CN115164855A - Tray identification method, device and equipment and readable storage medium - Google Patents
Tray identification method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN115164855A CN115164855A CN202210940002.3A CN202210940002A CN115164855A CN 115164855 A CN115164855 A CN 115164855A CN 202210940002 A CN202210940002 A CN 202210940002A CN 115164855 A CN115164855 A CN 115164855A
- Authority
- CN
- China
- Prior art keywords
- tray
- laser detection
- straight line
- fitting
- detection point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 220
- 230000015654 memory Effects 0.000 claims description 28
- 238000012216 screening Methods 0.000 claims description 10
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 239000000523 sample Substances 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C15/00—Surveying instruments or accessories not provided for in groups G01C1/00 - G01C13/00
- G01C15/002—Active optical surveying means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
Abstract
The invention relates to the technical field of intelligent identification, and discloses a tray identification method, a device, equipment and a readable storage medium. Wherein, the method comprises the following steps: acquiring a laser detection point set of a tray to be identified; performing linear fitting on the laser detection point set to obtain at least one fitting linear line; and determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line. By implementing the invention, the position and posture detection of the tray is realized, the tray picking is convenient to carry out according to the position and posture of the tray, and the tray picking is more intelligent.
Description
Technical Field
The invention relates to the technical field of intelligent identification, in particular to a tray identification method, a device, equipment and a readable storage medium.
Background
With the rapid development of computers and robotics, the wide application of intelligent forklifts in logistics industry marks the development of warehouse logistics technology towards automation and intelligence. However, in a complex environment of an unstructured warehouse, due to the influences of factors such as operation processes, equipment precision and manual operation, the position and posture of stacking the trays are greatly uncertain, flexible picking of the trays by an intelligent forklift is influenced, and therefore how to realize detection of the position and posture of the trays becomes a technical problem to be solved urgently.
Disclosure of Invention
In view of this, embodiments of the present invention provide a tray identification method, apparatus, device and readable storage medium, so as to solve the problem that it is difficult to detect the pose of a tray.
According to a first aspect, an embodiment of the present invention provides a tray identification method, including: acquiring a laser detection point set of a tray to be identified; performing linear fitting on the laser detection point set to obtain at least one fitting linear line; and determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line.
According to the tray identification method provided by the embodiment of the invention, the laser detection point set aiming at the tray to be identified is obtained, the straight line point set is extracted from the laser detection point set for straight line fitting, and then the current pose of the tray can be determined by combining the characteristics of the tray and the parameters of a plurality of fitting straight lines, so that the pose detection of the tray is realized, the tray pickup is convenient to be carried out according to the pose of the tray, and the tray pickup is more intelligent.
With reference to the first aspect, in a first implementation manner of the first aspect, the acquiring a set of laser detection points of a tray to be identified includes: acquiring an initial laser detection point set of a tray to be identified; screening out a target detection point set forming a continuous curve from the initial laser detection point set; and determining the target detection point set as the laser detection point set.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the screening out a target detection point set constituting a continuous curve from the initial laser detection point set includes: performing curve fitting on the initial laser detection point set to obtain the continuous curve; and forming the target detection point set by a plurality of detection points on the continuous curve.
According to the tray identification method provided by the embodiment of the invention, as the boundaries of the trays are connected, the target detection point set for representing the position of the tray can be determined by screening the target detection point sets forming the continuous curve, so that the influence of irrelevant detection points can be avoided, and the accuracy of the subsequent identification of the tray pose is improved.
With reference to the first aspect, in a third implementation manner of the first aspect, the performing line fitting on the set of laser detection points to obtain at least one fitted line includes: sequencing all the laser detection points in the laser detection point set to obtain the arrangement sequence of the laser detection points; sequentially extracting a preset number of laser detection points based on the arrangement sequence; and sequentially performing linear fitting on the preset number of laser detection points to obtain at least one fitting linear line.
According to the tray identification method provided by the embodiment of the invention, the laser detection points are sequenced and then are subjected to fitting processing according to the sequenced laser detection points, so that the laser detection points are sequentially processed, and a line segment meeting the geometric constraint of the tray can be conveniently determined according to the change of the spatial position of the laser detection points.
With reference to the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the sequentially extracting a preset number of laser detection points based on the arrangement order includes: extracting the 1 st to nth laser detection points, and constructing a target window aiming at the extracted n laser detection points; moving the target window based on the arrangement sequence, sequentially adding a next laser detection point into the target window, and releasing a first laser detection point in the target window; wherein n is a positive integer.
According to the tray identification method provided by the embodiment of the invention, the number of the laser detection points in the target window is kept unchanged by constructing the target window containing the preset number of the laser detection points, and then the straight line fitting is carried out according to the laser detection points contained in the target window, so that the tray pose can be estimated through the change of different fitting straight lines.
With reference to the fourth embodiment of the first aspect, in a fifth embodiment of the first aspect, the method further comprises: when the next laser detection point is added into the target window and the first laser detection point in the target window is released, re-fitting the preset number of laser detection points in the target window to generate a current fitting straight line; determining a first included angle between the fitting straight line generated last time and the horizontal direction and a second included angle between the current fitting straight line and the horizontal direction; judging whether the difference value between the first included angle and the second included angle is smaller than a first preset threshold value or not, and whether the first included angle is smaller than a second preset threshold value or not; and when the difference value is smaller than the preset threshold value and the first included angle is smaller than the second preset threshold value, judging that the next laser detection point added into the target window is positioned on the current fitting straight line.
According to the tray identification method provided by the embodiment of the invention, the accuracy of the generated fitting straight line is ensured by detecting whether the laser detection point is positioned on the fitting straight line. The fitted straight line contains the tray pose characteristics, so that the accuracy of subsequent tray pose recognition is ensured.
With reference to the fifth embodiment of the first aspect, in a sixth embodiment of the first aspect, the method further comprises: when the difference value is larger than the preset threshold value and/or the first included angle is smaller than the second preset threshold value, acquiring the number of laser detection points of the current fitting straight line and the length of the current fitting straight line; and when the number of the laser detection points of the current fitting straight line is larger than a preset value and the length is smaller than a preset length, extracting a third included angle between the current fitting straight line and the horizontal direction, adding a next laser detection point into the target window, and releasing a first laser detection point in the target window.
According to the tray identification method provided by the embodiment of the invention, the fitted straight line is screened by combining the change of the included angle and the length of the fitted straight line and the number of laser detection points, so that the fitted straight line can accurately reflect the position and posture characteristics of the tray to the greatest extent.
With reference to the first aspect, in a seventh implementation manner of the first aspect, the determining the target pose of the tray to be recognized based on the parameters of the at least one fitted straight line includes: acquiring geometric information of the tray to be identified; determining a candidate position point set of the tray to be identified based on the matching relation between the parameters and the geometric information; performing cluster analysis on the candidate position point set to determine the central position of the tray; and determining the target pose of the tray to be identified based on the central position of the tray to be identified.
According to the tray identification method provided by the embodiment of the invention, the candidate position point set is subjected to cluster analysis to determine the central position of the tray, and then the target pose of the tray can be determined according to the central position of the tray, so that the detection of the pose of the tray is realized.
With reference to the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the determining the set of candidate position points of the tray to be identified based on the matching relationship between the parameter and the geometric information includes: acquiring the number of line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments corresponding to the fitted straight line; when the number of the line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments of the fitting straight line meet preset conditions, extracting the slope of the fitting straight line; and determining a candidate position point set of the tray to be identified based on the matching relation between the slope of the fitted straight line and the geometric information.
According to the tray identification method provided by the embodiment of the invention, the geometric information of the tray is matched with the slope of the fitting straight line, and the candidate position point set of the tray is determined based on the matching relation, so that the candidate position points can represent the pose characteristics of the tray to the maximum extent, and the subsequent identification precision is improved.
According to a second aspect, an embodiment of the present invention provides a tray identifying apparatus, including: the acquisition module is used for acquiring a laser detection point set of the tray to be identified; the generating module is used for extracting a straight line point set from the laser detection point set and generating at least one fitting straight line based on the straight line point set; and the determining module is used for determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line.
According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing therein computer instructions, and the processor executing the computer instructions to perform the pallet identification method according to the first aspect or any of the embodiments of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to cause a computer to execute the tray identification method according to the first aspect or any of the embodiments of the first aspect.
It should be noted that, for corresponding beneficial effects of the tray identification apparatus, the electronic device and the computer-readable storage medium provided in the embodiment of the present invention, please refer to the description of corresponding contents in the tray identification method, which is not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a pallet identification method according to an embodiment of the present invention;
FIG. 2 is another flow chart of a pallet identification method according to an embodiment of the present invention;
FIG. 3 is yet another flow chart of a pallet identification method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of detection of a lidar in accordance with an embodiment of the invention;
FIG. 5 is another schematic illustration of detection of a lidar in accordance with an embodiment of the invention;
FIG. 6 is a schematic diagram of generation of a fitted straight line according to an embodiment of the invention;
fig. 7 is a block diagram of the structure of a tray recognition apparatus according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In accordance with an embodiment of the present invention, there is provided an embodiment of a pallet identification method, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that herein.
The embodiment provides a tray identification method, which can be used for electronic equipment such as a host, a server and the like, wherein the electronic equipment is arranged on an intelligent forklift to guide the intelligent forklift to grab a tray. Fig. 1 is a flowchart of a tray identification method according to an embodiment of the present invention, as shown in fig. 1, the flowchart includes the following steps:
s11, acquiring a laser detection point set of the tray to be identified.
The pallet to be identified is usually composed of a top surface, a bottom surface and several (e.g. 9) pallet holders. Set up laser radar on intelligent fork truck, be connected laser radar with the electronic equipment of setting on intelligent fork truck. In the advancing process of the intelligent forklift, the laser radar sends out laser beams to act on each tray to be identified, and when the laser radar vertically scans the tray support, the electronic equipment can collect a set of laser detection points, namely a laser detection point set, obtained after the laser beams act on the tray to be identified. The set of laser probe points obtained when the lidar scans vertically to the tray support as shown in fig. 4.
It should be noted that the principle of the lidar detecting tray is as follows:
the laser radar is a 2-D laser radar, and is mainly based on a Time of flight (TOF) measuring method to realize active ranging, and distance data can be arranged according to laser beam sequence numbers. Along with the increase of the detection distance H of the laser radar, laser beams of the laser radar become sparse, the farther the distance is, the fewer the laser beams for detecting the tray support are, and if the laser beams are too few, the tray cannot be identified.
And S12, performing straight line fitting on the laser detection point set to obtain at least one fitting straight line.
In the laser detection point concentration, for the tray support, the tray support is mainly represented by a short line segment composed of discrete points, and the straight line of the line segment contains the tray position characteristic and the tray posture characteristic. The electronic equipment performs linear fitting once or multiple times on each laser detection point contained in the laser detection point set, and extracts at least one fitted linear line from the laser detection set.
And S13, determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line.
The electronic equipment of the intelligent forklift is pre-loaded with a binary image template corresponding to the tray to be identified, and the binary image template is constructed based on parameters of a fitted straight line and geometric information of the tray to be identified. The electronic equipment can determine the matched binary image template and the geometric information of the tray to be recognized based on the obtained fitting straight line, and then the target pose of the tray to be recognized can be determined according to the binary image template and the geometric information of the tray to be recognized.
According to the tray identification method, the laser detection point set aiming at the tray to be identified is obtained, so that the straight line point set is extracted from the laser detection point set for straight line fitting, and then the current position and posture of the tray can be determined by combining the characteristics of the tray and the parameters of a plurality of fitting straight lines, so that the position and posture detection of the tray is realized, the tray pickup is convenient to be carried out according to the position and posture of the tray, and the tray pickup is more intelligent.
The embodiment provides a tray identification method, which can be used for electronic equipment such as a host, a server and the like, wherein the electronic equipment is arranged on an intelligent forklift to guide the intelligent forklift to grab a tray. Fig. 2 is a flowchart of a tray identification method according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
and S21, acquiring a laser detection point set of the tray to be identified.
For detailed description, reference is made to the corresponding related description of the above embodiments, and details are not repeated herein.
And S22, performing linear fitting on the laser detection point set to obtain at least one fitting linear line.
As an alternative implementation, the step S22 may include:
and S221, sequencing the laser detection points in the laser detection point set to obtain the arrangement sequence of the laser detection points.
The electronic equipment takes the laser radar as a central point, and the laser beam is emitted by taking the position of the laser radar as the center so as to strike the side face of the tray to be identified. Taking an example that the surface to be detected of the tray to be recognized is parallel to the horizontal direction, as shown in fig. 5, the electronic device sorts the laser detection points in the laser detection point set according to the laser beam sequence numbers to obtain the arrangement sequence of the laser detection point set corresponding to the laser detection points.
It should be noted that the inclination of the to-be-detected surface of the tray to be recognized with respect to the horizontal direction does not affect the detection range and the detection accuracy of the laser radar, and mainly affects the orientation of the detection range. Specifically, the laser beam is emitted with the laser radar as the center, and when the laser detection point in fig. 4 is rotated by a certain angle with the origin, i.e., the laser radar, as the center until the surface to be measured of the tray to be identified is parallel to the horizontal direction (x-axis) as shown in fig. 5, the relative positions of the laser radar, the laser beam, and the tray are not changed. Therefore, the method is suitable for the situation of the tray to be identified at any angle.
S222, sequentially extracting a preset number of laser detection points based on the arrangement order.
The preset number is the number of laser detection points preset for performing straight line fitting, and the preset number may be 3, may be 4, or may be other values, and is not specifically limited herein, and may be determined by those skilled in the art according to actual needs. The electronic equipment sequentially extracts a preset number of laser detection points from head to tail according to the arrangement sequence of the laser detection points.
Specifically, the step S222 may include:
(1) Extracting the 1 st to nth laser detection points, and constructing a target window for the extracted n laser detection points.
Wherein n is a positive integer and represents a preset number.
The electronic device in the intelligent forklift extracts the laser detection points from the 1 st laser detection point in the sequence according to the arrangement sequence of the laser detection points, and establishes a target window for the n laser detection points, as shown in fig. 6.
(2) And moving the target window based on the arrangement sequence, sequentially adding the next laser detection point into the target window, and releasing the first laser detection point in the target window.
And controlling the target window to move according to the arrangement sequence, and ensuring that the number of the laser detection points contained in the target window is unchanged in the moving process of the target window, namely sequentially adding the next laser detection point into the target window and releasing the first laser detection point in the target window in the moving process of the target window.
Specifically, taking n =4 as an example, if the laser detection points currently included in the target window are from 1 st to 4 th, after moving the target window once, the laser detection points included in the target window are from 2 nd to 5 th, and so on until all the laser detection points are traversed, as shown in fig. 6.
The number of the laser detection points in the target window is kept unchanged by constructing the target window containing the preset number of the laser detection points, and then straight line fitting is carried out according to the laser detection points contained in the target window, so that the pose of the tray can be estimated through the change of different fitting straight lines.
And S223, sequentially performing straight line fitting on the preset number of laser detection points to obtain at least one fitting straight line.
The electronic equipment in the intelligent forklift can acquire the coordinate positions of the laser detection points with the preset number in the target window, and linear fitting is carried out according to the coordinate positions of the laser detection points to obtain corresponding fitted straight lines. As shown in fig. 6, according to the movement of the target window, straight line fitting may be sequentially performed, thereby obtaining a plurality of fitted straight lines.
As an optional implementation, the method further includes:
(1) And when the next laser detection point is added into the target window and the first laser detection point in the target window is released, re-fitting the preset number of laser detection points in the target window to generate the current fitted straight line.
(2) And determining an initial included angle between the fitted straight line obtained by the primary fitting and the horizontal direction, a first included angle between the fitted straight line generated last time and the horizontal direction, and a second included angle between the current fitted straight line and the horizontal direction.
After the fitted straight lines are generated, the electronic equipment can determine included angles between the fitted straight lines and the horizontal direction according to the inclination of the fitted straight lines relative to the horizontal direction, namely an initial included angle, a first included angle and a second included angle.
(3) And judging whether the difference value between the first included angle and the second included angle is smaller than a first preset threshold value or not and whether the initial included angle is smaller than a second preset threshold value or not.
The first preset threshold is a preset included angle difference value, and the second preset threshold is a preset initial included angle value. The first preset threshold and the second preset threshold are determined by technicians according to experience values, and whether the laser detection point is on the fitting straight line is represented through the first preset threshold and the second preset threshold.
The electronic equipment in the intelligent forklift can determine the difference value of the included angle between the first included angle and the second included angle according to the first included angle and the second included angle, and compares the difference value with a first preset threshold value to determine whether the difference value is smaller than the first preset threshold value. Meanwhile, the initial included angle is compared with a second preset threshold value to determine whether the initial included angle is smaller than the second preset threshold value.
(4) And when the difference value is smaller than a preset threshold value and the first included angle is smaller than a second preset threshold value, judging that the next laser detection point added into the target window is positioned on the current fitting straight line.
And when the difference value is smaller than a preset threshold value and the first included angle is smaller than a second preset threshold value, the fitting straight line does not have a sudden change, namely, the next laser detection point added into the target window can be recorded as a point on the current fitting straight line, namely, the laser detection point is positioned on the current fitting straight line.
(5) And when the difference value is larger than a preset threshold value and/or the initial included angle is smaller than a second preset threshold value, acquiring the number of laser detection points of the current fitting straight line and the length of the current fitting straight line.
And when the difference value is larger than a preset threshold value and/or the initial included angle is smaller than a second preset threshold value, continuously acquiring the number of laser detection points forming the current fitting straight line and the length of the current fitting straight line. The length of the current fitting straight line is the distance between the starting laser detection point and the ending laser detection point which form the fitting straight line, and the length of the current fitting straight line can be obtained according to a distance formula between the two points.
(6) And if the number of the laser detection points of the current fitting straight line is larger than a preset value and the length of the current fitting straight line is smaller than the preset length, extracting a third included angle between the current fitting straight line and the horizontal direction, returning to execute the steps of adding the next laser detection point into the target window and releasing the first laser detection point in the target window.
The preset value is the minimum number of points for generating a fitting straight line which is preset; the preset length is the maximum length allowed for fitting a straight line. And if the number of the laser detection points of the current fitting straight line is larger than the preset value and the length of the current fitting straight line is smaller than the preset length, the current fitting straight line is a line segment which accords with the geometric constraint of the tray to be identified. At this time, the step of adding the next laser detection point into the target window and releasing the first laser detection point in the target window is continuously executed to continue the generation of the fitting straight line.
The accuracy of the generated fitting straight line is ensured by detecting whether the laser detection point is positioned on the fitting straight line. The fitted straight line contains the tray pose characteristics, so that the accuracy of subsequent tray pose recognition is ensured. The fitted straight line is screened according to the change of the included angle, the length and the number of laser detection points of the combined fitted straight line, so that the fitted straight line can accurately reflect the pose characteristics of the tray to the maximum extent.
And S23, determining the target pose of the tray to be recognized based on the parameters of the at least one fitting straight line.
For a detailed description, refer to the corresponding related description of the above embodiments, which is not repeated herein.
According to the tray identification method provided by the embodiment, the laser detection points are sequenced, then fitting processing is carried out according to the sequenced laser detection points, ordered processing of the laser detection points is realized, and a line segment meeting geometric constraint of the tray can be conveniently determined according to the change of the spatial positions of the laser detection points.
The embodiment provides a tray identification method, which can be used for electronic equipment such as a host, a server and the like, and the electronic equipment is arranged on an intelligent forklift to guide the intelligent forklift to grab a tray. Fig. 3 is a flowchart of a tray identification method according to an embodiment of the present invention, and as shown in fig. 3, the flowchart includes the following steps:
and S31, acquiring a laser detection point set of the tray to be identified.
As an alternative implementation, the step S31 may include:
s311, acquiring an initial laser detection point set of the tray to be identified.
The initial laser detection point set is a set of all laser detection points obtained when the laser radar scans the tray to be identified. In the advancing process of the intelligent forklift, the laser radar sends out a laser beam to scan the tray to be identified, and an initial laser detection point set corresponding to the tray to be identified is collected.
S312, screening out a target detection point set forming a continuous curve from the initial laser detection point set.
If some invalid points exist in the initial set of laser detection points, for example, the stacking position of the tray is close to a wall or other trays, there may exist laser detection points representing the wall or other trays in the collected initial set of laser detection points.
The laser detection points belonging to the tray to be identified can form a continuous curve, and the electronic equipment in the intelligent forklift filters the initial laser detection point set to remove invalid points, so as to screen out a target detection point set forming the continuous curve.
As an alternative implementation, the step S312 may include:
(1) And performing curve fitting on the initial laser detection point set to obtain a continuous curve.
The electronic equipment in the intelligent forklift takes the laser radar as a central point to construct a coordinate system, then the coordinate positions of all laser detection points contained in the initial laser detection point set can be obtained, curve fitting is carried out according to the coordinate positions of all the laser detection points, and one or more continuous curves are obtained.
(2) And forming a target detection point set by using a plurality of detection points positioned on the continuous curve.
And filtering the obtained continuous curve to filter invalid points outside the continuous curve, and smoothing the curve to remove invalid singularities. After the processing for the continuous curve is completed, a plurality of detection points currently constituting the continuous curve are determined as a target detection point set.
And S313, determining the target detection point set as a laser detection point set.
The electronic equipment in the intelligent forklift determines a target detection point set forming a continuous curve as a laser detection point set, and performs subsequent straight line extraction on the laser detection point set, and takes a plurality of extracted straight lines as candidate objects of the tray support.
And S32, performing linear fitting on the laser detection point set to obtain at least one fitting linear line.
For a detailed description, refer to the corresponding related description of the above embodiments, which is not repeated herein.
And S33, determining the target pose of the tray based on the parameters of the at least one fitting straight line.
As an alternative implementation, the step S33 may include:
and S331, acquiring the geometric information of the tray to be identified.
The geometric information is used to characterize the spatial structure of the pallet to be identified. The geometric information of the tray to be identified may be pre-stored in the electronic device of the intelligent forklift, or may be stored in other storage spaces (such as cloud space), where the storage location of the geometric information is not limited, and those skilled in the art may determine the geometric information according to actual needs.
Correspondingly, the electronic equipment in the intelligent forklift can acquire the geometric information of the tray to be identified from the local storage space and can also call the geometric information of the tray to be identified from other storage spaces.
S332, determining a candidate position point set of the tray to be identified based on the matching relation between the parameters and the geometric information.
And the fitting straight line contains the pose characteristics of the tray to be identified, so that the parameters of the fitting straight line and the geometric information of the tray to be identified have a matching relation. The electronic equipment in the intelligent forklift can collect laser detection points in the neighborhood of the fitting straight line according to the matching degree between the parameters of the fitting straight line and the geometric information of the tray to be identified, and determines the laser detection points on the fitting straight line and the laser detection points in the neighborhood thereof as a candidate position point set of the tray to be identified.
Specifically, the parameter of the fitted straight line includes a slope of the fitted straight line, and accordingly, the step S332 may include:
(1) And acquiring the number of line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments corresponding to the fitted straight line.
And counting the number of line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments of the currently generated fitting straight line corresponding to the tray to be identified. The distance between line segments is the distance between every two adjacent fitting straight lines, and the proportion between the line segments is the distance proportion between every two adjacent fitting straight lines.
(2) And when the line segment number, the line segment length, the distance between the line segments and the proportion between the line segments of the fitting straight line meet preset conditions, extracting the slope of the fitting straight line.
The preset conditions include a preset line segment quantity value, a preset line segment length value and line segment interval proportion. The electronic equipment in the intelligent forklift sequentially judges whether the line segment number of the fitting straight lines meets a preset line segment number value, whether the line segment length meets a preset line segment length value, and whether the intervals between every two adjacent fitting straight lines are proportional.
And when the number of the line segments of the fitting straight line meets the preset line segment number value, the length of the line segment meets the preset line segment length value, and the interval between every two adjacent fitting straight lines is proportional, the number of the line segments of the fitting straight line, the length of the line segment, the distance between the line segments and the proportion between the line segments meet preset conditions. At this time, the electronic device in the intelligent forklift can extract the slope of each fitting straight line to obtain the slope of each fitting straight line.
(3) And determining a candidate position point set of the tray to be identified based on the matching relation between the slope of the fitting straight line and the geometric information.
The electronic equipment of the intelligent forklift is stored with a tray binary image template constructed according to the slope of the fitting straight line and the geometric information of the tray to be identified. And determining a binary image template matched with the fitting straight line according to the slope of the fitting straight line, and determining a candidate position point set of the tray to be recognized according to the binary image template of the tray to be recognized.
And S333, performing cluster analysis on the candidate position point set, and determining the central position of the tray to be identified.
And the electronic equipment of the intelligent forklift carries out clustering analysis on the candidate position point set by adopting a clustering algorithm to determine the weight of each class, selects the class with the maximum weight from the weights, determines the core of the class with the maximum weight, and determines the core as the central position of the tray to be identified.
And S334, determining the target pose of the tray to be recognized based on the central position of the tray to be recognized.
After the central position of the tray to be recognized is determined, the electronic equipment of the intelligent forklift can determine the spatial position of the tray to be recognized according to the central position and the geometric information of the tray to be recognized, and then the target pose of the tray to be recognized is determined.
According to the tray identification method provided by the embodiment, because the boundaries of the trays are connected, the target detection point set for representing the position of the tray can be determined by screening the target detection point sets forming the continuous curve, so that the influence of irrelevant detection points can be avoided, and the accuracy of the subsequent identification of the tray pose is improved. The geometric information of the tray is matched with the slope of the fitting straight line, and the candidate position point set of the tray is determined based on the matching relation, so that the candidate position points can represent the pose characteristics of the tray to the maximum extent, and the subsequent identification precision is improved. The central position of the tray is determined by carrying out cluster analysis on the candidate position point set, and then the target pose of the tray can be determined according to the central position of the tray, so that the detection of the pose of the tray is realized.
In this embodiment, a tray identification apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description of the apparatus is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
This embodiment provides a tray recognition device, can be used to intelligent fork truck to guide intelligent fork truck to snatch the tray. As shown in fig. 7, includes:
and the obtaining module 41 is configured to obtain a set of laser detection points of the tray to be identified.
And the generating module 42 is configured to perform straight line fitting on the laser detection point set to obtain at least one fitted straight line.
And the determining module 43 is used for determining the target pose of the tray based on the parameters of the at least one fitting straight line.
Optionally, the obtaining module 41 may include:
and the first acquisition submodule is used for acquiring an initial laser detection point set of the tray to be identified.
And the screening submodule is used for screening out a target detection point set forming a continuous curve from the initial laser detection point set.
And the first determining submodule is used for determining the target detection point set as a laser detection point set.
Optionally, the screening submodule may include:
and the fitting subunit is used for performing curve fitting on the initial laser detection point set to obtain a continuous curve.
A determining subunit, configured to determine a plurality of detection points located on the continuous curve as a target detection point set.
Optionally, the generating module 42 may include:
and the sequencing submodule is used for sequencing all the laser detection points in the laser detection point set to obtain the arrangement sequence of the laser detection points.
And the extraction submodule is used for sequentially extracting a preset number of laser detection points based on the arrangement sequence.
And the fitting submodule is used for carrying out linear fitting on the preset number of laser detection points in sequence to obtain at least one fitting linear line.
Optionally, the extracting sub-module may include:
and the extraction subunit is used for extracting the 1 st to nth laser detection points and constructing a target window aiming at the extracted n laser detection points, wherein n is a positive integer and represents a preset number.
And the moving subunit is used for moving the target window based on the arrangement sequence, sequentially adding the next laser detection point into the target window and releasing the first laser detection point in the target window.
Optionally, the generating module 42 may further include:
and the re-fitting sub-module is used for re-fitting the preset number of laser detection points in the target window to generate a current fitting straight line when the next laser detection point is added into the target window and the first laser detection point in the target window is released.
And the second determining submodule is used for determining an initial included angle between the fitted straight line obtained by the primary fitting and the horizontal direction, a first included angle between the fitted straight line generated last time and the horizontal direction, and a second included angle between the current fitted straight line and the horizontal direction.
And the first judgment submodule is used for judging whether the difference value between the first included angle and the second included angle is smaller than a first preset threshold value and whether the initial included angle is smaller than a second preset threshold value.
And the first judgment submodule is used for judging that the next laser detection point added into the target window is positioned on the current fitting straight line when the difference value is smaller than the preset threshold value and the first included angle is smaller than the second preset threshold value.
And the second obtaining submodule is used for obtaining the number of laser detection points of the current fitting straight line and the length of the current fitting straight line when the difference value is greater than the preset threshold value and/or the initial included angle is smaller than the second preset threshold value.
And the circulation submodule is used for extracting a third included angle between the current fitting straight line and the horizontal direction if the number of the laser detection points of the current fitting straight line is larger than a preset value and the length is smaller than the preset length, returning to execute the steps of adding the next laser detection point into the target window and releasing the first laser detection point in the target window.
Optionally, the determining module 43 may include:
and the third acquisition submodule is used for acquiring the geometric information of the tray to be identified.
And the third determining submodule is used for determining a candidate position point set of the tray to be identified based on the matching relation between the parameters and the geometric information.
And the fourth determining submodule is used for carrying out cluster analysis on the candidate position point set and determining the central position of the tray to be identified.
And the fifth determining submodule is used for determining the target pose of the tray to be identified based on the central position of the tray to be identified.
Optionally, the parameter of the fitted straight line includes a slope of the fitted straight line, and accordingly, the third determining submodule may include:
and the obtaining subunit is used for obtaining the number of line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments corresponding to the fitting straight line.
And the slope extraction subunit is used for extracting the slope of the fitting straight line when the line segment number, the line segment length, the distance between the line segments and the proportion between the line segments of the fitting straight line meet preset conditions.
And the point set determining subunit is used for determining a candidate position point set of the tray to be identified based on the matching relation between the slope of the fitting straight line and the geometric information.
The tray identification mechanism in this embodiment is in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and/or other devices that may provide the above-described functionality.
Further functional descriptions of the modules are the same as those of the corresponding embodiments, and are not repeated herein.
The tray recognition device that this embodiment provided is through acquireing the laser detection point set to treating discernment tray to extract the sharp point set from it and carry out the sharp fitting, combine the characteristic of tray and the parameter of many fitting straight lines then can determine the current position appearance of tray, realized the position appearance of tray and surveyed, be convenient for carry out the tray according to the tray position appearance and pick up, make the tray pick up more intellectuality.
An embodiment of the present invention further provides an electronic device, which has the tray identification apparatus shown in fig. 7.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, and as shown in fig. 8, the electronic device may include: at least one processor 501, such as a CPU (Central Processing Unit), at least one communication interface 503, memory 504, and at least one communication bus 502. Wherein a communication bus 502 is used to enable connective communication between these components. The communication interface 503 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 503 may also include a standard wired interface and a standard wireless interface. The Memory 504 may be a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 504 may alternatively be at least one memory device located remotely from the processor 501. Wherein the processor 501 may be in connection with the apparatus described in fig. 7, an application program is stored in the memory 504, and the processor 501 calls the program code stored in the memory 504 for performing any of the above-mentioned method steps.
The communication bus 502 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 502 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.
The memory 504 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: flash memory), such as a Hard Disk Drive (HDD) or a solid-state drive (SSD); the memory 504 may also comprise a combination of the above types of memory.
The processor 501 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of CPU and NP.
The processor 501 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 504 is also used to store program instructions. The processor 501 may call program instructions to implement the tray identification method as shown in the embodiments of fig. 1 to 3 of the present application.
An embodiment of the present invention further provides a non-transitory computer storage medium, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions may execute the tray identification method in any method embodiment described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the above-mentioned kind.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (12)
1. A pallet identification method, comprising:
acquiring a laser detection point set of a tray to be identified;
performing linear fitting on the laser detection point set to obtain at least one fitting linear line;
and determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line.
2. The method of claim 1, wherein said obtaining a set of laser probe points for a pallet to be identified comprises:
acquiring an initial laser detection point set of a tray to be identified;
screening out a target detection point set forming a continuous curve from the initial laser detection point set;
and determining the target detection point set as the laser detection point set.
3. The method of claim 2, wherein said screening out a set of target probe points from said set of initial laser probe points that form a continuous curve comprises:
performing curve fitting on the initial laser detection point set to obtain the continuous curve;
determining a plurality of detection points located on the continuous curve as the target detection point set.
4. The method of claim 1, wherein said fitting a straight line to the set of laser probe points to obtain at least one fitted straight line comprises:
sequencing all the laser detection points in the laser detection point set to obtain the arrangement sequence of the laser detection points;
sequentially extracting a preset number of laser detection points based on the arrangement sequence;
and sequentially performing straight line fitting on the preset number of laser detection points to obtain at least one fitting straight line.
5. The method according to claim 4, wherein the sequentially extracting a preset number of laser detection points based on the arrangement order comprises:
extracting the 1 st to nth laser detection points, and constructing a target window aiming at the extracted n laser detection points;
moving the target window based on the arrangement sequence, sequentially adding a next laser detection point into the target window, and releasing a first laser detection point in the target window;
wherein n is a positive integer and represents a preset number.
6. The method of claim 5, further comprising:
when the next laser detection point is added into the target window and the first laser detection point in the target window is released, re-fitting the preset number of laser detection points in the target window to generate a current fitting straight line;
determining an initial included angle between a fitting straight line obtained by primary fitting and the horizontal direction, a first included angle between a fitting straight line generated last time and the horizontal direction, and a second included angle between a current fitting straight line and the horizontal direction;
judging whether the difference value between the first included angle and the second included angle is smaller than a first preset threshold value or not, and whether the initial included angle is smaller than a second preset threshold value or not;
and when the difference value is smaller than the preset threshold value and the initial included angle is smaller than the second preset threshold value, judging that the next laser detection point added into the target window is positioned on the current fitting straight line.
7. The method of claim 6, further comprising:
when the difference value is larger than the preset threshold value and/or the initial included angle is smaller than the second preset threshold value, acquiring the number of laser detection points of the current fitting straight line and the length of the current fitting straight line;
and when the number of the laser detection points of the current fitting straight line is larger than a preset value and the length is smaller than a preset length, extracting a third included angle between the current fitting straight line and the horizontal direction, returning to execute the step of adding the next laser detection point into the target window and releasing the first laser detection point in the target window.
8. The method according to claim 1, wherein the determining the target pose of the tray to be identified based on the parameters of the at least one fitted straight line comprises:
acquiring geometric information of the tray to be identified;
determining a candidate position point set of the tray to be identified based on the matching relation between the parameters and the geometric information;
performing cluster analysis on the candidate position point set to determine the central position of the tray;
and determining the target pose of the tray to be identified based on the central position of the tray to be identified.
9. The method of claim 8, wherein the parameters comprise a slope of a fitted straight line, and wherein determining the set of candidate position points of the tray to be identified based on the matching relationship between the parameters and the geometric information comprises:
acquiring the number of line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments corresponding to the fitted straight line;
when the number of the line segments, the length of the line segments, the distance between the line segments and the proportion between the line segments of the fitting straight line meet preset conditions, extracting the slope of the fitting straight line;
and determining a candidate position point set of the tray to be identified based on the matching relation between the slope of the fitted straight line and the geometric information.
10. A pallet recognition apparatus, comprising:
the acquisition module is used for acquiring a laser detection point set of the tray to be identified;
the generating module is used for extracting a straight line point set from the laser detection point set and generating at least one fitting straight line based on the straight line point set;
and the determining module is used for determining the target pose of the tray to be identified based on the parameters of the at least one fitting straight line.
11. An electronic device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the pallet identification method according to any one of claims 1 to 9.
12. A computer-readable storage medium storing computer instructions for causing a computer to perform the pallet identification method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210940002.3A CN115164855A (en) | 2022-08-05 | 2022-08-05 | Tray identification method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210940002.3A CN115164855A (en) | 2022-08-05 | 2022-08-05 | Tray identification method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115164855A true CN115164855A (en) | 2022-10-11 |
Family
ID=83479735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210940002.3A Pending CN115164855A (en) | 2022-08-05 | 2022-08-05 | Tray identification method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115164855A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| US20210089040A1 (en) * | 2016-02-29 | 2021-03-25 | AI Incorporated | Obstacle recognition method for autonomous robots |
| US20210370968A1 (en) * | 2019-01-30 | 2021-12-02 | Baidu Usa Llc | A real-time map generation system for autonomous vehicles |
| US20220198706A1 (en) * | 2019-09-12 | 2022-06-23 | Huawei Technologies Co., Ltd. | Positioning method, apparatus, and system |
| US20220211026A1 (en) * | 2019-02-28 | 2022-07-07 | Precision Al Inc. | System and method for field treatment and monitoring |
-
2022
- 2022-08-05 CN CN202210940002.3A patent/CN115164855A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210089040A1 (en) * | 2016-02-29 | 2021-03-25 | AI Incorporated | Obstacle recognition method for autonomous robots |
| 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 |
| US20210370968A1 (en) * | 2019-01-30 | 2021-12-02 | Baidu Usa Llc | A real-time map generation system for autonomous vehicles |
| US20220211026A1 (en) * | 2019-02-28 | 2022-07-07 | Precision Al Inc. | System and method for field treatment and monitoring |
| US20220198706A1 (en) * | 2019-09-12 | 2022-06-23 | Huawei Technologies Co., Ltd. | Positioning method, apparatus, and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3506158B1 (en) | Method and apparatus for determining lane line on road | |
| CN110619333B (en) | Text line segmentation method, text line segmentation device and electronic equipment | |
| JP2019058960A (en) | Robot system and workpiece take-out method | |
| CN112837371A (en) | Object grabbing method and device based on 3D matching and computing equipment | |
| CN111768450A (en) | Automatic detection method and device for line deviation of structured light camera based on speckle pattern | |
| CN111383261B (en) | Mobile robot, pose estimation method thereof and pose estimation device | |
| WO2022126522A1 (en) | Object recognition method, apparatus, movable platform, and storage medium | |
| CN112435222A (en) | Circuit board detection method and device and computer readable storage medium | |
| JP2014160370A (en) | Object detection method and object detection device | |
| CN113887433A (en) | Obstacle detection method and device, computer equipment and storage medium | |
| KR102283197B1 (en) | A method and device for determining the type of product | |
| CN115164855A (en) | Tray identification method, device and equipment and readable storage medium | |
| CN111080701A (en) | Intelligent cabinet object detection method and device, server and storage medium | |
| CN112183463B (en) | Ship identification model verification method and device based on radar image | |
| CN113156453A (en) | Moving object detection method, apparatus, device and storage medium | |
| CN112861708A (en) | Semantic segmentation method and device for radar image and storage medium | |
| CN112837370A (en) | Object stacking judgment method and device based on 3D bounding box and computing equipment | |
| CN112149687A (en) | Method for object recognition | |
| JP5222314B2 (en) | Surface measurement method and apparatus | |
| CN111723797B (en) | Method and system for determining bounding box of three-dimensional target | |
| CN116494253B (en) | Target object grabbing pose acquisition method and robot grabbing system | |
| CN117671637A (en) | Object point cloud overlapping identification method, device, equipment, robot and storage medium | |
| CN115390051B (en) | Laser radar calibration method, device, equipment and storage medium | |
| CN115861426A (en) | Material sampling method and device, computer equipment and storage medium | |
| CN117853893A (en) | Target detection method and device for hollow object and electronic equipment |
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 |