CN115629043B - Zinc concentrate material recovery sampling detection method and detection system - Google Patents
Zinc concentrate material recovery sampling detection method and detection system Download PDFInfo
- Publication number
- CN115629043B CN115629043B CN202211496706.2A CN202211496706A CN115629043B CN 115629043 B CN115629043 B CN 115629043B CN 202211496706 A CN202211496706 A CN 202211496706A CN 115629043 B CN115629043 B CN 115629043B
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- zinc concentrate
- preset
- key frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/04—Devices for withdrawing samples in the solid state, e.g. by cutting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Abstract
The application discloses a zinc concentrate material recycling, sampling and detecting method and a detecting system. The zinc concentrate material recovery sampling detection method comprises the following steps: controlling a camera shooting mechanism to collect images of zinc concentrate materials; when the image shot by the camera meets the preset definition requirement, shooting a video stream by controlling the shooting mechanism; selecting images in a video stream as key frame images according to a preset time interval, and dividing each key frame image into a material imaging area; according to the material imaging area, calculating a material imaging angle of a corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle; according to the imaging angle, the image depth of field distance and the current position information of the camera, a first actual distance between the camera and the zinc concentrate material in a first direction is obtained, a second actual distance is determined according to the first actual distance, and the sampling device is controlled to move by the second actual distance to take out a sample to be detected. The sampling detection method is high in efficiency.
Description
Technical Field
The application relates to the technical field of zinc concentrate material sampling detection, in particular to a zinc concentrate material recycling sampling detection method and a zinc concentrate material recycling sampling detection system.
Background
In recent years, with the rapid development of economy in China, the demand for metal zinc is larger, the consumption of zinc in nonferrous metal consumption in China is only inferior to copper and aluminum, and as a global large zinc production country and consumption country, the zinc industry in China faces double pressures of ensuring market demand to improve productivity and saving energy, reducing carbon and reducing pollution, so that the zinc-containing secondary zinc concentrate material treatment and recovery have become a future development trend. In the market background of global fatigue in the nonferrous industry, the secondary recovery treatment of zinc-containing concentrate materials is urgently needed. At present, zinc smelting mainly comprises two processes of a pyrogenic process and a wet process. In the two processes, during the secondary recovery treatment of zinc, the zinc concentrate material is extracted before a smelting furnace to analyze the components of the zinc concentrate material. During sampling, the zinc concentrate material is not timely extracted, the accuracy of analysis of the components of the zinc concentrate material is poor after long time consumption, and the effectiveness of sampling and checking results is influenced, so that a sampling, detecting and analyzing method which has good reproducibility and high accuracy and can simultaneously measure high and low content elements is required to be researched.
Disclosure of Invention
The application provides a zinc concentrate material recovery sampling detection method, which can solve the problem of poor sampling detection result in the zinc concentrate material recovery process.
In a first aspect, the application provides a method for detecting recovery sampling of zinc concentrate materials, which comprises the following steps:
controlling a material conveying mechanism to convey zinc concentrate materials along a preset direction;
controlling a camera shooting mechanism to collect images of the zinc concentrate materials;
when the image shot by the camera of the camera mechanism meets the preset definition requirement, the controller controls the camera mechanism to shoot a video stream;
selecting images in the video stream as key frame images according to a preset time interval through an image analysis module, and dividing each key frame image into a material imaging area;
according to the material imaging area, calculating a material imaging angle of the corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle;
acquiring a first actual distance between a camera of the camera mechanism and the zinc concentrate material in a first direction according to the imaging angle, the image depth distance and the current position information of the camera; the first direction is perpendicular to the preset direction;
the controller determines a second actual distance according to the first actual distance, and controls the sampling device to move the second actual distance along the first direction so as to take out a sample to be detected from the zinc concentrate material.
In some exemplary embodiments, before segmenting each of the key frame images into the material imaging region, further comprises:
inputting the key frame images into a zinc concentrate material classification model, wherein the zinc concentrate material classification model outputs the key frame images of sufficient zinc concentrate materials;
dividing each key frame image into a material imaging area as follows: and dividing a material imaging area for each key frame image of the output zinc concentrate material.
In some exemplary embodiments, the preset feature region algorithm is a caddy feature region algorithm; the calculating of the material imaging angle of the corresponding key frame image by adopting the caddy characteristic region algorithm comprises the following steps:
acquiring characteristic region information of the material imaging region by adopting a characteristic region SIFT detection algorithm;
and according to the characteristic region information, adopting a characteristic region matching algorithm to take the imaging angle of the image matched with the characteristic region information of the material imaging region as the material imaging angle corresponding to the key frame image.
In some exemplary embodiments, the capturing the image of the zinc concentrate material by the camera mechanism comprises: a camera holder is adopted to drive a binocular camera to move along at least one direction of the preset direction and the second direction, so that a preset shooting area of the binocular camera covers the zinc concentrate material to acquire an image of the zinc concentrate material; the first direction, the second direction and the preset direction are perpendicular in pairs.
In some exemplary embodiments, obtaining a first actual distance of a camera of the camera mechanism from the zinc concentrate material in a first direction comprises: and carrying out coordinate conversion on the depth of field distance of the image by adopting a three-dimensional point cloud reconstruction algorithm based on space mapping of OpenCV, and obtaining a first actual distance between a camera of the camera mechanism and the zinc concentrate material in a first direction.
In some exemplary embodiments, when the first actual distance is greater than a preset sampling distance, the image analysis module determines that the current thickness of the zinc concentrate material in the first direction is too thin or no material exists, and the control module of the controller controls the sampling device to not sample; or when the first actual distance is smaller than a preset sampling distance, the image analysis module judges that the thickness of the zinc concentrate material in the first direction is too thick at present, and the control module of the controller controls the sampling device not to sample.
In some exemplary embodiments, the controller further includes acquiring initial position information of the camera before controlling the camera to capture an image; and when the camera shoots an image, acquiring moving distance information of the camera, and acquiring current position information of the camera according to the initial position information and the moving distance information.
In some exemplary embodiments, a control module of the controller controls the camera to shoot an image, and when an image analysis module of the controller judges that the image meets a preset definition according to the image shot by the camera, the control module controls the camera to shoot the video stream;
the method for judging that the image meets the preset definition according to the image shot by the camera by the image analysis module comprises the following steps: and acquiring a gray level image of the image shot by the camera, acquiring the connectivity of the edges of the gray level image, and judging that the corresponding image meets the preset definition when the connectivity of the edges of the gray level image is larger than the preset connectivity.
In some exemplary embodiments, when an image photographed by a camera of the photographing mechanism satisfies a preset definition, a control module of the controller controls a position of the camera and controls the camera to photograph the video stream after a preset time.
In a second aspect, the application provides a zinc concentrate material retrieves sample detecting system, include:
the conveying mechanism is used for bearing zinc concentrate materials and conveying the zinc concentrate materials along a preset direction;
the camera shooting mechanism comprises a camera, and the camera is used for collecting images of the zinc concentrate materials;
the controller comprises a control module and an image analysis module, wherein the image analysis module is used for judging imaging definition according to the edge connectivity of an image shot by the acquired camera;
when the image analysis module analyzes that the image shot by the camera meets the preset definition requirement, the control module controls the camera to shoot a video stream;
the image analysis module selects images in the video stream as key frame images according to a preset time interval, and partitions each key frame image into a material imaging area; according to the material imaging area, calculating a material imaging angle of the corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle; acquiring a first actual distance between the camera and the zinc concentrate material in a first direction according to the imaging angle, the image depth distance and the current position information of the camera; the first direction is perpendicular to a preset direction;
the image analysis module determines a second actual distance according to the first actual distance, and the control module controls the sampling device to move along the first direction by the second actual distance so as to take out a sample to be detected from the zinc concentrate material.
According to the zinc concentrate material recycling sampling detection method and detection system, through the material imaging area for obtaining the key frame images, the imaging angle of the corresponding key frame images is obtained according to the material imaging area, the image depth distance is obtained according to the imaging angle, and the first actual distance between the camera and the zinc concentrate materials is obtained according to the imaging angle, the image depth distance and the current position information of the camera. In the process of dividing the material imaging area according to the key frame image, the material characteristics can be obtained so as to judge whether the zinc concentrate material passing through the shooting area of the camera is abnormal or not, and whether sampling operation is carried out or not is judged. In addition, the related data acquired in the process of acquiring the first actual distance can be stored in a controlled storage module so as to be used for optimizing and acquiring the related parameters of the first actual distance on line in real time, and the accuracy and the recognition speed of the recognition result of the zinc concentrate material are continuously improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting recovery sampling of zinc concentrate materials according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a zinc concentrate material recovery sampling detection system according to an embodiment of the present application;
FIG. 3 is a flow diagram of one embodiment of the present application;
fig. 4 is a schematic circuit diagram of a zinc concentrate material recovery sampling detection system according to an embodiment of the present application.
Reference numerals:
10. a zinc concentrate material recycling, sampling and detecting system; 20. zinc concentrate material;
100. a material conveying mechanism; 110. a conveyor belt;
200. an image pickup mechanism; 210. a camera; 220. and a cradle head.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The zinc smelting process flow is longer, and the components of the zinc concentrate entering the roasting furnace need to be measured before the zinc concentrate is roasted, so that the final yield of zinc smelting is estimated in advance. Based on the detection method, the application provides a zinc concentrate material recovery sampling detection method. As shown in fig. 1, which is a flowchart of a zinc concentrate material recovery sampling detection method according to an embodiment of the present application, the zinc concentrate material recovery sampling detection method according to the present application may use the zinc concentrate material recovery sampling detection system 10 shown in fig. 2 to sample the zinc concentrate material 20. Specifically, the zinc concentrate material recovery sampling detection method comprises the following steps:
step S110, controlling the material conveying mechanism 100 to convey the zinc concentrate material 20 along a preset direction.
Step S120, controlling the camera mechanism 200 to collect images of the zinc concentrate material 20.
In step S130, when the image captured by the camera 210 of the image capturing mechanism 200 meets the preset definition requirement, the control module of the controller controls the image capturing mechanism 200 to capture a video stream.
Step S140, selecting images in the video stream as key frame images according to a preset time interval by an image analysis module of the controller, and dividing each key frame image into a material imaging area.
Step S150, calculating the imaging angle of the zinc concentrate material 20 of the corresponding key frame image by adopting a preset characteristic area algorithm according to the material imaging area by an image analysis module of the controller, and obtaining the image depth distance according to the material imaging angle.
In step S160, the image analysis module of the controller obtains a first actual distance between the camera 210 of the camera mechanism 200 and the zinc concentrate material 20 in a first direction according to the imaging angle, the depth of field distance of the image and the current position information of the camera 210.
Step S170, determining a second actual distance according to the first actual distance through an image analysis module of the controller, and controlling the sampling device to move the second actual distance along the first direction through a control module of the controller, wherein the sampling device takes out a sample to be detected from the zinc concentrate material 20 on the conveying mechanism 100.
According to the zinc concentrate material recycling sampling detection method, through the material imaging area of the key frame image, the imaging angle of the corresponding key frame image is obtained according to the material imaging area, the image depth distance is obtained according to the imaging angle, and the first actual distance between the camera 210 and the zinc concentrate material 20 is obtained according to the imaging angle, the image depth distance and the current position information of the camera 210. In the process of dividing the material imaging area according to the key frame image, the material characteristics can also be obtained to judge whether the zinc concentrate material 20 passing through the shooting area of the camera 210 is abnormal or not, so as to judge whether the sampling operation is performed or not. In addition, the related data acquired in the process of acquiring the first actual distance can be stored in a controlled storage module, so as to be used for optimizing and acquiring the related parameters of the first actual distance on line in real time, and the accuracy and the recognition speed of the recognition result of the zinc concentrate material 20 are continuously improved.
In some exemplary embodiments, as shown in fig. 3, before the separation of the keyframe images into the material imaging areas by the image analysis module further includes: inputting each key frame image into a zinc concentrate material classification model, classifying each key frame image, wherein the classification types comprise: and judging the current material state according to the enough material key frame image, the no-material key frame image, the insufficient material key frame image and the excessive material key frame image. And judging by the image analysis module according to the material-free key frame image and the material-shortage key frame image, and sampling the corresponding material due to the shortage. The image analysis module determines that the corresponding excessive material is easily contacted with the camera 210 according to the excessive material key frame image, and sampling is not performed. And judging by the image analysis module according to the enough material key frame image, wherein the corresponding material is excessive and suitable, and sampling can be performed.
The zinc concentrate material classification model has been pre-trained by a target tracking detection algorithm with 20000 images of zinc concentrate material 20, and the model accuracy after training is 96.5%.20000 images of zinc concentrate materials 20 comprise images of materials in various states such as sufficient materials, no materials, insufficient materials, excessive materials, materials with various granularities, materials with various types, materials with impurities and the like. The target tracking detection algorithm includes a pad algorithm. The target tracking detection algorithm is built based on a PADLE neural network deep learning platform.
In some exemplary embodiments, the zinc concentrate material classification model classifies each key frame image, outputs a key frame image of the foot zinc concentrate material, and segments each key frame image of the foot zinc concentrate material output into a material imaging region. Optionally, the zinc concentrate material classification model further comprises adding positioning anchor points when outputting the key frame images of the zinc concentrate material 20, and dividing the area of each key frame image by the positioning anchor points to divide the material imaging area. For example, the anchor points are located out of the contour of the edge area of the zinc concentrate material 20, etc.
In some exemplary embodiments, the preset feature region algorithm is a caddy feature region algorithm.
In some exemplary embodiments, calculating the material imaging angle of the corresponding keyframe image using the caddy feature region algorithm comprises: and acquiring the characteristic region information of the material imaging region by adopting a characteristic region SIFT detection algorithm. And according to the characteristic region information, adopting a characteristic region matching algorithm, and taking the imaging angle of the image matched with the characteristic region information of the material imaging region as the material imaging angle of the corresponding key frame image. For example, the characteristic region of the material imaging region may be an edge region, and the characteristic region information includes contour information, size information, and the like of the edge region.
And obtaining the depth of field distance of the image according to the imaging angle of the material and the depth of field distance algorithm of the image. Optionally, the image capturing mechanism 200 captures an image with a binocular camera, and the image depth-of-field distance algorithm is a binocular depth-of-field distance algorithm.
In some exemplary embodiments, acquiring a first actual distance of the camera 210 of the camera mechanism 200 from the zinc concentrate material 20 in a first direction includes: and carrying out coordinate conversion on the depth of field distance of the image by adopting a three-dimensional point cloud reconstruction algorithm based on the space mapping of OpenCV, and obtaining a first actual distance between the camera 210 of the camera mechanism 200 and the zinc concentrate material 20 in a first direction.
The thickness of the zinc concentrate material 20 can be determined on the basis of the first actual distance. When the first actual distance is greater than the preset sampling distance, the image analysis module judges that the current zinc concentrate material 20 is too thin or has no material in the thickness of the first direction, and the control module of the controller controls the sampling device to not sample. Or when the first actual distance is smaller than the preset sampling distance, the image analysis module judges that the thickness of the current zinc concentrate material 20 in the first direction is too thick, and the control module of the controller controls the sampling device to not sample. Or, when the thickness of the zinc concentrate material 20 in the first direction is too thick, the zinc concentrate material 20 collides with the camera 210, so that the image cannot be acquired due to the complete black, at this time, the control module of the controller controls the material conveying mechanism 100 to stop conveying the zinc concentrate material 20, and the controller sends an alarm signal to the limiting device to prompt abnormal sample feeding. In the first direction, the sampling device performs a sampling operation when the distance between the camera 210 and the zinc concentrate material 20 meets a preset sampling distance.
The zinc concentrate material 20 may be a powdery, granular or block zinc concentrate material 20, and the control module of the controller takes out a preset amount of sample to be detected from the zinc concentrate material 20 on the feed mechanism 100 by controlling the sampling device to move a second actual distance in the first direction.
In some exemplary embodiments, the capturing of images of the zinc concentrate material 20 by the camera mechanism 200 includes: the camera cradle head 220 is adopted to drive the binocular camera to move along at least one direction of the second direction and the preset direction, so that a preset shooting area of the binocular camera covers the zinc concentrate material 20 to acquire images of the zinc concentrate material 20; the first direction, the second direction and the preset direction are perpendicular to each other, for example, the first direction is a vertical direction.
In some exemplary embodiments, before the image analysis module of the controller controls the camera 210 to capture an image, the method further includes acquiring initial position information of the camera 210 by the image analysis module of the controller, acquiring moving distance information of the camera 210 by the image analysis module when the camera 210 captures an image, and the image analysis module acquiring current position information of the camera 210 according to the initial position information and the moving distance information. The moving distance information includes distance information that the camera 210 moves in the second direction from the initial position, and distance information that the camera 210 moves in the preset direction from the initial position.
In some exemplary embodiments, the control module of the controller controls the camera 210 to capture an image, and when the image analysis module determines that the image satisfies a preset definition according to the image captured by the camera 210, the control module of the controller controls the camera 210 to capture a video stream.
The method for judging that the image meets the preset definition according to the image shot by the camera 210 by the image analysis module comprises the following steps: the image analysis module obtains the gray level image of the image shot by the camera 210, and obtains the connectivity of the edge of the gray level image, optionally, the connectivity of the edge of the gray level image after noise reduction is obtained after the gray level image is subjected to noise reduction. When the connectivity of the gray level image edge is larger than the preset connectivity, the image analysis module judges that the corresponding image meets the preset definition. The connectivity is counted as the Euclidean distance of the gray map edges.
When the image captured by the camera 210 of the image capturing mechanism 200 meets the preset definition, the control module controls the position of the camera 210 to be unchanged, and controls the camera 210 to capture a video stream after a preset time. The preset time range is 30s or more and 40s or less. After the imaging of the camera 210 is stable, the control module controls the camera 210 to shoot the video stream.
As shown in fig. 2, the zinc concentrate material recycling, sampling and detecting system 10 according to the embodiment of the present application includes a material conveying mechanism 100, a camera mechanism 200, a controller and a sampling device.
The feed mechanism 100 is for carrying the zinc concentrate material 20 and for conveying the zinc concentrate material 20 in a predetermined direction. The feeding mechanism 100 comprises a driving assembly and a conveyor belt 110, the zinc concentrate material 20 is carried on the conveyor belt 110, and the driving assembly drives the conveyor belt 110 to rotate so as to drive the zinc concentrate material 20 to move along a preset direction.
The camera mechanism 200 includes a camera 210, the camera 210 being used to capture images of the zinc concentrate material 20. For example, camera 210 is a binocular camera. The camera mechanism 200 further includes a camera pan-tilt 220, the camera 210 is mounted on the camera pan-tilt 220, and the camera pan-tilt 220 is configured to drive the binocular camera to move along at least one of the second direction and the preset direction, so that a preset shooting area of the binocular camera covers the zinc concentrate material 20, so that the camera 210 collects images of the corresponding zinc concentrate material 20.
The controller comprises a control module and an image analysis module. As shown in FIG. 4, the control module may employ an AM5728 processor for performing system communication, image acquisition, analysis, calculation, etc. The AM5728 has MIPI parallel data bus, AHB peripheral cache bus, ethernet, etc. functional modules for communicating with cameras, electrical cabinets and servers. The control module adopts EIP field bus to control the driving component and the frequency converter in real time. For convenience of field operation, the zinc concentrate material recovery sampling detection system 10 further comprises an explosion-proof touch screen display terminal, and the states of all the components can be displayed and manually controlled.
The image analysis module is used for judging imaging definition according to the edge connectivity of the acquired image shot by the camera 210; when the image analysis module analyzes that the image captured by the camera 210 meets the preset definition requirement, the control module controls the camera 210 to capture a video stream.
The image analysis module selects images in the video stream as key frame images according to a preset time interval, and partitions each key frame image into a material imaging area; according to the material imaging area, calculating a material imaging angle of a corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle; acquiring a first actual distance between the camera 210 of the camera mechanism 200 and the zinc concentrate material 20 in a first direction according to the imaging angle, the image depth distance and the current position information of the camera 210; the first direction is perpendicular to the preset direction.
The image analysis module determines a second actual distance of the sampling device moving along the first direction according to the first actual distance, and the control module controls a servo driver of the sampling device to drive a material taking part to move along the first direction by the second actual distance, and the material taking part takes out a sample to be detected from the zinc concentrate material 20. For example, the material taking piece is a material taking claw, the material taking claw grabs a sample to be detected, or the sampling device is a vacuum sampling device, the material taking claw is a material taking pipe, and the sample to be detected is sucked in a suction mode.
The controller further includes a memory module, and various parameters in capturing the obtained image information and obtaining the first actual distance by the camera 210 may be stored in the memory module.
The zinc concentrate material recycling, sampling and detecting system 10 of the application samples the zinc concentrate material 20 by adopting the method, and has high sampling precision and sampling efficiency.
The applicant states that the detailed method of the present invention is illustrated by the above examples, but the present invention is not limited to the detailed method described above, i.e. it does not mean that the present invention must be practiced in dependence upon the detailed method described above. It should be apparent to those skilled in the art that any modification of the present invention, equivalent substitution of raw materials for the product of the present invention, addition of auxiliary components, selection of specific modes, etc., falls within the scope of the present invention and the scope of disclosure.
Claims (10)
1. The method for detecting the recovery and sampling of the zinc concentrate material is characterized by comprising the following steps of:
controlling a material conveying mechanism to convey zinc concentrate materials along a preset direction;
controlling a camera shooting mechanism to collect images of the zinc concentrate materials;
when the image shot by the camera of the camera mechanism meets the preset definition requirement, the controller controls the camera mechanism to shoot a video stream;
selecting images in the video stream as key frame images according to a preset time interval through an image analysis module, and dividing each key frame image into a material imaging area;
according to the material imaging area, calculating a material imaging angle of the corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle;
acquiring a first actual distance between a camera of the camera mechanism and the zinc concentrate material in a first direction according to the imaging angle, the image depth distance and the current position information of the camera; the first direction is perpendicular to the preset direction;
the controller judges the thickness of the zinc concentrate material according to the first actual distance, determines a second actual distance according to the first actual distance when the first actual distance meets a preset sampling distance, and controls the sampling device to move the second actual distance along the first direction so as to take out a sample to be detected from the zinc concentrate material.
2. The method for detecting the recovery sampling of zinc concentrate materials according to claim 1, wherein before dividing each key frame image into a material imaging area, the method further comprises:
inputting the key frame images into a zinc concentrate material classification model, wherein the zinc concentrate material classification model outputs the key frame images of sufficient zinc concentrate materials;
dividing each key frame image into a material imaging area as follows: and dividing a material imaging area for each key frame image of the output zinc concentrate material.
3. The zinc concentrate material recycling sampling detection method according to claim 1, wherein the preset characteristic region algorithm is caddy characteristic region algorithm; the calculating of the material imaging angle of the corresponding key frame image by adopting the caddy characteristic region algorithm comprises the following steps:
acquiring characteristic region information of the material imaging region by adopting a characteristic region SIFT detection algorithm;
and according to the characteristic region information, adopting a characteristic region matching algorithm to take the imaging angle of the image matched with the characteristic region information of the material imaging region as the material imaging angle corresponding to the key frame image.
4. The zinc concentrate material recycling sampling detection method according to claim 1, wherein the capturing of the image of the zinc concentrate material by the camera mechanism comprises: a camera holder is adopted to drive a binocular camera to move along at least one direction of the preset direction and the second direction, so that a preset shooting area of the binocular camera covers the zinc concentrate material to acquire an image of the zinc concentrate material; the first direction, the second direction and the preset direction are perpendicular in pairs.
5. The zinc concentrate material recycling sampling detection method according to claim 1, wherein obtaining a first actual distance between a camera of the camera mechanism and the zinc concentrate material in a first direction comprises: and carrying out coordinate conversion on the depth of field distance of the image by adopting a three-dimensional point cloud reconstruction algorithm based on space mapping of OpenCV, and obtaining a first actual distance between a camera of the camera mechanism and the zinc concentrate material in a first direction.
6. The method for detecting the recovery sampling of zinc concentrate materials according to claim 1, wherein,
when the first actual distance is larger than the preset sampling distance, the image analysis module judges that the thickness of the zinc concentrate material in the first direction is too thin or no material exists currently, and the control module of the controller controls the sampling device to not sample; or (b)
When the first actual distance is smaller than the preset sampling distance, the image analysis module judges that the thickness of the zinc concentrate material in the first direction is too thick at present, and the control module of the controller controls the sampling device to not sample.
7. The zinc concentrate material recycling sampling detection method according to claim 1, wherein the controller further comprises acquiring initial position information of the camera before controlling the camera to shoot images; and when the camera shoots an image, acquiring moving distance information of the camera, and acquiring current position information of the camera according to the initial position information and the moving distance information.
8. The zinc concentrate material recycling sampling detection method according to claim 1, wherein a control module of the controller controls the camera to shoot an image, and when an image analysis module of the controller judges that the image meets a preset definition according to the image shot by the camera, the control module controls the camera to shoot the video stream;
the method for judging that the image meets the preset definition according to the image shot by the camera by the image analysis module comprises the following steps:
and acquiring a gray level image of the image shot by the camera, acquiring the connectivity of the edges of the gray level image, and judging that the corresponding image meets the preset definition when the connectivity of the edges of the gray level image is larger than the preset connectivity.
9. The zinc concentrate material recycling sampling detection method according to claim 8, wherein when an image shot by a camera of the camera mechanism meets a preset definition, a control module of the controller controls the position of the camera, and after a preset time, the camera is controlled to shoot the video stream.
10. A zinc concentrate material recovery sampling detection system, comprising:
the conveying mechanism is used for bearing zinc concentrate materials and conveying the zinc concentrate materials along a preset direction;
the camera shooting mechanism comprises a camera, and the camera is used for collecting images of the zinc concentrate materials;
the controller comprises a control module and an image analysis module, wherein the image analysis module is used for judging imaging definition according to the edge connectivity of an image shot by the acquired camera;
when the image analysis module analyzes that the image shot by the camera meets the preset definition requirement, the control module controls the camera to shoot a video stream;
the image analysis module selects images in the video stream as key frame images according to a preset time interval, and partitions each key frame image into a material imaging area; according to the material imaging area, calculating a material imaging angle of the corresponding key frame image by adopting a preset characteristic area algorithm, and acquiring an image depth distance according to the material imaging angle; acquiring a first actual distance between the camera and the zinc concentrate material in a first direction according to the imaging angle, the image depth distance and the current position information of the camera; the first direction is perpendicular to a preset direction;
the image analysis module judges the thickness of the zinc concentrate material according to the first actual distance, when the first actual distance meets the preset sampling distance, the second actual distance is determined according to the first actual distance, and the control module controls the sampling device to move along the first direction by the second actual distance so as to take out a sample to be detected from the zinc concentrate material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211496706.2A CN115629043B (en) | 2022-11-28 | 2022-11-28 | Zinc concentrate material recovery sampling detection method and detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211496706.2A CN115629043B (en) | 2022-11-28 | 2022-11-28 | Zinc concentrate material recovery sampling detection method and detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115629043A CN115629043A (en) | 2023-01-20 |
| CN115629043B true CN115629043B (en) | 2023-04-28 |
Family
ID=84910610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211496706.2A Active CN115629043B (en) | 2022-11-28 | 2022-11-28 | Zinc concentrate material recovery sampling detection method and detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115629043B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116091234B (en) * | 2023-03-27 | 2023-06-23 | 深圳上善智能有限公司 | Precious metal intelligent exchange method and system based on Internet |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019002114A1 (en) * | 2017-06-26 | 2019-01-03 | Krones Ag | Device and method for all-round inspection of containers on a conveyor belt |
| CN114897762A (en) * | 2022-02-18 | 2022-08-12 | 众信方智(苏州)智能技术有限公司 | Automatic positioning method and device for coal mining machine on coal mine working face |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005189179A (en) * | 2003-12-26 | 2005-07-14 | Jfe Steel Kk | Method for measuring granularity of powder granular material |
| CN101872423A (en) * | 2010-05-27 | 2010-10-27 | 天津大学 | Method for tracking moving object on production line |
| US8902422B2 (en) * | 2011-10-21 | 2014-12-02 | Chesner Engineering, Pc | Bulk material sampling and laser targeting system |
| CN104786226A (en) * | 2015-03-26 | 2015-07-22 | 华南理工大学 | Posture and moving track positioning system and method of robot grabbing online workpiece |
| CN110450153B (en) * | 2019-07-08 | 2021-02-19 | 清华大学 | Mechanical arm object active picking method based on deep reinforcement learning |
| CN212527798U (en) * | 2020-06-11 | 2021-02-12 | 鄂尔多斯市中钰泰德煤炭有限公司 | Sorting manipulator |
-
2022
- 2022-11-28 CN CN202211496706.2A patent/CN115629043B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019002114A1 (en) * | 2017-06-26 | 2019-01-03 | Krones Ag | Device and method for all-round inspection of containers on a conveyor belt |
| CN114897762A (en) * | 2022-02-18 | 2022-08-12 | 众信方智(苏州)智能技术有限公司 | Automatic positioning method and device for coal mining machine on coal mine working face |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115629043A (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229362B (en) | Binocular face recognition living body detection method based on access control system | |
| CN110866903B (en) | Ping-pong ball identification method based on Hough circle transformation technology | |
| US11605169B2 (en) | Method and system for detecting flow velocity of high-temperature molten fluid | |
| CN106886216B (en) | Robot automatic tracking method and system based on RGBD face detection | |
| JP6305171B2 (en) | How to detect objects in a scene | |
| CN115629043B (en) | Zinc concentrate material recovery sampling detection method and detection system | |
| WO2021103837A1 (en) | Smoke-emitting vehicle detection method and device, and electronic apparatus | |
| CN106052575A (en) | Pantograph carbon slide plate wear online detection method based on train high speed running | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN105044122A (en) | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model | |
| CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN110633671A (en) | Bus passenger flow real-time statistical method based on depth image | |
| WO2023168984A1 (en) | Area-array camera-based quality inspection method and system for cathode copper | |
| CN112862744B (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| CN102610104B (en) | Onboard front vehicle detection method | |
| CN111091057A (en) | Information processing method and device and computer readable storage medium | |
| JPWO2018020638A1 (en) | Image pickup apparatus, image pickup system and image pickup processing method | |
| CN114140384A (en) | Transverse vibration image recognition algorithm for hoisting steel wire rope based on contour fitting and centroid tracking | |
| CN114004814A (en) | Coal gangue identification method and system based on deep learning and gray scale third moment analysis | |
| CN101320477B (en) | Human body tracing method and equipment thereof | |
| CN112215825A (en) | Quality analysis method and system based on machine vision in new energy battery manufacturing | |
| CN114897762B (en) | Automatic positioning method and device for coal mining machine on coal mine working face | |
| CN115346197A (en) | Driver distraction behavior identification method based on bidirectional video stream | |
| JP2009211122A (en) | Image processor and object estimation program |
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 |