[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN116524010A - Unmanned crown block positioning method, system and storage medium for bulk material storage - Google Patents

Unmanned crown block positioning method, system and storage medium for bulk material storage Download PDF

Info

Publication number
CN116524010A
CN116524010A CN202310456002.0A CN202310456002A CN116524010A CN 116524010 A CN116524010 A CN 116524010A CN 202310456002 A CN202310456002 A CN 202310456002A CN 116524010 A CN116524010 A CN 116524010A
Authority
CN
China
Prior art keywords
bulk material
grabbing
storage area
points
bulk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310456002.0A
Other languages
Chinese (zh)
Other versions
CN116524010B (en
Inventor
李永
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Yunzhong Future Technology Co ltd
Original Assignee
Beijing Yunzhong Future Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Yunzhong Future Technology Co ltd filed Critical Beijing Yunzhong Future Technology Co ltd
Priority to CN202310456002.0A priority Critical patent/CN116524010B/en
Publication of CN116524010A publication Critical patent/CN116524010A/en
Application granted granted Critical
Publication of CN116524010B publication Critical patent/CN116524010B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/80Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10028Range image; Depth image; 3D point clouds
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method, a system and a storage medium for positioning an unmanned crown block in bulk material storage, which comprise the following steps: acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area; acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile; extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, selecting the feature points with highest grabbing evaluation scores as grabbing points, carrying out grabbing point space positioning through a binocular system, and carrying out accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points. According to the invention, the grabbing positions in the bulk storage area are optimized, and meanwhile, the grabbing points of the unmanned crown block are accurately positioned, so that the production efficiency is improved, and the safety and stability of production work are ensured.

Description

Unmanned crown block positioning method, system and storage medium for bulk material storage
Technical Field
The invention relates to the technical field of unmanned crown blocks, in particular to a method, a system and a storage medium for positioning an unmanned crown block for bulk storage.
Background
With the rapid development of modern science and technology and the increasing demand of enterprise production logistics, the running efficiency of the crown block is improved, and the operation accuracy of the crown block is thinned, so that the crown block becomes an urgent issue. At present, the handling and warehouse management business of bulk cargo mostly adopts a manual operation mode, a large amount of personnel are needed to participate, the labor cost is high, the operation level is uneven, the safety risk is high, and the production efficiency is low. In recent years, due to the influence of safety, quality, cost and the like, the realization of intelligent management of logistics in a warehouse area becomes more and more important, and particularly in some high-risk high-strength operation areas, the intelligent requirement on accurate operation positioning of an unmanned crown block is needed to be solved.
In order to enable the positioning of the unmanned crown block for bulk material storage to be more convenient and finer, a system needs to be developed to be matched with the unmanned crown block for implementation, and the system is used for automatically identifying the operation position based on the unmanned crown block system, so that the defect of the system in the positioning technology is overcome, and the unmanned crown block system of various warehouses is ensured to be implemented smoothly. The automatic identification system for the operation position is put into use, solves the problem of material pile positioning, shortens the downtime, the round trip and the searching time caused by manual operation, reduces the number of times of warehouse reversing, and greatly reduces the labor cost. In the implementation process of the system, how to optimize the grabbing points of bulk material storage and how to accurately position the grabbing points are all the problems which need to be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides an unmanned crown block positioning method, an unmanned crown block positioning system and a storage medium for bulk material storage.
The first aspect of the invention provides an unmanned crown block positioning method for bulk material storage, which comprises the following steps:
acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, and selecting the feature points with highest grabbing evaluation scores as grabbing points;
and acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and carrying out the accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points.
In the scheme, the image information of a bulk material storage area is acquired, the position of a target bulk material is determined by identifying the bulk material according to the image information of the bulk material storage area, and the distribution characteristics of the target bulk material storage area are acquired, specifically:
Acquiring image information of a bulk material storage area through a preset visual sensor of the bulk material storage area, and preprocessing the image information to acquire color characteristics and texture characteristics of a bulk material storage area in the bulk material storage area;
constructing a bulk material identification model, carrying out initialization training on the bulk material identification model by utilizing a related database, inputting the color characteristics and the texture characteristics into the bulk material identification model for identification, and obtaining a storage area of a target bulk material in a bulk material bin storage area;
acquiring image information and three-dimensional scanning data of a target bulk storage area, and performing joint calculation on the image information and the three-dimensional scanning data to generate three-dimensional point cloud data of the target bulk storage area;
and acquiring the distribution characteristics of the visible parts of the bulk materials in the target bulk material storage area according to the three-dimensional point cloud data.
In this scheme, according to the distribution characteristic obtain bulk cargo distribution profile in the target bulk cargo storage area, specifically be:
image segmentation is carried out according to the image information of the target bulk storage area to obtain an image of a candidate grabbing area, denoising is carried out on the image of the candidate grabbing area, and binarization is carried out on the image through a threshold segmentation method;
Acquiring edge contour information in binarized images of different angles by using a Canny operator, and registering and splicing the edge contour information of different angles;
and extracting three-dimensional point cloud data of the candidate grabbing area through the three-dimensional point cloud data of the target bulk material storage area, optimizing the spliced edge profile information, and generating a bulk material distribution profile in the candidate grabbing area.
In the scheme, the candidate grabbing area of the target bulk cargo is judged according to the bulk cargo distribution profile, and specifically:
preliminary coarse positioning is carried out on grabbing of the bulk material storage area according to the position information of the target bulk material storage area, and a bulk material distribution profile of the target bulk material storage area is obtained;
acquiring a plurality of contour line segments forming a bulk material distribution contour, acquiring end points of the contour line segments as contour points, optimizing the contour points, dividing the bulk material distribution contour through the optimized contour points, and generating a contour segmentation result;
acquiring geometric features of bulk distribution profiles in a target bulk storage area according to slopes of all profile line segments and fluctuation degrees of adjacent profile line segments in a profile segmentation result;
partitioning the target bulk storage area according to the geometric features, obtaining a contour line segment with the slope larger than a preset slope threshold value in the bulk distribution contour, and judging whether the fluctuation degree of the contour line segment and the adjacent contour line segment is positive and larger than the preset threshold value;
If the undulation degree is judged to be positive and larger than the preset threshold value, taking the areas where the contour line segment and the adjacent contour line segment are located as candidate grabbing areas of the target bulk material;
the standard line is preset according to the bulk material distribution profile in the target bulk material storage area, the waviness is positive when the adjacent profile line sections are located above the standard line, and the waviness is negative when the adjacent profile line sections are located below the standard line.
In the scheme, feature points are extracted according to the bulk material distribution profile of a candidate grabbing area, grabbing evaluation is carried out on the feature points through deep learning, and the feature points with highest grabbing evaluation scores are selected as grabbing points, specifically:
acquiring the material level depth in the candidate grabbing area through the bulk cargo distribution profile in the candidate grabbing area, and determining the average material level depth according to the material level depth information;
acquiring a characteristic point with slope change larger than a preset slope change threshold value in a bulk material distribution profile of a candidate grabbing area, acquiring a height difference between the characteristic point and an average material level depth, and selecting the characteristic point with the height difference larger than a preset height difference threshold value as a marked characteristic point;
establishing a grabbing point evaluation model based on a neural network, taking grabbing safety, grabbing convenience and grabbing full rate as evaluation indexes, inputting the height difference between the marked characteristic points and the average material level depth, the distance between the marked characteristic points and the neighbor characteristic points, the height difference and the slope included angle of the contour line segments before and after the characteristic points, and outputting the evaluation result of the characteristic points;
Carrying out normalization processing on the input data, acquiring the score condition of the characteristic point in each evaluation index through a grabbing point evaluation model, and acquiring grabbing evaluation scores of the characteristic point according to the score condition of each evaluation index and a preset weight;
and sorting the characteristic points according to the evaluation result scores, and selecting the characteristic point with the highest grabbing evaluation score as a grabbing point.
In this scheme, obtain the space location of snatching the point according to the binocular system of unmanned overhead traveling crane, carry out the accurate positioning of unmanned overhead traveling crane according to the space coordinate who snatchs the point, specifically do:
calibrating a binocular system of the unmanned crown block, and simultaneously correcting distortion to obtain inner and outer parameter matrixes of the left and right vision sensors;
acquiring left-eye images and right-eye images of grabbing points in a binocular system, and acquiring image coordinate information of grabbing points according to the left-eye images and the right-eye images;
and converting the image coordinate information into world coordinate information through left transformation according to the internal and external parameter matrix and the parallax mean value of the binocular system, and carrying out accurate positioning of the unmanned crown block according to the world coordinate information of the grabbing point.
The second aspect of the invention also provides an unmanned crown block positioning system for bulk material storage, which comprises: the automatic positioning device comprises a memory and a processor, wherein the memory comprises an unmanned crown block positioning method program for bulk material storage, and the unmanned crown block positioning method program for bulk material storage realizes the following steps when being executed by the processor:
Acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, and selecting the feature points with highest grabbing evaluation scores as grabbing points;
and acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and carrying out the accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points.
The third aspect of the present invention also provides a computer readable storage medium, wherein the computer readable storage medium includes a method program for positioning an unmanned aerial vehicle for bulk material storage, and when the method program is executed by a processor, the method for positioning an unmanned aerial vehicle for bulk material storage is implemented.
The invention discloses a method, a system and a storage medium for positioning an unmanned crown block in bulk material storage, which comprise the following steps: acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area; acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile; extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, selecting the feature points with highest grabbing evaluation scores as grabbing points, carrying out grabbing point space positioning through a binocular system, and carrying out accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points. According to the invention, the grabbing positions in the bulk storage area are optimized, and meanwhile, the grabbing points of the unmanned crown block are accurately positioned, so that the production efficiency is improved, and the safety and stability of production work are ensured; in addition, the automatic identification of the operation position of the unmanned overhead travelling crane makes up the defect of the system positioning technology and ensures that the unmanned system of the overhead travelling crane is smoothly implemented in bulk storage. The automatic identification system for the operation position is put into use, solves the problem of material pile positioning, shortens the downtime, the round trip and the searching time caused by manual operation, reduces the number of times of warehouse reversing, and greatly reduces the labor cost.
Drawings
FIG. 1 shows a flow chart of an unmanned crown block positioning method for bulk storage of the present invention;
FIG. 2 shows a flow chart of a method of the present invention for determining candidate gripping areas of a target bulk material based on a bulk material distribution profile;
FIG. 3 is a flow chart of a method for selecting the feature point with the highest grasping evaluation score as the grasping point according to the invention;
fig. 4 shows a block diagram of an unmanned crown block positioning system for bulk storage according to the invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of an unmanned crown block positioning method for bulk material storage according to the invention.
As shown in fig. 1, a first aspect of the present invention provides a method for positioning an unmanned crown block in bulk storage, including:
S102, acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
s104, acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
s106, extracting characteristic points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the characteristic points through deep learning, and selecting the characteristic points with highest grabbing evaluation scores as grabbing points;
s108, acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and accurately positioning the unmanned crown block according to the space coordinates of the grabbing points.
The method is characterized by acquiring image information of a bulk material storage area, identifying and determining a target bulk material position according to the image information of the bulk material storage area, and acquiring distribution characteristics of the target bulk material storage area, and specifically comprising the following steps: acquiring image information of a bulk storage area through a preset vision sensor of the bulk storage area, and performing preprocessing such as filtering and denoising on the image information to acquire and texture characteristics; calculating chromaticity coordinates of each pixel in the image information of the bulk material storage area in the LUV color space, establishing a chromaticity library through the chromaticity coordinates of the image information, obtaining color characteristics of a bulk material storage area in the bulk material storage area, extracting shape characteristics and texture characteristics through the preprocessed image information, constructing a bulk material identification model based on a deep learning method such as a support vector machine or a neural network, initializing the bulk material identification model by using a relevant database, inputting the color characteristics and the texture characteristics into the bulk material identification model for identification, identifying target bulk materials, and obtaining a storage area of the target bulk materials according to a material area in the bulk material storage area; acquiring image information and three-dimensional scanning data of a target bulk storage area through a visual sensor and three-dimensional laser scanning, and performing joint calculation on the image information and the three-dimensional scanning data to generate three-dimensional point cloud data of the target bulk storage area; and acquiring the distribution characteristics of the visible parts of the bulk materials in the target bulk material storage area according to the three-dimensional point cloud data.
The method is characterized in that the bulk material distribution profile in the target bulk material storage area is obtained according to the distribution characteristics, and specifically comprises the following steps: image segmentation is carried out according to the image information of the target bulk storage area to obtain an image of a candidate grabbing area, denoising is carried out on the image of the candidate grabbing area, and binarization is carried out on the image through a threshold segmentation method; acquiring edge contour information in binarized images of different angles by using a Canny operator, and registering and splicing the edge contour information of different angles; and extracting three-dimensional point cloud data of the candidate grabbing area through the three-dimensional point cloud data of the target bulk material storage area, optimizing the spliced edge profile information, and generating a bulk material distribution profile in the candidate grabbing area.
Fig. 2 shows a flow chart of a method of the invention for determining candidate gripping areas of a target bulk material from a bulk material distribution profile.
According to the embodiment of the invention, the candidate grabbing area of the target bulk cargo is judged according to the bulk cargo distribution profile, specifically:
s202, carrying out preliminary coarse positioning on grabbing of a bulk material storage area according to position information of a target bulk material storage area, and obtaining a bulk material distribution profile of the target bulk material storage area;
S204, acquiring a plurality of contour line segments forming a bulk material distribution contour, acquiring end points of the contour line segments as contour points, optimizing the contour points, dividing the bulk material distribution contour through the optimized contour points, and generating a contour segmentation result;
s206, obtaining geometric features of bulk distribution profiles in the target bulk storage area according to the slope of each profile line segment and the fluctuation degree of adjacent profile line segments in the profile segmentation result;
s208, partitioning the target bulk storage area according to the geometric features, obtaining a contour line segment with the slope larger than a preset slope threshold value in the bulk distribution contour, and judging whether the fluctuation degree of the contour line segment and the adjacent contour line segment is positive and larger than the preset threshold value;
and S210, if the undulation degree is judged to be positive and larger than the preset threshold value, taking the area where the contour line segment and the adjacent contour line segment are located as a candidate grabbing area of the target bulk material.
It should be noted that, the preference is performed according to the contribution degree of the contour points, the contour point with the smallest contribution degree is selected, the contour line segments at the two ends of the contour point are deleted, and the two non-adjacent end points are connected to form a new contour curve, wherein the calculation formula of the contribution degree g of the contour point is as follows:
Wherein k (x i ) Representing a contour line segment x i Length information of k (x) i+1 ) Representing a contour line segment x i+1 Length information of θ (x) i ,x i+1 ) Representing a contour line segment x i And contour line segment x i+1 Included angle information g i Representing the contribution degree of the contour point i;
judging whether the fluctuation degree of the contour line segments at the two ends of the contour point is positive and larger than a preset threshold value, and defining the contour line segments at the two ends of the contour point i as x 1,i X is a group i,2 Connecting two non-adjacent endpoints 1,2 to obtain segment x 1,2 Selecting a point of selecting preset data including contour points on contour curves at two ends of the contour point i to a line segment x 1,2 The standard deviation of the distance of (2) is used as the fluctuation degree, a standard line is preset according to the distribution profile of bulk materials in the target bulk material storage area, the fluctuation degree is positive when the adjacent profile line section is positioned above the standard line, the fluctuation degree is negative when the adjacent profile line section is positioned below the standard line, and the average material level depth of the target bulk material area or the candidate grabbing area is usually used as the preset standard line for the convenience of subsequent calculation.
Fig. 3 shows a flow chart of a method for selecting the feature point with the highest grasping evaluation score as the grasping point according to the invention.
According to the embodiment of the invention, the characteristic points are extracted according to the bulk material distribution profile of the candidate grabbing area, grabbing evaluation is carried out on the characteristic points through deep learning, and the characteristic point with the highest grabbing evaluation score is selected as the grabbing point, specifically:
S302, acquiring the material level depth in the candidate grabbing area through the bulk cargo distribution profile in the candidate grabbing area, and determining the average material level depth according to the material level depth information;
s304, acquiring a characteristic point with slope change larger than a preset slope change threshold value in a bulk material distribution profile of a candidate grabbing area, acquiring a height difference between the characteristic point and the average material level depth, and selecting the characteristic point with the height difference larger than the preset height difference threshold value as a marking characteristic point;
s306, a grabbing point evaluation model is established based on a neural network, grabbing safety, grabbing convenience and grabbing full rate are used as evaluation indexes, the height difference between the marked characteristic points and the average material level depth, the distance between the marked characteristic points and the neighbor characteristic points, the height difference and the slope included angle of the contour line segments before and after the characteristic points are input, and the evaluation result of the characteristic points is output;
s308, carrying out normalization processing on the input data, acquiring the score condition of the characteristic points in each evaluation index through a grabbing point evaluation model, and acquiring grabbing evaluation scores of the characteristic points according to the score condition of each evaluation index and a preset weight;
and S310, sorting the characteristic points according to the evaluation result scores, and selecting the characteristic point with the highest grabbing evaluation score as a grabbing point.
The method is characterized in that the grabbing safety, grabbing convenience and grabbing full load rate are used as evaluation indexes, the height difference between the marked feature points and the average material level depth, the distance and the height difference between the marked feature points and the neighbor feature points and the slope included angle of the profile line section before and after the feature points are used as inputs, the higher the height of the bulk pile where the feature points are located is indicated when the height difference between the feature points and the average material level depth and the height difference between the feature points are positive, the higher the relative safety and the convenience are achieved, and conversely, when the negative height difference between the feature points and the neighbor feature points is large and the distance between the feature points is close to the neighbor feature points, the feature points are indicated to be lower than the neighbor feature points around, the neighbor feature points are prone to collapse, the risk is high, the neighbor feature points around hinder grabbing of the feature points, grabbing convenience is low, in addition, the standard grabbing full load rate of the grab bucket is preset, and the feature point grabbing condition is judged according to the maximum grabbing angle and the included angle of the profile line section before and after the feature points and the neighbor feature points are located. The neural network comprises an input layer, an implicit layer and an output layer, parameters such as the number of neurons, a transfer function, a learning function, a target error value and the like of the input layer, the implicit layer and the output layer are preset, characteristic point evaluation data of subjective evaluation of expert decision is selected, and the neural network is subjected to initialization training to construct a grabbing point evaluation model.
It should be noted that, according to the binocular system of unmanned overhead traveling crane obtain the space location of snatching the point, carry out the accurate positioning of unmanned overhead traveling crane according to the space coordinate of snatching the point, specifically do: calibrating a binocular system of the unmanned crown block, and simultaneously correcting distortion to obtain inner and outer parameter matrixes of the left and right vision sensors; acquiring left-eye images and right-eye images of grabbing points in a binocular system, and acquiring image coordinate information of grabbing points according to the left-eye images and the right-eye images; and converting the image coordinate information into world coordinate information through left transformation according to the internal and external parameter matrix and the parallax mean value of the binocular system, and carrying out accurate positioning of the unmanned crown block according to the world coordinate information of the grabbing point.
According to the embodiment of the invention, after the unmanned crown block takes the material, the placing planning is carried out on the discharging area according to the target taking amount, and the method specifically comprises the following steps:
acquiring target bulk material type information and target cargo taking amount, and judging whether the facility condition of the discharging area is suitable for storing the target bulk material according to the target bulk material type information and the target cargo taking amount;
if the storage of the target bulk cargo is suitable, acquiring the regional distribution characteristics of the discharging region according to the distribution of the material taking equipment, the channel condition and the barrier information of the discharging region, and planning the preliminary discharging position of the target bulk cargo according to the distribution characteristics;
Acquiring single material taking quantity of the target bulk material, placing according to the initial material placing position after the single material taking quantity reaches a material placing area, judging the distribution characteristics of the target bulk material after the placement, updating the area distribution characteristics according to the distribution characteristics, and determining the next material placing position;
if the situation that bulk cargo blocks equipment operation and a channel passes occurs in the target bulk cargo placing process, an area in a preset range is defined as a temporary placing area by taking the blocking area as a center, bulk cargo placing in the temporary placing area is suspended, early warning information is generated, and the early warning information is sent to field staff in a preset mode.
Fig. 4 shows a block diagram of an unmanned crown block positioning system for bulk storage according to the invention.
The second aspect of the present invention also provides an unmanned crown block positioning system 5 for bulk material storage, the system comprising: the storage 41 and the processor 42, wherein the storage comprises an unmanned crown block positioning method program for bulk material storage, and the unmanned crown block positioning method program for bulk material storage realizes the following steps when being executed by the processor:
acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
Acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, and selecting the feature points with highest grabbing evaluation scores as grabbing points;
and acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and carrying out the accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points.
The method is characterized by acquiring image information of a bulk material storage area, identifying and determining a target bulk material position according to the image information of the bulk material storage area, and acquiring distribution characteristics of the target bulk material storage area, and specifically comprising the following steps: acquiring image information of a bulk storage area through a preset vision sensor of the bulk storage area, and performing preprocessing such as filtering and denoising on the image information to acquire and texture characteristics; calculating chromaticity coordinates of each pixel in the image information of the bulk material storage area in the LUV color space, establishing a chromaticity library through the chromaticity coordinates of the image information, obtaining color characteristics of a bulk material storage area in the bulk material storage area, extracting shape characteristics and texture characteristics through the preprocessed image information, constructing a bulk material identification model based on a deep learning method such as a support vector machine or a neural network, initializing the bulk material identification model by using a relevant database, inputting the color characteristics and the texture characteristics into the bulk material identification model for identification, identifying target bulk materials, and obtaining a storage area of the target bulk materials according to a material area in the bulk material storage area; acquiring image information and three-dimensional scanning data of a target bulk storage area through a visual sensor and three-dimensional laser scanning, and performing joint calculation on the image information and the three-dimensional scanning data to generate three-dimensional point cloud data of the target bulk storage area; and acquiring the distribution characteristics of the visible parts of the bulk materials in the target bulk material storage area according to the three-dimensional point cloud data.
The method is characterized in that the bulk material distribution profile in the target bulk material storage area is obtained according to the distribution characteristics, and specifically comprises the following steps: image segmentation is carried out according to the image information of the target bulk storage area to obtain an image of a candidate grabbing area, denoising is carried out on the image of the candidate grabbing area, and binarization is carried out on the image through a threshold segmentation method; acquiring edge contour information in binarized images of different angles by using a Canny operator, and registering and splicing the edge contour information of different angles; and extracting three-dimensional point cloud data of the candidate grabbing area through the three-dimensional point cloud data of the target bulk material storage area, optimizing the spliced edge profile information, and generating a bulk material distribution profile in the candidate grabbing area.
According to the embodiment of the invention, the candidate grabbing area of the target bulk cargo is judged according to the bulk cargo distribution profile, specifically:
preliminary coarse positioning is carried out on grabbing of the bulk material storage area according to the position information of the target bulk material storage area, and a bulk material distribution profile of the target bulk material storage area is obtained;
acquiring a plurality of contour line segments forming a bulk material distribution contour, acquiring end points of the contour line segments as contour points, optimizing the contour points, dividing the bulk material distribution contour through the optimized contour points, and generating a contour segmentation result;
Acquiring geometric features of bulk distribution profiles in a target bulk storage area according to slopes of all profile line segments and fluctuation degrees of adjacent profile line segments in a profile segmentation result;
partitioning the target bulk storage area according to the geometric features, obtaining a contour line segment with the slope larger than a preset slope threshold value in the bulk distribution contour, and judging whether the fluctuation degree of the contour line segment and the adjacent contour line segment is positive and larger than the preset threshold value;
and if the undulation degree is judged to be positive and is larger than the preset threshold value, taking the area where the contour line segment and the adjacent contour line segment are located as a candidate grabbing area of the target bulk cargo.
It should be noted that, the preference is performed according to the contribution degree of the contour points, the contour point with the smallest contribution degree is selected, the contour line segments at the two ends of the contour point are deleted, and the two non-adjacent end points are connected to form a new contour curve, wherein the calculation formula of the contribution degree g of the contour point is as follows:
wherein k (x i ) Representing a contour line segment x i Length information of k (x) i+1 ) Representing a contour line segment x i+1 Length information of θ (x) i ,x i+1 ) Representing a contour line segment x i And contour line segment x i+1 Included angle information g i Representing the contribution degree of the contour point i;
judging whether the fluctuation degree of the contour line segments at the two ends of the contour point is positive and larger than a preset threshold value, and defining the contour line segments at the two ends of the contour point i as x 1,i X is a group i,2 Connecting two non-adjacent endpoints 1,2 to obtain segment x 1,2 Selecting a point of selecting preset data including contour points on contour curves at two ends of the contour point i to a line segment x 1,2 As the waviness, presetting a standard line according to the distribution profile of bulk materials in the target bulk material storage area when adjacentThe relief of the contour line segment is positive when the contour line segment is positioned above the standard line, and the relief of the contour line segment is negative when the contour line segment is positioned below the standard line, and the average material level depth of the target bulk material area or the candidate grabbing area is usually used as a preset standard line for facilitating subsequent calculation.
According to the embodiment of the invention, the characteristic points are extracted according to the bulk material distribution profile of the candidate grabbing area, grabbing evaluation is carried out on the characteristic points through deep learning, and the characteristic point with the highest grabbing evaluation score is selected as the grabbing point, specifically:
acquiring the material level depth in the candidate grabbing area through the bulk cargo distribution profile in the candidate grabbing area, and determining the average material level depth according to the material level depth information;
acquiring a characteristic point with slope change larger than a preset slope change threshold value in a bulk material distribution profile of a candidate grabbing area, acquiring a height difference between the characteristic point and an average material level depth, and selecting the characteristic point with the height difference larger than a preset height difference threshold value as a marked characteristic point;
Establishing a grabbing point evaluation model based on a neural network, taking grabbing safety, grabbing convenience and grabbing full rate as evaluation indexes, inputting the height difference between the marked characteristic points and the average material level depth, the distance between the marked characteristic points and the neighbor characteristic points, the height difference and the slope included angle of the contour line segments before and after the characteristic points, and outputting the evaluation result of the characteristic points;
carrying out normalization processing on the input data, acquiring the score condition of the characteristic point in each evaluation index through a grabbing point evaluation model, and acquiring grabbing evaluation scores of the characteristic point according to the score condition of each evaluation index and a preset weight;
and sorting the characteristic points according to the evaluation result scores, and selecting the characteristic point with the highest grabbing evaluation score as a grabbing point.
The method is characterized in that the grabbing safety, grabbing convenience and grabbing full load rate are used as evaluation indexes, the height difference between the marked feature points and the average material level depth, the distance and the height difference between the marked feature points and the neighbor feature points and the slope included angle of the profile line section before and after the feature points are used as inputs, the higher the height of the bulk pile where the feature points are located is indicated when the height difference between the feature points and the average material level depth and the height difference between the feature points are positive, the higher the relative safety and the convenience are achieved, and conversely, when the negative height difference between the feature points and the neighbor feature points is large and the distance between the feature points is close to the neighbor feature points, the feature points are indicated to be lower than the neighbor feature points around, the neighbor feature points are prone to collapse, the risk is high, the neighbor feature points around hinder grabbing of the feature points, grabbing convenience is low, in addition, the standard grabbing full load rate of the grab bucket is preset, and the feature point grabbing condition is judged according to the maximum grabbing angle and the included angle of the profile line section before and after the feature points and the neighbor feature points are located. The neural network comprises an input layer, an implicit layer and an output layer, parameters such as the number of neurons, a transfer function, a learning function, a target error value and the like of the input layer, the implicit layer and the output layer are preset, characteristic point evaluation data of subjective evaluation of expert decision is selected, and the neural network is subjected to initialization training to construct a grabbing point evaluation model.
It should be noted that, according to the binocular system of unmanned overhead traveling crane obtain the space location of snatching the point, carry out the accurate positioning of unmanned overhead traveling crane according to the space coordinate of snatching the point, specifically do: calibrating a binocular system of the unmanned crown block, and simultaneously correcting distortion to obtain inner and outer parameter matrixes of the left and right vision sensors; acquiring left-eye images and right-eye images of grabbing points in a binocular system, and acquiring image coordinate information of grabbing points according to the left-eye images and the right-eye images; and converting the image coordinate information into world coordinate information through left transformation according to the internal and external parameter matrix and the parallax mean value of the binocular system, and carrying out accurate positioning of the unmanned crown block according to the world coordinate information of the grabbing point.
The third aspect of the present invention also provides a computer readable storage medium, wherein the computer readable storage medium includes a method program for positioning an unmanned aerial vehicle for bulk material storage, and when the method program is executed by a processor, the method for positioning an unmanned aerial vehicle for bulk material storage is implemented.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. The unmanned aerial vehicle positioning method for bulk material storage is characterized by comprising the following steps of:
acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, and selecting the feature points with highest grabbing evaluation scores as grabbing points;
and acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and carrying out the accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points.
2. The unmanned aerial vehicle positioning method for bulk cargo storage according to claim 1, wherein the method is characterized in that the image information of a bulk cargo storage area is obtained, the bulk cargo identification is performed according to the image information of the bulk cargo storage area to determine the position of a target bulk cargo, and the distribution characteristics of the target bulk cargo storage area are obtained, specifically:
acquiring image information of a bulk material storage area through a preset visual sensor of the bulk material storage area, and preprocessing the image information to acquire color characteristics and texture characteristics of a bulk material storage area in the bulk material storage area;
Constructing a bulk material identification model, carrying out initialization training on the bulk material identification model by utilizing a related database, inputting the color characteristics and the texture characteristics into the bulk material identification model for identification, and obtaining a storage area of a target bulk material in a bulk material bin storage area;
acquiring image information and three-dimensional scanning data of a target bulk storage area, and performing joint calculation on the image information and the three-dimensional scanning data to generate three-dimensional point cloud data of the target bulk storage area;
and acquiring the distribution characteristics of the visible parts of the bulk materials in the target bulk material storage area according to the three-dimensional point cloud data.
3. The unmanned aerial vehicle positioning method for bulk material storage according to claim 1, wherein the bulk material distribution profile in the target bulk material storage area is obtained according to the distribution characteristics, specifically:
image segmentation is carried out according to the image information of the target bulk storage area to obtain an image of a candidate grabbing area, denoising is carried out on the image of the candidate grabbing area, and binarization is carried out on the image through a threshold segmentation method;
acquiring edge contour information in binarized images of different angles by using a Canny operator, and registering and splicing the edge contour information of different angles;
And extracting three-dimensional point cloud data of the candidate grabbing area through the three-dimensional point cloud data of the target bulk material storage area, optimizing the spliced edge profile information, and generating a bulk material distribution profile in the candidate grabbing area.
4. The unmanned aerial vehicle positioning method for bulk cargo storage according to claim 1, wherein the method is characterized in that the candidate grabbing area of the target bulk cargo is judged according to the bulk cargo distribution profile, specifically:
preliminary coarse positioning is carried out on grabbing of the bulk material storage area according to the position information of the target bulk material storage area, and a bulk material distribution profile of the target bulk material storage area is obtained;
acquiring a plurality of contour line segments forming a bulk material distribution contour, acquiring end points of the contour line segments as contour points, optimizing the contour points, dividing the bulk material distribution contour through the optimized contour points, and generating a contour segmentation result;
acquiring geometric features of bulk distribution profiles in a target bulk storage area according to slopes of all profile line segments and fluctuation degrees of adjacent profile line segments in a profile segmentation result;
partitioning the target bulk storage area according to the geometric features, obtaining a contour line segment with the slope larger than a preset slope threshold value in the bulk distribution contour, and judging whether the fluctuation degree of the contour line segment and the adjacent contour line segment is positive and larger than the preset threshold value;
If the undulation degree is judged to be positive and larger than the preset threshold value, taking the areas where the contour line segment and the adjacent contour line segment are located as candidate grabbing areas of the target bulk material;
the standard line is preset according to the bulk material distribution profile in the target bulk material storage area, the waviness is positive when the adjacent profile line sections are located above the standard line, and the waviness is negative when the adjacent profile line sections are located below the standard line.
5. The unmanned aerial vehicle positioning method for bulk cargo storage according to claim 1, wherein feature points are extracted according to bulk cargo distribution profiles of candidate grabbing areas, grabbing evaluation is performed on the feature points through deep learning, and feature points with highest grabbing evaluation scores are selected as grabbing points, specifically:
acquiring the material level depth in the candidate grabbing area through the bulk cargo distribution profile in the candidate grabbing area, and determining the average material level depth according to the material level depth information;
acquiring a characteristic point with slope change larger than a preset slope change threshold value in a bulk material distribution profile of a candidate grabbing area, acquiring a height difference between the characteristic point and an average material level depth, and selecting the characteristic point with the height difference larger than a preset height difference threshold value as a marked characteristic point;
Establishing a grabbing point evaluation model based on a neural network, taking grabbing safety, grabbing convenience and grabbing full rate as evaluation indexes, inputting the height difference between the marked characteristic points and the average material level depth, the distance between the marked characteristic points and the neighbor characteristic points, the height difference and the slope included angle of the contour line segments before and after the characteristic points, and outputting the evaluation result of the characteristic points;
carrying out normalization processing on the input data, acquiring the score condition of the characteristic point in each evaluation index through a grabbing point evaluation model, and acquiring grabbing evaluation scores of the characteristic point according to the score condition of each evaluation index and a preset weight;
and sorting the characteristic points according to the evaluation result scores, and selecting the characteristic point with the highest grabbing evaluation score as a grabbing point.
6. The unmanned aerial vehicle positioning method for bulk cargo storage according to claim 1, wherein the unmanned aerial vehicle positioning method is characterized in that the space positioning of the grabbing points is obtained according to a binocular system of the unmanned aerial vehicle, and the unmanned aerial vehicle is precisely positioned according to the space coordinates of the grabbing points, specifically:
calibrating a binocular system of the unmanned crown block, and simultaneously correcting distortion to obtain inner and outer parameter matrixes of the left and right vision sensors;
acquiring left-eye images and right-eye images of grabbing points in a binocular system, and acquiring image coordinate information of grabbing points according to the left-eye images and the right-eye images;
And converting the image coordinate information into world coordinate information through left transformation according to the internal and external parameter matrix and the parallax mean value of the binocular system, and carrying out accurate positioning of the unmanned crown block according to the world coordinate information of the grabbing point.
7. An unmanned aerial vehicle positioning system for bulk storage, comprising: the automatic positioning device comprises a memory and a processor, wherein the memory comprises an unmanned crown block positioning method program for bulk material storage, and the unmanned crown block positioning method program for bulk material storage realizes the following steps when being executed by the processor:
acquiring image information of a bulk material storage area, carrying out bulk material identification according to the image information of the bulk material storage area to determine a target bulk material position, and acquiring distribution characteristics of a target bulk material storage area;
acquiring a bulk material distribution profile in a target bulk material storage area according to the distribution characteristics, and judging a candidate grabbing area of the target bulk material according to the bulk material distribution profile;
extracting feature points according to the bulk material distribution profile of the candidate grabbing area, carrying out grabbing evaluation on the feature points through deep learning, and selecting the feature points with highest grabbing evaluation scores as grabbing points;
and acquiring the space positioning of the grabbing points according to the binocular system of the unmanned crown block, and carrying out the accurate positioning of the unmanned crown block according to the space coordinates of the grabbing points.
8. The unmanned aerial vehicle positioning system for bulk cargo storage according to claim 7, wherein the method for determining the candidate grabbing area of the target bulk cargo according to the bulk cargo distribution profile is specifically as follows:
preliminary coarse positioning is carried out on grabbing of the bulk material storage area according to the position information of the target bulk material storage area, and a bulk material distribution profile of the target bulk material storage area is obtained;
acquiring a plurality of contour line segments forming a bulk material distribution contour, acquiring end points of the contour line segments as contour points, optimizing the contour points, dividing the bulk material distribution contour through the optimized contour points, and generating a contour segmentation result;
acquiring geometric features of bulk distribution profiles in a target bulk storage area according to slopes of all profile line segments and fluctuation degrees of adjacent profile line segments in a profile segmentation result;
partitioning the target bulk storage area according to the geometric features, obtaining a contour line segment with the slope larger than a preset slope threshold value in the bulk distribution contour, and judging whether the fluctuation degree of the contour line segment and the adjacent contour line segment is positive and larger than the preset threshold value;
if the undulation degree is judged to be positive and larger than the preset threshold value, taking the areas where the contour line segment and the adjacent contour line segment are located as candidate grabbing areas of the target bulk material;
The standard line is preset according to the bulk material distribution profile in the target bulk material storage area, the waviness is positive when the adjacent profile line sections are located above the standard line, and the waviness is negative when the adjacent profile line sections are located below the standard line.
9. The unmanned aerial vehicle positioning system for bulk cargo storage according to claim 7, wherein the unmanned aerial vehicle positioning system acquires the space positioning of the grabbing points according to the binocular system of the unmanned aerial vehicle, and performs the accurate positioning of the unmanned aerial vehicle according to the space coordinates of the grabbing points, specifically:
calibrating a binocular system of the unmanned crown block, and simultaneously correcting distortion to obtain inner and outer parameter matrixes of the left and right vision sensors;
acquiring left-eye images and right-eye images of grabbing points in a binocular system, and acquiring image coordinate information of grabbing points according to the left-eye images and the right-eye images;
and converting the image coordinate information into world coordinate information through left transformation according to the internal and external parameter matrix and the parallax mean value of the binocular system, and carrying out accurate positioning of the unmanned crown block according to the world coordinate information of the grabbing point.
10. A computer-readable storage medium, characterized by: the computer readable storage medium comprises a procedure of an unmanned aerial vehicle positioning method for bulk material storage, and when the procedure of the unmanned aerial vehicle positioning method for bulk material storage is executed by a processor, the steps of the unmanned aerial vehicle positioning method for bulk material storage are realized.
CN202310456002.0A 2023-04-25 2023-04-25 Unmanned crown block positioning method, system and storage medium for bulk material storage Active CN116524010B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310456002.0A CN116524010B (en) 2023-04-25 2023-04-25 Unmanned crown block positioning method, system and storage medium for bulk material storage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310456002.0A CN116524010B (en) 2023-04-25 2023-04-25 Unmanned crown block positioning method, system and storage medium for bulk material storage

Publications (2)

Publication Number Publication Date
CN116524010A true CN116524010A (en) 2023-08-01
CN116524010B CN116524010B (en) 2024-02-02

Family

ID=87393492

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310456002.0A Active CN116524010B (en) 2023-04-25 2023-04-25 Unmanned crown block positioning method, system and storage medium for bulk material storage

Country Status (1)

Country Link
CN (1) CN116524010B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108381549A (en) * 2018-01-26 2018-08-10 广东三三智能科技有限公司 A kind of quick grasping means of binocular vision guided robot, device and storage medium
CN109508707A (en) * 2019-01-08 2019-03-22 中国科学院自动化研究所 The crawl point acquisition methods of robot stabilized crawl object based on monocular vision
CN111844019A (en) * 2020-06-10 2020-10-30 安徽鸿程光电有限公司 Method and device for determining grabbing position of machine, electronic device and storage medium
CN113291847A (en) * 2021-03-31 2021-08-24 湖南千盟工业智能系统股份有限公司 Intelligent bulk material stacking and taking method based on three-dimensional imaging
CN113610833A (en) * 2021-08-20 2021-11-05 三一建筑机器人(西安)研究院有限公司 Material grabbing method and device, electronic equipment and storage medium
CN114494463A (en) * 2022-02-11 2022-05-13 黎明职业大学 Robot sorting method and device based on binocular stereoscopic vision technology
CN114834918A (en) * 2022-03-16 2022-08-02 武汉理工大学 Anti-collision automatic grabbing and unloading method and system for grab ship unloader
CN114888790A (en) * 2022-04-18 2022-08-12 金陵科技学院 Space coordinate locating method based on three-dimensional characteristic distribution of bulk materials
CN115620004A (en) * 2022-09-30 2023-01-17 北京思灵机器人科技有限责任公司 Disordered wire grabbing method and device and electronic equipment
CN115760932A (en) * 2022-09-06 2023-03-07 中联重科股份有限公司 Material identification method and device and computer storage medium

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108381549A (en) * 2018-01-26 2018-08-10 广东三三智能科技有限公司 A kind of quick grasping means of binocular vision guided robot, device and storage medium
CN109508707A (en) * 2019-01-08 2019-03-22 中国科学院自动化研究所 The crawl point acquisition methods of robot stabilized crawl object based on monocular vision
CN111844019A (en) * 2020-06-10 2020-10-30 安徽鸿程光电有限公司 Method and device for determining grabbing position of machine, electronic device and storage medium
CN113291847A (en) * 2021-03-31 2021-08-24 湖南千盟工业智能系统股份有限公司 Intelligent bulk material stacking and taking method based on three-dimensional imaging
CN113610833A (en) * 2021-08-20 2021-11-05 三一建筑机器人(西安)研究院有限公司 Material grabbing method and device, electronic equipment and storage medium
CN114494463A (en) * 2022-02-11 2022-05-13 黎明职业大学 Robot sorting method and device based on binocular stereoscopic vision technology
CN114834918A (en) * 2022-03-16 2022-08-02 武汉理工大学 Anti-collision automatic grabbing and unloading method and system for grab ship unloader
CN114888790A (en) * 2022-04-18 2022-08-12 金陵科技学院 Space coordinate locating method based on three-dimensional characteristic distribution of bulk materials
CN115760932A (en) * 2022-09-06 2023-03-07 中联重科股份有限公司 Material identification method and device and computer storage medium
CN115620004A (en) * 2022-09-30 2023-01-17 北京思灵机器人科技有限责任公司 Disordered wire grabbing method and device and electronic equipment

Also Published As

Publication number Publication date
CN116524010B (en) 2024-02-02

Similar Documents

Publication Publication Date Title
WO2019228063A1 (en) Product inspection terminal, method and system, computer apparatus and readable medium
CN106407893B (en) A kind of method, apparatus and equipment detecting lane line
CN110245663B (en) Method for identifying steel coil information
CN111223180A (en) Three-dimensional modeling method and device for stock ground, storage medium and electronic terminal
CN111680681B (en) Image post-processing method and system for eliminating abnormal recognition target and counting method
CN101114337A (en) Ground buildings recognition positioning method
CN117671607B (en) Real-time detection method and system for abnormality of belt conveyor based on computer vision
CN112561989B (en) Recognition method for hoisting object in construction scene
CN115661064A (en) Container identification method based on combination of image and point cloud
CN113240682A (en) Overturn-preventing construction driving map generation method and system for crawler crane
CN116255912A (en) Method and system for measuring static volume of package
CN110567383A (en) pantograph abrasion early warning system and detection method based on structural forest and sub-pixels
CN110322428A (en) Detect the method, apparatus and electronic equipment of tunnel defect
CN110472640B (en) Target detection model prediction frame processing method and device
CN115841633A (en) Power tower and power line associated correction power tower and power line detection method
CN116524010B (en) Unmanned crown block positioning method, system and storage medium for bulk material storage
CN113239832B (en) Hidden danger intelligent identification method and system based on image identification
CN113128346B (en) Target identification method, system and device for crane construction site and storage medium
CN112528829B (en) Visual-based unstructured road centered driving method
KR102457425B1 (en) Quantity measurement method of Construction materials using drone
CN116843742B (en) Calculation method and system for stacking volume after point cloud registration for black coal loading vehicle
CN117853403A (en) Novel bridge inspection method
CN112149687A (en) Method for object recognition
KR100954137B1 (en) Edge-based text localization and segmentation algorithms for automatic slab information recognition
CN118365696B (en) Intelligent measuring method for blade size of industrial fan

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