CN110780276A - Tray identification method and system based on laser radar and electronic equipment - Google Patents
Tray identification method and system based on laser radar and electronic equipment Download PDFInfo
- Publication number
- CN110780276A CN110780276A CN201911048691.1A CN201911048691A CN110780276A CN 110780276 A CN110780276 A CN 110780276A CN 201911048691 A CN201911048691 A CN 201911048691A CN 110780276 A CN110780276 A CN 110780276A
- Authority
- CN
- China
- Prior art keywords
- tray
- cluster
- clustering result
- fitting
- straight line
- 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
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
Abstract
The invention discloses a tray identification method based on a laser radar, which comprises the following steps: acquiring laser real-time measurement point cloud data; clustering to obtain clustering result clusters; performing linear fitting extraction to obtain a fitting linear segment; matching to obtain pairwise matched cluster pairs; determining a middle leg of the tray and two side legs of the tray; the center position and angle of the tray are determined. According to the invention, the tray point cloud data is obtained by using the laser radar, the advantages of high measurement precision and strong anti-interference performance of the laser radar are utilized, the precision of tray identification is improved, the environmental adaptability of tray identification is enhanced, and the relative position relation of the point cloud data is analyzed and identified to identify the two side legs and the middle leg of the tray, so that the central position and the angle of the tray are identified, a tray template is not required to be established in advance, and the adaptability of the tray identification method is enhanced. The invention also discloses a tray identification system based on the laser radar and electronic equipment.
Description
Technical Field
The invention relates to the technical field of identification, in particular to a tray identification method and system based on a laser radar and electronic equipment.
Background
Nowadays, intelligent manufacturing is increasingly developed, the robot is in intense demand for changing people, and in the process of industrial material production and circulation, the autonomous mobile robot technology has wide development space, and for pallet carrying, the robot is required to have pallet identification capability so as to accurately acquire the position and the angle of a pallet.
The schematic view of the tray is shown in fig. 1. According to the relevant national standards, the current pallets have a relatively uniform structural form: all pallets have two side legs, a middle leg, and the distance between the two side legs is twice the distance between the middle leg and the side legs.
The autonomous mobile robot takes the position of the middle point of the middle leg and the direction perpendicular to the middle leg as the position and angle of the pallet.
The following problems mainly exist in the current tray identification: the RFID technology is mostly adopted, and the positioning precision is low; and by adopting an image recognition technology, the requirement on ambient light is high, and the interference is easy to occur. The existing technology for identifying the tray by adopting the laser radar can achieve higher identification precision and stronger environmental adaptability, but has the problem of weak adaptability due to the fact that a tray template needs to be established in advance.
Disclosure of Invention
The invention provides a tray identification method and system based on a laser radar and electronic equipment based on the above problems.
The technical scheme for solving the technical problems is as follows: a tray identification method based on laser radar comprises the following steps:
s1, acquiring laser real-time measurement point cloud data;
s2, clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
s3, performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
s4, obtaining pairwise matched cluster pairs according to the correlation between the fitted straight line segments of every two clustering result clusters;
s5, determining the middle leg of the tray and the two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and S6, determining the central position and the angle of the tray according to the middle leg and the two side legs.
The invention has the beneficial effects that: the tray point cloud data are obtained by the aid of the laser radar, the accuracy of tray identification and the environmental adaptability of tray identification are improved by the aid of the advantages of high measurement accuracy and high anti-interference performance of the laser radar, and two side legs and a middle leg of the tray are identified by analyzing and identifying the relative position relation of the point cloud data, so that the central position and the angle of the tray are identified, a tray template does not need to be established in advance, and the adaptability of a tray identification method is enhanced.
The invention also provides a laser radar-based pallet identification system, comprising,
the data acquisition module is used for acquiring laser real-time measurement point cloud data;
the clustering module is used for clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
the straight line extraction module is used for performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
the cluster pair obtaining module is used for obtaining pairwise matched cluster pairs according to the correlation between the fitting straight lines of every two clustering result clusters;
the leg acquisition module is used for determining a middle leg of the tray and two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and the tray position angle acquisition module is used for determining the central position and the angle of the tray according to the middle leg and the two side legs.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the laser radar-based tray identification method is realized.
The technical scheme has the advantages that the tray point cloud data are obtained by the aid of the laser radar, the accuracy of tray identification is improved and the environmental adaptability of tray identification is enhanced by the aid of the advantages of high measurement accuracy and high anti-interference performance of the laser radar, and the two side legs and the middle leg of the tray are identified by analyzing and identifying the relative position relation of the point cloud data, so that the central position and the angle of the tray are identified, a tray template does not need to be established in advance, and the adaptability of the tray identification method is enhanced.
Drawings
FIG. 1 shows a schematic view of a tray;
FIG. 2 is a flow chart illustrating a method for identifying a laser radar-based pallet according to an embodiment of the present invention;
FIG. 3 shows a schematic view of a lidar scanning tray provided in accordance with an embodiment of the invention;
FIG. 4 illustrates a laser radar scanning pallet point cloud data schematic provided in accordance with an embodiment of the present invention;
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the features of the embodiments of the present invention, i.e., the embodiments, may be combined with each other without conflict.
Fig. 2 shows a flowchart of a lidar-based pallet recognition method according to an embodiment of the present invention.
As shown in fig. 2, in this embodiment, a method for identifying a tray based on a laser radar includes the following steps:
s1, acquiring laser real-time measurement point cloud data;
s2, clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
s3, performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
s4, obtaining pairwise matched cluster pairs according to the correlation between the fitted straight line segments of every two clustering result clusters;
s5, determining the middle leg of the tray and the two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and S6, determining the central position and the angle of the tray according to the middle leg and the two side legs.
The pallet used in the material handling process of the industrial autonomous mobile robot has a relatively uniform structural form, and a schematic diagram of the common pallet is shown in fig. 1. As shown in fig. 1, the pallets all have two side legs, a middle leg, the distance between the two side legs is twice the distance between the middle leg and the side legs, and the two side legs and the middle leg are on the same plane. The embodiment of the invention utilizes the relative position relation of each leg of the tray to identify. Generally, the position and angle of the tray are taken as the position of the middle point of the middle leg and the direction perpendicular to the middle leg.
In the process of identifying by using the laser radar, the laser radar is arranged on the same horizontal plane with the tray legs, and the laser radar rotates 360 degrees in the scanning process to acquire point cloud data of surrounding objects. Fig. 3 shows a schematic view of a lidar scanning tray according to an embodiment of the invention.
Fig. 4 shows a point cloud data map of a laser radar front scanning tray according to an embodiment of the present invention. As shown in fig. 4, when the laser radar scans an obstacle, point data corresponding to the distance is generated. When the laser radar just scans the tray, the point cloud data of the middle leg is approximately distributed in a straight line section, the straight line is perpendicular to the incident light of the laser radar, the straight line section corresponds to the front face of the middle leg, and the point cloud data of the side legs are approximately distributed in an L shape and respectively correspond to the front face and the depth side face of the side legs.
In the embodiment, the characteristics of good anti-interference performance and high precision of the laser radar are utilized to obtain high-precision original point cloud data; the point cloud data are classified into a plurality of clusters, straight line fitting is carried out on the clusters, the fitted straight lines are identified according to the structural characteristics of the tray, and two side legs and a middle leg of the tray are determined, so that the central position and the angle of the tray are identified. By utilizing the general structural characteristics of the tray for identification, a tray template does not need to be established in advance, and the adaptability of the tray identification method is enhanced.
Optionally, the step S2 includes performing rolling processing according to the sequence of the point cloud data collected by the laser radar, dividing the point cloud data that conforms to the set neighborhood range and the set density value range into the current cluster, ending the current cluster when the continuously set number of point cloud data exceeds the set density value range, and repeating the process until the point cloud data is processed.
Clustering using set domain ranges and set density values is a well-known means in the art. In the traditional density clustering algorithm, all the other points need to be traversed for judging each point, and the operation speed is low.
In the embodiment, the characteristics of point cloud data obtained by sequential scanning of the laser radar are combined, a rolling processing method is adopted, and only the subsequent points are traversed, so that the operation speed is greatly increased.
As can be seen from the structural features of the pallet, the point cloud data of each leg of the pallet are independent of each other and correspond to the clustering result cluster data.
Optionally, the step S3 includes, including,
performing straight line fitting on the point cloud data in each clustering result cluster, and if the fitting result accords with a set straight line correlation coefficient, acquiring a current fitting straight line segment;
and if the fitting result does not accord with the set linear correlation coefficient, selecting a point with the maximum gradient in the cluster of the clustering result as a data segmentation point, carrying out data segmentation according to the data segmentation point, respectively carrying out linear fitting on the segmented data in the cluster, stopping data segmentation until the fitting result accords with the set correlation coefficient, and obtaining the current fitting linear segment.
Straight line fitting of scattered points is a common technical means in the art.
And selecting the point with the maximum gradient in the clustering result cluster, and obtaining the gradient between the point cloud data by performing differential convolution on the point cloud data in the clustering result cluster so as to obtain the point with the maximum gradient by comparison.
In the above embodiment, the straight line fitting is performed on the points in the clusters to obtain the fitting straight line segment, so that the position relationship can be conveniently identified.
Optionally, the step S4 includes, including,
and matching any two clustering result clusters pairwise, judging the position relationship between the two clustering result clusters, and when the fitting straight-line segments between the two clustering result clusters are in a mutually parallel or mutually perpendicular relationship, enabling the two clustering result clusters to be pairwise matched clusters.
As mentioned above, according to the structural features of the tray, the straight line segments fitted to the clusters corresponding to the feet of the tray have a parallel or perpendicular relationship with each other, and a cluster pair may correspond to a group of leg combinations. And the data size and range of the tray identification are further reduced by identifying pairwise matched cluster pairs.
Optionally, determining a key point of each clustering result cluster according to the fitting straight line segment of each clustering result cluster, and sorting the clustering result clusters according to the ordinate of the key point;
and pairwise matching any two sorted clustering result clusters, judging the position relationship between the two clustering result clusters, and when the fitting straight-line sections between the two clustering result clusters are in a mutually parallel or mutually perpendicular relationship, enabling the two clustering result clusters to be pairwise matched clusters.
The ordinate axis is as shown in fig. 4, and in the identification process, a coordinate system in which the laser center point is the center of a circle, the direction from the center of the circle to the tray is the coordinate horizontal axis, and the direction perpendicular to the coordinate horizontal axis is the coordinate vertical axis can be established.
In the above embodiment, the clustering result clusters are sorted according to the key points, that is, the clustering result clusters are sorted according to the laser scanning sequence, and by sorting, the speed and efficiency of identification are further improved.
Optionally, the determining a key point of each cluster of the clustering results according to the fitted straight-line segment of each cluster of the clustering results includes:
when the clustering result cluster only has one fitting straight-line segment and the slope of the fitting straight-line segment is smaller than a preset slope, the middle point of the fitting straight-line segment is a key point;
when the clustering result cluster only has one fitting straight line segment and the slope of the fitting straight line segment is greater than or equal to a preset slope, the end point of one end of the fitting straight line segment close to the laser central point is a key point;
and when the clustering result cluster has a plurality of fitting straight line segments, the point which is closest to the laser central point in the intersection points of the plurality of fitting straight line segments is a key point.
As mentioned above, the number of the fitting straight line segments of the cluster may be one or more, when the number of the fitting straight line segments is one, the slope of the fitting straight line segment may be two, when the slope of the fitting straight line segment is smaller than the preset slope, as shown in fig. 4, the slope of the fitting straight line segment on the front side of the middle leg is 0, the middle point of the fitting straight line segment is taken as the key point of the cluster, and when the slope of the fitting straight line segment is larger than the preset slope (for example, on the longitudinal depth side of the side leg), the end point of the fitting straight. When the laser straight line segments are a plurality of fitting straight line segments, the intersection point between the straight line segments closest to the center point of the laser is selected as a key point.
In the above embodiment, the position of the cluster is determined by determining the key point.
Optionally, the S5 includes the step of,
s51, determining the distance of the cluster pair according to the key point of the clustering result cluster;
s52, traversing all the cluster pairs, and when two cluster pairs meet preset conditions at the same time, setting the clusters corresponding to the cluster pairs with the distance of twice as two edge leg candidate objects, and setting the clusters corresponding to the cluster pairs with the distance of one time as middle leg candidate objects to obtain a leg candidate object combination; wherein the preset conditions include: the distance between one cluster pair is twice that of the other cluster pair, the two cluster pairs have a common cluster, and the key points of the clustering result clusters corresponding to the two cluster pairs meet the preset linear correlation;
s53, determining the two side legs and the middle leg according to the number of vertical or parallel relations in the leg candidate object combination and the position of the center point of the laser.
As described above, the inter-leg structure of the tray has the features: the tray all has that all trays all have two limit legs, a middle leg, and the distance between two limit legs is twice between middle leg and the limit leg, and two limit legs and a middle leg are on same plane. It can be seen that, accordingly, when the following relationship exists between the cluster pairs: the distance of one cluster pair is twice the distance of the other cluster pair, the two cluster pairs have a common cluster, and the key points of the clusters corresponding to the two cluster pairs meet the preset linear correlation, so that the size corresponding to the distance of 2 times is large, namely the size of the tray, and correspondingly, the two side legs and the middle leg of the tray can be corresponding to the clusters corresponding to 2 distance relationships.
In the embodiment, the side legs and the middle legs are identified by using the structural characteristics of the tray, and the template of the tray is not required to be input, so that the tray identification method has universal applicability.
Optionally, the step S53 includes, including,
s531, comparing the number of vertical or parallel relations in the corresponding cluster pair in the leg candidate object combination, selecting the leg candidate object combination with the largest vertical or parallel relation from the leg candidate object combinations, and taking the two side leg candidate objects and the middle leg candidate object corresponding to the leg candidate object combination as the two side legs and the middle leg;
s532, when the number of the vertical or parallel relations of the leg candidate object combinations is the largest at the same time, selecting the leg candidate object combination closest to the laser center point, and taking the two side leg candidate objects and the middle leg candidate object corresponding to the leg candidate object combination as the two side legs and the middle leg.
According to the structure of the tray, when the leg candidate object combination corresponds to the real side legs and the middle legs, the corresponding vertical or parallel relation is the largest, and when the number of the vertical or parallel relations is the same, the leg candidate object combination closest to the laser central point is selected to determine the side legs and the middle legs, so that the identification accuracy is further improved.
Optionally, between the step S52 and the step S53, further comprising,
s52-53, according to the size range of the preset tray, deleting the leg candidate object combination beyond the size range of the preset tray.
The trays have a range of sizes according to the relevant standard. The distance between the legs on two sides corresponds to the size of the tray, and leg candidate object combinations which do not meet the requirements can be further deleted through the range of the size of the preset tray, so that the recognition efficiency and accuracy are improved.
Optionally, the step S6 includes, including,
s61, acquiring a first position and a first angle of the tray according to the middle leg;
s62, acquiring a second position and a second angle of the tray according to the two side legs;
s63, averaging the first position and the second position of the tray to obtain the central position of the tray, and averaging the first angle and the second angle of the tray to obtain the angle of the tray.
The position of the tray can be defined as the position of the tray using the position of the center of the legs at both sides, i.e., the position of the center of the middle leg.
The position and angle of the tray are obtained from the middle leg, and the key point of the middle leg can be used as the position of the tray. The angle of the tray can be obtained by simple geometric operation and the fitting straight line segment corresponding to the middle leg.
It should be noted that, the middle point of the key point corresponding to the legs on both sides is used as the position of the tray, and the angle of the tray can be obtained through simple geometric operation.
The accuracy and precision of the identification is further improved by averaging the tray position and angle obtained from the middle leg and the tray position and angle obtained from the two side legs.
The embodiment of the invention also provides a tray identification system based on the laser radar, which comprises,
the data acquisition module is used for acquiring laser real-time measurement point cloud data;
the clustering module is used for clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
the straight line extraction module is used for performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
the cluster pair obtaining module is used for obtaining pairwise matched cluster pairs according to the correlation between the fitting straight lines of every two clustering result clusters;
the leg acquisition module is used for determining a middle leg of the tray and two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and the tray position angle acquisition module is used for determining the central position and the angle of the tray according to the middle leg and the two side legs.
The embodiment of the invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, wherein when the processor executes the program, the laser radar-based tray identification method in the technical scheme is realized.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (12)
1. A tray identification method based on laser radar is characterized by comprising the following steps:
s1, acquiring laser real-time measurement point cloud data;
s2, clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
s3, performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
s4, obtaining pairwise matched cluster pairs according to the correlation between the fitted straight line segments of every two clustering result clusters;
s5, determining the middle leg of the tray and the two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and S6, determining the central position and the angle of the tray according to the middle leg and the two side legs.
2. The lidar-based pallet recognition method of claim 1, wherein the step S2 comprises,
and rolling according to the sequence of collecting the point cloud data by the laser radar, dividing the point cloud data which accord with a set neighborhood range and a set density value range into a current cluster, ending the current cluster when the point cloud data with continuously set number exceed the set density value range, and repeating the process until the point cloud data is processed.
3. The lidar-based pallet recognition method of claim 1, wherein the step S3 comprises,
performing straight line fitting on the point cloud data in each clustering result cluster, and if the fitting result accords with a set straight line correlation coefficient, acquiring a current fitting straight line segment;
and if the fitting result does not accord with the set linear correlation coefficient, selecting a point with the maximum gradient in the cluster of the clustering result as a data segmentation point, carrying out data segmentation according to the data segmentation point, respectively carrying out linear fitting on the segmented data in the cluster, stopping data segmentation until the fitting result accords with the set correlation coefficient, and obtaining the current fitting linear segment.
4. The lidar-based pallet recognition method of claim 1, wherein the step S4 comprises,
and matching any two clustering result clusters pairwise, judging the position relationship between the two clustering result clusters, and when the fitting straight-line segments between the two clustering result clusters are in a mutually parallel or mutually perpendicular relationship, enabling the two clustering result clusters to be pairwise matched clusters.
5. The lidar-based pallet recognition method of claim 1, wherein the step S4 comprises,
determining key points of each clustering result cluster according to the fitting straight line segment of each clustering result cluster, and sequencing the clustering result clusters according to the vertical coordinates of the key points;
and pairwise matching any two sorted clustering result clusters, judging the position relationship between the two clustering result clusters, and when the fitting straight-line sections between the two clustering result clusters are in a mutually parallel or mutually perpendicular relationship, enabling the two clustering result clusters to be pairwise matched clusters.
6. The lidar-based tray identification method according to claim 5, wherein the determining the key point of each cluster of the clustering results according to the fitted straight line segment of each cluster of the clustering results comprises:
when the clustering result cluster only has one fitting straight-line segment and the slope of the fitting straight-line segment is smaller than a preset slope, the middle point of the fitting straight-line segment is a key point;
when the clustering result cluster only has one fitting straight line segment and the slope of the fitting straight line segment is greater than or equal to a preset slope, the end point of one end of the fitting straight line segment close to the laser central point is a key point;
and when the clustering result cluster has a plurality of fitting straight line segments, the point which is closest to the laser central point in the intersection points of the plurality of fitting straight line segments is a key point.
7. The lidar-based pallet recognition method of claim 5, wherein the S5 comprises,
s51, determining the distance of the cluster pair according to the key point of the clustering result cluster;
s52, traversing all the cluster pairs, and when two cluster pairs meet preset conditions at the same time, setting the clusters corresponding to the cluster pairs with the distance of twice as two edge leg candidate objects, and setting the clusters corresponding to the cluster pairs with the distance of one time as middle leg candidate objects to obtain a leg candidate object combination; wherein the preset conditions include: the distance between one cluster pair is twice that of the other cluster pair, the two cluster pairs have a common cluster, and the key points of the clustering result clusters corresponding to the two cluster pairs meet the preset linear correlation;
s53, determining the two side legs and the middle leg according to the number of vertical or parallel relations in the leg candidate object combination and the position of the center point of the laser.
8. The lidar-based pallet recognition method of claim 7, wherein the step S53 comprises,
s531, comparing the number of vertical or parallel relations in the corresponding cluster pair in the leg candidate object combination, selecting the leg candidate object combination with the largest vertical or parallel relation from the leg candidate object combinations, and taking the two side leg candidate objects and the middle leg candidate object corresponding to the leg candidate object combination as the two side legs and the middle leg;
s532, when the number of the vertical or parallel relations of the leg candidate object combinations is the largest at the same time, selecting the leg candidate object combination closest to the laser center point, and taking the two side leg candidate objects and the middle leg candidate object corresponding to the leg candidate object combination as the two side legs and the middle leg.
9. The lidar-based tray identification method according to claim 7, wherein between the step S52 and the step S53, further comprising,
s52-53, according to the size range of the preset tray, deleting the leg candidate object combination beyond the size range of the preset tray.
10. The lidar-based pallet recognition method of claim 7, wherein the step S6 comprises,
s61, acquiring a first position and a first angle of the tray according to the middle leg;
s62, acquiring a second position and a second angle of the tray according to the two side legs;
s63, averaging the first position and the second position of the tray to obtain the central position of the tray, and averaging the first angle and the second angle of the tray to obtain the angle of the tray.
11. A tray identification system based on laser radar is characterized by comprising,
the data acquisition module is used for acquiring laser real-time measurement point cloud data;
the clustering module is used for clustering the point cloud data by adopting a density clustering algorithm to obtain at least one clustering result cluster;
the straight line extraction module is used for performing straight line fitting extraction on each clustering result cluster to obtain one or more fitting straight line segments;
the cluster pair obtaining module is used for obtaining pairwise matched cluster pairs according to the correlation between the fitting straight lines of every two clustering result clusters;
the leg acquisition module is used for determining a middle leg of the tray and two side legs of the tray according to the distance and the mutual relation of the cluster pairs;
and the tray position angle acquisition module is used for determining the central position and the angle of the tray according to the middle leg and the two side legs.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the lidar-based tray identification method of any of claims 1-10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911048691.1A CN110780276A (en) | 2019-10-29 | 2019-10-29 | Tray identification method and system based on laser radar and electronic equipment |
| PCT/CN2020/088238 WO2021082380A1 (en) | 2019-10-29 | 2020-04-30 | Laser radar-based pallet recognition method and system, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911048691.1A CN110780276A (en) | 2019-10-29 | 2019-10-29 | Tray identification method and system based on laser radar and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110780276A true CN110780276A (en) | 2020-02-11 |
Family
ID=69387895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911048691.1A Pending CN110780276A (en) | 2019-10-29 | 2019-10-29 | Tray identification method and system based on laser radar and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110780276A (en) |
| WO (1) | WO2021082380A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082380A1 (en) * | 2019-10-29 | 2021-05-06 | 杭州易博特科技有限公司 | Laser radar-based pallet recognition method and system, and electronic device |
| CN112784799A (en) * | 2021-02-01 | 2021-05-11 | 三一机器人科技有限公司 | AGV (automatic guided vehicle) backward pallet and obstacle identification method and device and AGV |
| CN115600118A (en) * | 2022-11-29 | 2023-01-13 | 山东亚历山大智能科技有限公司（Cn） | Tray leg identification method and system based on two-dimensional laser point cloud |
| CN115816416A (en) * | 2022-12-15 | 2023-03-21 | 锐趣科技(北京)有限公司 | Butt joint robot and butt joint method thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020014533A1 (en) * | 1995-12-18 | 2002-02-07 | Xiaxun Zhu | Automated object dimensioning system employing contour tracing, vertice detection, and forner point detection and reduction methods on 2-d range data maps |
| CN107390679A (en) * | 2017-06-13 | 2017-11-24 | 合肥中导机器人科技有限公司 | Storage device, laser navigation fork truck |
| CN107507167A (en) * | 2017-07-25 | 2017-12-22 | 上海交通大学 | A kind of cargo pallet detection method and system matched based on a cloud face profile |
| DE102017215334A1 (en) * | 2016-09-21 | 2018-03-22 | Carl Zeiss Industrielle Messtechnik Gmbh | Method, computer program product and measuring system for operating at least one triangulation laser scanner for identifying surface properties of a workpiece to be measured |
| CN109270543A (en) * | 2018-09-20 | 2019-01-25 | 同济大学 | A kind of system and method for pair of target vehicle surrounding vehicles location information detection |
| CN109520418A (en) * | 2018-11-27 | 2019-03-26 | 华南农业大学 | A kind of pallet method for recognizing position and attitude based on two dimensional laser scanning instrument |
| CN110222642A (en) * | 2019-06-06 | 2019-09-10 | 上海黑塞智能科技有限公司 | A kind of planar architectural component point cloud contour extraction method based on global figure cluster |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103645480B (en) * | 2013-12-04 | 2015-11-18 | 北京理工大学 | Based on the topography and landform character construction method of laser radar and fusing image data |
| CN104880160B (en) * | 2015-05-27 | 2017-05-17 | 西安交通大学 | Two-dimensional-laser real-time detection method of workpiece surface profile |
| WO2019041267A1 (en) * | 2017-08-31 | 2019-03-07 | SZ DJI Technology Co., Ltd. | Systems and methods for an apd array solid-state laser radar |
| CN109993192A (en) * | 2018-01-03 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Recongnition of objects method and device, electronic equipment, storage medium |
| CN109785335B (en) * | 2018-12-18 | 2021-05-18 | 歌尔光学科技有限公司 | Method and device for determining linear profile of scanning object and storage medium |
| CN110780276A (en) * | 2019-10-29 | 2020-02-11 | 杭州易博特科技有限公司 | Tray identification method and system based on laser radar and electronic equipment |
-
2019
- 2019-10-29 CN CN201911048691.1A patent/CN110780276A/en active Pending
-
2020
- 2020-04-30 WO PCT/CN2020/088238 patent/WO2021082380A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020014533A1 (en) * | 1995-12-18 | 2002-02-07 | Xiaxun Zhu | Automated object dimensioning system employing contour tracing, vertice detection, and forner point detection and reduction methods on 2-d range data maps |
| DE102017215334A1 (en) * | 2016-09-21 | 2018-03-22 | Carl Zeiss Industrielle Messtechnik Gmbh | Method, computer program product and measuring system for operating at least one triangulation laser scanner for identifying surface properties of a workpiece to be measured |
| CN107390679A (en) * | 2017-06-13 | 2017-11-24 | 合肥中导机器人科技有限公司 | Storage device, laser navigation fork truck |
| CN107507167A (en) * | 2017-07-25 | 2017-12-22 | 上海交通大学 | A kind of cargo pallet detection method and system matched based on a cloud face profile |
| CN109270543A (en) * | 2018-09-20 | 2019-01-25 | 同济大学 | A kind of system and method for pair of target vehicle surrounding vehicles location information detection |
| CN109520418A (en) * | 2018-11-27 | 2019-03-26 | 华南农业大学 | A kind of pallet method for recognizing position and attitude based on two dimensional laser scanning instrument |
| CN110222642A (en) * | 2019-06-06 | 2019-09-10 | 上海黑塞智能科技有限公司 | A kind of planar architectural component point cloud contour extraction method based on global figure cluster |
Non-Patent Citations (1)
| Title |
|---|
| 赵俊宏等: "基于激光雷达的托盘位姿识别算法及验证", 《仪器仪表学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082380A1 (en) * | 2019-10-29 | 2021-05-06 | 杭州易博特科技有限公司 | Laser radar-based pallet recognition method and system, and electronic device |
| CN112784799A (en) * | 2021-02-01 | 2021-05-11 | 三一机器人科技有限公司 | AGV (automatic guided vehicle) backward pallet and obstacle identification method and device and AGV |
| CN115600118A (en) * | 2022-11-29 | 2023-01-13 | 山东亚历山大智能科技有限公司（Cn） | Tray leg identification method and system based on two-dimensional laser point cloud |
| CN115600118B (en) * | 2022-11-29 | 2023-08-08 | 山东亚历山大智能科技有限公司 | Tray leg identification method and system based on two-dimensional laser point cloud |
| CN115816416A (en) * | 2022-12-15 | 2023-03-21 | 锐趣科技(北京)有限公司 | Butt joint robot and butt joint method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021082380A1 (en) | 2021-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108228798B (en) | Method and device for determining matching relation between point cloud data | |
| CN110780276A (en) | Tray identification method and system based on laser radar and electronic equipment | |
| CN107610176B (en) | Pallet dynamic identification and positioning method, system and medium based on Kinect | |
| Kang et al. | Automatic targetless camera–lidar calibration by aligning edge with gaussian mixture model | |
| Tazir et al. | CICP: Cluster Iterative Closest Point for sparse–dense point cloud registration | |
| CN108107444B (en) | Transformer substation foreign matter identification method based on laser data | |
| WO2021109575A1 (en) | Global vision and local vision integrated robot vision guidance method and device | |
| CN103793712A (en) | Image recognition method and system based on edge geometric features | |
| CN111624622B (en) | Obstacle detection method and device | |
| CN110349260B (en) | Automatic pavement marking extraction method and device | |
| CN104040590A (en) | Method for estimating pose of object | |
| CN110853081B (en) | Ground and airborne LiDAR point cloud registration method based on single-tree segmentation | |
| El‐Sayed et al. | Plane detection in 3D point cloud using octree‐balanced density down‐sampling and iterative adaptive plane extraction | |
| CN105783786A (en) | Part chamfering measuring method and device based on structured light vision | |
| CN110390706B (en) | Object detection method and device | |
| CN114926699A (en) | Indoor three-dimensional point cloud semantic classification method, device, medium and terminal | |
| CN107895166B (en) | Method for realizing target robust recognition based on feature descriptor by geometric hash method | |
| CN113728360A (en) | Method and apparatus for pose, size and shape measurement of objects in 3D scene | |
| CN107274446B (en) | Method for identifying sharp geometric edge points by using normal consistency | |
| An et al. | Extracting statistical signatures of geometry and structure in 2D occupancy grid maps for global localization | |
| CN108629315B (en) | Multi-plane identification method for three-dimensional point cloud | |
| Tian et al. | Robust segmentation of building planar features from unorganized point cloud | |
| CN107843261B (en) | Method and system for positioning robot position based on laser scanning data | |
| CN112529891A (en) | Hollow hole identification and contour detection method and device based on point cloud and storage medium | |
| CN112130166A (en) | AGV positioning method and device based on reflector network |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Shangjin Inventor before: Tang Xu Inventor before: Wang Shangjin |