CN110694921A - Vegetable sorting system and control method thereof - Google Patents
Vegetable sorting system and control method thereof Download PDFInfo
- Publication number
- CN110694921A CN110694921A CN201910840248.1A CN201910840248A CN110694921A CN 110694921 A CN110694921 A CN 110694921A CN 201910840248 A CN201910840248 A CN 201910840248A CN 110694921 A CN110694921 A CN 110694921A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- sorting
- vegetables
- cylinder
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims abstract description 130
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims description 29
- 238000005192 partition Methods 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 235000021384 green leafy vegetables Nutrition 0.000 claims description 10
- 230000004075 alteration Effects 0.000 claims description 6
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 239000013589 supplement Substances 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 10
- 230000004308 accommodation Effects 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000012216 screening Methods 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 description 6
- 239000000047 product Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 235000012055 fruits and vegetables Nutrition 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000007723 transport mechanism Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000003578 releasing effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000219112 Cucumis Species 0.000 description 1
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23N—MACHINES OR APPARATUS FOR TREATING HARVESTED FRUIT, VEGETABLES OR FLOWER BULBS IN BULK, NOT OTHERWISE PROVIDED FOR; PEELING VEGETABLES OR FRUIT IN BULK; APPARATUS FOR PREPARING ANIMAL FEEDING- STUFFS
- A23N15/00—Machines or apparatus for other treatment of fruits or vegetables for human purposes; Machines or apparatus for topping or skinning flower bulbs
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23N—MACHINES OR APPARATUS FOR TREATING HARVESTED FRUIT, VEGETABLES OR FLOWER BULBS IN BULK, NOT OTHERWISE PROVIDED FOR; PEELING VEGETABLES OR FRUIT IN BULK; APPARATUS FOR PREPARING ANIMAL FEEDING- STUFFS
- A23N15/00—Machines or apparatus for other treatment of fruits or vegetables for human purposes; Machines or apparatus for topping or skinning flower bulbs
- A23N2015/008—Sorting of fruit and vegetables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0081—Sorting of food items
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Polymers & Plastics (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention relates to the technical field of vegetable sorting production lines, and discloses a vegetable sorting system and a control method thereof, wherein the vegetable sorting system comprises a conveying mechanism for placing vegetables, a controller, a vegetable recognition mechanism and a sorting mechanism which are sequentially arranged along the conveying direction of the conveying mechanism; the vegetable recognition mechanism comprises an image acquisition component and an image recognition processor which are connected with each other, a lens of the image acquisition component faces the transmission mechanism, and a neural network module is arranged in the image recognition processor to judge whether vegetables in an image acquired by the image acquisition component are qualified or not; the sorting mechanism is used for selectively moving the vegetables; the sorting mechanism and the image recognition processor are electrically connected to the controller. This vegetables letter sorting system combines together machine vision and mechanical sorting production line, and accommodation is wider, and the flexibility is higher, through the degree of depth learning training, can realize automatic identification, grading and the screening to the leaf dish.
Description
Technical Field
The invention relates to the technical field of vegetable sorting production lines, in particular to a vegetable sorting system and a control method thereof.
Background
The sorting technology is an indispensable link in the packaging process of agricultural products, and the sorting of the non-fresh products is of great importance in the fruit and vegetable industry. A rotten fruit or vegetable can easily destroy the whole batch of fruit or vegetable, thereby causing serious economic loss. At present, the manual sorting is mostly adopted in the leaf vegetable sorting of China, and in order to facilitate the operation, the fruit and vegetable preliminary processing still need be carried out earlier, and the mode of this kind of manual sorting not only wastes time and energy, and is inefficient, and the standard of letter sorting varies from person to person in addition, leads to sorting quality to differ, and the long-time work of letter sorting personnel can also produce fatigue, causes the fruit and vegetable that does not accord with the standard not to be separated out. In addition, as labor costs increase, production costs further increase. With the development of agricultural informatization, people begin to use sorting equipment in order to improve production efficiency and stabilize production quality.
At present, the intelligent sorting system which is really applied in the field of agricultural vegetables in China is still in the starting stage. The existing sorting system in the market is mostly applied to the field of fruit or fruit and vegetable sorting, because the appearance of the melons and fruits is relatively uniform, and the sorting standard is easier to specify. Due to irregular shape, complex characteristics and poor structure of leaf vegetables, the traditional visual and spectral sorting technology can only identify one or more characteristics, so that the sorting error is large.
Disclosure of Invention
The embodiment of the invention provides a vegetable sorting system and a control method thereof, which are used for solving the problems of single identification characteristic and large sorting error of the conventional vegetable sorting system so as to improve the sorting efficiency and precision.
The embodiment of the invention provides a vegetable sorting system, which comprises a conveying mechanism for placing vegetables, a controller, a vegetable identification mechanism and a sorting mechanism, wherein the vegetable identification mechanism and the sorting mechanism are sequentially arranged along the conveying direction of the conveying mechanism; the vegetable recognition mechanism comprises an image acquisition component and an image recognition processor which are connected with each other, a lens of the image acquisition component faces the vegetables on the conveying mechanism, and a neural network module is arranged in the image recognition processor to judge whether the vegetables are qualified or not according to the vegetable images acquired by the image acquisition component; the sorting mechanism is used for selectively moving the vegetables; the conveying mechanism, the sorting mechanism and the image recognition processor are all electrically connected to a controller.
The sorting mechanism comprises a first support and a pushing assembly, and the first support is fixedly connected to one side of the conveying mechanism; the pushing assembly comprises a first air cylinder, a cylinder body of the first air cylinder is connected to the first support, and a piston rod of the first air cylinder faces the vegetables on the conveying mechanism.
The first support is fixedly connected with a first rotating motor, and an output shaft of the first rotating motor is connected to a cylinder body of the first air cylinder; the output shaft of the first rotating motor is provided with a first rotary encoder, and the first rotating motor and the first rotary encoder are electrically connected to the controller.
Wherein, the promotion subassembly still includes first chuck, first chuck includes first centre gripping cylinder, first push pedal, first left connecting rod, first right connecting rod, first left clamp indicate and first right clamp indicate, the cylinder body rigid coupling of first centre gripping cylinder in the piston rod of first cylinder, the piston rod rigid coupling of first centre gripping cylinder in the middle part of first push pedal, the left end of first push pedal first left connecting rod with first left clamp indicates to articulate in proper order, the right-hand member of first push pedal first right connecting rod with first right clamp indicates to articulate in proper order, first left clamp indicate with first right clamp indicate all to articulate on the cylinder body of first centre gripping cylinder.
The sorting mechanism comprises a second support and a pulling assembly, and the second support is fixedly connected to one side of the conveying mechanism; the pulling assembly comprises a second air cylinder and a second chuck, the cylinder body of the second air cylinder is connected to the second support, and the piston rod of the second air cylinder faces the conveying mechanism; the second chuck includes that second centre gripping cylinder, second push pedal, the left connecting rod of second, the right connecting rod of second, the left clamp of second indicate and the right clamp of second indicate, the cylinder body rigid coupling of second centre gripping cylinder in the piston rod of second cylinder, the piston rod rigid coupling of second centre gripping cylinder in the middle part of second push pedal, the left end of second push pedal the left connecting rod of second with the left clamp of second indicates articulated in proper order, the right-hand member of second push pedal the right connecting rod of second with the right clamp of second is articulated in proper order, the left clamp of second indicate with the right clamp of second indicates all articulate on the cylinder body of second centre gripping cylinder.
The second bracket is fixedly connected with a second rotating motor, and an output shaft of the second rotating motor is connected to a cylinder body of the second air cylinder; and a second rotary encoder is mounted on an output shaft of the second rotary motor, and the second rotary motor and the second rotary encoder are electrically connected to the controller.
The image acquisition assembly comprises a camera bellows fixedly connected to the conveying mechanism, and a 3D point cloud camera and a light supplement lamp which are arranged in the camera bellows, wherein the 3D point cloud camera is electrically connected to the image recognition processor.
The two opposite side walls of the camera bellows along the conveying direction are respectively provided with a sliding door capable of moving up and down, and a driving component of the sliding door is electrically connected with the controller.
The conveying mechanism is provided with a plurality of baffle plates, and the baffle plates can slide on the surface of the conveying mechanism along the direction perpendicular to the conveying direction.
The vegetable identification mechanism and the sorting mechanism are arranged on the bearing frame, the conveying belt is wound on the bearing frame, and the conveying motor is used for driving the conveying belt to rotate.
The embodiment of the invention also provides a control method of the vegetable sorting system, which comprises the following steps:
the method comprises the following steps of putting vegetables in a first partition of a conveying mechanism in a centralized mode, and sequentially collecting images of the vegetables by an image collecting assembly;
identifying the image of the vegetable based on a neural network model prestored in a neural network module to obtain a classification result of the vegetable;
and when the vegetable classification result is unqualified, the vegetable is moved to a second partition of the conveying mechanism by using a sorting mechanism.
The training method of the neural network model comprises the following steps:
acquiring RGB color images and 3D point cloud information of a sample, taking the RGB color images as a first training set, and labeling the first training set;
training the marked first training set by using YOLOv3 to obtain a first neural network model for classifying and identifying the projection area, the leaf surface chromatic aberration and the quality grade of the sample, and acquiring a two-dimensional training result;
carrying out segmentation processing on the RGB color image to obtain a target detection object and a region where the target detection object is located, and then carrying out gray processing and cutting to obtain a gray image only containing the target detection object and the region where the target detection object is located;
the target detection objects in the gray-scale image correspond to the 3D point cloud information one by one, and the corresponding point cloud is randomly selected as a second training set;
and training the two-dimensional training result and the second training set pair by using a PointNet network to obtain a second neural network model for classifying and identifying the leaf vegetable weight, the projection area, the leaf surface chromatic aberration and the quality grade of the sample.
The method for acquiring the RGB color image and the 3D point cloud information of the sample, taking the RGB color image as a first training set, and labeling the first training set further comprises the following steps:
carrying out adaptive histogram equalization preprocessing on the RGB color image;
and performing data amplification on the preprocessed RGB color images in a random cutting, horizontal turning and/or random rotation angle mode, and taking the amplified RGB color images as the first training set.
The segmenting processing of the RGB color image to obtain a target detection object and a region where the target detection object is located, performing gray processing and cutting to obtain a gray map only including the target detection object and the region where the target detection object is located, further includes:
segmenting the RGB color image by utilizing a semantic segmentation algorithm to segment the region where the target detection object is located;
and carrying out gray level processing on the RGB color image in which the target detection object and the area thereof are obtained by utilizing a binarization algorithm.
The vegetable sorting system comprises a conveying mechanism for placing vegetables, a controller, a vegetable recognition mechanism and a sorting mechanism, wherein the vegetable recognition mechanism is used for collecting and recognizing images of the vegetables, and a neural network module arranged in an image recognition processor is used for judging whether the vegetables in the acquired images are qualified or not. Vegetables are sorted by a sorting mechanism. This vegetables letter sorting system combines together machine vision and mechanical sorting production line, and accommodation is wider, and the flexibility is higher, through degree of depth study training, can realize automatic identification, grading and the screening to the leaf dish, and is more accurate high-efficient than artifical letter sorting, and it is slow to have solved artifical letter sorting speed, and the unstable shortcoming of letter sorting quality, and the fault-tolerant rate is higher, has practiced thrift the human cost, has saved the resource, has improved product quality simultaneously.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a vegetable sorting system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a vegetable sorting system according to an embodiment of the present invention;
FIG. 3 is a schematic view of a first chuck in an embodiment of the present invention;
description of reference numerals:
1: a transport mechanism; 11: a carrier; 12: a conveyor belt;
121: a first partition; 122: a second partition; 13: a transfer motor;
2: a controller; 21: a PLC control system; 22: a human-computer interaction system;
3: a vegetable recognition mechanism; 31: an image acquisition component; 311: a dark box;
312: a 3D point cloud camera; 313: a light supplement lamp; 314: a sliding door;
32: an image recognition processor; 321: a neural network module; 322: a signal output module;
4: a sorting mechanism; 41: a first bracket; 42: a pushing assembly;
421: a first cylinder; 422: a first chuck; 423: a first clamping cylinder;
424: a first push plate; 425: a first left link; 426: a first right link;
427: a first left gripping finger; 428: a first right clamping finger; 43: a pulling assembly;
5: and a baffle plate.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the embodiments of the present invention, it should be noted that the terms "first" and "second" are used for the sake of clarity in describing the numbering of the components of the product and do not represent any substantial difference, unless explicitly stated or limited otherwise. The directions of "up", "down", "left" and "right" are all based on the directions shown in the attached drawings. Specific meanings of the above terms in the embodiments of the present invention can be understood by those of ordinary skill in the art according to specific situations.
It is to be understood that, unless otherwise expressly specified or limited, the term "coupled" is used broadly, and may, for example, refer to directly coupled devices or indirectly coupled devices through intervening media. Specific meanings of the above terms in the embodiments of the invention will be understood to those of ordinary skill in the art in specific cases.
Fig. 1 is a schematic structural diagram of a vegetable sorting system in an embodiment of the present invention, and fig. 2 is a schematic composition diagram of a vegetable sorting system in an embodiment of the present invention, as shown in fig. 1 to fig. 2, a vegetable sorting system provided in an embodiment of the present invention includes a conveying mechanism 1 for placing vegetables, and further includes a controller 2, and a vegetable recognition mechanism 3 and a sorting mechanism 4 which are sequentially arranged along a conveying direction of the conveying mechanism 1.
The vegetable recognition mechanism 3 comprises an image acquisition component 31 and an image recognition processor 32 which are connected with each other, a lens of the image acquisition component 31 faces the vegetables on the conveying mechanism 1, and the image recognition processor 32 is internally provided with a neural network module 321 so as to judge whether the vegetables are qualified according to the vegetable images acquired by the image acquisition component 31. The sorting mechanism 4 is used to selectively move the vegetables. The conveying mechanism 1, the sorting mechanism 4 and the image recognition processor 32 are electrically connected to the controller 2.
Specifically, fig. 1 is a top view of the vegetable sorting system in this embodiment, with the conveying direction from bottom to top. The conveying mechanism 1 may adopt a conveyor belt structure or a conveying roller structure. Vegetables can be placed on transport mechanism 1 with the cultivation container together, both can keep the clean and tidy of vegetables letter sorting system, avoid the pollution of impurity such as soil and water, can guarantee the stability of conveying again, form unified background reference, be favorable to discerning the leaf dish quality fast accurately.
The controller 2 is a control center of the system and may include a PLC control system 21 (lower computer) and a human-computer interaction system 22 (upper computer). PLC control system 21 may be implemented as a siemens S7-1200 system, including a power supply, a central processing unit, a memory, an input unit, and an output unit, all in a coordinated arrangement. The PLC control system 21 is used for monitoring the running state of the conveying mechanism 1 and controlling the starting, stopping, speed and direction of the conveying mechanism 1; the vegetable recognition mechanism is also used for receiving the recognition result of the vegetable recognition mechanism 3 and controlling the vegetable recognition mechanism 3 to collect images; and the automatic sorting machine is also used for monitoring the running state of the sorting mechanism 4 and controlling the sorting mechanism 4 to sort unqualified vegetables. The human-computer interaction system 22 can adopt a PC terminal or a mobile terminal, and the human-computer interaction system 22 is connected with the PLC control system 21 through an ethernet network. The operator can set the operating parameters of the transport mechanism 1 and the sorting mechanism 4 on the human-computer interaction system 22, such as the transport speed, direction and start-stop of the transport mechanism 1, the exit speed, travel, time interval of the sorting mechanism 4, etc. Meanwhile, the vegetable recognition mechanism 3 is set to extract characteristic parameters of the leaf vegetables in the collected image, such as the type, weight, volume coefficient, quality grade and the like of the leaf vegetables. The PLC control system 21 can receive instructions from the human-computer interaction system 22, correspondingly control the conveying mechanism 1 and the sorting mechanism 4, realize sorting action, and move the leaf vegetables to designated positions in a classified manner. In addition, the controller 2 may be implemented by other integrated processors as long as the above functions are realized.
The vegetable recognition mechanism 3 comprises an image acquisition component 31 and an image recognition processor 32 which are connected with each other, the image acquisition component 31 is used for acquiring images of vegetables and converting the images into digital signals to be sent to the image recognition processor 32, a neural network module 321 is arranged in the image recognition processor 32, and a pre-trained neural network model is prestored in the neural network module 321 and used for recognizing and classifying the acquired vegetable image signals. Meanwhile, the image recognition processor 32 is further provided with a signal output module 322 connected to the PLC control system 21 for transmitting the detection result to the controller 2 as an input of the sorting operation.
The sorting mechanism 4 may be installed at a side of the conveying mechanism 1 for selectively moving the vegetables, and performs a sorting action according to a detection result of the vegetable recognition mechanism 3. Sorting mechanism 4 can adopt the mode of pushing vegetables with vegetables letter sorting, also can adopt the mode of pulling vegetables. Initially, all the vegetables are placed in the first partition 121 of the conveying mechanism 1 and sequentially pass through the vegetable recognition mechanism 3, and if the current vegetables are recognized to be a certain type of vegetables (for example, unqualified vegetables) which need to be sorted out, the sorting mechanism 4 can be started to push or pull the vegetables out of the queue to the second partition 122, so that the sorting of the vegetables is realized.
The vegetable sorting system provided by the embodiment comprises a conveying mechanism for placing vegetables, a controller, a vegetable recognition mechanism and a sorting mechanism, wherein the vegetable recognition mechanism is used for collecting and recognizing images of the vegetables, and a built-in neural network module of an image recognition processor is used for judging whether the vegetables in the obtained images are qualified or not. Vegetables are sorted by a sorting mechanism. This vegetables letter sorting system combines together machine vision and mechanical sorting production line, and accommodation is wider, and the flexibility is higher, through degree of depth study training, can realize automatic identification, grading and the screening to the leaf dish, and is more accurate high-efficient than artifical letter sorting, and it is slow to have solved artifical letter sorting speed, and the unstable shortcoming of letter sorting quality, and the fault-tolerant rate is higher, has practiced thrift the human cost, has saved the resource, has improved product quality simultaneously.
Further, as shown in fig. 1, the conveying mechanism 1 includes a carrier 11, a conveyor belt 12 and a conveying motor 13, the vegetable recognition mechanism 3 and the sorting mechanism 4 are both mounted on the carrier 11, the conveyor belt 12 is wound around the carrier 11, and the conveying motor 13 may be connected to the conveyor belt 12 through a transmission structure such as a gear or a chain to drive the conveyor belt 12 to rotate. The conveyor belt 12 is provided with a first partition 121 on the right side and a second partition 122 on the left side, vegetables before sorting are collected in the first partition 121 and conveyed, and then the unqualified vegetables are moved to the second partition 122 by the sorting mechanism 4, so that the sorting of the vegetables is realized. Specifically, the conveyor belt 12 has a width of 0.5 meter and a length of 1.6 meters. The conveying motor 13 is a servo motor.
Further, as shown in fig. 1, the sorting mechanism 4 includes a first bracket 41 and a pushing assembly 42, and the first bracket 41 is fixedly connected to the right side of the conveying mechanism 1. The pushing assembly 42 comprises a first cylinder 421, the cylinder body of the first cylinder 421 is connected to the first bracket 41, and the piston rod of the first cylinder 421 faces the vegetables on the conveying mechanism 1. Specifically, the cylinder body of the first cylinder 421 is communicated with an external compressed air system through an air inlet valve and an air outlet valve. The air inlet valve and the air outlet valve are both electrically operated valves or electromagnetic valves and are electrically connected to the controller 2 to receive start and stop signals. The push-pull of the piston rod of the first cylinder 421 is realized by adjusting the air pressure in the cylinder body of the first cylinder 421. More specifically, the piston rod of the first cylinder 421 can be freely adjusted within a length range of 0-15 cm.
Further, a first rotating motor (not shown) is fixed to the first bracket 41, and an output shaft of the first rotating motor is connected to a cylinder body of the first cylinder 421. The output shaft of the first rotating motor is provided with a first rotary encoder (not shown in the figure), and the first rotating motor and the first rotary encoder are electrically connected to the controller 2. Specifically, the rotation speed and the deflection angle of the first rotating motor can be both sent to the controller 2 for monitoring, so that feedback control can be realized conveniently. The first rotating motor can drive the first air cylinder 421 to swing left and right, sorting operation in a large range can be achieved, and the vegetable cultivation container can be prevented from being pushed down by adjusting the pushing angle of the vegetable; the automatic sorting machine can adapt to the conveying speed of the conveying mechanism 1, can quickly and timely execute a plurality of sorting operations, and does not omit the sorting operations. More specifically, the first cylinder 421 can be freely adjusted within an angle range of 0 to 30 °.
Further, as shown in fig. 1 and 3, the pushing assembly 42 further includes a first collet 422, and the first collet 422 includes a first clamping cylinder 423, a first push plate 424, a first left link 425, a first right link 426, a first left clamping finger 427, and a first right clamping finger 428. The cylinder body of the first chuck cylinder 423 is fixed to the piston rod of the first cylinder 421, so that the entire first chuck 422 can move back and forth and swing left and right along with the piston rod of the first cylinder 421. The piston rod of the first clamping cylinder 423 is fixedly connected to the middle of the first push plate 424, the left end of the first push plate 424, the first left connecting rod 425 and the first left clamping finger 427 are sequentially hinged, the right end of the first push plate 424, the first right connecting rod 426 and the first right clamping finger 428 are sequentially hinged, and the first left clamping finger 427 and the first right clamping finger 428 are both hinged to the cylinder body of the first clamping cylinder 423. Therefore, when the piston rod of the first clamping cylinder 423 moves back and forth, the first left clamping finger 427 and the first right clamping finger 428 can be opened and closed along with the piston rod, so that the clamping and releasing of the vegetables are realized.
Specifically, the cylinder body of the first clamping cylinder 423 is communicated with an external compressed air system through an intake valve and an exhaust valve. The air inlet valve and the air outlet valve are both electrically operated valves or electromagnetic valves and are electrically connected to the controller 2 to receive start and stop signals. The piston rod of the first clamping cylinder 423 is pushed and pulled by adjusting the air pressure in the cylinder body of the first clamping cylinder 423, and then the clamping and releasing actions of the first clamping head 422 are controlled. More specifically, one side of the first chuck 422 facing the vegetables may be further provided with an inductive switch, when the vegetables are sensed to be contacted, the first chuck 422 is controlled to be closed to clamp the vegetables and push the vegetables to the second partition 122, after the vegetables are pushed to a preset position, the first chuck 422 is immediately controlled to be opened to release the vegetables, and a piston rod of the first cylinder 421 timely drives the first chuck 422 to reset to wait for next sorting. Can realize the centre gripping to the cultivation container of vegetables through setting up first chuck 422, guarantee that the container is not pushed down, pollute letter sorting system. In addition, the first clamping head 422 can also be directly replaced by an arc-shaped push plate.
Further, the sorting mechanism 4 may further include a second bracket (not shown) fixed to the left side of the conveying mechanism, and a pulling assembly 43. The pulling assembly 43 comprises a second cylinder, the cylinder of which is connected to the second support, and a second chuck (neither of which is shown in the figures), the piston rod of which faces the transfer mechanism; the second chuck comprises a second clamping cylinder, a second push plate, a second left connecting rod, a second right connecting rod, a second left clamping finger and a second right clamping finger, the cylinder body of the second clamping cylinder is fixedly connected to the piston rod of the second cylinder, the piston rod of the second clamping cylinder is fixedly connected to the middle of the second push plate, the left end of the second push plate, the second left connecting rod and the second left clamping finger are sequentially hinged, the right end of the second push plate, the second right connecting rod and the second right clamping finger are sequentially hinged, and the second left clamping finger and the second right clamping finger are both hinged to the cylinder body of the second clamping cylinder.
Specifically, the pulling assembly and the pushing assembly are similar in structure and composition, except that the pushing assembly 42 is disposed on one side of the conveying mechanism 1 close to the first partition 121, and the piston rod of the first cylinder 421 drives the first chuck 422 to push the unqualified vegetables to the second partition 122. The pulling assembly 43 is disposed on one side of the conveying mechanism 1 close to the second partition 122, and the piston rod of the second cylinder drives the second chuck to pull the unqualified vegetables to the second partition 122.
Further, the second bracket is fixedly connected with a second rotating motor (not shown in the figure), and an output shaft of the second rotating motor is connected with the cylinder body of the second air cylinder. The output shaft of the second rotating motor is provided with a second rotary encoder (not shown in the figure), and the second rotating motor and the second rotary encoder are electrically connected to the controller. Specifically, the rotation speed and the deflection angle of the second rotating motor can be both sent to the controller 2 for monitoring, so that feedback control can be realized conveniently. Utilize the second to rotate the horizontal hunting that the motor can drive the second cylinder, can realize the letter sorting operation in the great scope.
Further, as shown in fig. 1 to 2, the image capturing assembly 31 includes a dark box 311 fixed on the conveying mechanism 1, and a 3D point cloud camera 312 and a fill light 313 installed in the dark box 311, wherein the 3D point cloud camera 312 is electrically connected to the image recognition processor 32. Specifically, the 3D point cloud camera 312 may employ a model FM810-IX, and may acquire an RGB color image of a photographed object and 3D point cloud information at the same time. The fill light 313 may be illuminated by an annular invisible light source, providing a relatively single light source environment for the 3D point cloud camera 312 to acquire images. More specifically, the light intensity and the light color of the light supplement lamp 313 may be adjusted according to the color and the brightness of the photographed leaf vegetables, may be manually adjusted, or may be automatically adjusted by electrically connecting an adjuster of the light supplement lamp 313 to the controller 2.
Furthermore, two opposite side walls of the dark box 311 along the conveying direction are respectively provided with a sliding door 314 capable of moving up and down, and a driving component of the sliding door 314 is electrically connected to the controller 2. Through the opening and closing of the sliding door 314, the illumination in the dark box 311 can be guaranteed to be stable and the same when the camera is shot at every time, and the influence of the external illumination is reduced. The sliding door 314 can be realized by adopting a transmission structure of a motor and a chain, and the sliding door 314 is the existing mature equipment and can be directly purchased in the market.
Further, as shown in fig. 1, the conveying mechanism 1 is provided with a baffle 5 at both sides thereof, and the baffle 5 is slidable on the surface of the conveying mechanism 1 in a direction perpendicular to the conveying direction. Specifically, the sliding length of the barrier 5 may be designed according to the size of the vegetables. The baffle 5 may be divided into a plurality of vertical plates, which are respectively installed at the front end portion of the vegetable recognition mechanism 3, and at the rear end portion of the vegetable recognition mechanism 3 on the side opposite to the sorting mechanism 4. The baffle 5 at the front end of the vegetable recognition mechanism 3 can move left and right during the conveying process, and the vegetables to be sorted are collected to the first partition 121 of the conveying mechanism 1 and are arranged in sequence. More specifically, the baffle 5 can be freely adjusted within the length range of 0-30 cm.
Through setting up baffle 5 both can prevent that the leaf dish from dropping outside the device in the transmission course on the conveyer belt, can adjust according to the projection area's of vegetables size again, guarantee that vegetables concentrate on first subregion 121 and convey, be convenient for carry on subsequent letter sorting operation.
The embodiment of the invention also provides a control method of the vegetable sorting system, which comprises the following steps:
step S1: the vegetables are intensively placed in the first subarea 121 of the conveying mechanism 1, and the image acquisition assembly 31 sequentially acquires the images of the vegetables.
Specifically, the vegetables are collected by the baffle 5 onto the first section 121 on the right side of the conveyor belt 12 in a sequential arrangement. And passes through the image acquisition assembly 31 in turn under the drive of the conveyor belt 12.
Step S2: based on the neural network model pre-stored in the neural network module 321, the images of the vegetables are identified, and the classification result of the vegetables is obtained.
Specifically, the image recognition processor 32 receives the image information acquired by the image acquisition component 31, recognizes the image by using a pre-trained neural network model, and outputs the classification result to the controller 2.
Step S3: when the sorted result of the vegetables is not good, the vegetables are moved to the second section 122 of the conveying mechanism 1 by the sorting mechanism 4.
Specifically, when the classification result is unqualified, the controller 2 sends a control signal to the sorting mechanism 4 to control the sorting mechanism to perform a sorting action, so as to move the unqualified vegetables to the second partition 122.
Further, the training method of the neural network model comprises the following steps:
step S10: acquiring RGB color images and 3D point cloud information of a sample, taking the RGB color images as a first training set, and labeling the first training set;
step S20: training the marked first training set by using YOLOv3 to obtain a first neural network model for classifying and identifying the projection area, the leaf surface chromatic aberration and the quality grade of the sample, and acquiring a two-dimensional training result;
step S30: dividing the RGB color image to obtain a target detection object and a region where the target detection object is located, performing gray level processing and cutting to obtain a gray level image only containing the target detection object and the region where the target detection object is located;
step S40: the target detection objects in the gray level image correspond to the 3D point cloud information one by one, and the corresponding point cloud is randomly selected as a second training set;
step S50: and training the two-dimensional training result and the second training set pair by using a PointNet network to obtain a second neural network model for classifying and identifying the leaf vegetable weight, the projection area, the leaf surface chromatic aberration and the quality grade of the sample.
Further, step S10 further includes:
step S11: carrying out adaptive histogram equalization pretreatment on the RGB color image;
step S12: and performing data amplification on the preprocessed RGB color image in a random cutting, horizontal turning and/or random rotation angle mode, and taking the amplified RGB color image as a first training set.
Further, step S30 further includes:
step S31: segmenting the RGB color image by utilizing a semantic segmentation algorithm to segment the region where the target detection object is located;
step S32: and carrying out gray level processing on the RGB color image of the obtained target detection object and the region thereof by utilizing a binarization algorithm.
According to the embodiment, the vegetable sorting system comprises the conveying mechanism for placing the vegetables, the controller, the vegetable recognition mechanism and the sorting mechanism, the vegetable recognition mechanism is used for collecting and recognizing the images of the vegetables, and the neural network module arranged in the image recognition processor is used for judging whether the vegetables in the acquired images are qualified or not. Unqualified vegetables are sorted through a sorting mechanism. This vegetables letter sorting system combines together machine vision and mechanical sorting production line, and accommodation is wider, and the flexibility is higher, through the degree of depth study training, can realize automatic identification, grading and the screening to the leaf dish, and more accurate high-efficient than manual sorting, it is slow to have solved manual sorting speed, the unstable shortcoming of letter sorting quality, and the fault-tolerant rate is higher. The non-structural target recognition and classification technology based on the combination of 2D and 3D is introduced into leaf vegetable sorting, and compared with the traditional visual recognition and spectral analysis technology, the sorting precision and speed are greatly improved, the labor cost is saved, the resources are saved, the product quality is improved, and the production efficiency is greatly improved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (14)
1. A vegetable sorting system comprises a conveying mechanism for placing vegetables, and is characterized by further comprising a controller, and a vegetable recognition mechanism and a sorting mechanism which are sequentially arranged along the conveying direction of the conveying mechanism; the vegetable recognition mechanism comprises an image acquisition component and an image recognition processor which are connected with each other, a lens of the image acquisition component faces the vegetables on the conveying mechanism, and a neural network module is arranged in the image recognition processor to judge whether the vegetables are qualified or not according to the vegetable images acquired by the image acquisition component; the sorting mechanism is used for selectively moving the vegetables; the conveying mechanism, the sorting mechanism and the image recognition processor are all electrically connected to a controller.
2. The vegetable sorting system of claim 1, wherein the sorting mechanism includes a first bracket and a pushing assembly, the first bracket being secured to one side of the conveyor mechanism; the pushing assembly comprises a first air cylinder, a cylinder body of the first air cylinder is connected to the first support, and a piston rod of the first air cylinder faces the vegetables on the conveying mechanism.
3. The vegetable sorting system according to claim 2, wherein the first bracket is fixedly connected with a first rotating motor, and an output shaft of the first rotating motor is connected to a cylinder body of the first air cylinder; the output shaft of the first rotating motor is provided with a first rotary encoder, and the first rotating motor and the first rotary encoder are electrically connected to the controller.
4. The vegetable sorting system according to claim 2, wherein the pushing assembly further comprises a first chuck, the first chuck comprises a first clamping cylinder, a first push plate, a first left connecting rod, a first right connecting rod, a first left clamping finger and a first right clamping finger, the cylinder body of the first clamping cylinder is fixedly connected to the piston rod of the first cylinder, the piston rod of the first clamping cylinder is fixedly connected to the middle portion of the first push plate, the left end of the first push plate, the first left connecting rod and the first left clamping finger are sequentially hinged, the right end of the first push plate, the first right connecting rod and the first right clamping finger are sequentially hinged, and the first left clamping finger and the first right clamping finger are both hinged to the cylinder body of the first clamping cylinder.
5. The vegetable sorting system of claim 1, wherein the sorting mechanism includes a second bracket and a pulling assembly, the second bracket being secured to one side of the conveyor mechanism; the pulling assembly comprises a second air cylinder and a second chuck, the cylinder body of the second air cylinder is connected to the second support, and the piston rod of the second air cylinder faces the conveying mechanism;
the second chuck includes that second centre gripping cylinder, second push pedal, the left connecting rod of second, the right connecting rod of second, the left clamp of second indicate and the right clamp of second indicate, the cylinder body rigid coupling of second centre gripping cylinder in the piston rod of second cylinder, the piston rod rigid coupling of second centre gripping cylinder in the middle part of second push pedal, the left end of second push pedal the left connecting rod of second with the left clamp of second indicates articulated in proper order, the right-hand member of second push pedal the right connecting rod of second with the right clamp of second is articulated in proper order, the left clamp of second indicate with the right clamp of second indicates all articulate on the cylinder body of second centre gripping cylinder.
6. The vegetable sorting system according to claim 5, wherein a second rotating motor is fixedly connected to the second bracket, and an output shaft of the second rotating motor is connected to a cylinder body of the second air cylinder; and a second rotary encoder is mounted on an output shaft of the second rotary motor, and the second rotary motor and the second rotary encoder are electrically connected to the controller.
7. The vegetable sorting system according to claim 1, wherein the image capturing assembly comprises a dark box fixedly connected to the conveying mechanism, and a 3D point cloud camera and a light supplement lamp installed in the dark box, wherein the 3D point cloud camera is electrically connected to the image recognition processor.
8. The vegetable sorting system according to claim 7, wherein the black box has two opposite side walls along the conveying direction respectively provided with a sliding door capable of moving up and down, and a driving assembly of the sliding door is electrically connected to the controller.
9. A vegetable sorting system according to claim 1, wherein baffles are mounted on both sides of the conveyor mechanism, the baffles being slidable on the surface of the conveyor mechanism in a direction perpendicular to the conveying direction.
10. The vegetable sorting system according to any one of claims 1 to 9, wherein the conveying mechanism includes a carrier, a conveyor belt, and a conveyor motor, the vegetable recognition mechanism and the sorting mechanism are mounted on the carrier, the conveyor belt is wound around the carrier, and the conveyor motor is used for driving the conveyor belt to rotate.
11. A control method of a vegetable sorting system according to any one of claims 1 to 10, comprising:
the method comprises the following steps of putting vegetables in a first partition of a conveying mechanism in a centralized mode, and sequentially collecting images of the vegetables by an image collecting assembly;
identifying the image of the vegetable based on a neural network model prestored in a neural network module to obtain a classification result of the vegetable;
and when the vegetable classification result is unqualified, the vegetable is moved to a second partition of the conveying mechanism by using a sorting mechanism.
12. The control method according to claim 11, wherein the training method of the neural network model includes:
acquiring RGB color images and 3D point cloud information of a sample, taking the RGB color images as a first training set, and labeling the first training set;
training the marked first training set by using YOLOv3 to obtain a first neural network model for classifying and identifying the projection area, the leaf surface chromatic aberration and the quality grade of the sample, and acquiring a two-dimensional training result;
carrying out segmentation processing on the RGB color image to obtain a target detection object and a region where the target detection object is located, and then carrying out gray processing and cutting to obtain a gray image only containing the target detection object and the region where the target detection object is located;
the target detection objects in the gray-scale image correspond to the 3D point cloud information one by one, and the corresponding point cloud is randomly selected as a second training set;
and training the two-dimensional training result and the second training set pair by using a PointNet network to obtain a second neural network model for classifying and identifying the leaf vegetable weight, the projection area, the leaf surface chromatic aberration and the quality grade of the sample.
13. The control method according to claim 12, wherein the obtaining of the RGB color image and the 3D point cloud information of the sample, the labeling of the first training set with the RGB color image as the first training set, further comprises:
carrying out adaptive histogram equalization preprocessing on the RGB color image;
and performing data amplification on the preprocessed RGB color images in a random cutting, horizontal turning and/or random rotation angle mode, and taking the amplified RGB color images as the first training set.
14. The control method according to claim 12, wherein the segmenting process is performed on the RGB color image to obtain a target detection object and a region thereof, and then the gray-scale process and the clipping are performed to obtain a gray-scale map only including the target detection object and the region thereof, further comprising:
segmenting the RGB color image by utilizing a semantic segmentation algorithm to segment the region where the target detection object is located;
and carrying out gray level processing on the RGB color image in which the target detection object and the area thereof are obtained by utilizing a binarization algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840248.1A CN110694921A (en) | 2019-09-06 | 2019-09-06 | Vegetable sorting system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840248.1A CN110694921A (en) | 2019-09-06 | 2019-09-06 | Vegetable sorting system and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110694921A true CN110694921A (en) | 2020-01-17 |
Family
ID=69194467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910840248.1A Pending CN110694921A (en) | 2019-09-06 | 2019-09-06 | Vegetable sorting system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110694921A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111617983A (en) * | 2020-05-16 | 2020-09-04 | 安徽昭日农业科技有限公司 | Vegetable sorting device |
| CN112115983A (en) * | 2020-08-28 | 2020-12-22 | 浙大城市学院 | Deep learning-based crop fruit sorting algorithm |
| CN112387622A (en) * | 2020-10-15 | 2021-02-23 | 湖北三峡职业技术学院 | Dried vegetable color selector and color selection method |
| CN112403948A (en) * | 2020-10-30 | 2021-02-26 | 南京鸟百香贸易有限公司 | Remote control sorting device based on internet of things |
| CN112547528A (en) * | 2021-03-01 | 2021-03-26 | 华鹏飞股份有限公司 | Logistics sorting method and system based on classification identification |
| CN113281114A (en) * | 2021-04-09 | 2021-08-20 | 河南中烟工业有限责任公司 | Intelligent shearing system for special-shaped tobacco leaves |
| CN113281115A (en) * | 2021-04-09 | 2021-08-20 | 河南中烟工业有限责任公司 | Control method for intelligent shearing of tobacco leaves |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040206882A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for evaluating image focus |
| CA2430737A1 (en) * | 2003-06-02 | 2004-12-02 | Centre De Recherche Industrielle Du Quebec | Method and apparatus for estimating surface moisture content of wood chips |
| CN101100156A (en) * | 2007-07-20 | 2008-01-09 | 苏州苏大维格数码光学有限公司 | False proof structure used for card and certificate and its identifying method |
| CN105058353A (en) * | 2015-08-17 | 2015-11-18 | 苏州速腾电子科技有限公司 | Clamp for sorting parts |
| CN205289022U (en) * | 2015-12-31 | 2016-06-08 | 中国农业大学 | Automatic grading system of leaf vegetable vegetables |
| CN106373127A (en) * | 2016-09-14 | 2017-02-01 | 东北林业大学 | Laser scanning parallel detection method for wood species and surface defects |
| CN107899966A (en) * | 2017-12-06 | 2018-04-13 | 罗凯缤 | The shaddock quality sorting unit of view-based access control model technology |
| CN108311411A (en) * | 2018-02-07 | 2018-07-24 | 陕西科技大学 | A kind of cordyceps sinensis intelligence sorting system and its application method |
| CN109242951A (en) * | 2018-08-06 | 2019-01-18 | 宁波盈芯信息科技有限公司 | A kind of face's real-time three-dimensional method for reconstructing |
| CN208466542U (en) * | 2018-03-14 | 2019-02-05 | 浙江大学 | A kind of kinds of goods sorting equipment for production |
| CN109590236A (en) * | 2019-01-26 | 2019-04-09 | 王弘睿 | A kind of sorting machine people and its control system for Campus Garbage classification |
| CN109759338A (en) * | 2018-11-22 | 2019-05-17 | 吴江市格瑞福金属制品有限公司 | A kind of mobile model sorter for storage |
| CN211437053U (en) * | 2019-09-06 | 2020-09-08 | 北京农业智能装备技术研究中心 | Vegetable sorting system |
-
2019
- 2019-09-06 CN CN201910840248.1A patent/CN110694921A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040206882A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for evaluating image focus |
| CA2430737A1 (en) * | 2003-06-02 | 2004-12-02 | Centre De Recherche Industrielle Du Quebec | Method and apparatus for estimating surface moisture content of wood chips |
| CN101100156A (en) * | 2007-07-20 | 2008-01-09 | 苏州苏大维格数码光学有限公司 | False proof structure used for card and certificate and its identifying method |
| CN105058353A (en) * | 2015-08-17 | 2015-11-18 | 苏州速腾电子科技有限公司 | Clamp for sorting parts |
| CN205289022U (en) * | 2015-12-31 | 2016-06-08 | 中国农业大学 | Automatic grading system of leaf vegetable vegetables |
| CN106373127A (en) * | 2016-09-14 | 2017-02-01 | 东北林业大学 | Laser scanning parallel detection method for wood species and surface defects |
| CN107899966A (en) * | 2017-12-06 | 2018-04-13 | 罗凯缤 | The shaddock quality sorting unit of view-based access control model technology |
| CN108311411A (en) * | 2018-02-07 | 2018-07-24 | 陕西科技大学 | A kind of cordyceps sinensis intelligence sorting system and its application method |
| CN208466542U (en) * | 2018-03-14 | 2019-02-05 | 浙江大学 | A kind of kinds of goods sorting equipment for production |
| CN109242951A (en) * | 2018-08-06 | 2019-01-18 | 宁波盈芯信息科技有限公司 | A kind of face's real-time three-dimensional method for reconstructing |
| CN109759338A (en) * | 2018-11-22 | 2019-05-17 | 吴江市格瑞福金属制品有限公司 | A kind of mobile model sorter for storage |
| CN109590236A (en) * | 2019-01-26 | 2019-04-09 | 王弘睿 | A kind of sorting machine people and its control system for Campus Garbage classification |
| CN211437053U (en) * | 2019-09-06 | 2020-09-08 | 北京农业智能装备技术研究中心 | Vegetable sorting system |
Non-Patent Citations (1)
| Title |
|---|
| 史美功等: "工业机器人", vol. 1, 31 March 1987, 上海科学技术出版社, pages: 21 - 23 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111617983A (en) * | 2020-05-16 | 2020-09-04 | 安徽昭日农业科技有限公司 | Vegetable sorting device |
| CN112115983A (en) * | 2020-08-28 | 2020-12-22 | 浙大城市学院 | Deep learning-based crop fruit sorting algorithm |
| CN112387622A (en) * | 2020-10-15 | 2021-02-23 | 湖北三峡职业技术学院 | Dried vegetable color selector and color selection method |
| CN112403948A (en) * | 2020-10-30 | 2021-02-26 | 南京鸟百香贸易有限公司 | Remote control sorting device based on internet of things |
| CN112547528A (en) * | 2021-03-01 | 2021-03-26 | 华鹏飞股份有限公司 | Logistics sorting method and system based on classification identification |
| CN113281114A (en) * | 2021-04-09 | 2021-08-20 | 河南中烟工业有限责任公司 | Intelligent shearing system for special-shaped tobacco leaves |
| CN113281115A (en) * | 2021-04-09 | 2021-08-20 | 河南中烟工业有限责任公司 | Control method for intelligent shearing of tobacco leaves |
| CN113281114B (en) * | 2021-04-09 | 2023-09-15 | 河南中烟工业有限责任公司 | Special-shaped tobacco leaf intelligent shearing system |
| CN113281115B (en) * | 2021-04-09 | 2023-09-15 | 河南中烟工业有限责任公司 | Control method for intelligent tobacco leaf shearing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110694921A (en) | Vegetable sorting system and control method thereof | |
| CN107952696B (en) | A kind of detection grading plant and detection method suitable for fresh tobacco leaf | |
| CN101627832B (en) | On-line automatic tobacco recognition and classification system | |
| CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
| CN102179374A (en) | Automatic detecting and sorting device for poultry egg quality and method thereof | |
| CN211437053U (en) | Vegetable sorting system | |
| CN105651782A (en) | Engine cylinder cover defect automatic detection equipment based on machine vision | |
| CN103090804A (en) | Automatic detection system and detection method of finished product magnet ring image | |
| CN210059040U (en) | Based on RGB fruit sorter | |
| CN109030504B (en) | Panoramic potato defect detection device and method based on virtual and real imaging combination | |
| CN201618694U (en) | Fruit grading and detecting device | |
| CN103109754A (en) | Online nondestructive inspection and sorting equipment and online nondestructive inspection and sorting method for eggs with blood spots | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| WO2012039597A2 (en) | Fruit ripeness grading system | |
| CN106203455A (en) | Material based on machine vision row's equipment and the recognition methods of cylindrical material characteristic attribute | |
| CN111054655A (en) | Crab sorting device and application method thereof | |
| CN202037127U (en) | Automatic egg quality detection and separation equipment | |
| CN207222383U (en) | Plank sorting system | |
| CN108318494A (en) | The red online vision detection and classification devices and methods therefor for putting forward fruit powder | |
| CN218835247U (en) | Crab intelligent sorting and grading system based on machine vision | |
| CN109926348A (en) | One kind being based on RGB fruit classification method and sorter | |
| CN105319166A (en) | Real-time soybean detection instrument | |
| CN208288480U (en) | A kind of tealeaves exterior quality self-grading device based on computer vision technique | |
| CN203120696U (en) | Online non-destructive testing sorting device for eggs with blood spots | |
| CN109507204B (en) | Chicken breast lignification grading method and device based on curvature detection |
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 |