane to obtain the space size of the hatch.
Thus, the hatch recognition of the bulk cargo ship is completed, and the recognition result is shown in fig. 10.
The invention has the advantages that: (1) the identification is directly carried out in a laser radar coordinate system without depending on the conversion relation between the deck plane of the cargo ship and the laser radar coordinate system, the laser radar is fixedly arranged on the ship loader, the identification result can be directly converted into the ship loader coordinate system, and the identification precision is not influenced by the shaking of the cargo ship; (2) the point cloud spherical mapping is lossless reversible transformation, namely the point cloud can still be converted back to the point cloud through inverse transformation after being converted into a plane image, and spatial three-dimensional information can be reserved; (3) the plane parameters of the four walls of the cabin can be identified and calculated, and the method can be used for collision detection of ship loading operation.
The method can realize the hatch identification of the bulk cargo ship only by using the data of a single laser radar, and has lower cost compared with a multi-laser radar identification scheme. By using the point cloud spherical mapping method, the image processing technology is applied to point cloud identification, the algorithm efficiency is high, and the calculation force requirement on a calculation platform is low.
The second embodiment, which is different from the first embodiment, is: and in the second step, preprocessing the collected point cloud data, wherein the preprocessing method is a voxel grid method.
In this embodiment, the original point cloud data is downsampled by using a voxel grid method, so that the number of point cloud data points can be reduced, the downsampled point cloud data is shown in fig. 2, the original point cloud in the experiment contains 24000 data points, and the downsampled point cloud is 14109.
The third embodiment is different from the second embodiment in that: and in the third step, performing clustering analysis on the preprocessed point cloud data by adopting an Euclidean clustering method.
And performing cluster analysis on the point cloud data after the down-sampling, wherein the cluster body with the largest point cloud number is a ship body after the cluster analysis because a cargo ship is taken as a main body in the collected point cloud data, and the extraction result is shown in fig. 3.
The fourth embodiment is different from the third embodiment in that: the concrete process of the step five is as follows:
respectively representing the screened point cloud data as p in a Cartesian coordinate system and a spherical coordinate systemi(x, y, z) andpi(x, y, z) andthe conversion relationship is as follows:
determining an angular range (Θ, Φ) of the lidar acquired point cloud data such thatThe angular resolution is set to (Δ Θ, Δ Φ), the resolution of the generated image isObtaining point cloud data ballThe conversion relation of pixel coordinates of a surface mapping two-dimensional image is as follows:
wherein (row)i,coli) And the point cloud data is spherically mapped into pixel coordinates of a two-dimensional image, and the generated two-dimensional image is a single-channel image.
For a point cloud data, if the point cloud data is expressed as a point cloud in a spherical coordinate systemThen, in the two-dimensional image, the pixel value of the pixel point corresponding to the point cloud data is r.
The spherical mapping results are shown in fig. 5.
The fifth embodiment is different from the fourth embodiment in that: the concrete process of the seventh step is as follows:
extracting the Contour of the connected domain graph by using a Canny operator to obtain a plurality of Contour point sets ContouriSetting the number of points in the contour point set to a large or small range (C)min,Cmax) The outline encloses an area size range (S)min,Smax) Will satisfy the range (C)min,Cmax) And (S)min,Smax) The Contour point set of (1) is screened out as a Contour point set Contour of the hatchhatch。
The range of the number of points in the contour point set and the range of the contour enclosed area are also determined based on data obtained by an actual field test, and the recognition result of the contour point set of the hatch is shown in fig. 7.
The sixth embodiment is different from the fifth embodiment in that: the concrete process of the ninth step is as follows:
contour point set Contour for hatcheshatchAt any point (x)2,y2) If the coordinates of two end points of a certain edge of the hatch outline are respectively (x)1,y1) And (x)3,y3) Then point (x)2,y2) The distance d to this edge is:
similarly, calculate out point (x)2,y2) Distances to the other three edges;
the distance threshold of the point belonging to each edge is set to dth1、dth2、dth3、dth4Points within the corresponding threshold belong to the corresponding edge;
contour point set Contour of traversal hatchhatchAfter all the points in the image, respectively extracting a data point set belonging to each edge of the hatch outline, namely a hatch outline point set ContourhatchDivided into four parts which respectively belong to the planes of the four walls of the hatch.
Contour point set Contour for hatcheshatchRespectively calculating the distance from the point to each side, and setting the distance threshold of the first side as dth1Setting the distance threshold of the second side as dth2Setting the distance threshold of the third side as dth3Setting the distance threshold of the fourth side as dth4If the distance from the point to the first side is less than or equal to dth1And the distance from the point to the second side is larger than dth2The distance from the point to the third side is larger than dth3The distance from the point to the fourth side is larger than dth4If the point meets the threshold of the first edge, if the point also meets the threshold of the second edge, or if the point also meets the threshold of the third edge, or if the point also meets the threshold of the fourth edge, namely the number of edges of the point meeting the threshold is more than or equal to 2, the point is screened out;
and similarly, extracting the data point set of each edge belonging to the hatch outline.
The seventh embodiment and the sixth embodiment are different from the seventh embodiment in that: in the eleventh step, plane fitting is performed on each group of three-dimensional point sets obtained in the tenth step, and a method adopted for plane fitting is an SVD (Singular Value decomposition) method.
The above-described calculation examples of the present invention are merely to explain the calculation model and the calculation flow of the present invention in detail, and are not intended to limit the embodiments of the present invention. It will be apparent to those skilled in the art that other variations and modifications of the present invention can be made based on the above description, and it is not intended to be exhaustive or to limit the invention to the precise form disclosed, and all such modifications and variations are possible and contemplated as falling within the scope of the invention.
Claims (7)
1. A single laser radar bulk cargo ship hatch position identification method is characterized by comprising the following steps:
arranging and installing a laser radar on a ship loader, and ensuring that point cloud data acquired by the laser radar comprises a cargo ship hatch through adjusting a visual angle, wherein the acquired point cloud data takes the cargo ship as a main body;
secondly, preprocessing the collected point cloud data to obtain preprocessed point cloud data;
performing cluster analysis on the preprocessed point cloud data to obtain a plurality of groups of point cloud sets, wherein the set containing the most point cloud data is used as a ship body point cloud data set;
step four, setting a point cloud reflectivity intensity threshold value IthScreening the point cloud data in the ship body point cloud data set obtained in the step three, and enabling the point cloud data to be larger than or equal to a reflectivity intensity threshold value IthScreening out point cloud data;
step five: acquiring an angular range of point cloud data acquired by the laser radar, performing spherical mapping on the point cloud data screened in the fourth step, and converting the point cloud data into a single-channel image;
step six: performing morphological 'closing' operation on the single-channel image obtained in the step five to form a connected domain image;
step seven: carrying out contour extraction on the connected domain graph generated in the step six to obtain a plurality of contour point sets; and screening the obtained Contour point set to obtain Contour point set Contour of the hatchhatch;
Step eight, carrying out Contour on the Contour point set obtained in the step sevenhatchSolving the bounding box with the minimum area to obtain four vertexes P of the bounding boxminBox1、PminBox2、PminBox3、PminBox4The four vertexes are sequentially connected end to form four edges of the hatch outline;
step nine, respectively calculating the distance from any point in the contour point set of the hatch to four edges, if the distance from the point to a certain edge is smaller than a threshold value corresponding to the edge, the point belongs to the edge, and after traversing all points in the contour point set of the hatch, respectively extracting a data point set of each edge of the contour of the hatch;
step ten, carrying out point cloud spherical surface inverse mapping on the data point set of each edge of the hatch outline extracted in the step nine to obtain four groups of three-dimensional point cloud sets hashpart1、hatchpart2、hatchpart3、hatchpart4;
Step eleven, performing plane fitting on each group of three-dimensional point cloud sets obtained in the step eleven to obtain four fitting planes, and taking the four fitting planes as the four-wall plane of the hatch;
step twelve: and respectively calculating the distances of the four walls of the hatch relative to the plane to obtain the space size of the hatch.
2. The method for identifying the hatch position of the single-laser radar bulk cargo ship according to claim 1, wherein in the second step, the collected point cloud data is preprocessed by a voxel grid method.
3. The method for identifying the hatch position of the single-laser radar bulk cargo ship according to claim 2, wherein in the third step, clustering analysis is performed on the preprocessed point cloud data by using a Euclidean clustering method.
4. The method for identifying the hatch position of the single laser radar bulk cargo ship according to claim 3, wherein the concrete process of the step five is as follows:
respectively representing the screened point cloud data as p in a Cartesian coordinate system and a spherical coordinate systemi(x, y, z) andpi(x, y, z) andthe conversion relationship is as follows:
determining an angular range (Θ, Φ) of the lidar acquired point cloud data such thatThe angular resolution is set to (Δ Θ, Δ Φ), the resolution of the generated image isObtaining a conversion relation of pixel coordinates of the point cloud data which are spherically mapped into a two-dimensional image:
wherein (row)i,coli) And the point cloud data is spherically mapped into pixel coordinates of a two-dimensional image, and the generated two-dimensional image is a single-channel image.
5. The method for identifying the hatch position of the single laser radar bulk cargo ship according to claim 4, wherein the specific process of the seventh step is as follows:
extracting the Contour of the connected domain graph by using a Canny operator to obtain a plurality of Contour point sets ContouriSetting the number of points in the contour point set to a large or small range (C)min,Cmax) The outline encloses an area size range (S)min,Smax) Will satisfy the range (C)min,Cmax) And (S)min,Smax) The Contour point set of (1) is screened out as a Contour point set Contour of the hatchhatch。
6. The method for identifying the hatch position of the single laser radar bulk cargo ship according to claim 5, wherein the specific process of the ninth step is as follows:
contour point set Contour for hatcheshatchAt any point (x)2,y2) If the coordinates of two end points of a certain edge of the hatch outline are respectively (x)1,y1) And (x)3,y3) Then point (x)2,y2) The distance d to this edge is:
similarly, calculate out point (x)2,y2) Distances to the other three edges;
the distance threshold of the point belonging to each edge is set to dth1、dth2、dth3、dth4Points within the corresponding threshold belong to the corresponding edge;
contour point set Contour of traversal hatchhatchAfter all the points in the image, respectively extracting a data point set belonging to each edge of the hatch outline, namely a hatch outline point set ContourhatchDivided into four parts which respectively belong to the planes of the four walls of the hatch.
7. The method for identifying the hatch position of the single-laser radar bulk cargo ship according to claim 6, wherein in the eleventh step, the plane fitting is performed on each three-dimensional point cloud set obtained in the tenth step, and the plane fitting is performed by using an SVD method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011434857.6A CN112529958B (en) | 2020-12-10 | 2020-12-10 | Single laser radar bulk cargo ship hatch position identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011434857.6A CN112529958B (en) | 2020-12-10 | 2020-12-10 | Single laser radar bulk cargo ship hatch position identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112529958A true CN112529958A (en) | 2021-03-19 |
CN112529958B CN112529958B (en) | 2022-08-26 |
Family
ID=74998987
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011434857.6A Active CN112529958B (en) | 2020-12-10 | 2020-12-10 | Single laser radar bulk cargo ship hatch position identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112529958B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113064179A (en) * | 2021-03-22 | 2021-07-02 | 上海商汤临港智能科技有限公司 | Point cloud data screening method and vehicle control method and device |
CN113340287A (en) * | 2021-08-04 | 2021-09-03 | 杭州集益科技有限公司 | Cabin hatch identification method for ship loader |
CN113538566A (en) * | 2021-07-15 | 2021-10-22 | 武汉港迪智能技术有限公司 | Cargo ship hatch position obtaining method and system based on laser radar |
WO2023202136A1 (en) * | 2022-04-22 | 2023-10-26 | 上海禾赛科技有限公司 | Data processing method and data processing apparatus for lidar, and lidar system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130231892A1 (en) * | 2007-12-28 | 2013-09-05 | Scanalyse Pty Ltd. | System and method for measuring and mapping a surface relative to a reference |
CN103336282A (en) * | 2013-06-17 | 2013-10-02 | 上海海事大学 | Automatic cabin positioning device and positioning method thereof |
WO2018025842A1 (en) * | 2016-08-04 | 2018-02-08 | 株式会社Hielero | Point group data conversion system, method, and program |
CN110118526A (en) * | 2019-03-08 | 2019-08-13 | 浙江中海达空间信息技术有限公司 | A kind of boat-carrying sandstone volume automatic calculating method for supporting real-time monitoring |
CN111238382A (en) * | 2020-01-21 | 2020-06-05 | 北京驭光科技发展有限公司 | Ship height measuring method and ship height measuring device |
CN111402404A (en) * | 2020-03-16 | 2020-07-10 | 贝壳技术有限公司 | Panorama complementing method and device, computer readable storage medium and electronic equipment |
-
2020
- 2020-12-10 CN CN202011434857.6A patent/CN112529958B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130231892A1 (en) * | 2007-12-28 | 2013-09-05 | Scanalyse Pty Ltd. | System and method for measuring and mapping a surface relative to a reference |
CN103336282A (en) * | 2013-06-17 | 2013-10-02 | 上海海事大学 | Automatic cabin positioning device and positioning method thereof |
WO2018025842A1 (en) * | 2016-08-04 | 2018-02-08 | 株式会社Hielero | Point group data conversion system, method, and program |
CN110118526A (en) * | 2019-03-08 | 2019-08-13 | 浙江中海达空间信息技术有限公司 | A kind of boat-carrying sandstone volume automatic calculating method for supporting real-time monitoring |
CN111238382A (en) * | 2020-01-21 | 2020-06-05 | 北京驭光科技发展有限公司 | Ship height measuring method and ship height measuring device |
CN111402404A (en) * | 2020-03-16 | 2020-07-10 | 贝壳技术有限公司 | Panorama complementing method and device, computer readable storage medium and electronic equipment |
Non-Patent Citations (2)
Title |
---|
SHEN YANG: "AN ANTI-COLLISION METHOD OF SLIP BARREL FOR AUTOMATIC SHIP LOADING IN BULK TERMINAL", 《POLISH MARITIME RESEARCH》 * |
包起帆等: "港口散货全自动装卸设备研究与开发", 《中国机械工程》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113064179A (en) * | 2021-03-22 | 2021-07-02 | 上海商汤临港智能科技有限公司 | Point cloud data screening method and vehicle control method and device |
CN113538566A (en) * | 2021-07-15 | 2021-10-22 | 武汉港迪智能技术有限公司 | Cargo ship hatch position obtaining method and system based on laser radar |
CN113538566B (en) * | 2021-07-15 | 2023-06-13 | 武汉港迪智能技术有限公司 | Cargo ship hatch position acquisition method and system based on laser radar |
CN113340287A (en) * | 2021-08-04 | 2021-09-03 | 杭州集益科技有限公司 | Cabin hatch identification method for ship loader |
WO2023202136A1 (en) * | 2022-04-22 | 2023-10-26 | 上海禾赛科技有限公司 | Data processing method and data processing apparatus for lidar, and lidar system |
Also Published As
Publication number | Publication date |
---|---|
CN112529958B (en) | 2022-08-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112529958B (en) | Single laser radar bulk cargo ship hatch position identification method | |
EP3683721A1 (en) | A material handling method, apparatus, and system for identification of a region-of-interest | |
CN110344621B (en) | Wheel point cloud detection method for intelligent garage | |
WO2021093240A1 (en) | Method and system for camera-lidar calibration | |
Zong et al. | Container ship cell guide accuracy check technology based on improved 3D point cloud instance segmentation | |
CN112417591B (en) | Vehicle modeling method, system, medium and equipment based on holder and scanner | |
CN113412505B (en) | Processing unit and method for ordered representation and feature extraction of a point cloud obtained by a detection and ranging sensor | |
Miądlicki et al. | Ground plane estimation from sparse LIDAR data for loader crane sensor fusion system | |
CN112233136A (en) | Method, system, equipment and storage medium for alignment of container trucks based on binocular recognition | |
CN113034600B (en) | Template matching-based texture-free planar structure industrial part identification and 6D pose estimation method | |
Miadlicki et al. | Loader crane working area monitoring system based on LIDAR scanner | |
Asvadi et al. | Two-stage static/dynamic environment modeling using voxel representation | |
CN115014371A (en) | Positioning and mapping method and device for grain transfer vehicle of intelligent grain depot and storage medium | |
CN113483664B (en) | Screen plate automatic feeding system and method based on line structured light vision | |
Tsai et al. | Viewer-centred surface completion for unsupervised domain adaptation in 3D object detection | |
Bansal et al. | A lidar streaming architecture for mobile robotics with application to 3d structure characterization | |
CN116843742B (en) | Calculation method and system for stacking volume after point cloud registration for black coal loading vehicle | |
CN113420648A (en) | Target detection method and system with rotation adaptability | |
TW202017784A (en) | Car detection method based on LiDAR by proceeding the three-dimensional feature extraction and the two-dimensional feature extraction on the three-dimensional point cloud map and the two-dimensional map | |
CN117011362A (en) | Method for calculating cargo volume and method for dynamically calculating volume rate | |
Wan et al. | 6DOF object positioning and grasping approach for industrial robots based on boundary point cloud features | |
CN116520351A (en) | Train state monitoring method, system, storage medium and terminal | |
CN113791400A (en) | Laser radar-based stair parameter autonomous detection method | |
Wan et al. | Online Obstacle Detection for USV based on Improved RANSAC Algorithm | |
CN117710725A (en) | Container door recognition method and system based on self-vehicle perception and vehicle |
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 |