CN112581451B - Warehouse coil position detection system and method based on laser radar - Google Patents
Warehouse coil position detection system and method based on laser radar Download PDFInfo
- Publication number
- CN112581451B CN112581451B CN202011519503.1A CN202011519503A CN112581451B CN 112581451 B CN112581451 B CN 112581451B CN 202011519503 A CN202011519503 A CN 202011519503A CN 112581451 B CN112581451 B CN 112581451B
- Authority
- CN
- China
- Prior art keywords
- laser radar
- point cloud
- warehouse
- coil
- coordinate system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009466 transformation Effects 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 45
- 238000001914 filtration Methods 0.000 claims description 24
- 230000033001 locomotion Effects 0.000 claims description 24
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000009434 installation Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 101100190621 Arabidopsis thaliana PLC4 gene Proteins 0.000 description 5
- 229910000831 Steel Inorganic materials 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 229910000838 Al alloy Inorganic materials 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Abstract
The invention provides a warehouse coil position detection system and method based on a laser radar.A calibration plate is placed in a warehouse area, a single-line laser radar dynamic scanning calibration plate is used for calibrating, external parameters of the single-line laser radar relative to a world coordinate system are obtained, and pose transformation is carried out to convert point cloud of the single-line laser radar coordinate system into the world coordinate system; dynamically scanning a reservoir area by using a single-line laser radar, and carrying out pose transformation by combining the coordinates of an unmanned crown block to generate a three-dimensional point cloud of the reservoir area; and obtaining the characteristic of the coil point cloud through point cloud processing and characteristic extraction, fitting the target point cloud, calculating the size information of the coil length, the outer diameter and the like, and transmitting the coordinates of the coil under the world coordinate system to a warehouse management system. Experiments prove that the detection method of the embodiment can accurately generate the coil point cloud, accurately detect the shape and the position of the coil, and has small error.
Description
Technical Field
The invention relates to the technical field of intelligent warehouse logistics, in particular to a warehouse coil position detection method and device based on a laser radar.
Background
The storage area is used as an important pivot for logistics connection and production rhythm control in the steel production flow, is a foundation for unmanned and intelligent construction of factories, and the crane is the most important execution unit of the storage area. The traditional steel rolling workshop storehouse area, hoist operation mainly relies on the manual work to accomplish, and workman intensity of labour is big, and storehouse area operating efficiency is low, and leads to personnel, equipment safety and data information loss scheduling problem easily. The unmanned crane and the intelligent warehouse management technology are researched and applied, so that the operation mode of a warehouse area is fundamentally changed, unmanned operation of the crane and intelligent warehouse area scheduling are realized, and the unmanned crane has important significance for improving the production efficiency, reducing the production cost and improving the product quality.
At present, the acquisition of the coil position information of the reservoir area mainly depends on the three-dimensional reconstruction technology of laser point cloud to the reservoir area environment, and along with the rapid development of the laser radar technology, the manufacturing and research cost of the laser radar technology is gradually reduced, so that the laser radar technology is increasingly widely applied to industrial sites. For example, in the first patent (a workshop steel coil laser radar three-dimensional positioning measurement system, CN 109782300A) uses two-dimensional laser radar cross section scanning to assist in laser range finder positioning to reconstruct space slices, so that the task of three-dimensional reconstruction by using a two-dimensional laser radar is effectively completed, and the target positioning classification of steel coil point clouds is realized by combining gradient descent smoothing, connected domain clustering method and radial distortion correction algorithm, but rail matching in experiments is needed, and the method is not suitable for intelligent reconstruction of the existing reservoir area; the first literature (Zhang Ming, wang, chen Keying. Design of three-dimensional reconstruction system of indoor scene based on laser radar [ J ]. Electronic design engineering, 2019.) is to design a three-dimensional reconstruction system of indoor scene by adopting a laser ranging method and combining technologies such as a sensor and a motor control, the laser radar, an inertia element and speed measuring code wheel data are fused together through Kalman filtering, position information of a robot is calculated, a three-dimensional point cloud map of indoor scene is obtained, but the problems of scanning precision and target recognition are not involved, and coil scanning in a warehouse area is required to perform feature extraction and target recognition on the basis of three-dimensional reconstruction. The patent two (three-dimensional laser SLAM system and control method based on 2D laser radar, CN 109358342A) proposes a real-time three-dimensional laser SLAM system and control method based on 2D laser radar, depth information and rotation angle information are obtained simultaneously through a continuous uniform rotation 2D laser radar device, and are synchronously fused to generate three-dimensional point cloud, so that a three-dimensional reconstruction map is built in real time, the pose of a sensor is calculated through SLAM algorithm, a real-time positioning function is realized, the system is only suitable for small scene areas, and an ICP algorithm used in the system is sensitive to initial values.
Disclosure of Invention
The invention provides a laser radar-based warehouse coil position detection system and a laser radar-based warehouse coil position detection method, which have the following problems that the existing coil detection has low scanning precision and target recognition precision, is not suitable for intelligent reconstruction of the existing warehouse area, is only suitable for small scene areas, is sensitive to initial values by an ICP algorithm, and the like
In order to solve the technical problems, the embodiment of the invention provides the following scheme:
the warehouse coil position detection system based on the laser radar comprises a single-wire laser radar, wherein the single-wire laser radar is arranged on a laser radar adjustment platform, the laser radar adjustment platform is arranged right below an unmanned crown block maintenance platform, the single-wire laser radar dynamically scans a warehouse area along with the movement of the unmanned crown block maintenance platform, the warehouse point cloud information obtained by scanning is transmitted to an unmanned crown block industrial personal computer, the unmanned crown block industrial personal computer processes the warehouse point cloud information and transmits the data to a warehouse area management system, and the warehouse area management system is connected with the unmanned crown block industrial personal computer to realize three-party communication of the warehouse area management system, the unmanned crown block PLC and the single-wire laser radar;
a calibration plate is arranged in the reservoir area, the single-line laser radar dynamically scans the calibration plate for calibration, external parameters of the single-line laser radar relative to a world coordinate system are obtained, and pose transformation is carried out to convert point cloud of the single-line laser radar coordinate system into the world coordinate system; dynamically scanning a reservoir area by using a single-line laser radar, and carrying out pose transformation by combining the coordinates of an unmanned crown block to generate a three-dimensional point cloud of the reservoir area; and obtaining the characteristic of the coil point cloud through point cloud processing and characteristic extraction, fitting the target point cloud, calculating the size information of the coil length, the outer diameter and the like, and transmitting the coordinates of the calculated coil under the world coordinate system to a warehouse management system.
The calibration plate is obliquely placed on the ground, and the normal direction of the plane of the calibration plate is the advancing direction of the unmanned crown block.
The laser radar adjusting platform comprises an upper supporting part, and a rotating platform is arranged below the upper supporting part and can rotate around a rotation center.
The system also comprises a flat touch screen, wherein the flat touch screen is connected with the warehouse area management system and is used for issuing single-line laser radar scanning tasks and confirming scanning results.
The warehouse area management system is connected with the unmanned aerial vehicle industrial personal computer through the Ethernet.
A warehouse coil position detection method based on a laser radar comprises the following steps:
step 1: the method comprises the steps of radar calibration, namely finishing the installation of a warehouse coil position detection system based on a laser radar, adjusting a single-line laser radar, obliquely placing a calibration plate in a warehouse coil area, scanning the calibration plate along with the movement of an unmanned crown block through the single-line laser radar, generating three-dimensional point cloud by combining with the attitude of a sky vehicle, and obtaining external parameters of a single-line laser radar coordinate system relative to a world coordinate system of a reservoir area after data processing;
step 2: the method comprises the steps that coil position detection is carried out, an operator presses a scanning button in a user touch panel, a single-line laser radar collects a group of point cloud data according to scanning signals sent by the button in the user touch panel while moving along with an unmanned crown block, the point cloud data information is transmitted to an information processing server through an Ethernet, after point cloud processing and data calculation, the coil position information of a storage area is obtained, and the coil position information of the storage area is sent to a storage area management system and displayed on the user touch panel.
The radar calibration method comprises the following steps:
step 1.1: generating a three-dimensional point cloud in the surrounding environment of the warehouse, combining a single-line laser radar coordinate system with unmanned crown block motion pose coordinates output by an unmanned crown block PLC, introducing homogeneous coordinates, and performing displacement transformation to form the three-dimensional point cloud in the environment of the warehouse;
step 1.2: calculating an initial calibration transformation matrix, screening three-dimensional point clouds in the surrounding environment of the warehouse to obtain a ground point cloud, fitting a ground plane, calculating relative variables of a single-line laser radar coordinate system and a world coordinate system of a warehouse area according to the ground plane, introducing homogeneous coordinates to obtain the initial calibration transformation matrix, and transforming a plane, perpendicular to a Z axis, of the laser radar coordinate system to be coincident with a horizontal plane of the world coordinate system to obtain an initial calibration coordinate system;
step 1.3: calculating a transformation matrix after secondary calibration, screening three-dimensional point clouds in the surrounding environment of the warehouse to obtain a calibration plate point cloud, carrying out denoising treatment on the calibration plate point cloud, fitting to obtain a calibration plate plane, and calculating relative variables of an initial calibrated coordinate system and a world coordinate system of a reservoir area according to the calibration plate plane to obtain the transformation matrix after secondary calibration;
step 1.4: and calculating a transformation matrix, namely calculating the transformation matrix subjected to initial calibration and the transformation matrix subjected to secondary calibration to obtain a transformation matrix, storing the transformation matrix, and transforming the point cloud data under the single-line laser radar coordinate system into the point cloud under the world coordinate system by utilizing the transformation matrix.
Wherein the coil position detection comprises the steps of:
step 2.1: generating a three-dimensional point cloud of the reservoir environment, issuing a task by a reservoir management system, and generating the three-dimensional point cloud of the reservoir environment by combining the motion pose coordinates of the crown block when the single-line laser radar scans the coil of the reservoir along with the crown block;
step 2.2: and (3) calculating the position information of the coil in the reservoir, and carrying out data processing and feature extraction on the three-dimensional point cloud of the reservoir environment generated in the step (2.1) to obtain the position information of the coil in the reservoir.
The three-dimensional point cloud generation of the reservoir area environment comprises the following steps:
step 2.1.1: calculating the displacement of scanning points in each scanning period of the single-line laser radar by combining the pose of the unmanned aerial vehicle and the scanning period of the single-line laser radar to eliminate the motion distortion of the single-line laser radar in the scanning process along with the aerial vehicle;
step 2.1.2: and (3) converting a coordinate system, calculating a scanning point conversion matrix by combining the displacement of the scanning points calculated in the step (2.1.1) and the conversion matrix obtained by calibration, and converting the single-line laser radar coordinate system into a world coordinate system.
Wherein, the calculation of the position information of the coil of the reservoir area comprises the following steps:
step 2.2.1: feature extraction and noise reduction processing, namely extracting the point cloud of interest in the point cloud, and performing noise reduction processing on the point cloud of interest;
step 2.2.2: ground filtering, namely performing ground point cloud filtering processing on the point cloud subjected to noise reduction processing by using the fitted ground plane;
step 2.2.3: performing partition clustering, namely performing partition clustering on the point cloud processed in the step 2.2.2 to obtain a point cloud cluster;
step 2.2.4: and (3) coil identification, namely fitting each point cloud cluster into a cylinder, calculating the outer diameter and the length of the cylinder, comparing the cylinder with coil model information sent by a reservoir management system, taking the coil identification result with the smallest error as a coil identification result, and sending the coil identification result to the reservoir management system to update the coil position coordinates.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, experiments prove that the laser radar-based warehouse coil position detection method can accurately generate coil point clouds, accurately detect the shape and position of coils, and is small in error. Compared with the scheme of acquiring the coil position information by utilizing machine vision, the detection method is less influenced by factors such as ambient light, can directly acquire depth information, has higher accuracy, and is suitable for indoor large scene mapping; compared with the scheme of acquiring coil position information by utilizing the multi-line laser radar, the detection method has the advantages of lower cost, more convenient data interpretation and higher accuracy, and is more suitable for the actual production of enterprises; compared with the external parameter calibration mode by adopting the customized calibration block, the detection method of the invention uses the calibration plate to calibrate, has simpler operation process, can store the calibration result and correct the installation error; the detection system disclosed by the invention has the advantages of simple and clear overall structure, easiness in installation and maintenance, strong algorithm robustness and high calculation speed, and the accuracy meets the positioning requirements of most warehouses on coil.
Drawings
FIG. 1 is a schematic diagram of a laser radar-based warehouse coil position detection system of the present invention;
FIG. 2 is a schematic diagram of a laser radar adjustment platform of the laser radar-based warehouse coil position detection system of the present invention;
FIG. 3 is a three-dimensional point cloud splicing effect diagram of the laser radar-based warehouse coil position detection method;
FIG. 4 is a graph of calibration results of a laser radar-based warehouse coil position detection method of the present invention;
FIG. 5 is a graph of statistical filtering results of the laser radar-based warehouse coil position detection method of the present invention;
fig. 6 is a graph of ground filtering results of the laser radar-based warehouse coil position detection method of the present invention.
Fig. 7 is a graph of a point cloud segmentation result of the laser radar-based warehouse coil position detection method of the present invention.
Reference numerals:
1. single line laser radar; 2. a laser radar adjustment platform; 21. an upper support portion; 22. rotating the platform; 23. a center of rotation; 3. an unmanned crown block overhauling platform; 4. unmanned overhead traveling crane PLC; 5. unmanned aerial vehicle industrial personal computer; 6. a warehouse management system; 7. a flat touch screen; 8. a calibration plate;
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the intelligent warehouse material loading and unloading process, accurately acquiring the position information of the coil is one of important preconditions for realizing automatic loading and unloading. Because machine vision is greatly influenced by factors such as light in the environment, and is difficult to adapt to severe environments, the wide application of a machine vision technology in a factory is limited, the laser radar is less influenced by the environment, has higher precision, can directly acquire depth information, and the single-wire laser radar 1 is lower in cost than the multi-wire laser radar, the embodiment provides a warehouse coil position detection system based on the laser radar, and the single-wire laser radar 1 scans a warehouse coil along with the movement of a crown block to accurately acquire the position information of a coil. The single-line laser radar 1 moves along with the crown block, dynamically scans the reservoir area environment, realizes three-dimensional reconstruction of the reservoir area scene, accurately identifies coil information, provides a basis for the control decision of the unmanned crown block lifting and dropping, and greatly increases logistics efficiency.
As shown in fig. 1-5, the embodiment provides a warehouse coil position detection system based on a laser radar, which comprises a single-line laser radar 1, a laser radar adjustment platform 2, an unmanned crown block maintenance platform 3, an unmanned crown block PLC4, an unmanned crown block industrial personal computer 5, a warehouse management system 6, a flat touch screen 7 and a calibration plate 8; the single-line laser radar 1 is arranged on the laser radar adjustment platform 2, the single-line laser radar 1 dynamically scans a reservoir area along with the movement of the unmanned aerial vehicle maintenance platform 3, vertically scans the reservoir area downwards, a calibration plate 8 is arranged in the reservoir area, the calibration plate 8 is obliquely arranged on the ground, the plane normal direction of the calibration plate is the advancing direction of the unmanned aerial vehicle, the warehouse point cloud information obtained by scanning is transmitted to the unmanned aerial vehicle industrial personal computer 5, and the unmanned aerial vehicle industrial personal computer 5 processes the warehouse point cloud information and then transmits the data to the reservoir area management system 6; the laser radar adjustment platform 2 is arranged right below the unmanned crown block overhaul platform 3 and moves along with the unmanned crown block overhaul platform 3; the warehouse management system 6 is connected with the unmanned aerial vehicle industrial personal computer 5, and the warehouse management system 6 is connected with the unmanned aerial vehicle industrial personal computer 5 through the Ethernet, so that three-party communication among the warehouse management system 6, the unmanned aerial vehicle PLC4 and the single-line laser radar 1 is realized. The flat touch screen 7 is connected with the warehouse management system 6, and the flat touch screen 7 is connected with the warehouse management system 6 through the Ethernet and is used for issuing the scanning task of the single-line laser radar 1 and confirming the scanning result.
A calibration plate 8 is arranged in the reservoir area, the single-line laser radar 1 dynamically scans the calibration plate 8 for calibration, external parameters of the single-line laser radar 1 relative to a world coordinate system are obtained, and pose transformation is carried out to convert point cloud of the single-line laser radar 1 coordinate system into the world coordinate system; the single-line laser radar 1 dynamically scans a reservoir area, and performs pose transformation by combining the coordinates of the unmanned crown block to generate a three-dimensional point cloud of the reservoir area; the coil point cloud characteristics are obtained through point cloud processing and characteristic extraction, fitting is carried out on the target point cloud, the size information such as coil length, outer diameter and the like is calculated, and the coordinates of the calculated coil under the world coordinate system are transmitted to the warehouse management system 6.
As shown in fig. 2, the laser radar adjustment platform 2 is of an aluminum alloy structure and is mounted on the unmanned crown block overhaul platform 3 through an angle steel support frame. The laser radar adjustment platform 2 of this embodiment includes an upper support portion 21, the upper support portion 21 is made of an aluminum alloy material, a rotation platform 22 is provided below the upper support portion, the rotation platform 22 can rotate around a rotation center 23, and the laser radar adjustment platform is locked after adjusting the laser radar scanning angle. The single-wire lidar 1 is attached to the rotating platform 22 by bolts.
The coil position detection system of the embodiment dynamically scans the reservoir area environment along with the movement of the crown block by utilizing the single-wire laser radar 1, then performs filtering pretreatment, cluster analysis and feature extraction on the three-dimensional point cloud data, identifies the position information of the target coil, and provides a basis for the movement decision of the unmanned crown block lifting and dropping. After the operator confirms the scanning task with the warehouse management system 6, the invention automatically carries out a series of processes, and finally sends the result to the warehouse management system 6 to update the outer diameter, length and central axis position coordinates of the coil.
The embodiment provides a warehouse coil position detection method based on a laser radar, which comprises the following steps:
step 1: the method comprises the steps of radar calibration, namely finishing the installation of a warehouse coil position detection system based on the laser radar, adjusting the single-wire laser radar 1, obliquely placing a calibration plate 8 in a warehouse coil area, scanning the calibration plate 8 along with the movement of an unmanned crown block through the single-wire laser radar 1, generating three-dimensional point cloud by combining with the attitude of a sky vehicle, and obtaining external parameters of a single-wire laser radar 1 coordinate system relative to a world coordinate system of a storehouse area after data processing;
step 2: the method comprises the steps that coil position detection is carried out, an operator presses a scanning button in a user touch panel, the single-wire laser radar 1 collects a group of point cloud data according to scanning signals sent by the button in the user touch panel while moving along with an unmanned crown block, the point cloud data information is transmitted to an information processing server through an Ethernet, and after point cloud processing and data calculation, coil position detection results are sent to a warehouse management system 6 and displayed on the user touch panel.
After the step 1 is finished, when the position of the coil is needed to be measured, the step 2 is only needed to be executed; if the installation position, the attitude and the like of the radar change, the radar calibration in the step 1 is required to be executed again, and then the coil position is measured in the step 2.
In the radar calibration of step 1 in this embodiment, a calibration plate 8 is obliquely placed in a warehouse coil area, the calibration plate 8 is scanned along with the movement of an unmanned crown block by a single-line laser radar 1, a three-dimensional point cloud is generated by combining with the attitude of a crown block, then, the external parameters of the single-line laser radar 1 relative to a world coordinate system of a reservoir area are obtained after data processing, and the external parameters are stored locally, wherein the point cloud processing and the data calculation are that the original point cloud data are spliced into the three-dimensional point cloud, and the calibration parameters are fitted and calculated. The method comprises the steps of generating three-dimensional point cloud in the surrounding environment of a warehouse in step 1.1, calculating a transformation matrix of initial calibration in step 1.2, calculating a transformation matrix of the secondary calibration in step 1.3 and calculating a transformation matrix in step 1.4.
Step 1.1: generating a three-dimensional point cloud in the surrounding environment of the warehouse, combining a single-line laser radar 1 coordinate system with unmanned crown block motion pose coordinates output by an unmanned crown block PLC4, introducing homogeneous coordinates, and performing displacement transformation to form the three-dimensional point cloud in the surrounding environment of the warehouse;
specifically, the single line lidar 1 scan plane is considered to be the radar coordinate system o l x l y l z l Is represented by x l Axes and y l The plane formed by the axes, i.e. vertically downwards y of the radar coordinate system l An axis arranged along the movement direction of the unmanned aerial vehicle as z of a radar coordinate system l An axis perpendicular to z in the radar coordinate system l Axes and y l The axis is x of radar coordinate system l Shaft pressThe coordinate system outputs the motion pose coordinate x of the unmanned crown block, which is output by the unmanned crown block PLC4 c 、y c 、z c In combination, homogeneous coordinates are introduced to perform displacement transformation, as shown in formula-1. A three-dimensional point cloud in the surrounding environment is composed as shown in fig. 3.
Step 1.2: calculating an initial calibrated transformation matrix, screening three-dimensional point clouds in the surrounding environment of the warehouse to obtain a ground point cloud, fitting a ground plane, calculating relative variables of a single-line laser radar 1 coordinate system and a world coordinate system of a warehouse area according to the ground plane, introducing homogeneous coordinates to obtain the initial calibrated transformation matrix, and transforming a plane, perpendicular to a Z axis, of the laser radar coordinate system to be coincident with a horizontal plane of the world coordinate system to obtain an initial calibrated coordinate system;
specifically, through filtering is used for screening out ground point cloud, a RANSAC method is used for fitting a ground plane, a ground plane fitting equation is obtained, as shown in a formula-2, and according to a ground fitting result parameter A g 、B g 、C g 、D g Calculating single-line laser radar 1 coordinate system x l y l z l Around the world coordinate system x w y w z w X in the middle w Rotation angle theta of shaft x And y w Rotation angle theta of shaft y And the lidar coordinate system along the world coordinate system z w Translation distance t of shaft z Introducing homogeneous coordinates to obtain an initial calibrated transformation matrix T 1 As shown in formula-3, x of the laser radar coordinate system l o l y l Plane transformation to x with world coordinate system w o w y w Plane coincidence is carried out to obtain a coordinate system x after initial calibration 1 y 1 z 1 Wherein x is w Direction to the left, y w The direction is the same as the projection direction of the normal vector of the fitting plane of the calibration plate 8 (namely the advancing direction of the unmanned aerial vehicle) on the horizontal plane, and z w Direction vertically upwards o w Origin of coordinates for a pool defined in the pool management system 6；
A g x+B g y+C g z+D g =0 equation-2
Step 1.3: the transformation matrix after secondary calibration is calculated, three-dimensional point clouds in the surrounding environment of the warehouse are screened to obtain point clouds of a calibration plate 8, the point clouds of the calibration plate 8 are subjected to denoising treatment and then are fitted to obtain a plane of the calibration plate 8, and relative variables of a coordinate system after initial calibration and a world coordinate system of a warehouse area are calculated according to the plane of the calibration plate 8 to obtain a transformation matrix after secondary calibration;
specifically, through filtering is used for screening point clouds of a calibration plate 8 which is obliquely placed, statistical filtering is used for removing noise points, and a RANSAC method is used for fitting a plane of the calibration plate 8 to obtain a current coordinate system x 1 y 1 z 1 The plane equation of the calibration plate 8 is shown in the formula-4, and the coordinate system x after initial calibration is calculated by the parameters of the plane fitting result of the calibration plate 8 1 y 1 z 1 Around the world coordinate system z w y w z w Middle z w Is the rotation angle theta of (2) z Along x w Amount of translation t of shaft x And along z w Amount of translation t of shaft z Obtaining a transformation matrix T after secondary calibration 2 As shown in formula-5, x is 1 y 1 z 1 Transformation of a coordinate system to a world coordinate system x w y w z w ；
A b x+B b y+C b z+D b =0 equation-4
Step 1.4: and calculating a transformation matrix, namely calculating the transformation matrix subjected to initial calibration and the transformation matrix subjected to secondary calibration to obtain a transformation matrix, storing the transformation matrix, and transforming the point cloud data under the coordinate system of the single-line laser radar 1 into the point cloud under the world coordinate system by using the transformation matrix.
Specifically, after calibration is completed, the transformation matrix T is used for 1 And T 2 The transformation matrix T is calculated and stored, the point cloud data under the coordinate system of the single-line laser radar 1 can be transformed into the world coordinate system through a formula-6, the calibration result is as shown in fig. 4, the origin of the world coordinate system is tentatively set as the projection point A of the corner point of the calibration plate 8 on the ground, and the fitting result of the ground plane equation is as follows: 0.083232 x-0.996350y+0.018940z+1.348637=0, the plane fitting result at calibration plate 8 is: 0.044279x-0.832118y+0.552828z-0.373667 =0; .
In the step 2 of coil position detection, a single-line laser radar 1 scans a library area, an operator presses a start scanning button in a user touch panel, the single-line laser radar 1 collects a group of point cloud data according to a scanning signal sent by the button in the user touch panel, the point cloud data information is transmitted to an information processing server through an Ethernet, after point cloud processing and data calculation, the result is transmitted to a library area management system 6 and displayed on the user touch panel, the point cloud processing and the data calculation comprise a step 2.1 library area environment three-dimensional point cloud generation and a step 2.2 library area coil position information calculation, wherein the step 2.1 library area environment three-dimensional point cloud generation comprises a step 2.1.1 scanning point displacement calculation and a step 2.1.2 coordinate system conversion; step 2.2 of calculation of the coil position information of the reservoir area comprises the steps of step 2.2.1 of feature extraction and noise reduction treatment and step 2.2.2: ground filtering, step 2.2.3 segmentation clustering, and step 2.2.4 coil identification.
Step 2.1: generating a three-dimensional point cloud of the reservoir environment, wherein the reservoir management system 6 issues a task, and the single-line laser radar 1 generates the three-dimensional point cloud of the reservoir environment by combining the motion pose coordinates of the crown block when scanning the coil of the reservoir along with the crown block;
specifically, the warehouse management system 6 issues tasks, and when the single-line laser radar 1 scans the coil of the warehouse along with the crown block, the motion pose coordinates x of the crown block are combined c 、y c 、z c Generating a three-dimensional point cloud map of the reservoir area environment;
step 2.1.1: calculating the displacement of scanning points in each scanning period of the single-line laser radar 1 by combining the pose of the unmanned aerial vehicle and the scanning period of the single-line laser radar 1 to eliminate the motion distortion of the single-line laser radar 1 in the scanning process along with the aerial vehicle;
specifically, combine unmanned sky parking position x c 、y c 、z c And single line laser radar 1 scanning period T l Eliminating motion distortion of single-line laser radar 1 in the scanning process of the crown block along with the crown block, wherein the motion direction of the unmanned crown block is y of a world coordinate system w The direction is interpolated between the pose transmission frequencies of the unmanned crown block according to the direction, and the y-th scanning point of the ith scanning period of the single-line laser radar 1 is calculated w Displacement in the directionAs shown in formula-7, wherein +.>And->Adjacent two times y transmitted by the unmanned crown block PLC4 before and after the nth scanning period of the single-line laser radar 1 respectively w Coordinates on the axis, N is the number of periods of radar scanning in a reservoir scanning session, p numn The total number of scanning points in the nth scanning period;
step 2.1.2: and (3) converting a coordinate system, calculating a scanning point conversion matrix by combining the displacement of the scanning points calculated in the step (2.1.1) and the conversion matrix obtained by calibration, and converting the single-line laser radar 1 coordinate system into a world coordinate system.
Specifically, y of scanning point in combination with single-line lidar 1 w Displacement of shaftCalculating the transformation matrix T of the ith scanning point in the nth scanning period of the single-line laser radar 1 according to the transformation matrix T stored after the sum is calibrated i n And thus the single-line lidar 1 coordinate system x l y l z l Conversion to world coordinate system x w y w z w The following is shown in equation-8;
step 2.2: and (3) calculating the position information of the coil in the reservoir, and carrying out data processing and feature extraction on the three-dimensional point cloud of the reservoir environment generated in the step (2.1) to obtain the position information of the coil in the reservoir.
Step 2.2.1: feature extraction and noise reduction processing, namely extracting the point cloud of interest in the point cloud, and performing noise reduction processing on the point cloud of interest;
specifically, the interested region in the point cloud is screened through the straight-through filtering, only the points in the corresponding direction within the threshold range are reserved, and the point cloud of the target scanning region is left, as shown in a formula-9, wherein x is as follows wmin 、x wmax 、y wmin 、y wmax 、z wmin 、z wmax Respectively x w 、y w 、z w The cut-through filtering threshold range in the direction and removing the noise point in the point cloud by statistical filtering, as shown in formula-10, assuming that the three-dimensional point cloud obeys gaussian distribution, its shape is determined by the average distance μ and standard deviation σ between points, if the average distance d between the target point and k neighboring points wk Outside the standard range, the outliers are removed, and in the invention, the standard range is [ mu-zsigma, mu+zsigma]In this embodiment, z=1, k=5, the point cloud before and after filtering is shown in fig. 5, the point cloud before statistical filtering is on the left side, and the point cloud after statistical filtering is on the right side;
step 2.2.2: ground filtering, namely performing ground point cloud filtering processing on the point cloud subjected to noise reduction processing by using the fitted ground plane;
specifically, ground filtering is carried out, and a ground plane equation A is obtained after a ground plane is fitted through a RANSAC method g x+B g y+C g z+D g =0, filtering out the ground point cloud, as shown in equation-11, the points satisfying the conditionI.e. the point cloud to be deleted, wherein +.>For the distance of this point to the ground plane, e in this embodiment g The ground filtering result is shown in fig. 6, wherein the left graph is the point cloud before ground filtering, and the right graph is the ground point cloud to be filtered;
step 2.2.3: performing partition clustering, namely performing partition clustering on the point cloud processed in the step 2.2.2 to obtain a point cloud cluster;
specifically, the rest point cloud with the ground points removed is subjected to segmentation clustering by a DBSCAN clustering method, the point cloud is divided into the maximum set of points with the density connected, as shown in a formula-12, if the target point (x w ，y w ，z w ) Is given by a radius r eps Inner point number f (x) w ，y w ，z w ，r eps ) Pts greater than minimum inclusion point min The clusters are regarded as the same type, the above operation is repeated at the points within the radius range, a series of cluster analysis is carried out on the clusters of different types, and the points with less than k are removed firstly num Cluster-like and coordinate range distribution of (d) and coil size difference d coor Oversized class clusters, finally outputting a series of class clusters (c 1 ，c 2 Λc n ) In the present embodiment, pts min Has a value of 5, k num Take the value of 300 d coor The value is 0.5m;
f(x w ，y w ，z w ，r eps )＞Pts min equation-12
Step 2.2.4: and (3) coil identification, namely fitting each point cloud cluster into a cylinder, calculating the outer diameter and the length of the cylinder, comparing the cylinder with coil model information sent by the reservoir management system 6, taking the coil identification result with the smallest error as a coil identification result, and sending the coil identification result to the reservoir management system 6 to update the coil position coordinates.
Specifically, the point cloud class cluster (c 1 ，c 2 Λc n ) Performing cylinder fitting by a RANSAC method, calculating the outer diameter and length of a cylinder fitting result, comparing the cylinder fitting result with coil model information sent by a reservoir management system 6, taking the coil identification result with the smallest error as the coil identification result, sending the identification result to the reservoir management system 6, and updating the coil position coordinates;
the accuracy of the detection direction of the embodiment is verified, three coils with the length of 200mm and the diameter of 50mm are placed on the ground side by side, so that the single-wire laser radar 1 moves along with a guide rail on a self-built experimental platform, a lower scene is dynamically scanned, a three-dimensional point cloud is generated, the point cloud segmentation result is shown in fig. 7, the point clouds with different gray scales correspond to different coil clusters, and as can be seen from fig. 7, the detection method of the embodiment can accurately generate the coil point cloud. The coil model fitting results are shown in table 1; as can be seen from table 1, the detection method of the present embodiment detects the shape and position of the coil more accurately, and the error is small.
Table 1 accuracy verification
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. The warehouse coil position detection system based on the laser radar is characterized by comprising a single-wire laser radar, wherein the single-wire laser radar is arranged on a laser radar adjustment platform, the laser radar adjustment platform is arranged right below an unmanned aerial vehicle maintenance platform, the single-wire laser radar dynamically scans a warehouse area along with the movement of the unmanned aerial vehicle maintenance platform, the warehouse point cloud information obtained by scanning is transmitted to an unmanned aerial vehicle industrial personal computer, the unmanned aerial vehicle industrial personal computer processes the warehouse point cloud information and transmits the processed warehouse point cloud information to a warehouse area management system, and the warehouse area management system is connected with the unmanned aerial vehicle industrial personal computer to realize three-party communication of the warehouse area management system, the unmanned aerial vehicle PLC and the single-wire laser radar;
a calibration plate is arranged in the reservoir area, the single-line laser radar dynamically scans the calibration plate for calibration, external parameters of the single-line laser radar relative to a world coordinate system are obtained, and pose transformation is carried out to convert point cloud of the single-line laser radar coordinate system into the world coordinate system; dynamically scanning a reservoir area by using a single-line laser radar, and carrying out pose transformation by combining the coordinates of an unmanned crown block to generate a three-dimensional point cloud of the reservoir area; and obtaining the characteristic of the coil point cloud through point cloud processing and characteristic extraction, fitting the target point cloud, calculating the size information of the coil length, the outer diameter and the like, and transmitting the coordinates of the calculated coil under the world coordinate system to a warehouse management system.
2. The laser radar-based warehouse coil position detection system as claimed in claim 1, wherein the calibration plate is obliquely placed on the ground, and the normal direction of the plane is the advancing direction of the unmanned crown block.
3. A lidar-based warehouse coil position detection system as claimed in claim 1, wherein the lidar adjustment platform includes an upper support portion, below which is provided a rotation platform that is rotatable about a centre of rotation.
4. The lidar-based warehouse coil position detection system of claim 1, further comprising a flat touch screen, wherein the flat touch screen is connected to the warehouse management system for issuing single-line lidar scanning tasks and validating scanning results.
5. The lidar-based warehouse coil position detection system of claim 1, wherein the warehouse management system is connected to the unmanned aerial vehicle industrial personal computer via an ethernet network.
6. The warehouse coil position detection method based on the laser radar is characterized by comprising the following steps of:
step 1: radar calibration, namely completing the installation of the warehouse coil position detection system based on the laser radar according to any one of claims 1-4, adjusting the single-wire laser radar, obliquely placing a calibration plate in a warehouse coil area, scanning the calibration plate along with the movement of an unmanned crown block through the single-wire laser radar, generating a three-dimensional point cloud by combining with the attitude of a sky vehicle, and obtaining the external parameters of a single-wire laser radar coordinate system relative to a world coordinate system of a storehouse area after data processing;
step 2: the method comprises the steps that coil position detection is carried out, an operator presses a scanning button in a user touch panel, a single-line laser radar collects a group of point cloud data according to scanning signals sent by the button in the user touch panel while moving along with an unmanned crown block, the point cloud data information is transmitted to an information processing server through an Ethernet, after point cloud processing and data calculation, the coil position information of a storage area is obtained, and the coil position information of the storage area is sent to a storage area management system and displayed on the user touch panel.
7. The method for laser radar-based warehouse coil position detection as claimed in claim 6, wherein the radar calibration includes the steps of:
step 1.1: generating a three-dimensional point cloud in the surrounding environment of the warehouse, combining a single-line laser radar coordinate system with unmanned crown block motion pose coordinates output by an unmanned crown block PLC, introducing homogeneous coordinates, and performing displacement transformation to form the three-dimensional point cloud in the environment of the warehouse;
step 1.2: calculating an initial calibration transformation matrix, screening three-dimensional point clouds in the surrounding environment of the warehouse to obtain a ground point cloud, fitting a ground plane, calculating relative variables of a single-line laser radar coordinate system and a world coordinate system of a warehouse area according to the ground plane, introducing homogeneous coordinates to obtain the initial calibration transformation matrix, and transforming a plane, perpendicular to a Z axis, of the laser radar coordinate system to be coincident with a horizontal plane of the world coordinate system to obtain an initial calibration coordinate system;
step 1.3: calculating a transformation matrix after secondary calibration, screening three-dimensional point clouds in the surrounding environment of the warehouse to obtain a calibration plate point cloud, carrying out denoising treatment on the calibration plate point cloud, fitting to obtain a calibration plate plane, and calculating relative variables of an initial calibrated coordinate system and a world coordinate system of a reservoir area according to the calibration plate plane to obtain the transformation matrix after secondary calibration;
step 1.4: and calculating a transformation matrix, namely calculating the transformation matrix subjected to initial calibration and the transformation matrix subjected to secondary calibration to obtain a transformation matrix, storing the transformation matrix, and transforming the point cloud data under the single-line laser radar coordinate system into the point cloud under the world coordinate system by utilizing the transformation matrix.
8. A method of laser radar based warehouse coil position detection as claimed in claim 6, wherein the coil position detection includes the steps of:
step 2.1: generating a three-dimensional point cloud of the reservoir environment, issuing a task by a reservoir management system, and generating the three-dimensional point cloud of the reservoir environment by combining the motion pose coordinates of the crown block when the single-line laser radar scans the coil of the reservoir along with the crown block;
step 2.2: and (3) calculating the position information of the coil in the reservoir, and carrying out data processing and feature extraction on the three-dimensional point cloud of the reservoir environment generated in the step (2.1) to obtain the position information of the coil in the reservoir.
9. The method for detecting the position of a warehouse coil based on a laser radar as claimed in claim 8, wherein the generating of the three-dimensional point cloud of the warehouse environment includes the steps of:
step 2.1.1: calculating the displacement of scanning points in each scanning period of the single-line laser radar by combining the pose of the unmanned aerial vehicle and the scanning period of the single-line laser radar to eliminate the motion distortion of the single-line laser radar in the scanning process along with the aerial vehicle;
step 2.1.2: and (3) converting a coordinate system, calculating a scanning point conversion matrix by combining the displacement of the scanning points calculated in the step (2.1.1) and the conversion matrix obtained by calibration, and converting the single-line laser radar coordinate system into a world coordinate system.
10. The method for laser radar-based warehouse coil position detection as claimed in claim 8, wherein the calculation of the reservoir coil position information includes the steps of:
step 2.2.1: feature extraction and noise reduction processing, namely extracting the point cloud of interest in the point cloud, and performing noise reduction processing on the point cloud of interest;
step 2.2.2: ground filtering, namely performing ground point cloud filtering processing on the point cloud subjected to noise reduction processing by using the fitted ground plane;
step 2.2.3: performing partition clustering, namely performing partition clustering on the point cloud processed in the step 2.2.2 to obtain a point cloud cluster;
step 2.2.4: and (3) coil identification, namely fitting each point cloud cluster into a cylinder, calculating the outer diameter and the length of the cylinder, comparing the cylinder with coil model information sent by a reservoir management system, taking the coil identification result with the smallest error as a coil identification result, and sending the coil identification result to the reservoir management system to update the coil position coordinates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011519503.1A CN112581451B (en) | 2020-12-21 | 2020-12-21 | Warehouse coil position detection system and method based on laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011519503.1A CN112581451B (en) | 2020-12-21 | 2020-12-21 | Warehouse coil position detection system and method based on laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112581451A CN112581451A (en) | 2021-03-30 |
| CN112581451B true CN112581451B (en) | 2024-02-23 |
Family
ID=75136548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011519503.1A Active CN112581451B (en) | 2020-12-21 | 2020-12-21 | Warehouse coil position detection system and method based on laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581451B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113204029B (en) * | 2021-04-19 | 2022-09-16 | 北京科技大学 | Hot-rolled plate blank warpage detection device and method |
| CN113359105A (en) * | 2021-06-15 | 2021-09-07 | 武汉米佳信息技术有限公司 | Method and system for generating three-dimensional point cloud data based on two-dimensional laser radar |
| CN113567964B (en) * | 2021-06-29 | 2023-07-25 | 苏州一径科技有限公司 | Laser radar automatic test method, device and system |
| CN113689351B (en) * | 2021-08-24 | 2023-10-10 | 北京石油化工学院 | Dangerous chemical storage monitoring method, device and equipment based on depth camera |
| CN113759906A (en) * | 2021-08-30 | 2021-12-07 | 广州文远知行科技有限公司 | Vehicle alignment method and device, computer equipment and storage medium |
| CN114455511A (en) * | 2021-12-27 | 2022-05-10 | 劢微机器人科技(深圳)有限公司 | Forklift loading method and equipment and computer readable storage medium |
| CN114777648B (en) * | 2022-04-20 | 2023-09-05 | 中冶赛迪信息技术(重庆)有限公司 | Plate blank sensing measurement method and system |
| CN114994648B (en) * | 2022-08-05 | 2022-11-08 | 聚时科技(深圳)有限公司 | External parameter calibration method for 2D laser radar on linear motion mechanism |
| CN115222826B (en) * | 2022-09-15 | 2022-12-27 | 深圳大学 | Three-dimensional reconstruction method and device with changeable relative poses of structured light and camera |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014052274A (en) * | 2012-09-06 | 2014-03-20 | Fujitsu Ltd | Object detection apparatus, object detection program, and vehicle |
| CN104793619A (en) * | 2015-04-17 | 2015-07-22 | 上海交通大学 | Warehouse roadway automatic guided vehicle navigation device based on swing single-line laser radar |
| CN108732582A (en) * | 2017-04-20 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Vehicle positioning method and device |
| CN109160452A (en) * | 2018-10-23 | 2019-01-08 | 西安中科光电精密工程有限公司 | Unmanned transhipment fork truck and air navigation aid based on laser positioning and stereoscopic vision |
| CN109541612A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | Self aligning system in robot chamber based on single line laser radar identification column |
| CN110118973A (en) * | 2019-05-27 | 2019-08-13 | 杭州亚美利嘉科技有限公司 | Warehouse Intellisense recognition methods, device and electronic equipment |
| CN110852180A (en) * | 2019-10-17 | 2020-02-28 | 上海快仓智能科技有限公司 | TOF camera calibration method for automatic guided vehicle and automatic guided vehicle |
| CN111103576A (en) * | 2019-12-31 | 2020-05-05 | 三一重工股份有限公司 | Method and device for calibrating single-line laser radar and multi-line laser radar |
| CN111369630A (en) * | 2020-02-27 | 2020-07-03 | 河海大学常州校区 | Method for calibrating multi-line laser radar and camera |
| CN111429501A (en) * | 2020-03-25 | 2020-07-17 | 贝壳技术有限公司 | Depth map prediction model generation method and device and depth map prediction method and device |
| CN111505606A (en) * | 2020-04-14 | 2020-08-07 | 武汉大学 | Method and device for calibrating relative pose of multi-camera and laser radar system |
| CN111664843A (en) * | 2020-05-22 | 2020-09-15 | 杭州电子科技大学 | SLAM-based intelligent storage checking method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10572854B2 (en) * | 2017-11-09 | 2020-02-25 | Locus Robotics Corporation | Order grouping in warehouse order fulfillment operations |
-
2020
- 2020-12-21 CN CN202011519503.1A patent/CN112581451B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014052274A (en) * | 2012-09-06 | 2014-03-20 | Fujitsu Ltd | Object detection apparatus, object detection program, and vehicle |
| CN104793619A (en) * | 2015-04-17 | 2015-07-22 | 上海交通大学 | Warehouse roadway automatic guided vehicle navigation device based on swing single-line laser radar |
| CN108732582A (en) * | 2017-04-20 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Vehicle positioning method and device |
| CN109160452A (en) * | 2018-10-23 | 2019-01-08 | 西安中科光电精密工程有限公司 | Unmanned transhipment fork truck and air navigation aid based on laser positioning and stereoscopic vision |
| CN109541612A (en) * | 2018-11-09 | 2019-03-29 | 同济大学 | Self aligning system in robot chamber based on single line laser radar identification column |
| CN110118973A (en) * | 2019-05-27 | 2019-08-13 | 杭州亚美利嘉科技有限公司 | Warehouse Intellisense recognition methods, device and electronic equipment |
| CN110852180A (en) * | 2019-10-17 | 2020-02-28 | 上海快仓智能科技有限公司 | TOF camera calibration method for automatic guided vehicle and automatic guided vehicle |
| CN111103576A (en) * | 2019-12-31 | 2020-05-05 | 三一重工股份有限公司 | Method and device for calibrating single-line laser radar and multi-line laser radar |
| CN111369630A (en) * | 2020-02-27 | 2020-07-03 | 河海大学常州校区 | Method for calibrating multi-line laser radar and camera |
| CN111429501A (en) * | 2020-03-25 | 2020-07-17 | 贝壳技术有限公司 | Depth map prediction model generation method and device and depth map prediction method and device |
| CN111505606A (en) * | 2020-04-14 | 2020-08-07 | 武汉大学 | Method and device for calibrating relative pose of multi-camera and laser radar system |
| CN111664843A (en) * | 2020-05-22 | 2020-09-15 | 杭州电子科技大学 | SLAM-based intelligent storage checking method |
Non-Patent Citations (3)
| Title |
|---|
| 基于激光雷达的托盘位姿识别算法及验证;赵俊宏;吕恩利;陆华忠;王昱;王飞仁;;仪器仪表学报;20171015(第10期);全文 * |
| 基于点云中心的激光雷达与相机联合标定方法研究;康国华;张琪;张晗;徐伟证;张文豪;;仪器仪表学报;20191215(第12期);全文 * |
| 融合RFID相位差和激光扫描的动态目标定位;何静;刘冉;肖宇峰;梁高丽;付余路;;仪器仪表学报;20180215(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112581451A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112581451B (en) | Warehouse coil position detection system and method based on laser radar | |
| WO2021103154A1 (en) | Robot control method for smart spray coating of multiple vehicle models | |
| CN107089599B (en) | Suspender safety anticollision system and method based on the identification of container case area contoured three-dimensional | |
| CN112418103B (en) | Bridge crane hoisting safety anti-collision system and method based on dynamic binocular vision | |
| CN110245663B (en) | Method for identifying steel coil information | |
| CN110243380B (en) | Map matching method based on multi-sensor data and angle feature recognition | |
| CN109872355B (en) | Shortest distance acquisition method and device based on depth camera | |
| CN112697058A (en) | Machine vision-based large-size plate assembly gap on-line measurement system and method | |
| CN114152677B (en) | Ultrasonic automatic detection device for complex die forging | |
| CN113860178B (en) | System and method for identifying and measuring collision information of hoisted object of tower crane | |
| CN112132875B (en) | Multi-platform point cloud matching method based on surface features | |
| CN111539446A (en) | 2D laser hole site detection method based on template matching | |
| CN113483664B (en) | Screen plate automatic feeding system and method based on line structured light vision | |
| CN115880296B (en) | Machine vision-based prefabricated part quality detection method and device | |
| CN111708356B (en) | Automatic path planning system and method for crane | |
| CN117115249A (en) | Container lock hole automatic identification and positioning system and method | |
| CN116659500A (en) | Mobile robot positioning method and system based on laser radar scanning information | |
| CN116486287A (en) | Target detection method and system based on environment self-adaptive robot vision system | |
| CN114353779A (en) | Method for rapidly updating local cost map of robot by point cloud projection | |
| CN111854678B (en) | Pose measurement method based on semantic segmentation and Kalman filtering under monocular vision | |
| CN111121639B (en) | Rigid-flexible integrated crack detection system for narrow building space | |
| CN112231848A (en) | Method and system for constructing vehicle spraying model | |
| CN115582840B (en) | Method and system for calculating sorting and grabbing pose of borderless steel plate workpiece and sorting method | |
| CN114136219B (en) | Tunnel wet spraying vehicle guniting thickness real-time detection device and method based on line structured light | |
| CN110232714B (en) | Calibration method and system of depth camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |