CN109916826B - Solid waste online identification system and method based on hyperspectral detection - Google Patents
Solid waste online identification system and method based on hyperspectral detection Download PDFInfo
- Publication number
- CN109916826B CN109916826B CN201910126775.6A CN201910126775A CN109916826B CN 109916826 B CN109916826 B CN 109916826B CN 201910126775 A CN201910126775 A CN 201910126775A CN 109916826 B CN109916826 B CN 109916826B
- Authority
- CN
- China
- Prior art keywords
- conveyor belt
- materials
- solid waste
- module
- camera
- 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
- 239000002910 solid waste Substances 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 239000000463 material Substances 0.000 claims abstract description 112
- 238000001228 spectrum Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 19
- 210000000078 claw Anatomy 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 239000006185 dispersion Substances 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010187 selection method Methods 0.000 description 7
- 230000036544 posture Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000013077 target material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011150 reinforced concrete Substances 0.000 description 1
- 238000009270 solid waste treatment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Abstract
The invention relates to the technical field of solid waste classification, in particular to a solid waste online identification system and method based on hyperspectral detection; the identification system comprises a material conveying device, a type identification device and a sorting device; the material conveying device conveys the materials to the type recognition device for data acquisition and then conveys the materials to the sorting device for sorting; the material conveying device comprises a first conveyor belt and a second conveyor belt; the material falls into the second conveyer belt after passing through the first conveyer belt transmission, and the operation direction of first conveyer belt and second conveyer belt is opposite. The solid waste online identification system provided by the invention can effectively disperse materials, avoid the difficulty of type identification caused by stacking the materials, and overcome the problem of low efficiency caused by artificial dispersion. Through the identification method, the two-dimensional images and the spectrum curves of the solid wastes can be acquired on line, the effect of accurately and effectively classifying the solid wastes is achieved, and the method has important practical application value.
Description
Technical Field
The invention relates to the technical field of solid waste classification, in particular to a solid waste online identification system and method based on hyperspectral detection.
Background
The land of our country is rich and rich in resources, but due to extremely large population, people occupy less land and resources, and in order to reasonably utilize the land, old buildings are required to be continuously dismantled, so that the original land can be updated to new buildings. A large amount of solid waste can be generated in the dismantling process, if the solid waste is improperly treated, the solid waste occupies a large amount of land, the urban capacity is seriously affected, a plurality of potential safety hazards can be generated by random accumulation, and a plurality of reusable resources, including a plurality of non-renewable resources, such as reinforced concrete and the like, are also generated in the solid waste.
At present, many cities are concerned about the recovery treatment of solid wastes, and many corresponding policies are updated continuously, but the recovery treatment efficiency of the solid wastes is low and the recovery utilization rate is low due to technical problems. The solid waste is often in a stacking state in the solid waste treatment process, and is difficult to effectively identify and separate the solid waste, so that an efficient and reliable solid waste identification scheme is urgently needed at present.
Disclosure of Invention
In order to solve the problem that the solid waste is difficult to identify and separate in the background technology, the invention provides a solid waste online identification system based on hyperspectral detection, which comprises a material conveying device, a type identification device and a sorting device; the material conveying device conveys the materials to the type recognition device for data acquisition and then conveys the materials to the sorting device for sorting;
the material conveying device comprises a first conveyor belt and a second conveyor belt; the material falls into the second conveyer belt after passing through the first conveyer belt transmission, the running direction of first conveyer belt and second conveyer belt is opposite.
On the basis of the technical scheme, further, the first conveyor belt is a constant-speed conveyor belt, and the second conveyor belt is a variable-speed conveyor belt; the transmission speed of the first conveyor belt is smaller than that of the second conveyor belt.
On the basis of the technical scheme, a hyperspectral camera is further arranged in the type recognition device, and the hyperspectral camera is in communication connection with the image processing module and the type recognition module.
On the basis of the technical scheme, the sorting device further comprises a four-axis rectangular coordinate mechanical shaft and a mechanical claw; the second conveyor belt passes through the sorting device, the mechanical claw is arranged above the second conveyor belt, and the mechanical claw is connected with the tail end of the four-axis rectangular coordinate mechanical shaft.
The invention also provides a solid waste online identification method based on hyperspectral detection, which comprises a material conveying module, a data acquisition module, a data analysis processing module and a sorting execution module;
the material conveying module is used for dispersing materials and conveying the materials to the data acquisition module;
the data acquisition module comprises an acquisition camera and is used for acquiring two-dimensional images and spectrum curve information of materials; the two-dimensional image is subjected to an image processing module to obtain geometric characteristics of the material; the type identification module obtains the type of the material according to the spectrum curve;
the data analysis processing module processes the geometric characteristics of the materials into outline, mass center and gesture information of the materials, determines the grabbing position of the materials and the grabbing gesture of the sorting execution module, and determines the final direction of the materials according to the types of the materials.
On the basis of the technical scheme, the contour acquisition method of the material is as follows:
taking the center of the acquisition camera as a coordinate origin, taking the material conveying direction as a y-axis forward direction, and taking the right side vertical to the material conveying direction as an x-axis forward direction;
the acquisition camera is a line scanning camera, so that the lower edge of each picture is the camera position, the y=0 position is set, the center of each picture is the x=0 position, and the position of the centroid in the camera coordinate system can be obtained by combining the position of the centroid in the picture; the gesture is an included angle between the long axis of the rectangle with the minimum enclosed outline and the y axis, which is not more than 90 degrees and not less than-90 degrees.
Based on the technical scheme, the sorting execution module further takes the obtained outlines as units, obtains mass centers and postures according to each outline, selects and identifies the types of specific pixel points in the corresponding outline by utilizing spectral curve information, determines the final types of the corresponding outline through statistics, determines the grabbing positions and postures of the materials according to the mass centers and the postures of the materials, and determines the final directions of the materials according to the types.
On the basis of the technical scheme, the selection method of the specific pixel point is as follows:
setting the frame rate as f and the unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixel;
identifying pointsWherein n is a positive integer.
On the basis of the technical scheme, the selection method of the specific pixel point is as follows: selecting a row of pixel points added with a column of pixel points at the centroid, and setting the frame rate as f and the unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixel; identifying pointsThe calculated amount of one frame at the centroid is n, the calculated amount of each frame is 1, and the total calculated amount is 2n-1; wherein n is a positive integer.
On the basis of the technical scheme, further, pixel points in a rectangular frame area near the centroid can be selected, the calculated amount is multiplied, the calculated amount of each frame is n points, and the calculated amount is n 2 However, the system stability is significantly increased.
On the basis of the technical scheme, furthermore, all pixel points in the outline can be selected, the calculated amount is larger, the specific points are obtained according to the outline size of the actual material, the outline can adapt to more complex working conditions, and the stability is high.
On the basis of the technical scheme, the type identification module further extracts data features from the spectrum curve information by adopting a collude wavelet algorithm.
The solid waste online identification system based on hyperspectral detection provided by the invention can play an effective role in dispersing materials, avoid the difficulty in identifying the types caused by stacking the materials, and overcome the problem of low efficiency caused by artificial dispersion. Through the identification method, two-dimensional images and spectrum curves of solid wastes can be acquired on line, the positions, centroids, postures and types of the wastes are judged in real time through the image processing module and the type identification module, and the obtained centroids, postures and types are output to the sorting device by taking the outline as a unit, so that the effect of accurately and effectively sorting the solid wastes is achieved, and the method has important practical application value.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic diagram of a solid waste online identification system based on hyperspectral detection;
fig. 2 is a flowchart of a method for on-line identification of solid waste based on hyperspectral detection.
Reference numerals:
sorting device of 10 material conveying device 20 type identification device 30
11 first conveyor 12 second conveyor 21 hyperspectral camera
22 image processing module 23 type identification module 31 four-axis rectangular coordinate mechanical axis
32 mechanical gripper
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, merely to facilitate description of the present invention and simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The invention provides a solid waste online identification system based on hyperspectral detection, which is shown in figure 1 and comprises a material conveying device 10, a type identification device 20 and a sorting device 30; the material conveying device 10 conveys the materials to the type recognition device 20 for data acquisition, and then conveys the materials to the sorting device 30 for sorting;
the material conveying device 10 comprises a first conveyor belt 11 and a second conveyor belt 12; the material falls into the second conveyor belt 12 after being transported by the first conveyor belt 11, and the running directions of the first conveyor belt 11 and the second conveyor belt 12 are opposite.
Specifically, according to the solid waste online identification system based on hyperspectral detection, the stacked materials are dispersed by arranging the conveyor belts with different heights and utilizing the difference of the conveying directions of the conveyor belts, the dispersed materials are subjected to data analysis by the type identification device 20, the type identification device 20 can be used for carrying out material identification by adopting the existing image identification device, the identified information is transmitted to the sorting device, and the sorting device sorts the materials of different types according to the identified information. The technical scheme avoids the difficulty of identifying the types caused by stacking materials, solves the problem of low efficiency caused by artificial dispersion, and has high practicability.
Preferably, the first conveyor belt 11 is a constant speed conveyor belt, and the second conveyor belt 12 is a variable speed conveyor belt; the first conveyor belt 11 has a smaller transport speed than the second conveyor belt 12. Specifically, when the accumulated materials fall from the first conveyor belt 11 with a uniform speed into the second conveyor belt 12 with a reverse speed direction, and the second conveyor belt 12 is in variable speed transmission, the speed is greater than that of the first conveyor belt 11, according to the arrangement, the accumulated materials can be better dispersed by utilizing inertia, so that the types of the materials can be conveniently identified.
Preferably, a hyperspectral camera 21 is arranged in the type recognition device 20, and the hyperspectral camera 21 is in communication connection with an image processing module 22 and an image processing module 23; the hyperspectral camera 21 can collect image information of materials, the collected information is transmitted to the image processing module 23 through the image processing module 22, the image processing module 23 judges the types of the materials after comparing according to stored data, and the sorting device 30 sorts the materials.
Further, the sorting device 30 comprises a four-axis rectangular coordinate mechanical shaft 31 and a mechanical claw 32; the second conveyor belt 12 passes through the sorting device 30, the gripper 32 is arranged above the second conveyor belt 12, and the gripper 32 is connected with the tail end of the four-axis rectangular coordinate mechanical shaft 31.
The invention also provides a solid waste online identification method based on hyperspectral detection, which is shown in a flow chart of fig. 2 and specifically comprises the following embodiments:
the system comprises a material conveying module, a data acquisition module, a data analysis processing module and a sorting execution module;
the material conveying module is used for dispersing materials and conveying the materials to the data acquisition module;
the data acquisition module comprises an acquisition camera and is used for acquiring two-dimensional images and spectrum curve information of materials; the two-dimensional image is subjected to an image processing module to obtain geometric characteristics of the material; the type identification module obtains the type of the material according to the spectrum curve; the image processing module comprises filtering, binarization, edge detection, contour extraction and calculation of contour moment to obtain the geometric features, wherein the geometric features comprise contours, barycenters and postures of materials; the type recognition module adopts characteristic extraction and a multi-layer perceptron algorithm to obtain the material type of the material and corresponds to the outline.
The data analysis processing module processes the geometric characteristics of the materials into outline, mass center and gesture information of the materials, determines the grabbing position of the materials and the grabbing gesture of the sorting execution module, and determines the final direction of the materials according to the types of the materials.
Specifically, the contour collection method of the material comprises the following steps:
taking the center of the acquisition camera as a coordinate origin, taking the material conveying direction as a y-axis forward direction, and taking the right side vertical to the material conveying direction as an x-axis forward direction;
the acquisition camera is a line scanning camera, so that the lower edge of each picture is the camera position, the y=0 position is set, the center of each picture is the x=0 position, and the position of the centroid in the camera coordinate system can be obtained by combining the position of the centroid in the picture; the gesture is an included angle between the long axis of the rectangle with the minimum enclosed outline and the y axis, which is not more than 90 degrees and not less than-90 degrees.
The sorting execution module takes the obtained outlines as units, obtains mass centers and gestures according to each outline, selects and identifies the types of specific pixel points in the corresponding outline by utilizing spectral curve information, determines the final types of the corresponding outline through statistics, determines the grabbing positions and the gestures of the materials according to the mass centers and the gestures of the materials, and determines the final directions of the materials according to the types.
The selection method of the specific pixel point can adopt the following four methods:
setting a frame rate as f and setting a unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixe l;
identifying pointsWherein n is a positive integer.
Selecting a row and a column of pixel points at the centroid, and setting the frame rate as f and the unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixe l; identifying pointsThe calculated amount of one frame at the centroid is n, the calculated amount of each frame is 1, and the total calculated amount is 2n-1; wherein n is a positive integer.
The third method can select a pixel point in a rectangular frame area near the centroid, the calculated amount is multiplied, the calculated amount of each frame is n points, and the calculated amount is n 2 The system stability can be significantly increased.
The method IV can also select all pixel points in the outline, the calculated amount is larger, the specific points are obtained according to the outline size of the actual material, and the method is adaptable to more complex working conditions and has strong stability.
The type identification module extracts data characteristics from the spectrum curve information by adopting a hook wavelet algorithm; specifically, two adjacent wave bands are used as right-angle edges, the corresponding hypotenuse length is calculated, and the hypotenuse length is used for replacing the data of the original two adjacent wave bands, namely, one-time dimension reduction of the original half of dimension reduction comprises the trend of improving the numerical value difference between different data and keeping the original data.
The specific calculation formula is as follows:where x is input data, y is processed feature data,i is an integer and k is the dimension of the input data. For example, there is a set of raw data x= (1, 2,3,4,5,6,7, 8), obtained after one feature extraction
According to the embodiment, the accuracy of material identification is tested, the test method is that a plurality of target materials are mixed into the stacked materials, the volume error of each material is not more than 10%, the ratio of the number of the target materials to be sorted to the total number of the stacked materials is used as the accuracy test, and the experiment is repeated 10 times to remove the average value. When the selection method of the specific pixel point is one method, the accuracy is 95.5%; when the selection method of the specific pixel point is the second method, the accuracy is 97.6%; when the selection method is the third method, the accuracy is 98.2%; when the selection method is method four, the accuracy is 99.4%.
Although terms such as material conveying device, type recognition device, sorting device, first conveyor belt, second conveyor belt, hyperspectral camera, type recognition module, four-axis rectangular coordinate machine axis, gripper, etc. are used more herein, the possibility of using other terms is not excluded. These terms are used merely for convenience in describing and explaining the nature of the invention; they are to be interpreted as any additional limitation that is not inconsistent with the spirit of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (10)
1. Solid waste on-line identification system based on hyperspectral detection, its characterized in that: comprises a material conveying device (10), a type identification device (20) and a sorting device (30); the material conveying device (10) conveys materials to the type recognition device (20) for data acquisition, and then conveys the materials to the sorting device (30) for sorting;
the material conveying device (10) comprises a first conveyor belt (11) and a second conveyor belt (12); the first conveyor belt (11) is positioned above the second conveyor belt (12), and the first conveyor belt (11) and the second conveyor belt (12) are arranged at intervals; the materials fall into the second conveyor belt (12) after being transmitted by the first conveyor belt (11), and the running directions of the first conveyor belt (11) and the second conveyor belt (12) are opposite.
2. The hyperspectral detection-based solid waste online identification system as claimed in claim 1, wherein: the first conveyor belt (11) is a constant-speed conveyor belt, and the second conveyor belt (12) is a variable-speed conveyor belt; the first conveyor belt (11) has a transport speed that is less than the transport speed of the second conveyor belt (12).
3. The hyperspectral detection-based solid waste online identification system as claimed in claim 1, wherein: a hyperspectral camera (21) is arranged in the type recognition device (20), and the hyperspectral camera (21) is in communication connection with an image processing module (22) and a type recognition module (23).
4. The hyperspectral detection-based solid waste online identification system as claimed in claim 1, wherein: the sorting device (30) comprises a four-axis rectangular coordinate mechanical shaft (31) and a mechanical claw (32); the second conveyor belt (12) passes through the sorting device (30), the mechanical claw (32) is arranged above the second conveyor belt (12), and the mechanical claw (32) is connected with the tail end of the four-axis rectangular coordinate mechanical shaft (31).
5. The solid waste online identification method based on hyperspectral detection is characterized by comprising a material conveying module, a data acquisition module, a data analysis processing module and a sorting execution module; the material conveying module comprises a first conveyor belt and a second conveyor belt; the first conveyor belt is positioned above the second conveyor belt, and the first conveyor belt and the second conveyor belt are arranged at intervals; the materials fall into the second conveyor belt after being transmitted by the first conveyor belt, and the running directions of the first conveyor belt and the second conveyor belt are opposite;
the material conveying module is used for dispersing materials and conveying the materials to the data acquisition module;
the data acquisition module comprises an acquisition camera and is used for acquiring two-dimensional images and spectrum curve information of materials; the two-dimensional image is subjected to an image processing module to obtain geometric characteristics of the material; the type identification module obtains the type of the material according to the spectrum curve;
the data analysis processing module processes the geometric characteristics of the materials into outline, mass center and gesture information of the materials, determines the grabbing position of the materials and the grabbing gesture of the sorting execution module, and determines the final direction of the materials according to the types of the materials.
6. The method for identifying solid waste on line based on hyperspectral detection as claimed in claim 5, wherein the contour acquisition method of the material is as follows:
taking the center of the acquisition camera as a coordinate origin, taking the material conveying direction as a y-axis forward direction, and taking the right side vertical to the material conveying direction as an x-axis forward direction;
the acquisition camera is a line scanning camera, so that the lower edge of each picture is the camera position, the y=0 position is set, the center of each picture is the x=0 position, and the position of the centroid in the camera coordinate system can be obtained by combining the position of the centroid in the picture; the gesture is an included angle between the long axis of the rectangle with the minimum enclosed outline and the y axis, which is not more than 90 degrees and not less than-90 degrees.
7. The hyperspectral detection-based solid waste online identification method as claimed in claim 5, wherein the method comprises the following steps: the sorting execution module takes the obtained outlines as units, obtains mass centers and gestures according to each outline, selects and identifies the types of specific pixel points in the corresponding outline by utilizing spectral curve information, determines the final types of the corresponding outline through statistics, determines the grabbing positions and the gestures of the materials according to the mass centers and the gestures of the materials, and determines the final directions of the materials according to the types.
8. The method for identifying the solid waste on line based on hyperspectral detection as claimed in claim 7, wherein the method for selecting the specific pixel point is as follows:
setting the frame rate as f and the unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixel;
identifying pointsWherein n is a positive integer.
9. The method for identifying the solid waste on line based on hyperspectral detection as claimed in claim 7, wherein the method for selecting the specific pixel point is as follows: selecting a row of pixel points added with a column of pixel points at the centroid, and setting the frame rate as f and the unit as FPS; the minimum identification material size is d, and the unit is mm; the speed of the conveyor belt is v, and the unit is mm/s; the spatial resolution of the camera is r, and the unit is mm/pixel; identifying pointsThe calculated amount of one frame at the centroid is n, the calculated amount of each frame is 1, and the total calculated amount is 2n-1; wherein n is a positive integer.
10. The hyperspectral detection-based solid waste online identification method as claimed in claim 5, wherein the method comprises the following steps: and the type identification module extracts data characteristics from the spectrum curve information by adopting a collude wavelet algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126775.6A CN109916826B (en) | 2019-02-20 | 2019-02-20 | Solid waste online identification system and method based on hyperspectral detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126775.6A CN109916826B (en) | 2019-02-20 | 2019-02-20 | Solid waste online identification system and method based on hyperspectral detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109916826A CN109916826A (en) | 2019-06-21 |
| CN109916826B true CN109916826B (en) | 2024-02-06 |
Family
ID=66961834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910126775.6A Active CN109916826B (en) | 2019-02-20 | 2019-02-20 | Solid waste online identification system and method based on hyperspectral detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109916826B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516570B (en) * | 2019-08-15 | 2022-09-23 | 广东弓叶科技有限公司 | Vision-based garbage classification and identification method and device |
| CN110749555B (en) * | 2019-10-30 | 2022-05-31 | 宜宾五粮液股份有限公司 | Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji |
| CN110665848A (en) * | 2019-10-31 | 2020-01-10 | 华侨大学 | Building solid waste sorting system based on CCD camera and high spectrum camera detection |
| CN111144322A (en) * | 2019-12-28 | 2020-05-12 | 广东拓斯达科技股份有限公司 | Sorting method, device, equipment and storage medium |
| CN111144426B (en) * | 2019-12-28 | 2023-05-30 | 广东拓斯达科技股份有限公司 | Sorting method, sorting device, sorting equipment and storage medium |
| CN112098340A (en) * | 2020-08-04 | 2020-12-18 | 中南民族大学 | Turquoise identification method based on hyperspectral imaging technology and assembly line process |
| CN112001961B (en) * | 2020-08-28 | 2023-08-11 | 广西科技大学 | Loading machine and material associated shovel loading system and method |
| CN117085970B (en) * | 2023-10-18 | 2023-12-26 | 北京大学 | Multi-class solid waste recycling intelligent system based on AI (advanced technology attachment) identification |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107999405A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | A kind of building waste on-line sorting system and method for sorting |
-
2019
- 2019-02-20 CN CN201910126775.6A patent/CN109916826B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107999405A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | A kind of building waste on-line sorting system and method for sorting |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109916826A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109916826B (en) | Solid waste online identification system and method based on hyperspectral detection | |
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| CN105388162B (en) | Raw material silicon chip surface scratch detection method based on machine vision | |
| CN101271514B (en) | Image detection method and device for fast object detection and objective output | |
| CN107096720A (en) | Express mail bar code automatic recognition system and method based on image procossing | |
| CN112893159B (en) | Coal gangue sorting method based on image recognition | |
| CN101059425A (en) | Method and device for identifying different variety green tea based on multiple spectrum image texture analysis | |
| CN101510258A (en) | Certificate verification method, system and certificate verification terminal | |
| CN102521589A (en) | Method and system for detecting lane marked lines | |
| CN111062938B (en) | Plate expansion plug detection system and method based on machine learning | |
| JPH10508709A (en) | Device for detecting air bubbles in cover slip adhesive | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN102855641A (en) | Fruit level classification system based on external quality | |
| CN111715540B (en) | Apparatus and method for sorting coal and gangue | |
| CN108280838A (en) | A kind of intermediate plate tooth form defect inspection method based on edge detection | |
| CN104881635A (en) | Image texture extraction and identification method by non-Gauss two-dimension Gabor filter | |
| CN106355174A (en) | Method and system for dynamically extracting key information of express sheets | |
| CN110866503B (en) | Abnormality detection method and abnormality detection system for finger vein equipment | |
| CN104484653A (en) | Bad corn kernel detecting method based on image recognition technology | |
| CN112528740A (en) | Pressing plate state identification method | |
| CN106067020A (en) | The system and method for quick obtaining effective image under real-time scene | |
| Wang et al. | Automatic separation system of coal gangue based on DSP and digital image processing | |
| CN113591973A (en) | Intelligent comparison method for appearance state changes of track slabs | |
| CN103198323A (en) | Pedestrian detection method based on curve fitting | |
| CN115672778A (en) | Intelligent visual recognition system |
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 |