CN113947631A - Method and device for stockyard inventory of scrap steel - Google Patents
Method and device for stockyard inventory of scrap steel Download PDFInfo
- Publication number
- CN113947631A CN113947631A CN202111233947.3A CN202111233947A CN113947631A CN 113947631 A CN113947631 A CN 113947631A CN 202111233947 A CN202111233947 A CN 202111233947A CN 113947631 A CN113947631 A CN 113947631A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- yard
- acquiring
- waste
- scrap
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T7/50—Depth or shape recovery
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a method and a device for stockyard inventory of scrap steel, which comprises the following steps: acquiring a three-dimensional point cloud image and a visible light image of a scrap steel stock yard; constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stockpiles of the scrap steel stock yard, and acquiring the volume of each stockpile; acquiring the waste material category of each stock pile in the waste yard through the visible light image, and acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile so as to acquire the total mass of the waste materials in the waste steel yard; the invention can effectively improve the precision of the inventory, reduce the manual participation, save the labor cost and improve the processing efficiency.
Description
Technical Field
The invention relates to the field of steel production and manufacturing, in particular to a method and a device for stockyard inventory of scrap steel.
Background
The scrap steel is used as a recyclable resource and has an important role in the steel industry. Along with the large-scale recycling of the scrap steel, the storage turnover amount in the scrap steel warehouse is larger and larger, and in order to improve the turnover efficiency of the scrap steel, the current storage amount of the scrap steel needs to be accurately counted by adopting a scrap steel warehouse method. The current scrap steel warehouse is mainly characterized in that the volume of the current scrap steel material pile is estimated manually according to historical experience, the warehouse precision is low, and the warehouse consistency of different workers is poor.
Disclosure of Invention
In view of the problems in the prior art, the invention provides a scrap steel stock yard inventory method and a scrap steel stock yard inventory device, which mainly solve the problem that the accuracy and consistency are insufficient due to the fact that the existing inventory is dependent on manual work.
In order to achieve the above and other objects, the present invention adopts the following technical solutions.
A scrap steel stock yard inventory method comprises the following steps:
acquiring a three-dimensional point cloud image and a visible light image of a scrap steel stock yard;
constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stockpiles of the scrap steel stock yard, and acquiring the volume of each stockpile;
and acquiring the waste material category of each stock pile in the waste yard through the visible light image, and acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile so as to acquire the total mass of the waste materials in the waste steel yard.
Optionally, the obtaining three-dimensional point cloud data and a visible light image of the scrap steel yard includes:
constructing a data acquisition platform based on an unmanned aerial vehicle, wherein the data acquisition platform comprises: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle;
the unmanned aerial vehicle travels according to a specified route, and point cloud data and a visible light image covering the whole scrap steel stock yard are obtained;
and calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
Optionally, calculating a three-dimensional point cloud image of the scrap yard according to the point cloud data, including:
acquiring the position and the posture of the unmanned aerial vehicle through the positioning equipment;
and combining the point cloud data according to the position and the posture, and acquiring a three-dimensional point cloud image of the scrap steel stock yard by adopting a three-dimensional reconstruction algorithm.
Optionally, the three-dimensional reconstruction algorithm includes a SLAM algorithm and a three-dimensional reconstruction algorithm.
Optionally, the semantic segmentation network comprises: the PointNet + network is combined with a deep learning three-dimensional point cloud semantic segmentation network.
Optionally, the point cloud data acquisition device comprises a lidar.
Optionally, the positioning device includes an inertial navigation module composed of two GPS antennas for measuring the position and attitude of the drone.
Optionally, the obtaining the waste material category of each pile in the waste yard through the visible light image, and obtaining the mass of each waste pile according to the waste material category and the volume of each waste pile includes:
constructing an identification network, and acquiring the waste material category of each material pile in the visible light image;
constructing a mass-volume calculation model of each waste material category;
and matching the corresponding mass-volume calculation model according to the waste material category corresponding to each material pile in the visible light image to obtain the mass of the corresponding material pile.
A scrap steel stock ground inventory device comprises:
the image acquisition module is used for acquiring a three-dimensional point cloud image and a visible light image of the scrap steel stock yard;
the stock pile segmentation module is used for constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stock piles of the scrap steel stock yard, and acquiring the volume of each stock pile;
and the inventory calculation module is used for acquiring the waste material category of each stock pile in the waste yard through the visible light image, acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile, and further acquiring the total mass of the waste materials in the waste steel yard.
Optionally, the image acquisition module comprises:
the acquisition platform constructs the unit for construct the data acquisition platform based on unmanned aerial vehicle, the data acquisition platform includes: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle;
the planning and collecting unit is used for enabling the unmanned aerial vehicle to travel according to a specified route and acquiring point cloud data and a visible light image covering the whole scrap yard;
and the image reconstruction unit is used for calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
As described above, the method and the device for stockyard inventory of scrap steel according to the present invention have the following advantageous effects.
The stockpile is automatically segmented according to the three-dimensional point cloud image, the stockpile quality is calculated based on the stockpile category and the visible light image, the stock checking process of the whole scrap steel stock yard is automatically completed, the accuracy and the consistency are high, the method does not depend on manpower, and the stock checking efficiency can be greatly improved.
Drawings
Fig. 1 is a schematic flow chart of a scrap yard inventory method according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, the present invention provides a scrap yard inventory method, which includes the following steps.
Step S1, acquiring a three-dimensional point cloud image and a visible light image of the scrap steel stock yard;
step S2, constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stockpiles of the scrap yard, and acquiring the volume of each stockpile;
and step S3, acquiring the waste material category of each stock pile in the waste yard through the visible light image, acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile, and further acquiring the total mass of the waste materials in the waste steel yard.
The specific steps of the steel scrap yard inventory method of the present invention will be described with reference to specific examples.
In step S1, the obtaining of the three-dimensional point cloud image and the visible light image of the scrap yard may include the following steps:
step S101, a data acquisition platform based on an unmanned aerial vehicle is constructed, and the data acquisition platform comprises: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle;
step S102, the unmanned aerial vehicle travels along a designated route, and point cloud data and a visible light image covering the whole scrap yard are obtained;
and S103, calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
In particular, the point cloud data acquisition device may employ a lidar. The laser radar is arranged at the bottom of the unmanned aerial vehicle, and in the process of executing tasks by the unmanned aerial vehicle, the laser radar emits laser beams downwards to scan a scrap steel stock yard, and the signals reflected by all objects in the scrap steel stock yard are compared with the emitted signals to determine the height, the direction, the posture and other parameters of all the objects in the scrap steel stock yard, so that point cloud data are generated. Illustratively, the point cloud data may be represented as a multi-dimensional coordinate matrix.
Visible light image acquisition equipment can adopt the camera, carries the camera in the unmanned aerial vehicle bottom, and unmanned aerial vehicle flies the in-process above the scrap steel stock yard, gathers the scrap steel stock yard visible light image of different positions at each moment through the camera.
Positioning device can include two GPS antennas, and two GPS antennas can be based on unmanned aerial vehicle's center pin along the horizontal direction symmetry setting, constitute and be used to lead the module. The inertial navigation module can carry out position calibration according to position signals measured by the two GPS antennas and the position relation of the two GPS antennas to obtain the position and the posture of the unmanned aerial vehicle. The relative positions of the two GPS antennas can be adjusted according to the actual application requirements, and are not limited herein.
In one embodiment, the traveling route of the unmanned aerial vehicle can be preset according to the layout of the scrap yard so as to obtain point cloud data covering the whole scrap yard. Exemplarily, assuming that the scrap yard is a rectangular yard, taking the upper left corner of the scrap yard as the starting point of the unmanned aerial vehicle, moving the lower left corner along a straight line, traversing a distance, and moving the scrap yard upwards along the straight line, so as to form a square wave-shaped moving track to cover the whole scrap yard. The specific track setting can be adjusted according to the actual field and application requirements, and is not limited herein.
In one embodiment, during the process that the unmanned aerial vehicle moves along the set track, a three-dimensional point cloud picture of the whole scrap steel stock yard can be created and drawn according to the pose and the position of the unmanned aerial vehicle and the laser radar collected point cloud data. Specifically, a three-dimensional point cloud graph can be constructed by adopting an SLAM algorithm and a three-dimensional reconstruction algorithm. The specific process is the prior art and is not described herein again.
In step S2, a semantic segmentation network is constructed, the three-dimensional point cloud image is input to the semantic segmentation network, three-dimensional point cloud maps of all stockpiles in the scrap yard are obtained, and the volume of each stockpile is obtained.
In one embodiment, the semantic segmentation network may employ a PointNet + network in combination with a deep learning three-dimensional point cloud semantic segmentation network. Specifically, the PointNet + network comprises two local feature extraction sub-networks, wherein each local feature extraction sub-network comprises a Sampling layer Sampling, a clustering layer Grouping and a feature extraction layer PointNet. The sampling is performed randomly through the sampling layer, and particularly, the sampling can be performed in a farthest point sampling manner. Furthermore, a circle is drawn by the clustering layer by taking the sampling point as the origin and setting the radius r, and the point cloud in the circle is taken as a cluster so as to divide a plurality of clusters. And finally, carrying out convolution operation through a feature extraction layer to extract features in the clusters.
The deep learning three-dimensional point cloud semantic segmentation network comprises a classification network and a segmentation network, wherein the classification network comprises a plurality of full connection layers and a classifier, the output of the feature extraction layer can be input into the full connection layers of the classification network to extract local features through the plurality of full connection layers, the global features are finally obtained, and classification results are obtained through the classifier. The specific classification process is not described in detail here. The segmentation network directly splices the features of each layer in the local feature extraction sub-network with the features of the corresponding layer with the same number of points in the segmentation network, and performs up-sampling on the global features to obtain a segmentation result.
And performing semantic segmentation processing on the three-dimensional point cloud image of the scrap steel stock yard to obtain a three-dimensional point cloud image of each stock pile. And calculating the volume of the corresponding stockpile according to the three-dimensional point cloud picture. The detailed description of the calculation process is omitted here.
In step S3, the waste classification of each dump in the scrap yard is obtained through the visible light image, the mass of each dump is obtained according to the waste classification and volume of each dump, and the total mass of the scrap in the scrap yard is obtained.
In one embodiment, the pile images containing various waste types can be pre-arranged as sample images, a training sample set is constructed, and waste categories of the piles in the sample images are labeled. And inputting the marked sample set into a recognition network for model training to obtain a recognition model. The identification network may employ a convolutional neural network. The specific network training process is the prior art and is not described herein again.
Inputting the three-dimensional point cloud image of each pile acquired in the step S2 into the identification model, and acquiring the waste material category corresponding to each pile.
Further, mass-volume computational models of different waste classes can be constructed. Specifically, the corresponding relationship between the waste material category and the waste material density can be established empirically, and the mass-volume calculation model is constructed based on the waste material density. Optionally, a fertilizer sample of a corresponding category can be collected to simulate a waste pile for waste density correction, and accuracy of the calculation model is guaranteed. And calculating the evaluation quality of each stock pile according to the density and the volume. And counting the mass of all the stockpiles to obtain the weight of the scrap steel in the whole scrap steel yard. Thereby completing the inventory of the scrap steel yard. In another embodiment, the quality of a plurality of stockpiles of the same category can be counted, and stockpiling is performed according to the waste categories corresponding to the stockpiles.
In an embodiment, there is also provided a scrap yard inventory device for performing the scrap yard inventory method described in the foregoing method embodiments. Since the technical principle of the system embodiment is similar to that of the method embodiment, repeated description of the same technical details is omitted.
In one embodiment, the scrap yard inventory apparatus includes: the image acquisition module is used for acquiring a three-dimensional point cloud image and a visible light image of the scrap steel stock yard; the stock pile segmentation module is used for constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stock piles of the scrap steel stock yard, and acquiring the volume of each stock pile; and the inventory calculation module is used for acquiring the waste material category of each stock pile in the waste yard through the visible light image, acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile, and further acquiring the total mass of the waste materials in the waste steel yard.
In one embodiment, the image acquisition module comprises: the acquisition platform constructs the unit for construct the data acquisition platform based on unmanned aerial vehicle, the data acquisition platform includes: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle; the planning and collecting unit is used for enabling the unmanned aerial vehicle to travel according to a specified route and acquiring point cloud data and a visible light image covering the whole scrap yard; and the image reconstruction unit is used for calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
In summary, according to the method and the device for stockyard inventory of the steel scrap, the unmanned aerial vehicle, the 3D laser radar and the camera are used for collecting the three-dimensional point cloud image and the visible light image of the steel scrap pile from the air downwards, meanwhile, the position and the posture of the unmanned aerial vehicle are obtained in real time, and the three-dimensional reconstruction image of the steel scrap yard is established through a three-dimensional reconstruction algorithm. Then, a three-dimensional stack image is divided from a three-dimensional reconstruction image of the scrap steel stock yard through a stack identification algorithm, so that the volume of each stack is calculated, the type of each scrap steel stock pile is identified, the mass of each scrap steel stock pile is calculated according to a stock pile volume-mass historical experience model of different scrap steel stock pile types, and finally, the mass of all scrap steel in the whole scrap steel stock yard is counted to complete a scrap steel coil warehouse; manual participation is reduced, the inventory is automatically finished, the consistency of the inventory data is ensured, and the processing efficiency is improved; the volume of the stock pile is identified according to the point cloud image, so that the quality is obtained, errors caused by estimation depending on manual experience are avoided, and the inventory precision is improved. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A method for stockyard inventory of scrap steel is characterized by comprising the following steps:
acquiring a three-dimensional point cloud image and a visible light image of a scrap steel stock yard;
constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stockpiles of the scrap steel stock yard, and acquiring the volume of each stockpile;
and acquiring the waste material category of each stock pile in the waste yard through the visible light image, and acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile so as to acquire the total mass of the waste materials in the waste steel yard.
2. The scrap yard inventory method according to claim 1, wherein obtaining three-dimensional point cloud data and visible light images of a scrap yard comprises:
constructing a data acquisition platform based on an unmanned aerial vehicle, wherein the data acquisition platform comprises: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle;
the unmanned aerial vehicle travels according to a specified route, and point cloud data and a visible light image covering the whole scrap steel stock yard are obtained;
and calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
3. The scrap yard inventory method according to claim 2, wherein calculating a three-dimensional point cloud image of the scrap yard from the point cloud data comprises:
acquiring the position and the posture of the unmanned aerial vehicle through the positioning equipment;
and combining the point cloud data according to the position and the posture, and acquiring a three-dimensional point cloud image of the scrap steel stock yard by adopting a three-dimensional reconstruction algorithm.
4. The scrap yard inventory method according to claim 3, wherein the three-dimensional reconstruction algorithm includes a SLAM algorithm and a three-dimensional reconstruction algorithm.
5. The scrap yard inventory method according to claim 1, wherein the semantic segmentation network comprises: the PointNet + network is combined with a deep learning three-dimensional point cloud semantic segmentation network.
6. The scrap yard inventory method of claim 2, wherein the point cloud data collection device comprises a laser radar.
7. The scrap yard inventory method according to claim 2, wherein the positioning device includes an inertial navigation module consisting of two GPS antennas for measuring the position and attitude of the drone.
8. The scrap yard inventory method according to claim 1, wherein the obtaining of the waste classification of each dump in the scrap yard through the visible light image, the obtaining of the mass of each dump according to the waste classification and volume of each dump comprises:
constructing an identification network, and acquiring the waste material category of each material pile in the visible light image;
constructing a mass-volume calculation model of each waste material category;
and matching the corresponding mass-volume calculation model according to the waste material category corresponding to each material pile in the visible light image to obtain the mass of the corresponding material pile.
9. The utility model provides a scrap steel stock ground inventory device which characterized in that includes:
the image acquisition module is used for acquiring a three-dimensional point cloud image and a visible light image of the scrap steel stock yard;
the stock pile segmentation module is used for constructing a semantic segmentation network, inputting the three-dimensional point cloud image into the semantic segmentation network, acquiring three-dimensional point cloud images of all stock piles of the scrap steel stock yard, and acquiring the volume of each stock pile;
and the inventory calculation module is used for acquiring the waste material category of each stock pile in the waste yard through the visible light image, acquiring the mass of each waste pile according to the waste material category and the volume of each waste pile, and further acquiring the total mass of the waste materials in the waste steel yard.
10. The scrap yard inventory apparatus according to claim 9, wherein the image acquisition module comprises:
the acquisition platform constructs the unit for construct the data acquisition platform based on unmanned aerial vehicle, the data acquisition platform includes: the system comprises an unmanned aerial vehicle, point cloud data acquisition equipment, visible light image acquisition equipment and positioning equipment; the point cloud data acquisition equipment, the visible light image acquisition equipment and the positioning equipment are all arranged on the unmanned aerial vehicle;
the planning and collecting unit is used for enabling the unmanned aerial vehicle to travel according to a specified route and acquiring point cloud data and a visible light image covering the whole scrap yard;
and the image reconstruction unit is used for calculating a three-dimensional point cloud image of the scrap steel stock yard according to the point cloud data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233947.3A CN113947631A (en) | 2021-10-22 | 2021-10-22 | Method and device for stockyard inventory of scrap steel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233947.3A CN113947631A (en) | 2021-10-22 | 2021-10-22 | Method and device for stockyard inventory of scrap steel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113947631A true CN113947631A (en) | 2022-01-18 |
Family
ID=79332291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111233947.3A Pending CN113947631A (en) | 2021-10-22 | 2021-10-22 | Method and device for stockyard inventory of scrap steel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113947631A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114519711A (en) * | 2022-02-22 | 2022-05-20 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and electronic terminal for measuring steel coils in depot area |
| CN115032989A (en) * | 2022-05-18 | 2022-09-09 | 用友网络科技股份有限公司 | Control method of mobile scrap steel grading system and mobile scrap steel grading system |
| CN116030425A (en) * | 2023-03-29 | 2023-04-28 | 山东朝辉自动化科技有限责任公司 | Material yard material monitoring method and system based on unmanned aerial vehicle laser scanning and application |
-
2021
- 2021-10-22 CN CN202111233947.3A patent/CN113947631A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114519711A (en) * | 2022-02-22 | 2022-05-20 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and electronic terminal for measuring steel coils in depot area |
| CN115032989A (en) * | 2022-05-18 | 2022-09-09 | 用友网络科技股份有限公司 | Control method of mobile scrap steel grading system and mobile scrap steel grading system |
| CN116030425A (en) * | 2023-03-29 | 2023-04-28 | 山东朝辉自动化科技有限责任公司 | Material yard material monitoring method and system based on unmanned aerial vehicle laser scanning and application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113947631A (en) | Method and device for stockyard inventory of scrap steel | |
| CN110222626B (en) | Unmanned scene point cloud target labeling method based on deep learning algorithm | |
| JP2022514974A (en) | Object detection methods, devices, electronic devices, and computer programs | |
| Maboudi et al. | A Review on Viewpoints and Path Planning for UAV-Based 3-D Reconstruction | |
| CN111527467A (en) | Method and apparatus for automatically defining computer-aided design files using machine learning, image analysis, and/or computer vision | |
| CN108921947A (en) | Generate method, apparatus, equipment, storage medium and the acquisition entity of electronic map | |
| Hardouin et al. | Next-Best-View planning for surface reconstruction of large-scale 3D environments with multiple UAVs | |
| Beinschob et al. | Semi-automated map creation for fast deployment of AGV fleets in modern logistics | |
| CN106529431B (en) | Road bank point based on Vehicle-borne Laser Scanning data automatically extracts and vectorization method | |
| CN110021072B (en) | Holographic mapping-oriented multi-platform point cloud intelligent processing method | |
| CN102074047A (en) | High-fineness urban three-dimensional modeling method | |
| CN110806585B (en) | Robot positioning method and system based on trunk clustering tracking | |
| CN114581619A (en) | Coal bunker modeling method based on three-dimensional positioning and two-dimensional mapping | |
| CN111709988A (en) | Method and device for determining characteristic information of object, electronic equipment and storage medium | |
| CN114089787A (en) | Ground three-dimensional semantic map based on multi-machine cooperative flight and construction method thereof | |
| CN117315146B (en) | Reconstruction method and storage method of three-dimensional model based on trans-scale multi-source data | |
| Ma et al. | An intelligent object detection and measurement system based on trinocular vision | |
| CN110095108B (en) | Surveying and mapping device and method based on BIM unmanned aerial vehicle | |
| CN115965790A (en) | Oblique photography point cloud filtering method based on cloth simulation algorithm | |
| CN117470246A (en) | Path planning method and device, storage medium and electronic equipment | |
| CN113448340B (en) | Unmanned aerial vehicle path planning method and device, unmanned aerial vehicle and storage medium | |
| CN116822159B (en) | Digital twin workshop rapid modeling method for dynamic and static fusion of man-machine environment | |
| CN117218063A (en) | Bridge construction progress monitoring method based on spatial position change of hanging basket in construction stage | |
| CN115454096B (en) | Course reinforcement learning-based robot strategy training system and training method | |
| CN115164769A (en) | Three-dimensional real estate measuring and calculating method based on oblique photography technology |
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 |