CN115731459A - Hatch edge identification method for large port machinery - Google Patents
Hatch edge identification method for large port machinery Download PDFInfo
- Publication number
- CN115731459A CN115731459A CN202211281477.2A CN202211281477A CN115731459A CN 115731459 A CN115731459 A CN 115731459A CN 202211281477 A CN202211281477 A CN 202211281477A CN 115731459 A CN115731459 A CN 115731459A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- hatch
- area
- core
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a hatch edge identification method for large port machinery, and belongs to the technical field of ship operation process calculation methods. The technical scheme of the invention is as follows: firstly, taking all collected point clouds as FULL complete point clouds; extracting a deck part of the AREA point cloud as an AREA AREA point cloud; extending five meters of point cloud overlapped with the AREA AREA point cloud from the middle position of the deck to the two sides of the ship to serve as CORE CORE point cloud; taking point clouds obtained by computing and screening CORE CORE point clouds as EDGE boundary point clouds; and calculating the boundary point information of each point cloud cluster through point cloud segmentation, and further obtaining the intersection point coordinates of the hatch edges corresponding to each cabin number. The invention has the beneficial effects that: the calculation speed is high, the applicability is strong, the ship hatch coordinates can be quickly and effectively identified and calculated, and a new key technology is provided for automatic modification of large-scale machinery of ports.
Description
Technical Field
The invention relates to a hatch edge identification method for large port machinery, and belongs to the technical field of ship operation process calculation methods.
Background
At present, the construction of the intelligent port is mainly concentrated in the field of container loading and unloading, the technical development of automation of large-scale port machinery is relatively backward, the large-scale port machinery is seriously dependent on personnel operation, and a mature large-scale port machinery automation solution is unavailable temporarily.
Disclosure of Invention
The invention aims to provide a hatch edge identification method for large port machinery, which establishes a working relation between a radar and a shore machine by means of point cloud extraction, clustering segmentation and the like through ship data entry before operation and laser radar point cloud data acquisition in an operation process so as to enable the shore machine to master the ship hatch condition in real time.
The technical scheme of the invention is as follows: a method for identifying the hatch edge of a large port machine comprises the following steps:
(1) A space rectangular coordinate system is established, the initial position of the ship loader is a bow, the self coordinate system of the radar is taken as a standard, the ground direction is the positive direction of an x axis, the land side direction is the positive direction of a y axis, and the bow direction is the positive direction of a z axis;
(2) Performing point cloud extraction in a space rectangular coordinate system, and taking all collected point clouds as FULL complete point clouds;
(3) Extracting a deck part in the FULL complete point cloud as AREA AREA point cloud through point cloud slicing;
(4) The point cloud is subjected to intersection, the middle position of the deck extends five meters towards the two sides of the ship to form an intersection interval with an AREA AREA, and points are taken from the intersection interval to form a CORE CORE point cloud;
(5) Comparing the point clouds, and taking the point cloud obtained by calculating and screening the CORE CORE point cloud as an EDGE boundary point cloud;
(6) Dividing EDGE boundary point cloud through point cloud segmentation to obtain point cloud cluster at a ship hatch;
(7) And calculating the boundary point information of each point cloud cluster so as to obtain the intersection point coordinates of the hatch edge corresponding to each cabin number.
In the step (3), the FULL point cloud is divided into slice sections along the z-axis forward direction according to the set step value, each point in the FULL point cloud sequentially falls into different slice sections, and each point is only in one corresponding slice section, so as to form an AREA point cloud belonging to the slice section.
In the step (5), calculating the maximum value and the minimum value of the AREA AREA point cloud along the x direction, the y direction and the z direction, calculating the maximum value and the minimum value of the CORE CORE point cloud along the x direction, the y direction and the z direction, and extracting the EDGE boundary point cloud; specifically, the method comprises the following three judgments:
(a) In order to deal with the situation that the slice interval is at the cabin edge, the difference value between the maximum CORE CORE point cloud value and the minimum CORE CORE point cloud value in the x-axis direction is smaller than the set height difference, so that the cabin bottom point cloud can be effectively removed;
(b) The point cloud data ship is ensured to have small X-axis numerical value, namely high height, and large X-axis numerical value, namely low height, of the middle bilge; the difference between the CORE CORE point cloud minimum value and the AREA AREA point cloud minimum value in the x direction is larger than the set height difference;
(c) Removing point clouds which are lower than the deck by a certain height, wherein the numerical value of the point clouds in the AREA on the x direction is smaller than the sum of the minimum value of the point clouds in the AREA on the x direction and the set cabin height;
and traversing all the intervals, and obtaining a point cloud set which is the EDGE boundary point cloud through the three judgments.
In the step (6), EDGE boundary point clouds are divided, and point cloud clusters at the positions of the ship cabins are output according to the Euclidean clustering principle; setting a point cloud clustering search radius smaller than the interval between the cabins; and sequentially numbering the point cloud clusters, wherein the point cloud cluster number in the positive y direction is an odd number, the point cloud cluster number in the negative y direction is an even number, and the point cloud cluster numbers are increased one by one along the negative z-axis direction.
In the step (7), the formula is passed
h＝(i+i％2)/2
Calculating to obtain a hatch number corresponding to each point cloud cluster, wherein h is the hatch number, i is the point cloud cluster number, and% is a remainder;
in point cloud clustering, the cross point of the outer olive and the rear olive is a hatch point No. 1, the cross point of the front olive and the outer olive is a hatch point No. 2, the cross point of the inner olive and the front olive is a hatch point No. 3, the cross point of the rear olive and the inner olive is a hatch point No. 4, four-point coordinates are marked in each cabin according to the rule, and a hatch coordinate value is obtained.
The invention has the beneficial effects that: the method has the advantages that the working relation between the radar and the shore machine is established by means of point cloud extraction, cluster segmentation and the like, through ship data entry before operation and laser radar point cloud data acquisition in the operation process, so that the shore machine can master the ship hatch condition in real time.
Drawings
FIG. 1 is a schematic diagram of a rectangular spatial coordinate system according to the present invention;
FIG. 2 is a schematic diagram of a complete point cloud of FULL according to the present invention;
FIG. 3 is a schematic view of a ship point cloud slice according to the present invention;
FIG. 4 is a schematic view of the AREA point cloud of the present invention;
FIG. 5 is a CORE CORE point cloud diagram of the present invention;
FIG. 6 is a schematic diagram of an EDGE boundary point cloud of the present invention;
FIG. 7 is a schematic diagram of point de-clustering in accordance with the present invention;
FIG. 8 is a four-point schematic view of the hatch of the present invention;
the labels in the figure are: FULL complete point cloud 1, point cloud slice interval 2, AREA AREA point cloud 3, CORE CORE point cloud 4, EDGE boundary point cloud 5, point cloud cluster No. 1 11, point cloud cluster No. 2, point cloud cluster No. 3, point cloud cluster No. 4, point cloud cluster No. 15, point cloud cluster No. 6, point cloud cluster No. 7, point cloud cluster No. 18, hatch No. 1 point 21, hatch No. 2 point 22, hatch No. 3 point 23 and hatch No. 4 point 24.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention with reference to the drawings of the embodiments, and it is obvious that the described embodiments are a small part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative work based on the embodiments of the present invention belong to the protection scope of the present invention.
A method for identifying the hatch edge of a large port machine comprises the following steps:
(1) Determining a space rectangular coordinate system, wherein the initial position of the ship loader is the bow, the self coordinate system of the radar is taken as the standard, the ground direction is the positive direction of an x axis, the land side direction is the positive direction of a y axis, and the bow direction is the positive direction of a z axis;
(2) Performing point cloud extraction in a space rectangular coordinate system, and taking all collected point clouds as FULL complete point clouds;
(3) Extracting a deck part in the FULL complete point cloud as AREA AREA point cloud through point cloud slicing;
(4) Taking an intersection from the point clouds, extending five meters from the middle position of the deck to the two sides of the ship to form an intersection interval with an AREA (AREA), and taking points from the intersection interval to form a CORE CORE point cloud;
(5) Point cloud comparison, wherein point clouds obtained by computing and screening the CORE CORE point cloud are used as EDGE boundary point clouds;
(6) Dividing EDGE boundary point clouds through point cloud segmentation to obtain point cloud clusters at the positions of ship cabins;
(7) And calculating the boundary point information of each point cloud cluster, and further obtaining the intersection point coordinates of the hatch edges corresponding to each cabin number.
In the step (3), the FULL point cloud is divided into slice sections along the z-axis forward direction according to the set step value, each point in the FULL point cloud sequentially falls into different slice sections, and each point is only in one corresponding slice section, so as to form an AREA point cloud belonging to the slice section.
In the step (5), calculating the maximum value and the minimum value of the AREA AREA point cloud along the x direction, the y direction and the z direction, calculating the maximum value and the minimum value of the CORE CORE point cloud along the x direction, the y direction and the z direction, and extracting the EDGE boundary point cloud; specifically, the method comprises the following three judgments:
(a) In order to deal with the situation that the slice interval is at the cabin edge, the difference value between the maximum value of the CORE CORE point cloud and the minimum value of the CORE CORE point cloud in the x-axis direction is smaller than the set height difference, so that the cabin bottom point cloud can be effectively removed;
(b) The point cloud data ship is ensured to have small numerical value of the two sides of the ship on the x axis, namely high height, and large numerical value of the x axis of the middle bilge, namely low height; the difference between the CORE CORE point cloud minimum value and the AREA AREA point cloud minimum value in the x direction is larger than the set height difference;
(c) Removing point clouds which are lower than the deck by a certain height, wherein the numerical value of the point clouds in the AREA on the x direction is smaller than the sum of the minimum value of the point clouds in the AREA on the x direction and the set cabin height;
traversing all the intervals, and obtaining a point cloud set which is the EDGE boundary point cloud through the three determinations.
In the step (6), EDGE boundary point cloud is divided, and point cloud cluster at the position of a ship hatch is output according to the Euclidean clustering principle; setting a point cloud clustering search radius smaller than the interval between the cabins; and sequentially numbering the point cloud clusters, wherein the point cloud cluster number in the positive y direction is an odd number, the point cloud cluster number in the negative y direction is an even number, and the point cloud cluster numbers are increased one by one along the negative z-axis direction.
In the step (7), the formula is passed
h＝(i+i％2)/2
Calculating to obtain a hatch number corresponding to each point cloud cluster, wherein h is the hatch number, i is the point cloud cluster number, and% is a remainder;
in point cloud clustering, the cross point of the outer olive and the rear olive is a hatch point No. 1, the cross point of the front olive and the outer olive is a hatch point No. 2, the cross point of the inner olive and the front olive is a hatch point No. 3, the cross point of the rear olive and the inner olive is a hatch point No. 4, four-point coordinates are marked in each cabin according to the rule, and a hatch coordinate value is obtained.
In practical application, in order to obtain the hatch data, all collected point clouds are used as FULL complete point clouds; extracting a deck part of the AREA point cloud as an AREA AREA point cloud; extending five meters of point cloud overlapped with the AREA AREA point cloud from the middle position of the deck to the two sides of the ship to serve as CORE CORE point cloud; and (4) taking the point cloud obtained by computing and screening the CORE CORE point cloud as the EDGE boundary point cloud. And calculating the boundary point information of each cluster through point cloud segmentation, and further obtaining the intersection point coordinates of the hatch edges corresponding to each cabin number. The method takes the initials of FULL, AREA, CORE and EDGE and is named as a FACE method.
1. Point cloud extraction (calculation of FULL complete point cloud)
Firstly, a space rectangular coordinate system is determined, before the program starts, the initial position of the ship loader is the bow, for the convenience of calculation, the program uses the coordinate system of the radar itself as the standard, the ground direction is the positive direction of the x axis, the land side direction is the positive direction of the y axis, and the bow direction is the positive direction of the z axis, as shown in fig. 1, the space coordinate system is near the bow, as shown in fig. 2, the FULL point cloud is FULL (the dot pattern is represented as point cloud, the same below).
2. Point cloud slice (obtaining AREA AREA point cloud)
To facilitate computer processing, the point cloud is segmented into slices of the same thickness. Too large a point cloud slice reduces accuracy, and too small a point cloud slice causes a large calculation load of a workstation, and the step value is set to be 0.5 m through balance. Dividing the FULL complete point cloud into a plurality of sections along the ship length direction (namely-z direction) according to a set step value, sequentially enabling each point in the FULL complete point cloud to fall into different slice sections, and enabling each point to be only in one corresponding slice section to form the AREA AREA point cloud belonging to the section.
3. Point cloud intersection (obtaining CORE CORE point cloud)
On the basis of the AREA AREA point cloud formed by each section interval, the point cloud belongs to an intersection interval between y = +/-5 m (namely the middle position of a deck extends five meters towards the directions of two sides of a ship), and the point cloud in the intersection interval is used as a CORE CORE point cloud.
4. Point cloud comparison (EDGE boundary point cloud from AREA AREA point cloud and CORE CORE point cloud)
Calculating the maximum value and the minimum value of the AREA AREA point cloud in the slice interval along the x direction, the y direction and the z direction and the maximum value and the minimum value of the CORE CORE point cloud falling into y = +/-5 m along the x direction, the y direction and the z direction, and extracting the EDGE boundary point cloud, wherein the method specifically comprises the following steps of:
(1) In order to deal with the situation that the slice interval is at the cabin edge, the difference value between the maximum CORE CORE point cloud value and the minimum CORE CORE point cloud value in the x-axis direction is smaller than the set height difference, and the height from the hatch to the cabin bottom is usually larger than 5 meters, so that the cabin bottom point cloud can be effectively removed, and the height difference is set to be 5 meters.
(2) The point cloud data ship two side is ensured to have small value (high height) on the x axis and large value (low height) on the x axis of the middle bilge. And the difference between the CORE CORE point cloud minimum value and the AREA AREA point cloud minimum value in the x direction is larger than the set height difference. Since the hatch to bilge height is typically greater than 5 meters, the difference in height is set to 5 meters.
(3) And removing point clouds, such as point clouds of the bilge position and the bulkhead position, which are lower than the deck by a certain height. The numerical value of the AREA point cloud in the x direction is smaller than the sum of the minimum value of the AREA point cloud in the x direction and the set cabin height. The hatch height is 5 meters.
And traversing all the slice intervals, and obtaining a point cloud set which is the EDGE boundary point cloud through the three judgments.
5. Point cloud segmentation (EDGE boundary point cloud partitioning using Euclidean clustering principle)
The neighbor query algorithm based on the KD-Tree is an important preprocessing method for accelerating Euclidean clustering algorithm (Euclidean Cluster Extraction).
The principle of the KD-Tree is that the KD-Tree is a binary Tree with each node being a K-dimensional point. All non-leaf nodes can be viewed as partitioning the space into two half-spaces with one hyperplane. The subtree to the left of the node represents a point to the left of the hyperplane and the subtree to the right of the node represents a point to the right of the hyperplane. The method for selecting the hyperplane is as follows: each node is associated with a dimension of the K dimensions that is perpendicular to the hyperplane. Thus, if the selection is divided according to the x-axis, all nodes with x values less than a specified value will appear in the left sub-tree and all nodes with x values greater than the specified value will appear in the right sub-tree. Thus, the hyperplane can be determined using this X value, with the normal being the unit vector of the X-axis.
The specific implementation method of the euclidean clustering principle is roughly as follows:
(1) Find a certain point A in space 1 Finding out the nearest points from KDTREE, and judging the points to A 1 The distance of (d);
(2) Point A with distance less than set threshold 2 、A 3 … in cluster Q;
(3) Find a point A in cluster Q m Repeating the step 1 to find A m+1 、A m+2 、A m+3 … all put into cluster Q;
(4) Find a point A in cluster Q n Repeating the step 1 to find A n+1 、A n+2 、A n+3 … all put in cluster Q;
(5) And when no new point can be added into the cluster Q any more, finishing the search.
Since the separation between cabins is typically greater than 3 meters, it is ensured that adjacent CLUSTERS (CLUSTERS) do not merge into one cluster, the cluster search radius is set to 3 meters. And inputting EDGE boundary point cloud, and outputting point cloud clusters at the position of a ship hatch by the method. And sequentially numbering the point cloud clusters, wherein the point cloud cluster number in the positive y direction is an odd number, the point cloud cluster number in the negative y direction is an even number, and the point cloud cluster numbers are increased one by one along the negative z-axis direction.
6. Point cloud computing (calculating cabin number and hatch coordinate value)
Supposing that the cabin number is h and the cluster number is i, the method passes the formula
h＝(i+i％2)/2
Such that each point cloud cluster corresponds to a corresponding hatch number (% as remainder). The point cloud cluster No. 1 and the point cloud cluster No. 2 correspond to the hatch No. 1, and so on.
In point cloud clustering, the cross point of the outer olive and the rear olive is a No. 1 hatch point; the cross point of the front olive and the outer olive is a No. 2 hatch point; the cross point of the inner olive and the front olive is a No. 3 hatch point; the cross point of the rear olive and the inner olive is a hatch No. 4. Each compartment is marked with four-point coordinates according to this rule.
Assuming that the bin number is h, the four-point coordinate formula is as follows:
P h1.x is the x coordinate of the point No. 1 of the h hatch;
and clustering the minimum value of the x coordinate for the i point cloud.
P h1.y Is the y coordinate of the point No. 1 of the h hatch;
and the maximum value of the y coordinate of the i point cloud cluster is obtained.
P h1.z Is the z coordinate of the point No. 1 of the h hatch;
clustering the z-coordinates for the i-point cloudA large value.
P h2.x Is the x coordinate of the point h hatch number 2;
and clustering the minimum value of the x coordinate for the i point cloud.
P h2.y Is the y coordinate of the point No. 2 of the h hatch;
and the minimum value of the y coordinate of the i point cloud cluster is obtained.
P h2.z Is the z coordinate of the h hatch number 2 point;
and clustering the maximum value of the z coordinate for the i point cloud.
P h3.x Is the x coordinate of the point h hatch 3;
and clustering the maximum value of the x coordinate for the i point cloud.
P h3.y Is the y coordinate of the point No. 3 of the hatch h;
and the minimum value of the y coordinate of the i point cloud cluster is obtained.
P h3.z Is the z coordinate of the point h hatch 3;
and clustering the minimum value of the z coordinate for the i point cloud.
P h4.x Is the x coordinate of the point h hatch 4;
and clustering the maximum value of the x coordinate for the i point cloud.
P h4.y Is the y coordinate of the point No. 4 of the hatch h;
and the maximum value of the y coordinate of the i point cloud cluster is obtained.
P h4.z Is the z coordinate of the point No. 4 of the h hatch;
and clustering the minimum value of the z coordinate for the i point cloud.
And the coordinates of four points of the rest cabins are analogized.
Claims (5)
1. A hatch edge identification method for a large port machine is characterized by comprising the following steps:
(1) A space rectangular coordinate system is established, the initial position of the ship loader is a bow, the self coordinate system of the radar is taken as a standard, the ground direction is the positive direction of an x axis, the land side direction is the positive direction of a y axis, and the bow direction is the positive direction of a z axis;
(2) Performing point cloud extraction in a space rectangular coordinate system, and taking all collected point clouds as FULL complete point clouds;
(3) Extracting a deck part in the FULL complete point cloud as AREA AREA point cloud through point cloud slicing;
(4) Taking an intersection from the point clouds, extending five meters from the middle position of the deck to the two sides of the ship to form an intersection interval with an AREA (AREA), and taking points from the intersection interval to form a CORE CORE point cloud;
(5) Point cloud comparison, wherein point clouds obtained by computing and screening the CORE CORE point cloud are used as EDGE boundary point clouds;
(6) Dividing EDGE boundary point clouds through point cloud segmentation to obtain point cloud clusters at the positions of ship cabins;
(7) And calculating the boundary point information of each point cloud cluster, and further obtaining the intersection point coordinates of the hatch edges corresponding to each cabin number.
2. The method for identifying the hatch edge of the large-sized port machine according to claim 1, wherein: in the step (3), the FULL point cloud is divided into slice sections along the z-axis forward direction according to the set step value, each point in the FULL point cloud sequentially falls into different slice sections, and each point is only in one corresponding slice section, so as to form an AREA point cloud belonging to the slice section.
3. The method for identifying the hatch edge of a large-sized port machine according to claim 2, wherein: in the step (5), calculating the maximum value and the minimum value of the AREA AREA point cloud along the x direction, the y direction and the z direction, calculating the maximum value and the minimum value of the CORE CORE point cloud along the x direction, the y direction and the z direction, and extracting the EDGE boundary point cloud; specifically, the method comprises the following three judgments:
(a) In order to deal with the situation that the slice interval is at the cabin edge, the difference value between the maximum CORE CORE point cloud value and the minimum CORE CORE point cloud value in the x-axis direction is smaller than the set height difference, so that the cabin bottom point cloud can be effectively removed;
(b) The point cloud data ship is ensured to have small numerical value of the two sides of the ship on the x axis, namely high height, and large numerical value of the x axis of the middle bilge, namely low height; the difference between the CORE CORE point cloud minimum value and the AREA AREA point cloud minimum value in the x direction is larger than the set height difference;
(c) Removing point clouds which are lower than the deck by a certain height, wherein the numerical value of the point clouds in the AREA on the x direction is smaller than the sum of the minimum value of the point clouds in the AREA on the x direction and the set cabin height;
and traversing all the intervals, and obtaining a point cloud set which is the EDGE boundary point cloud through the three judgments.
4. The method for identifying the hatch edge of the large-sized port machine according to claim 1, wherein: in the step (6), EDGE boundary point clouds are divided, and point cloud clusters at the positions of the ship cabins are output according to the Euclidean clustering principle; setting a point cloud clustering search radius smaller than the interval between the cabins; and sequentially numbering the point cloud clusters, wherein the point cloud cluster number in the positive y direction is an odd number, the point cloud cluster number in the negative y direction is an even number, and the point cloud cluster numbers are increased one by one along the negative z-axis direction.
5. The method for identifying the hatch edge of a large-sized port machine according to claim 1, wherein: in the step (7), the formula is passed
h＝(i+i％2)/2
Calculating to obtain a hatch number corresponding to each point cloud cluster, wherein h is the hatch number, i is the point cloud cluster number, and% is a remainder;
in point cloud clustering, the cross point of the outer olive and the rear olive is a hatch point No. 1, the cross point of the front olive and the outer olive is a hatch point No. 2, the cross point of the inner olive and the front olive is a hatch point No. 3, the cross point of the rear olive and the inner olive is a hatch point No. 4, four-point coordinates are marked in each cabin according to the rule, and a hatch coordinate value is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211281477.2A CN115731459A (en) | 2022-10-19 | 2022-10-19 | Hatch edge identification method for large port machinery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211281477.2A CN115731459A (en) | 2022-10-19 | 2022-10-19 | Hatch edge identification method for large port machinery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115731459A true CN115731459A (en) | 2023-03-03 |
Family
ID=85293727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211281477.2A Pending CN115731459A (en) | 2022-10-19 | 2022-10-19 | Hatch edge identification method for large port machinery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115731459A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116817904A (en) * | 2023-08-29 | 2023-09-29 | 深圳市镭神智能系统有限公司 | Door machine detecting system |
-
2022
- 2022-10-19 CN CN202211281477.2A patent/CN115731459A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116817904A (en) * | 2023-08-29 | 2023-09-29 | 深圳市镭神智能系统有限公司 | Door machine detecting system |
| CN116817904B (en) * | 2023-08-29 | 2023-11-10 | 深圳市镭神智能系统有限公司 | Door machine detecting system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510516A (en) | A kind of the three-dimensional line segment extracting method and system of dispersion point cloud | |
| CN107292276B (en) | Vehicle-mounted point cloud clustering method and system | |
| CN111222516B (en) | Method for extracting point cloud key outline features of printed circuit board | |
| CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
| CN107369161A (en) | A kind of workpiece point cloud segmentation method at random based on the European cluster of improvement | |
| CN113298833A (en) | Target object point cloud characteristic line and surface extraction method and system | |
| CN104134219A (en) | Color image segmentation algorithm based on histograms | |
| CN115731459A (en) | Hatch edge identification method for large port machinery | |
| CN111626120B (en) | Target detection method based on improved YOLO-6D algorithm in industrial environment | |
| Rosenfeld | Fuzzy geometry: An updated overview | |
| CN113255677B (en) | Method, equipment and medium for rapidly extracting rock mass structural plane and occurrence information | |
| CN113936215A (en) | Mining area road surface pit identification method and system and unmanned truck | |
| CN115293287A (en) | Vehicle-mounted radar-based target clustering method, memory and electronic device | |
| CN112070787B (en) | Aviation three-dimensional point cloud plane segmentation method based on opponent reasoning theory | |
| CN106446472A (en) | STL-model-based intersection loop calculation algorithm for numerical control machining geometrical simulation | |
| CN113744389A (en) | Point cloud simplification method for complex part curved surface feature retention | |
| CN116071694B (en) | Ship detection method, device and computer readable storage medium | |
| CN110390337B (en) | Ship individual identification method | |
| CN114037724B (en) | Heterogeneous parallel computing system and method for threshold image segmentation and electronic equipment | |
| CN115909072A (en) | Improved YOLOv4 algorithm-based impact point water column detection method | |
| Liu et al. | Graph cut based mesh segmentation using feature points and geodesic distance | |
| CN112989470B (en) | Indoor space layout extraction method based on point cloud data | |
| CN111986223B (en) | Method for extracting trees in outdoor point cloud scene based on energy function | |
| CN110781963B (en) | K-means clustering-based aerial target clustering method | |
| Aguilera et al. | Domain extension for the extreme vertices model (EVM) and set membership classification |
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 |