CN109916826A - A kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection - Google Patents
A kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection Download PDFInfo
- Publication number
- CN109916826A CN109916826A CN201910126775.6A CN201910126775A CN109916826A CN 109916826 A CN109916826 A CN 109916826A CN 201910126775 A CN201910126775 A CN 201910126775A CN 109916826 A CN109916826 A CN 109916826A
- Authority
- CN
- China
- Prior art keywords
- solid waste
- conveyer belt
- module
- hyperion
- online recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000002910 solid waste Substances 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 94
- 238000001228 spectrum Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 14
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 239000006185 dispersion Substances 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 238000009825 accumulation Methods 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000013077 target material Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Sorting Of Articles (AREA)
Abstract
The present invention relates to solid waste sorting technique field, in particular to a kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection；Identifying system includes device for transporting objects, category identification device, sorting equipment；After material transferring to category identification device is carried out data acquisition by device for transporting objects, it is transmitted to sorting equipment and material is sorted；Device for transporting objects includes the first conveyer belt and the second conveyer belt；Material, which passes through, falls into the second conveyer belt after the first conveyer belt transmits, the traffic direction of the first conveyer belt and the second conveyer belt is opposite.The problem of solid waste online recognition system provided by the invention can play effective peptizaiton to material, avoid the difficulty for causing category identification because of material stacking, also overcome low efficiency caused by artificial dispersion.By recognition methods, it is capable of the two dimensional image and the curve of spectrum of online acquisition solid waste, achievees the effect that accurate and effective classifies to solid waste, there is important practical application value.
Description
Technical field
The present invention relates to solid waste sorting technique field, in particular to a kind of solid waste online recognition system based on EO-1 hyperion detection
System and recognition methods.
Background technique
China soil is richly endowed, resourceful, but since population amount is very big, causes to take up an area per capita and resource is all less, be
Reasonable utilization soil, need to constantly remove Old building so that original soil can update new building.It will be produced in demolishing process
Raw a large amount of solid waste, if dealing with improperly, solid waste not only a large amount of land occupations seriously affect the appearance of the city, and arbitrarily accumulation can also generate
Many security risks, while there are many more recycling resources in solid waste, including many non-renewable resources, as reinforcing bar is mixed
Solidifying soil etc..
Currently, many cities all have begun the recovery processing of concern solid waste, many corresponding policies have been constantly updated, but
It is due to technical problem, so that solid waste is recycled low efficiency, recovery utilization rate is low.And heap is usually in during fixed-end forces
Cumuliformis state, it is difficult to effectively identification separation be formed to solid waste, therefore there is an urgent need to a kind of solid waste identifying schemes of high efficient and reliable at present.
Summary of the invention
To solve the problems, such as that the solid waste mentioned in above-mentioned background technique is difficult to separation, the present invention provides a kind of based on height
The solid waste online recognition system of spectral detection, including device for transporting objects, category identification device, sorting equipment；The material is defeated
After sending device that material transferring to category identification device is carried out data acquisition, it is transmitted to sorting equipment and material is sorted；
The device for transporting objects includes the first conveyer belt and the second conveyer belt；Material is transmitted by first conveyer belt
After fall into second conveyer belt, the traffic direction of first conveyer belt and the second conveyer belt is opposite.
Based on the above technical solution, further, first conveyer belt is at the uniform velocity transmission belt, and described second passes
Defeated band is variable rate transmissions band；The transmission speed that the transmission speed size of first conveyer belt is less than second transmission belt is big
It is small.
Based on the above technical solution, further, EO-1 hyperion camera, institute are provided in the category identification device
It states EO-1 hyperion camera and image processing module and category identification module communicates to connect.
It based on the above technical solution, further, include four axis rectangular co-ordinate mechanical axis in the sorting equipment
And gripper；Second conveyer belt passes through the sorting equipment, is provided with the gripper, institute above second conveyer belt
Gripper is stated to connect with the four axis rectangular co-ordinate machinery the tip of the axis.
The present invention also provides a kind of solid waste online recognition methods based on EO-1 hyperion detection, including material conveyor module, number
According to acquisition module, Data Analysis Services module and sorting execution module；
The material conveyor module is for dispersed material and is delivered to data acquisition module；
The data acquisition module includes acquisition camera, for acquiring the two dimensional image and curve of spectrum information of material；Institute
It states two dimensional image and obtains the geometrical characteristic of material by image processing module；Category identification module is obtained according to the curve of spectrum
The classification of material；
The Data Analysis Services module is processed into the profile, mass center and posture information of material according to the geometrical characteristic of material
It determines the crawl position of material and the crawl posture of sorting execution module, and finally going for material is determined according to the type of material
To.
Based on the above technical solution, further, the profile acquisition method of material are as follows:
To acquire image center as coordinate origin, material conveying direction is that y-axis is positive, perpendicular to the right side of material conveying direction
Side is that x-axis is positive；
The acquisition camera is line scan camera, therefore the lower edge of every picture is camera position, if y=0 at this, often
The center of picture is that the position at x=0, in conjunction with where mass center in picture can obtain position of the mass center in camera coordinates system
It sets；The posture is the long axis of profile minimum area-encasing rectangle and the angle no more than 90 ° and not less than -90 ° of y-axis.
Based on the above technical solution, further, the sorting execution module, as unit of the profile of acquisition,
Mass center is obtained according to each profile, posture selects the type of specific pixel point in identification corresponding contour using curve of spectrum information,
By the final type of statistical decision corresponding contour, the crawl that execution module determines material according to the mass center and posture of material is sorted
Position and posture, and determine according to type the final whereabouts of material.
Based on the above technical solution, further, the choosing method of the specific pixel point are as follows:
If frame per second is f, unit FPS；Minimum identification material size is d, unit mm；Conveyor belt speed is v, and unit is
mm/s；Camera space resolution ratio is r, unit mm/pixel；
Identification pointsWherein, n is positive integer.
Based on the above technical solution, further, the choosing method of the specific pixel point are as follows: at selection mass center
A line adds a column pixel, if frame per second is f, unit FPS；Minimum identification material size is d, unit mm；Conveyor belt speed
For v, unit mm/s；Camera space resolution ratio is r, unit mm/pixel；Identification pointsAt mass center
A frame calculation amount be n, remaining every frame calculation amount be 1, the amount of calculation 2n-1；Wherein, n is positive integer.
Based on the above technical solution, further, the picture in one rectangle frame region of center of mass also may be selected
Vegetarian refreshments, calculation amount are multiplied, and the calculation amount of each frame is n point, the amount of calculation n2Point, but keep system stability significant
Increase.
Based on the above technical solution, further, it is also an option that all pixels point in profile, calculation amount is more
Greatly, the profile size of specific several factually border materials obtains, and is suitable for more complex operating condition, stability is strong.
Based on the above technical solution, further, the category identification module is by curve of spectrum information using hook
Stock wavelet algorithm extracts data characteristics.
A kind of solid waste online recognition system based on EO-1 hyperion detection provided by the invention can play effectively material
Peptizaiton avoids the difficulty for causing category identification because of material stacking, also overcomes low efficiency caused by artificial dispersion
The problem of.By recognition methods, it is capable of the two dimensional image and the curve of spectrum of online acquisition solid waste, passes through image processing module and kind
Class identification module judges position, mass center, posture and the type of rubbish out in real time, and as unit of profile, by the mass center of acquisition, appearance
State and type are exported to sorting equipment, achieve the effect that accurate and effective classifies to solid waste, have important practical application valence
Value.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the solid waste online recognition system structure diagram provided by the invention based on EO-1 hyperion detection；
Fig. 2 is the solid waste online recognition method flow diagram provided by the invention based on EO-1 hyperion detection.
Appended drawing reference:
10 device for transporting objects, 20 category identification device, 30 sorting equipment
11 first 12 second conveyer belt of conveyer belt, 21 EO-1 hyperion camera
22 image processing module, 23 category identification module, 31 4 axis rectangular co-ordinate mechanical axis
32 grippers
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
The present invention provides a kind of solid waste online recognition system based on EO-1 hyperion detection, as shown in Figure 1, including that material conveys
Device 10, category identification device 20, sorting equipment 30；The device for transporting objects 10 is by material transferring to category identification device 20
After carrying out data acquisition, it is transmitted to sorting equipment 30 and material is sorted；
The device for transporting objects 10 includes the first conveyer belt 11 and the second conveyer belt 12；Material is transmitted by described first
Band 11 falls into second conveyer belt 12 after transmitting, and the traffic direction of first conveyer belt 11 and the second conveyer belt 12 is opposite.
Specifically, the solid waste online recognition system provided by the invention based on EO-1 hyperion detection is different by setting height
Conveyer belt, and using conveyer belt transmission direction difference, the material of accumulation is dispersed, the material after dispersion passes through kind
Note identification apparatus 20 carries out data analysis, and the category identification device 20 can be carried out using existing pattern recognition device
Material recognition, and the information after identification is transmitted to sorting equipment, sorting equipment is according to the information of identification by different types of object
Material is classified, and the program can also transmit instruction by existing signal and realize.Above scheme design, avoids because of material heap
Difficulty that is folded and causing category identification, has very high practicability at the problem of also overcoming low efficiency caused by artificial dispersion.
Preferably, first conveyer belt 11 is that at the uniform velocity transmission belt, second transmission belt 12 are variable rate transmissions band；It is described
The transmission speed size of first conveyer belt 11 is less than the transmission speed size of second transmission belt 12.Specifically, when accumulation
When material falls into the second opposite transmission belt 12 of directional velocity from the first conveyer belt 11 at the uniform velocity, and the second transmission belt 12 is speed change
Transmission, speed is greater than the first conveyer belt 11, according to the setting, and utilizes inertia, preferably the material of accumulation can be divided
It dissipates, in order to the category identification of material.
Preferably, EO-1 hyperion camera 21, the EO-1 hyperion camera 21 and image are provided in the category identification device 20
Processing module 22 and image processing module 23 communicate to connect；The image information of material can be adopted by EO-1 hyperion camera 21
Collection, and the information of acquisition is transmitted to image processing module 23 by image processing module 22, image processing module 23 is according to storage
After the data deposited are compared, the type of material is judged, then sorted by sorting equipment 30.
It further, include four axis rectangular co-ordinate mechanical axis 31 and gripper 32 in the sorting equipment 30；Described second
Conveyer belt 12 passes through the sorting equipment 30, is provided with the gripper 32, the gripper above second conveyer belt 12
32 connect with the end of the four axis rectangular co-ordinate mechanical axis 31.
The present invention also provides a kind of solid waste online recognition methods based on EO-1 hyperion detection, as shown in Fig. 2 flow chart, specifically
Including following embodiment:
Using material conveyor module, data acquisition module, Data Analysis Services module and sorting execution module；
The material conveyor module is for dispersed material and is delivered to data acquisition module；
The data acquisition module includes acquisition camera, for acquiring the two dimensional image and curve of spectrum information of material；Institute
It states two dimensional image and obtains the geometrical characteristic of material by image processing module；Category identification module is obtained according to the curve of spectrum
The classification of material；Described image processing module includes that filtering, binaryzation, edge detection, contours extract and calculating Contour moment obtain
The geometrical characteristic, geometrical characteristic include the profile, mass center and posture of material；Category identification module uses feature to spectral information
The material category of extraction and multi-layer perception (MLP) algorithm acquisition material is simultaneously corresponding with profile.
The Data Analysis Services module is processed into the profile, mass center and posture information of material according to the geometrical characteristic of material
It determines the crawl position of material and the crawl posture of sorting execution module, and finally going for material is determined according to the type of material
To.
Specifically, the profile acquisition method of material are as follows:
To acquire image center as coordinate origin, material conveying direction is that y-axis is positive, perpendicular to the right side of material conveying direction
Side is that x-axis is positive；
The acquisition camera is line scan camera, therefore the lower edge of every picture is camera position, if y=0 at this, often
The center of picture is that the position at x=0, in conjunction with where mass center in picture can obtain position of the mass center in camera coordinates system
It sets；The posture is the long axis of profile minimum area-encasing rectangle and the angle no more than 90 ° and not less than -90 ° of y-axis.
The sorting execution module obtains mass center according to each profile, posture utilizes light as unit of the profile of acquisition
The type of specific pixel point in spectral curve information selection identification corresponding contour, by the final type of statistical decision corresponding contour,
Sorting execution module determines crawl position and the posture of material according to the mass center and posture of material, and determines material according to type
Final whereabouts.
Wherein, the choosing method of the specific pixel point can use following four method:
Method one sets frame per second as f, unit FPS；Minimum identification material size is d, unit mm；Conveyor belt speed is
V, unit mm/s；Camera space resolution ratio is r, unit mm/pixel；
Identification pointsWherein, n is positive integer.
A line adds a column pixel at method two, selection mass center, if frame per second is f, unit FPS；Minimum identification material ruler
Very little is d, unit mm；Conveyor belt speed is v, unit mm/s；Camera space resolution ratio is r, unit mm/pixel；Identification
PointsIn addition to the frame calculation amount at mass center is n, remaining every frame calculation amount is 1, the amount of calculation 2n-1；Its
In, n is positive integer.
Pixel in method three, also optional one rectangle frame region of center of mass, calculation amount are multiplied, each frame
Calculation amount be n point, the amount of calculation n2Point can be such that system stability dramatically increases.
Method four is also an option that all pixels point in profile, and calculation amount is bigger, the wheel of specific several factually border materials
Wide size obtains, and is suitable for more complex operating condition, and stability is strong.
Curve of spectrum information is extracted data characteristics using stock wavelet algorithm is hooked by the category identification module；Specifically
Corresponding the length of the hypotenuse is sought using two adjacent bands as right-angle side in ground, and the data of former adjacent two wave band are replaced with the length of the hypotenuse size,
I.e. the original half of linear transformation dimension dimensionality reduction includes the numerical value difference improved between different data, and keeps becoming for initial data
Gesture.
Specific formula for calculation are as follows:Wherein x is input data, and y is treated characteristic,I is integer, and k is the dimension of input data.For example, there are one group of initial data x=(1,2,
3,4,5,6,7,8) it, is obtained after a feature extraction
According to above-described embodiment, the accuracy rate of material recognition is tested, test method is to be mixed into stacking material
The volume Size Error of a number of target material, each material is no more than 10%, and the quantity of sorting is prepared with target material
It is tested with the ratio of stacking material total quantity as accuracy rate, experiment is repeated 10 times, and removes average value.Wherein, when specific pixel point
Choosing method is method a period of time, accuracy rate 95.5%；When the choosing method of specific pixel point is method two, accuracy rate is
97.6%；When choosing method is method three, accuracy rate 98.2%；When choosing method is method four, accuracy rate is
99.4%.
Although more herein used such as device for transporting objects, category identification device, sorting equipment, the first transmission
The terms such as band, the second conveyer belt, EO-1 hyperion camera, category identification module, four axis rectangular co-ordinate mechanical axis, gripper, but not
It rules out the possibility of using other terms.The use of these items is only for be more convenient to describe and explain sheet of the invention
Matter；Being construed as any additional limitation is disagreed with spirit of that invention.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of solid waste online recognition system based on EO-1 hyperion detection, it is characterised in that: including device for transporting objects (10), kind
Note identification apparatus (20), sorting equipment (30)；The device for transporting objects (10) is by material transferring to category identification device (20)
After carrying out data acquisition, it is transmitted to sorting equipment (30) and material is sorted；
The device for transporting objects (10) includes the first conveyer belt (11) and the second conveyer belt (12)；Material is passed by described first
Second conveyer belt (12), the operation of first conveyer belt (11) and the second conveyer belt (12) are fallen into after sending band (11) transmission
It is contrary.
2. the solid waste online recognition system according to claim 1 based on EO-1 hyperion detection, it is characterised in that: described first
Conveyer belt (11) is that at the uniform velocity transmission belt, second transmission belt (12) are variable rate transmissions band；The biography of first conveyer belt (11)
Defeated velocity magnitude is less than the transmission speed size of second transmission belt (12).
3. the solid waste online recognition system according to claim 1 based on EO-1 hyperion detection, it is characterised in that: the type
It is provided with EO-1 hyperion camera (21) in identification device (20), the EO-1 hyperion camera (21) and image processing module (22) and type
Identification module (23) communication connection.
4. the solid waste online recognition system according to claim 1 based on EO-1 hyperion detection, it is characterised in that: the sorting
It include four axis rectangular co-ordinate mechanical axis (31) and gripper (32) in device (30)；Second conveyer belt (12) passes through described point
It picks device (30), is provided with the gripper (32) above second conveyer belt (12), the gripper (32) and described four
The end of axis rectangular co-ordinate mechanical axis (31) connects.
5. a kind of solid waste online recognition method based on EO-1 hyperion detection, which is characterized in that adopted including material conveyor module, data
Collect module, Data Analysis Services module and sorting execution module；
The material conveyor module is for dispersed material and is delivered to data acquisition module；
The data acquisition module includes acquisition camera, for acquiring the two dimensional image and curve of spectrum information of material；Described two
Dimension image obtains the geometrical characteristic of material by image processing module；Category identification module obtains material according to the curve of spectrum
Classification；
The Data Analysis Services module is determined according to the profile, mass center and posture information that the geometrical characteristic of material is processed into material
The crawl posture of the crawl position of material and sorting execution module, and determine according to the type of material the final whereabouts of material.
6. the solid waste online recognition method according to claim 1 based on EO-1 hyperion detection, which is characterized in that the wheel of material
Wide acquisition method are as follows:
To acquire image center as coordinate origin, material conveying direction is that y-axis is positive, and the right side perpendicular to material conveying direction is
X-axis is positive；
The acquisition camera is line scan camera, therefore the lower edge of every picture is camera position, if y=0 at this, every figure
The center of piece is that the position at x=0, in conjunction with where mass center in picture can obtain position of the mass center in camera coordinates system；
The posture is the long axis of profile minimum area-encasing rectangle and the angle no more than 90 ° and not less than -90 ° of y-axis.
7. the solid waste online recognition method according to claim 1 based on EO-1 hyperion detection, it is characterised in that: the sorting
Execution module obtains mass center according to each profile, posture selects to know using curve of spectrum information as unit of the profile of acquisition
The type of specific pixel point in other corresponding contour, by the final type of statistical decision corresponding contour, sort execution module according to
The mass center and posture of material determine crawl position and the posture of material, and the final whereabouts of material is determined according to type.
8. the solid waste online recognition method according to claim 1 based on EO-1 hyperion detection, which is characterized in that described specific
The choosing method of pixel are as follows:
If frame per second is f, unit FPS；Minimum identification material size is d, unit mm；Conveyor belt speed is v, unit mm/
s；Camera space resolution ratio is r, unit mm/pixel；
Identification pointsWherein, n is positive integer.
9. the solid waste online recognition method according to claim 1 based on EO-1 hyperion detection, which is characterized in that described specific
The choosing method of pixel are as follows: a line adds a column pixel at selection mass center, if frame per second is f, unit FPS；Minimum identification object
Material is having a size of d, unit mm；Conveyor belt speed is v, unit mm/s；Camera space resolution ratio is r, unit mm/pixel；
Identification pointsIn addition to the frame calculation amount at mass center is n, remaining every frame calculation amount is 1, the amount of calculation 2n-
1；Wherein, n is positive integer.
10. the solid waste online recognition method according to claim 1 based on EO-1 hyperion detection, it is characterised in that: described kind
Curve of spectrum information is extracted data characteristics using stock wavelet algorithm is hooked by class identification module.
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 true CN109916826A (en) | 2019-06-21 |
| CN109916826B 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) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516570A (en) * | 2019-08-15 | 2019-11-29 | 东莞弓叶互联科技有限公司 | A kind of garbage classification recognition methods of view-based access control model and device |
| 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 |
| CN110749555A (en) * | 2019-10-30 | 2020-02-04 | 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 |
| CN112001961A (en) * | 2020-08-28 | 2020-11-27 | 广西科技大学 | Loader and material associated shoveling system and method |
| 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 |
| WO2021129527A1 (en) * | 2019-12-28 | 2021-07-01 | 广东拓斯达科技股份有限公司 | Sorting method and apparatus, device, and storage medium |
| WO2021129528A1 (en) * | 2019-12-28 | 2021-07-01 | 广东拓斯达科技股份有限公司 | Sorting method and apparatus, and device and storage medium |
| CN117085970A (en) * | 2023-10-18 | 2023-11-21 | 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 |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516570A (en) * | 2019-08-15 | 2019-11-29 | 东莞弓叶互联科技有限公司 | A kind of garbage classification recognition methods of view-based access control model and device |
| CN110749555A (en) * | 2019-10-30 | 2020-02-04 | 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 |
| 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 |
| WO2021129527A1 (en) * | 2019-12-28 | 2021-07-01 | 广东拓斯达科技股份有限公司 | Sorting method and apparatus, device, and storage medium |
| WO2021129528A1 (en) * | 2019-12-28 | 2021-07-01 | 广东拓斯达科技股份有限公司 | Sorting method and apparatus, and device 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 |
| CN112001961A (en) * | 2020-08-28 | 2020-11-27 | 广西科技大学 | Loader and material associated shoveling system and method |
| CN112001961B (en) * | 2020-08-28 | 2023-08-11 | 广西科技大学 | Loading machine and material associated shovel loading system and method |
| CN117085970A (en) * | 2023-10-18 | 2023-11-21 | 北京大学 | Multi-class solid waste recycling intelligent system based on AI (advanced technology attachment) identification |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109916826B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109916826A (en) | A kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection | |
| CN104134209B (en) | A kind of feature extracting and matching method and system in vision guided navigation | |
| DE60014959T2 (en) | DEVICE FOR LAYING DETERMINATION OF LABELS, USING MULTIPLE RESOLUTIONS | |
| CN108491892A (en) | fruit sorting system based on machine vision | |
| CN113643280B (en) | Computer vision-based plate sorting system and method | |
| CN108971190A (en) | A kind of separating domestic garbage method based on machine vision | |
| CN102034254B (en) | Method for recognizing geometric figure | |
| CN101403703A (en) | Real-time detection method for foreign fiber in lint | |
| CN104624505A (en) | Waste plastic separating method and system based on image recognition | |
| CN104951775A (en) | Video technology based secure and smart recognition method for railway crossing protection zone | |
| CN101807257A (en) | Method for identifying information of image tag | |
| CN102645679A (en) | Mesocyclone identification method based on Doppler radar echo images | |
| CN110321769A (en) | A kind of more size commodity on shelf detection methods | |
| CN102999886A (en) | Image edge detector and ruler raster grid line precision detection system | |
| CN109063789A (en) | The classification method of shaft tower and power line, device and system | |
| CN108009538A (en) | A kind of automobile engine cylinder-body sequence number intelligent identification Method | |
| CN109949229A (en) | A kind of target cooperative detection method under multi-platform multi-angle of view | |
| CN106355174A (en) | Method and system for dynamically extracting key information of express sheets | |
| CN102855641A (en) | Fruit level classification system based on external quality | |
| CN110263795A (en) | One kind is based on implicit shape and schemes matched object detection method | |
| CN107403451A (en) | Adaptive binary feature monocular vision odometer method and computer, robot | |
| CN108038482A (en) | A kind of automobile engine cylinder-body sequence number Visual intelligent identifying system | |
| CN107121436A (en) | The Intelligent detecting method and identification device of a kind of silicon material quality | |
| KR102391501B1 (en) | Classification System and method for atypical recycled goods using Deep learning | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |