CN106797894B - Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology - Google Patents
Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology Download PDFInfo
- Publication number
- CN106797894B CN106797894B CN201710039502.9A CN201710039502A CN106797894B CN 106797894 B CN106797894 B CN 106797894B CN 201710039502 A CN201710039502 A CN 201710039502A CN 106797894 B CN106797894 B CN 106797894B
- Authority
- CN
- China
- Prior art keywords
- eggs
- egg
- timer
- hatching
- 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.)
- Active
Links
- 235000013601 eggs Nutrition 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 238000011534 incubation Methods 0.000 title claims abstract description 6
- 230000012447 hatching Effects 0.000 claims abstract description 62
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 230000000007 visual effect Effects 0.000 claims abstract description 16
- 238000003709 image segmentation Methods 0.000 claims abstract description 11
- 230000006698 induction Effects 0.000 claims abstract description 6
- 238000005070 sampling Methods 0.000 claims abstract description 6
- 238000010586 diagram Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000003111 delayed effect Effects 0.000 claims description 5
- 239000004033 plastic Substances 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims 1
- 230000000630 rising effect Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 5
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 244000144977 poultry Species 0.000 description 3
- 241000894006 Bacteria Species 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000721623 Myzus Species 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- ONTQJDKFANPPKK-UHFFFAOYSA-L chembl3185981 Chemical compound [Na+].[Na+].CC1=CC(C)=C(S([O-])(=O)=O)C=C1N=NC1=CC(S([O-])(=O)=O)=C(C=CC=C2)C2=C1O ONTQJDKFANPPKK-UHFFFAOYSA-L 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 210000002257 embryonic structure Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K43/00—Testing, sorting or cleaning eggs ; Conveying devices ; Pick-up devices
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a device and a method for identifying clear eggs and weak eggs in the late incubation period based on a vision technology, and relates to the field of detection technology and equipment for incubated eggs. The device is as follows: the hatching egg is arranged on the egg pushing unit, the light source unit is arranged right below the egg pushing unit, the visual units are uniformly distributed right above the hatching egg, the driving unit is connected with the light source unit, and the electrical unit is respectively connected with the visual units, the driving unit and the egg pushing unit through signal lines, gas conveying pipes and magnetic induction. The method comprises the following steps: firstly, sampling; setting a threshold value; image segmentation and numbering; and fourthly, detection. The invention is easy to operate and convenient to maintain; the collected image has no fatigue and human errors, so the accuracy is good and the precision is high; machine vision combines with machinery, can realize modernized intelligent detection, and high efficiency is favorable to the popularization and the application of clear egg and weak clear egg nondestructive test.
Description
Technical Field
The invention relates to the field of hatching egg detection technology and equipment, in particular to a device and a method for identifying clear eggs and weak eggs in the late hatching period based on a vision technology. The invention mainly utilizes machine vision to collect the image of the hatching egg, establishes a clear egg and weak clear egg distinguishing model through a series of image processing, and provides an intelligent nondestructive testing device and method for the automatic detection of the hatching egg.
Background
China has the largest poultry breeding industry in the world, and for the huge hatching industry, clear eggs and weak clear eggs in the hatching process can be accurately detected so as to optimize poultry breeding. The quality of the hatching eggs directly affects the hatchability and the quality of the newborn chick and the future health, living ability and productivity of the newborn chick. Generally, the hatching eggs are subjected to egg-lighting for 2-3 times and clear eggs with no sperm and weak sperm during the hatching process. The egg-lighting process is the quality detection of the hatched eggs, and aims to observe the development condition of embryos and remove clear eggs and weak eggs. However, in the prior art, the hatching eggs can be damaged in the identification process, so that bacteria are bred in the hatching process to pollute the hatching environment, the contact to the hatching eggs is reduced as much as possible in the hatching process, the damage and pollution to the hatching environment are prevented, and the hatching efficiency and the hatching quality are improved.
At the end of the 30 s in the 20 th century, foreign researchers used nondestructive testing techniques to study hatching egg hatching quality, but generally, the related studies are few, and the actual practical application is few. At present, the non-destructive method applied to hatching egg incubation quality detection abroad mainly comprises the following steps: machine vision, tapping vibration, optical detection, and hyperspectral image detection. However, the current research is a cyclic operation of continuous damage and contamination for the whole hatching period. As bacteria in the environment may contaminate the hatching egg during testing and may damage the hatching egg during testing and return to the hatching environment. At present, most of domestic hatching enterprises still adopt an artificial egg-lighting method to carry out hatching egg quality detection. The method is influenced by artificial subjective factors, has the problems of one-sided detection index, low efficiency, high labor consumption and the like, and cannot meet the requirement of modern production. Therefore, it is an important task to research an intelligent detection method for the quality of the hatching eggs in the hatching production process and design a set of modern detection device.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a device and a method for identifying clear eggs and weak eggs in the later hatching period based on a vision technology, so as to accurately identify the clear eggs and the weak eggs.
The technical scheme of the invention is as follows:
visual technology-based identification device for clear eggs and weak eggs in late hatching period (device for short)
The device comprises a working object, namely an egg hatching object, wherein an egg pushing unit, a light source unit, a driving unit, a visual unit and an electric unit are arranged on a rack;
the hatching egg is arranged on the egg pushing unit, the light source unit is arranged right below the egg pushing unit, the visual units are uniformly distributed right above the hatching egg, the driving unit is connected with the light source unit, and the electrical unit is respectively connected with the visual units, the driving unit and the egg pushing unit through signal lines, gas conveying pipes and magnetic induction.
Visual technology-based method for identifying clear eggs and weak eggs in late hatching period (method for short)
The method comprises the following steps:
sampling-701
Turning on a power supply main switch, directly transferring 120 hatching eggs 00 of 18 days old placed on the egg tray 12 onto the push plate 13 from the hatching trolley, and when the push plate 13 reaches a left limit position, controlling an industrial camera to acquire images by the electric unit 50 and storing the images in the computer 51;
② setting threshold-702
Fertilized eggs, non-sperm eggs and weak sperm eggs are placed on the egg tray 12 in two batches, an industrial camera collects images once each time, a database is established in a classified mode, image segmentation processing is carried out, energy characteristic parameters of images of each small area are extracted, and threshold values for judging the non-sperm eggs and the weak sperm eggs are set;
image segmentation and numbering-703
Because the positions of the industrial camera and the egg support 12 on the push plate 13 are relatively fixed during each shooting, the position of the hatching egg 00 to be tested in each image is also relatively fixed, so that the whole image is divided into small fixed area areas, each egg 00 is divided into corresponding small areas, and each small area is numbered according to a certain rule;
fourthly, detection-704
Taking the G component of the small-area image with the number of 1, extracting the corresponding energy characteristic parameter, judging by using the threshold set in the step II, and outputting the identification result by using the computer 51;
and after the detection of the first round of 120 18-day-old hatching eggs 00 is finished, continuing the second round of detection, and sequentially and circularly performing the first step to the fourth step.
The working principle of the invention is as follows:
in a darkroom environment, four egg holders containing 120 eggs to be hatched are placed on a push plate, the push plate is pushed to reach a left limit position, a magnetic sensor senses a magnetic signal sent by a magnetic block on the push plate, an air valve switch is controlled to be opened, a cylinder is utilized to drive a light source unit, and a light source is controlled to be opened at the same time.
The invention has the following advantages and positive effects
1. The operation is easy, and the maintenance is convenient;
2. compared with the traditional domestic egg-shooting method by naked eyes, the method has the advantages that the fatigue and human error are avoided when an industrial camera collects the images, so that the accuracy is good and the precision is high;
3. machine vision combines with machinery, can realize modernized intelligent detection, and high efficiency is favorable to the popularization and the application of clear egg and weak clear egg nondestructive test.
Drawings
FIG. 1 is a block diagram showing the structure of the apparatus;
FIG. 2 is a schematic structural view (front view) of the present apparatus;
FIG. 3 is a schematic structural view (top view) of the apparatus;
FIG. 4 is a schematic view (left side view) of the structure of the present apparatus;
FIG. 5 is a schematic view of a light source condensing;
FIG. 6 is a schematic view of the structure of the vision unit and the electrical unit;
FIG. 7 is a general operational flow diagram of the method;
FIG. 8 is a sub-workflow diagram of sampling;
FIG. 9 is a sub-workflow diagram of image segmentation and numbering;
FIG. 10 is a schematic diagram of image segmentation and numbering;
FIG. 11 is a sub-workflow diagram of detection.
In the figure:
00-hatching eggs;
10-an egg pushing unit, wherein,
11-handle, 12-egg holder, 13-push plate, 14-bottom plate;
20 light source unit
21-light source frame, 22-lamp holder, 23-LED lamp, 24-rubber light-gathering column;
30-a drive unit for driving the motor,
31-the 1 st cylinder, 32-the 2 nd cylinder, 33-the plastic guide block;
40-a visual element, the visual element,
41-1 st industrial camera, 42-2 nd industrial camera, 43-3 rd industrial camera,
44-4 th industrial camera, 45-camera holder, 46-camera holder;
50-electric unit
51-computer, 52-2 nd magnetic inductor, 53-data line, 54-signal line,
55-1 st timer, 56-2 nd timer, 57-3 rd timer,
58-air valve switch, 59-the 1 st magnetic inductor, 510-air tank, 511-air pipe,
512-1 st magnetic block, 513-2 nd magnetic block;
60-a frame.
The specific implementation mode is as follows:
the following detailed description is made with reference to the accompanying drawings and examples.
A, device
1. General of
Referring to fig. 1 to 4, the apparatus includes a work object, a hatching egg 00, on which an egg pushing unit 10, a light source unit 20, a driving unit 30, a vision unit 40 and an electric unit 50 are provided on a housing 60;
the hatching eggs 00 are arranged on the egg pushing units 10, the light source units 20 are arranged right below the egg pushing units 10, the visual units 40 are uniformly distributed right above the hatching eggs 00, the driving units 30 are connected with the light source units 20, and the electric units 50 are respectively connected with the visual units 40, the driving units 30 and the egg pushing units 10 through signal lines, gas transmission pipes and magnetic induction.
2. Functional unit
0) Hatching eggs 00
Hatching eggs 00 refers to 18 day old eggs.
1) Egg pushing unit 10
As shown in fig. 2 and 3, the egg pushing unit 10 includes a handle 11, an egg tray 12, a push plate 13 and a bottom plate 14;
the rack 60 is provided with a bottom plate 14, the bottom plate 14 is sequentially connected with a push plate 13, an egg tray 12 and an incubation egg 00, and the left end and the right end of the push plate 13 are respectively provided with a handle 11.
The handles 11 are fixed at two ends of the push plate 13, the hatching eggs 00 are placed in the egg holders 12, the egg holders 12 are placed in the limiting area at the upper end of the push plate 13, and the clamping grooves at the lower end of the push plate 13 are in clamping fit with the supporting sheets at the upper end of the bottom plate 14.
2) Light source unit 20
As shown in fig. 5, the plurality of light source units 20 are arranged in a matrix of 6 (pieces/row/ton) × 5 (rows) × 4 (ton) ═ 120 (pieces);
the single light source unit 20 comprises a light source frame 21, a lamp holder 22, an LED lamp 23 and a rubber light gathering column 24 which are sequentially connected from bottom to top, and the hatching eggs 00 are placed on the rubber light gathering column 24;
the rubber light gathering column 24 is a rubber product with elasticity and no clearance fit with the eggs 00.
In a dark room environment, light is concentrated at the lower end of the egg 00 by the rubber light-concentrating column 24, so that light leakage is avoided.
3) Drive unit 30
As shown in fig. 2 and 3, the driving unit 30 includes a 1 st cylinder 31, a 2 nd cylinder 32, and a plastic guide block 33;
the 1 st cylinder 31 and the 2 nd cylinder 32 are symmetrically arranged at the left end and the right end of the frame 60 respectively, and piston rods in the cylinders are connected with the light source unit 20; 4 guide posts are uniformly distributed at the lower end of the 4 corners of the light source frame 21, the 4 guide posts are respectively matched with 4 plastic guide blocks 33 arranged on the rack 60, and the piston rod moves up and down by the inflation and deflation of the air cylinder to drive the light source frame 21 to move up and down.
4) Visual element 40
Referring to fig. 2, 3 and 4, the vision unit 40 includes 1 st, 2 nd, 3 rd and 4 th industrial cameras 41, 42, 43 and 44, camera holders 45 and camera holders 46, which constitute 4 groups of vision assemblies connected in series from top to bottom, and the lens of each industrial camera is aligned with the hatching egg 00.
The vision unit 40 can adjust the field range and the object distance by adjusting the height of the camera fixing frame 46, so as to obtain a clearer image.
5) Electrical unit 50
As shown in fig. 6, the electric unit 50 includes a computer 51, a 2 nd magnetic sensor 52, a data line 53, a signal line 54, a 1 st timer 55, a 2 nd timer 56, a 3 rd timer 57, a gas valve switch 58, a 1 st magnetic sensor 59, a gas tank 510, a gas pipe 511, a 1 st magnetic block 512, and a 2 nd magnetic block 513;
the air tank 510, the air valve switch 58 and the input end of the air pipe 511 are sequentially connected, and the output end of the air pipe 511 is respectively connected with the 1 st air cylinder 31 and the 2 nd air cylinder 32 to provide air pressure;
the 1 st magnetic inductor 59 is connected with the air valve switch 58 through a signal line 54 to control the opening or closing of the air valve switch 58;
the 1 st timer 55, the 2 nd timer 56 and the 3 rd timer 57 are respectively connected with the 2 nd, 3 rd and 4 th industrial cameras 42, 43 and 44, the 2 nd magnetic inductor 52 is connected with the 1 st industrial camera 41, the 2 nd magnetic inductor 52, the 1 st timer 55, the 2 nd timer 56 and the 3 rd timer 57 are sequentially connected in series through a signal wire 54, and the 4 industrial cameras are sequentially controlled to acquire images;
the 1 st, 2 nd, 3 rd and 4 th industrial cameras 41, 42, 43 and 44 are connected to the computer 51 through data lines 53, respectively, and store the acquired images.
6) Rack 60
The frame 60 is the support of the apparatus.
3. The working mechanism is as follows:
the 1 st magnetic block 512 is positioned at the upper end of the push plate 13, when the push plate 13 is blocked by the baffle plate at the left end of the bottom plate 14, the 1 st magnetic sensor 59 positioned on the rack 60 senses the magnetic signal of the 1 st magnetic block 512, the air valve switch 58 is opened through the signal line 54, the air in the air tank 510 reaches the air cylinder through the air pipe 511, when the piston rod in the air cylinder rises to the limit position, the 2 nd magnetic sensor 52 positioned on the rack 60 senses the magnetic signal of the 2 nd magnetic block 513 positioned on the light source frame 21, the 1 st timer 55 counts time through the signal line 54, the 1 st industrial camera 41 collects images at the same time, and the image 1 is stored in the computer 51 through the data line; when the 1 st timer 55 reaches the limit of 10ms, the 2 nd timer 56 starts to count time, and simultaneously the 2 nd industrial camera 42 acquires images and stores the images 2 in the computer 51 through the data line 53; when the 2 nd timer 56 reaches the limit of 10ms, the 3 rd timer 57 starts to count time, and simultaneously the 3 rd industrial camera 43 acquires images and stores the images 3 in the computer 51 through the data line 53; when the 3 rd timer 57 reaches the 10ms limit, the 4 th industrial camera 44 captures an image and saves the image 4 to the computer 51 through the data line 53. When the push plate 13 leaves the left end baffle of the cover plate 14, the 1 st magnetic sensor 59 cannot sense a magnetic signal, at the moment, the air valve switch 58 is automatically closed, the two air cylinders 31 and 32 automatically deflate, and the light source frame 21 descends to the lower end limit position.
Second, method
1. Sub-workflow of sampling
As in fig. 8, the sub-workflow of sampling is as follows:
A. when the push plate reaches the limit position, the 1 st magnetic inductor induces a magnetic signal-801
When the push plate reaches the left limit position, the 1 st magnetic inductor 59 induces the magnetic signal of the 1 st magnetic block 512;
B. light source device and air valve switch simultaneously receiving magnetic signal-802
The light source device and the air valve switch 58 receive magnetic signals simultaneously, so that the LED lamp 23 in the light source device is electrified to provide light source, and the air valve switch 58 is controlled to be opened simultaneously, so that the air tank 510 supplies air and supplies pressure;
C. cylinder up, magnetic sensor induction magnetic signal 2-803
When the 1 st and 2 nd air cylinders 31 and 32 rise to the upper end limit positions, the 2 nd magnetic inductor 52 receives the magnetic signals of the 2 nd magnetic block 513;
D. the 1 st camera acquires images, and the 1 st timer times for 10ms-804
The 1 st industrial camera 41 and the 1 st timer 55 receive the magnetic signals at the same time, and the 1 st industrial camera 41 acquires the image 1 and stores the image in the computer 51;
E. the 2 nd camera acquires images, and the 2 nd timer counts time for 10ms-805
The 2 nd industrial camera 42 and the 2 nd timer 56 simultaneously receive the magnetic signals delayed by the 1 st timer 55 for 10ms, and the 2 nd industrial camera 42 acquires the image 2 and stores the image to the computer 51;
F. the 3 rd camera acquires images, and the 3 rd timer times for 10ms-806
The 3 rd industrial camera 43 and the 3 rd timer 57 simultaneously receive the magnetic signal delayed by the 2 nd timer 56 for 10ms, and the 3 rd industrial camera 43 acquires the image 3 and stores the image in the computer 51;
G. image taken by the 4 th camera-807
The 4 th industrial camera 44 receives the magnetic signal after delaying for 10ms by the 3 rd timer 57, and the 4 th industrial camera 44 acquires the image 4 and stores the image in the computer 51.
2. Image segmentation and numbering sub-workflow
As in fig. 9, the image segmentation and numbering sub-workflow is as follows:
i, image segmentation and numbering-901
Dividing and numbering images acquired by known samples according to a principle of dividing and numbering the images as shown in fig. 10, dividing the images according to a matrix of 6 (pieces/line/support) × 5 (lines) × 4 (support) ═ 120 (pieces), and sequentially numbering the images as 1-120;
II, extracting characteristic parameters-902
Extracting energy characteristic parameters of each sample egg to obtain an E value of the sample egg:
the range of E values when the sample egg is a fertilized egg is: e is more than or equal to 0.5;
when the sample eggs are clear eggs and weak eggs, the E value range is as follows: e is less than 0.5;
wherein E is: the sum of squares of the gray level co-occurrence matrix elements;
III, setting the E value to-903
Setting the threshold value for distinguishing the eggs without sperm from the eggs with weak sperm to be 0.5;
when E is less than 0.5, judging the egg as a clear egg or a weak clear egg;
when E is more than or equal to 0.5, the egg is judged as a fertilized egg.
3. Sub-workflow of detection
As in fig. 11, the sub-workflow of detection is as follows:
a. g component map-111 of corresponding number is extracted
A G component diagram of the original small area image after numbering is obtained by using software Matlab 2012;
b. energy-112 of each image is extracted from No. 1
The characteristic parameters of the energy (angular second moment) of each small region are extracted from the region with the number 1, and the formula is as follows:
c. judging condition E is less than 0.5-113
Will be provided with
d-1 substitution formula [1]Judging by using a threshold value 0.5 set in the step III through a characteristic parameter E extracted by a computer, if E is less than 0.5, judging that the detected egg is a clear egg or a weak clear egg-114, outputting 0 by the computer, and then entering the step d; otherwise, if E is more than or equal to 0.5, the detected egg is a fertilized egg-115, the computer outputs 1, and then the step d is carried out;
d. numbering plus 1-116
The computer outputs 0 or 1 and then adds 1 to the serial number;
e. number 120-
Judging whether the serial number is 120-;
f. end-118.
Thirdly, detecting results:
the test sample of this example was a beijing red No. 1 white-shell egg purchased from myzus valley poultry ltd, and 18-day-old hatching eggs were classified into two types, respectively: fertilized eggs, clear eggs or weak eggs.
The accuracy rate of distinguishing the eggs without sperm or the eggs with weak sperm is 100 percent, and the total accuracy rate is 100 percent.
Claims (4)
1. A visual technology-based method for identifying clear eggs and weak eggs in the late hatching period comprises a working object, namely a hatching egg (00);
an egg pushing unit (10), a light source unit (20), a driving unit (30), a visual unit (40) and an electric unit (50) are arranged on the rack (60);
the hatching eggs (00) are arranged on the egg pushing units (10), the light source units (20) are arranged right below the egg pushing units (10), the visual units (40) are uniformly distributed right above the hatching eggs (00), the driving units (30) are connected with the light source units (20), and the electric units (50) are respectively connected with the visual units (40), the driving units (30) and the egg pushing units (10) through signal lines, gas transmission pipes and magnetic induction;
the egg pushing unit (10) comprises a handle (11), an egg support (12), a push plate (13) and a bottom plate (14);
a bottom plate (14) is arranged on the rack (60), a push plate (13), an egg tray (12) and an incubation egg (00) are sequentially connected to the bottom plate (14), and handles (11) are respectively arranged at the left end and the right end of the push plate (13);
a plurality of the light source units (20) are arranged in a matrix of 6 (pieces/row/ton) × 5 (rows) × 4 (ton) ═ 120 (pieces);
the single light source unit (20) comprises a light source frame (21), a lamp holder (22), an LED lamp (23) and a rubber light gathering column (24) which are sequentially connected from bottom to top, and the hatching eggs (00) are placed on the rubber light gathering column (24);
the rubber light gathering column (24) is a rubber product which has telescopic elasticity and is in gapless fit with the incubated eggs (00);
the driving unit (30) comprises a 1 st air cylinder (31), a 2 nd air cylinder (32) and a plastic guide block (33);
the 1 st cylinder (31) and the 2 nd cylinder (32) are respectively and symmetrically arranged at the left end and the right end of the rack (60), and piston rods in the 1 st cylinder (31) and the 2 nd cylinder (32) are connected with the light source unit (20); 1 guide post is respectively arranged at the lower end of 4 corners of the light source frame (21), 4 guide posts are respectively matched with 4 plastic guide blocks (33) arranged on the rack (60), and the piston rod moves up and down by the inflation and deflation of a 1 st air cylinder (31) and a 2 nd air cylinder (32) to drive the light source frame (21) to move up and down;
the vision unit (40) comprises 1 st, 2 nd, 3 th and 4 th industrial cameras (41, 42, 43 and 44), a camera support (45) and a camera fixing frame (46), 4 groups of vision components which are sequentially connected from top to bottom are formed, and the lens of each industrial camera is aligned to a hatching egg (00);
the electric unit (50) comprises a computer (51), a 2 nd magnetic inductor (52), a data line (53), a signal line (54), a 1 st timer (55), a 2 nd timer (56), a 3 rd timer (57), an air valve switch (58), a 1 st magnetic inductor (59), an air tank (510), an air conveying pipe (511), a 1 st magnetic block (512) and a 2 nd magnetic block (513);
the input ends of the air tank (510), the air valve switch (58) and the air pipe (511) are sequentially connected, and the output end of the air pipe (511) is respectively connected with the 1 st air cylinder (31) and the 2 nd air cylinder (32) to provide air pressure;
the 1 st magnetic inductor (59) is connected with the air valve switch (58) through a signal line (54) to control the opening or closing of the air valve switch (58);
the 1 st timer (55), the 2 nd timer (56) and the 3 rd timer (57) are respectively connected with the 2 nd, 3 rd and 4 th industrial cameras (42, 43 and 44), the 2 nd magnetic inductor (52) is connected with the 1 st industrial camera (41), the 2 nd magnetic inductor (52), the 1 st timer (55), the 2 nd timer (56) and the 3 rd timer (57) are sequentially connected in series through a signal wire (54), and the 4 industrial cameras are sequentially controlled to acquire images;
the 1 st, 2 nd, 3 th and 4 th industrial cameras (41, 42, 43 and 44) are respectively connected with a computer (51) through data lines (53) and store the acquired images;
the method is characterized in that:
sampling (701)
Turning on a power supply main switch, directly transferring 120 hatching eggs of 18 days old placed on the egg tray from the hatching trolley onto a push plate, and when the push plate reaches a left limit position, controlling 1 st, 2 nd, 3 rd and 4 th industrial cameras (41, 42, 43 and 44) to collect images by an electric unit and storing the images into a computer;
② setting threshold (702)
Fertilized eggs, non-sperm eggs and weak sperm eggs are placed on an egg tray in two batches, images of 1 st, 2 nd, 3 th and 4 th industrial cameras (41, 42 th, 43 th and 44 th) are collected once each time, a database is established in a classified mode, image segmentation processing is carried out, energy characteristic parameters of images of each small area are extracted, and threshold values for judging the non-sperm eggs and the weak sperm eggs are set;
image division and numbering (703)
Because the positions of the 1 st, 2 nd, 3 th and 4 th industrial cameras (41, 42, 43 and 44) and the egg tray on the push plate are relatively fixed during each shooting, the position of the hatching egg in each image is also relatively fixed, so that the whole image is divided into fixed small-area areas, each hatching egg is divided into corresponding small areas, and each small area is numbered according to a certain rule;
detecting (704)
Taking the G component of the small-area image with the number of 1, extracting the corresponding energy characteristic parameter, judging by using the threshold set in the step II, and outputting the identification result by using a computer;
and after the detection of the 120 eggs incubated for 18 days old in the first round is finished, continuing the detection in the second round, and sequentially and circularly performing the steps I-IV.
2. The method for identifying clear eggs and weak eggs during the late stage of hatching according to claim 1, wherein:
the sub-workflow of the sampling is as follows:
A. when the push plate reaches the limit position, the 1 st magnetic inductor inducts a magnetic signal (801)
When the push plate reaches the left limit position, the 1 st magnetic inductor induces the magnetic signal of the 1 st magnetic block;
B. the light source unit and the air valve switch receive the magnetic signal at the same time (802)
The light source unit and the air valve switch simultaneously receive the magnetic signals, so that the LED lamp in the light source unit is electrified to provide a light source, and the air valve switch is simultaneously controlled to be opened, so that the air tank supplies air and supplies pressure;
C. cylinder rising, 2 nd magnetic sensor induction magnetic signal (803)
The 1 st cylinder and the 2 nd cylinder rise to the upper end limit positions, and the 2 nd magnetic inductor receives the magnetic signals of the 2 nd magnetic block;
D. the 1 st camera collects images, the 1 st timer times (804)
The 1 st industrial camera and the 1 st timer receive the magnetic signal at the same time, and the 1 st industrial camera acquires an image 1 and stores the image to a computer;
E. the 2 nd camera collects images, the 2 nd timer counts time (805)
The 2 nd industrial camera and the 2 nd timer simultaneously receive the magnetic signal delayed by the 1 st timer for 10ms, and the 2 nd industrial camera acquires an image 2 and stores the image to the computer;
F. the 3 rd camera captures images, the 3 rd timer counts (806)
The 3 rd industrial camera and the 3 rd timer simultaneously receive the magnetic signal delayed by 10ms by the 2 nd timer, and the 3 rd industrial camera acquires an image 3 and stores the image in a computer;
G. image collected by the 4 th camera (807)
And the 4 th industrial camera receives the magnetic signal delayed by 10ms by the 3 rd timer, and the 4 th industrial camera acquires the image 4 and stores the image to the computer.
3. The method of claim 1 for identifying clear eggs and weak eggs after hatching, comprising:
the sub-workflow of image segmentation and numbering is as follows:
i, image segmentation and numbering (901)
Dividing and numbering images acquired by known samples, dividing the images according to a matrix of 6 multiplied by 5 multiplied by 4 which is 120, and numbering the images in sequence as 1-120;
II, extracting characteristic parameters (902)
Extracting energy characteristic parameters of each sample egg to obtain an E value of the sample egg:
the range of E values when the sample egg is a fertilized egg is: e is more than or equal to 0.5;
when the sample eggs are clear eggs and weak eggs, the E value range is as follows: e < 0.5;
wherein E is: the sum of squares of the gray level co-occurrence matrix elements;
III, set E value (903)
Setting the threshold value for distinguishing the eggs without sperm from the eggs with weak sperm to be 0.5;
when E is less than 0.5, judging the eggs are clear eggs or weak clear eggs;
when E is more than or equal to 0.5, the egg is judged as a fertilized egg.
4. The method of claim 1 for identifying clear eggs and weak eggs after hatching, comprising:
the sub-workflow of the detection is as follows:
a. g component diagram of corresponding number is extracted (111)
Extracting a G component diagram of the original small area image after numbering by using software Matlab 2012;
b. energy of each image is extracted from No. 1 (112)
Extracting energy characteristic parameters of each small region from the region with the number of 1, wherein the formula is as follows:
c. judgment Condition E <0.5 (113)
Will be provided with
Substituting d into 1
In the method, the characteristic parameter E extracted by the computer is judged by using the threshold value 0.5 set in the step III, and if E is judged<0.5, the detected egg is a clear egg or a weak clear egg (114), the computer outputs 0, and then the step d is carried out; otherwise, if E is more than or equal to 0.5, the detected egg is a fertilized egg (115), the computer outputs 1 and then the egg entersStep d;
d. number plus 1(116)
The computer outputs 0 or 1 and then adds 1 to the serial number;
e. number 120(117)
Judging whether the serial number is 120, if so, entering the step f, otherwise, skipping to the step b;
f. and (118) finishing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710039502.9A CN106797894B (en) | 2017-01-19 | 2017-01-19 | Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710039502.9A CN106797894B (en) | 2017-01-19 | 2017-01-19 | Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106797894A CN106797894A (en) | 2017-06-06 |
| CN106797894B true CN106797894B (en) | 2022-05-20 |
Family
ID=58986829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710039502.9A Active CN106797894B (en) | 2017-01-19 | 2017-01-19 | Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106797894B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109324161A (en) * | 2017-07-31 | 2019-02-12 | 爱科维申科技（天津）有限公司 | A kind of egg embryo's fertility detection system based on machine vision |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102217559B (en) * | 2011-05-27 | 2013-03-20 | 华中农业大学 | On-line automatic detection and sorting equipment and method for incubated egg quality |
| US9131666B2 (en) * | 2012-05-18 | 2015-09-15 | Yamamoto Corp. | Hatching egg inspection apparatus |
| CN103283639A (en) * | 2013-06-18 | 2013-09-11 | 四川农业大学 | LED high-clearness egg candling box |
| CN206658834U (en) * | 2017-01-19 | 2017-11-24 | 华中农业大学 | A kind of hatching later stage infertile egg of view-based access control model technology and weak smart egg identification device |
-
2017
- 2017-01-19 CN CN201710039502.9A patent/CN106797894B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106797894A (en) | 2017-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103026984B (en) | Visual inspection grading device and method for survival rates of eggs incubated in groups | |
| CN106872465B (en) | Poultry fertilized egg detection and screening device based on machine vision | |
| CN103611690B (en) | Solar battery sheet sorting unit | |
| CN102217559B (en) | On-line automatic detection and sorting equipment and method for incubated egg quality | |
| CN102445456B (en) | Device and method for nondestructively detecting egg quality based on DSP (Dynamic Signal Processing) machine vision | |
| CN111134047A (en) | Method and system for monitoring egg laying performance of laying hen zone of cage laying hen | |
| CN105028347B (en) | Cocoon Quality automatic sorting picking machine based on paper cocooning frame | |
| CN104198355B (en) | Automatic detection method for red cells in feces | |
| CN102960265B (en) | Non-invasive method and device for detecting survival status of egg embryo | |
| CN114418995B (en) | Cascade algae cell statistical method based on microscope image | |
| CN111462058B (en) | Method for rapidly detecting effective rice ears | |
| CN103229614A (en) | Automatic corn ear test method | |
| CN107064150B (en) | Machine vision technology-based brown shell clear egg and fertilized egg identification device and identification method | |
| CN205958008U (en) | A fish monitoring device that dies for aquaculture | |
| CN106797894B (en) | Device and method for identifying clear eggs and weak eggs in late incubation period based on vision technology | |
| CN109765195A (en) | Intelligent rice ear character analysis system based on Led-red light transmission imaging | |
| CN109509173A (en) | A kind of method of counting and counting device of bacterial clump | |
| CN210236448U (en) | Egg tray separating device for automatic egg inspection machine | |
| CN113057212B (en) | Dead shrimp sorting device | |
| CN111570330B (en) | Machine vision selection device and method for clear eggs in whole-tray duck egg planting | |
| CN206658834U (en) | A kind of hatching later stage infertile egg of view-based access control model technology and weak smart egg identification device | |
| CN110208472A (en) | A kind of automatic inspection egg machine | |
| CN208207889U (en) | Egg of oak silkworm counting device in a kind of agricultural breeding | |
| CN202999054U (en) | Visual inspection grading device for survival rate of group hatched eggs | |
| CN109663747A (en) | A kind of Chinese chestnut small holes caused by worms intelligent detecting method |
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 |