CN116343257A - Seed-sowing livestock screening method, system, equipment and medium based on deep learning - Google Patents
Seed-sowing livestock screening method, system, equipment and medium based on deep learning Download PDFInfo
- Publication number
- CN116343257A CN116343257A CN202111568868.8A CN202111568868A CN116343257A CN 116343257 A CN116343257 A CN 116343257A CN 202111568868 A CN202111568868 A CN 202111568868A CN 116343257 A CN116343257 A CN 116343257A
- Authority
- CN
- China
- Prior art keywords
- livestock
- information
- screening
- deep learning
- breeding
- 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
- 244000144972 livestock Species 0.000 title claims abstract description 142
- 238000012216 screening Methods 0.000 title claims abstract description 49
- 238000013135 deep learning Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000009331 sowing Methods 0.000 title claims abstract description 9
- 238000009395 breeding Methods 0.000 claims abstract description 64
- 230000001488 breeding effect Effects 0.000 claims abstract description 64
- 238000003860 storage Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013136 deep learning model Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000010899 nucleation Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 3
- 239000002609 medium Substances 0.000 description 11
- 241000282887 Suidae Species 0.000 description 8
- 241001465754 Metazoa Species 0.000 description 2
- 241001494479 Pecora Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/44—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing persons
- G01G19/50—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing persons having additional measuring devices, e.g. for height
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The invention relates to a seed-sowing livestock screening method, a seed-sowing livestock screening system, seed-sowing livestock screening equipment and seed-sowing livestock screening media based on deep learning, which comprise the following steps: s1: acquiring multi-angle image data of breeding livestock to be screened; s2: constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized; s3: acquiring weight information, strain information and basic information of breeding livestock to be screened; s4: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a discrimination model, and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock. Compared with the prior art, the invention has the advantages of high screening accuracy, low cost, high efficiency and the like.
Description
Technical Field
The invention relates to the field of livestock screening, in particular to a method, a system, equipment and a medium for screening breeding livestock based on deep learning.
Background
With the development of animal husbandry, the animal husbandry mode gradually shifts from traditional artificial breeding to fine management of livestock. The effective improvement of the livestock yield and quality is a goal of the breeding industry, and the livestock yield and quality directly affect the breeding income. Most of traditional breeding industry breeds through the manual work, has consumed a large amount of manpower financial resources and can't carry out effectual supervision to the health of livestock simultaneously.
Livestock used for breeding, such as breeding pigs, sheep and the like, are specially bred and cultivated in the farm, and the health and strain of the livestock used for breeding influence the yield quality and quantity of the farm. The cultivation of the breeding livestock is a key link of cultivation, and high-quality breeding livestock groups are required to realize high benefit so as to continuously and uniformly produce high-quality and large quantity of livestock. The existing breeding pig health and strain screening is based on artificial experience, so subjectivity is too strong, and the breeding pigs cannot be objectively and scientifically screened.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method, a system, equipment and a medium for screening breeding livestock based on deep learning.
The aim of the invention can be achieved by the following technical scheme:
a kind of breeding livestock screening method based on deep learning includes the following steps:
s1: acquiring multi-angle image data of breeding livestock to be screened;
s2: constructing a multi-parameter physique recognition model, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
s3: acquiring weight information, strain information and basic information of breeding livestock to be screened;
s4: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a discrimination model, and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
Preferably, the step S2 specifically includes:
s21: acquiring multi-angle image samples of livestock, and calibrating to form an image database;
s22: constructing a multi-parameter build recognition model;
s23: dividing a sample in an image database into a training set and a testing set, and training a multi-parameter physique recognition model;
s24: and sending the multi-angle image data of the livestock to be identified into a trained multi-parameter physique identification model, and outputting physique information of the livestock to be identified.
Preferably, the multi-angle image data includes a horizontal right side image, a horizontal rear side image, and a vertical back image of the livestock.
Preferably, the physical information includes height, hip circumference, waist circumference and body length.
Preferably, the step S4 specifically includes:
s41: acquiring physique information, weight information, strain information and basic information of livestock, and calibrating to form a screening database;
s42: constructing a discrimination model based on deep learning;
s43: dividing samples in a screening database into a training set and a testing set, and training a discrimination model;
s44: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a trained discrimination model, and outputting whether the livestock to be identified is high-quality livestock or non-high-quality livestock.
Preferably, the type of the deep learning model adopted by the discriminant model includes, but is not limited to, one of the following arbitrary models: YOLO series, faster RCNN, maskRCNN, SSD, centerNet and DyHead.
Preferably, the strain information comprises a male parent variety and a female parent variety, and the basic information comprises day-to-day age, sex, feeding amount and disease occurrence frequency.
A seed-sowing livestock screening system based on deep learning comprises an image acquisition module, a physical information identification module, an information acquisition module and a screening and distinguishing module,
the image acquisition module is used for acquiring multi-angle image data of the breeding livestock to be screened;
the physique information recognition module is used for constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of the breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
the information acquisition module is used for acquiring weight information, strain information and basic information of the breeding livestock to be screened;
the screening and distinguishing module is used for inputting physique information, weight information, strain information and basic information of the livestock to be identified into the distinguishing model and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of seed livestock screening based on deep learning as described above.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the method of seed livestock screening based on deep learning as described above when executing said computer program.
Compared with the prior art, the invention has the following advantages:
(1) The method utilizes the image and weight acquisition equipment to acquire the image, weight and other data of the pigs at a specific angle, calculates the height, hip circumference and waistline of the pigs through the deep learning model, and inputs the weight information and strain information into the discrimination model to judge the quality and the non-quality;
(2) The invention is based on the first step of image acquisition and data acquisition, the second step of information processing and screening judgment, effectively synthesizes the multi-aspect information of the breeding livestock, improves the accuracy and reliability, reduces the labor cost, improves the screening precision of the breeding livestock of the farm, reduces the dependence on experience, can effectively screen excellent breeding pigs, is beneficial to improving the supervision of the breeding pigs, reduces the risk of the farm, and improves the production quality and the yield of the subsequent farm.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of multi-angle image acquisition of livestock in an embodiment of the invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. Note that the following description of the embodiments is merely an example, and the present invention is not intended to be limited to the applications and uses thereof, and is not intended to be limited to the following embodiments.
Example 1
As shown in FIG. 1, the breeding livestock screening method based on deep learning is a breeding livestock such as breeding pigs and sheep, and in the embodiment, the breeding pigs are taken as an example, and the method comprises the following steps:
s1: and obtaining multi-angle image data of the breeding livestock to be screened.
As shown in fig. 2, by installing three cameras in a designated area, the three cameras are respectively provided at the top to shoot downwards, at the rear to shoot forwards, at the right to shoot leftwards, and acquire a horizontal right side image, a horizontal rear side image and a vertical back image of livestock.
S2: and constructing a multi-parameter physique recognition model, recognizing multi-angle image data of the breeding livestock to be screened, and obtaining physique information of the livestock to be recognized.
The multi-parameter physique recognition model in the embodiment can directly acquire physique information of livestock based on the size and proportion of the livestock in the image, and can also be acquired through a deep learning model.
If a deep learning model is used, the type of the deep learning model used in the multi-parameter build recognition model in this embodiment includes, but is not limited to, one of the following arbitrary models: YOLO series, faster RCNN, maskRCNN, SSD, centerNet and DyHead.
Specifically, step S2 includes:
s21: acquiring multi-angle image samples of livestock, and calibrating to form an image database;
s22: constructing a multi-parameter build recognition model based on deep learning;
s23: dividing a sample in an image database into a training set and a testing set, and training a multi-parameter physique recognition model;
s24: and sending the multi-angle image data of the livestock to be identified into a trained multi-parameter physique identification model, and outputting physique information of the livestock to be identified, wherein the physique information comprises height, hip circumference, waistline and body length.
S3: and acquiring weight information, strain information and basic information of the breeding livestock to be screened. Here, the strain information and the basic information may be acquired through a data storage system in the farm, and the weight information may be synchronously acquired by setting a weight scale in the designated area in S1. In this embodiment, the strain information includes a male parent variety and a female parent variety, and the basic information includes age of day, sex, feeding amount, and number of times of illness.
In this embodiment, the discrimination model of step S4 may employ a deep learning model, such as one of any of the following models: YOLO series, fast RCNN, maskRCNN, SSD, centerNet and DyHead models, and makes a judgment of quality and non-quality of the breeding livestock, specifically including:
s41: acquiring physique information, weight information, strain information and basic information of livestock, and calibrating to form a screening database;
s42: constructing a judging model;
s43: dividing samples in a screening database into a training set and a testing set, and training a discrimination model;
s44: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a trained discrimination model, and outputting whether the livestock to be identified is high-quality livestock or non-high-quality livestock.
In another embodiment of the present invention, the discrimination model may score the weight information, the strain information and the basic information input by calculating the score based on a preset weight scoring rule, obtain the score of the livestock to be screened, and determine that the livestock is high quality if the score is higher than a set threshold, or determine that the livestock is not high quality if the score is not high quality.
Example 2
A seed-sowing livestock screening system based on deep learning is characterized by comprising an image acquisition module, a physical information identification module, an information acquisition module and a screening and distinguishing module,
the image acquisition module is used for acquiring multi-angle image data of the breeding livestock to be screened;
the physique information recognition module is used for constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
the information acquisition module is used for acquiring weight information, strain information and basic information of the breeding livestock to be screened;
the screening and distinguishing module is used for inputting physique information, weight information, strain information and basic information of the livestock to be identified into the distinguishing model and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
The deep learning-based breeding livestock screening system disclosed in embodiment 2 corresponds to the deep learning-based breeding livestock screening method disclosed in embodiment 1, and the implementation method of this embodiment refers to embodiment 1 and is not described herein.
Example 3
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a deep learning based method of breeding stock screening:
s1: acquiring multi-angle image data of breeding livestock to be screened;
s2: constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
s3: acquiring weight information, strain information and basic information of breeding livestock to be screened;
s4: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a discrimination model, and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
The storage medium is any of various types of memory electronics or storage electronics. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; nonvolatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected by a network). The storage medium may store program instructions (e.g., embodied as a computer program) executable by one or more processors.
The method for screening the breeding livestock based on the deep learning disclosed in embodiment 3 corresponds to the method for screening the breeding livestock based on the deep learning disclosed in embodiment 1, and the implementation method of this embodiment refers to embodiment 1 and is not described herein again.
Example 4
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a deep learning based seeding livestock screening method when executing the computer program:
s1: acquiring multi-angle image data of breeding livestock to be screened;
s2: constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
s3: acquiring weight information, strain information and basic information of breeding livestock to be screened;
s4: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a discrimination model, and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
The method for screening the breeding livestock based on the deep learning disclosed in embodiment 4 corresponds to the method for screening the breeding livestock based on the deep learning disclosed in embodiment 1, and the implementation method of this embodiment refers to embodiment 1 and is not described herein again.
The above embodiments are merely examples, and do not limit the scope of the present invention. These embodiments may be implemented in various other ways, and various omissions, substitutions, and changes may be made without departing from the scope of the technical idea of the present invention.
Claims (10)
1. The seed production livestock screening method based on deep learning is characterized by comprising the following steps of:
s1: acquiring multi-angle image data of breeding livestock to be screened;
s2: constructing a multi-parameter physique recognition model, recognizing multi-angle image data of breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
s3: acquiring weight information, strain information and basic information of breeding livestock to be screened;
s4: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a discrimination model, and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
2. The method for screening breeding livestock based on deep learning according to claim 1, wherein the step S2 specifically comprises:
s21: acquiring multi-angle image samples of livestock, and calibrating to form an image database;
s22: constructing a multi-parameter build recognition model;
s23: dividing a sample in an image database into a training set and a testing set, and training a multi-parameter physique recognition model;
s24: and sending the multi-angle image data of the livestock to be identified into a trained multi-parameter physique identification model, and outputting physique information of the livestock to be identified.
3. The method for deep learning based breeding stock screening of claim 1, wherein the multi-angle image data includes a horizontal right side image, a horizontal rear side image and a vertical back image of the stock.
4. The method for deep learning based breeding stock screening according to claim 1, wherein the physical information includes height, hip circumference, waist circumference and body length.
5. The method for screening breeding livestock based on deep learning according to claim 1, wherein the step S4 specifically comprises:
s41: acquiring physique information, weight information, strain information and basic information of livestock, and calibrating to form a screening database;
s42: constructing a discrimination model based on deep learning;
s43: dividing samples in a screening database into a training set and a testing set, and training a discrimination model;
s44: inputting physique information, weight information, strain information and basic information of the livestock to be identified into a trained discrimination model, and outputting whether the livestock to be identified is high-quality livestock or non-high-quality livestock.
6. The method for screening breeding livestock based on deep learning according to claim 1, wherein the type of the deep learning model adopted by the discrimination model comprises, but is not limited to, one of the following arbitrary models: YOLO series, faster RCNN, maskRCNN, SSD, centerNet and DyHead.
7. The method for screening breeding livestock based on deep learning according to claim 1, wherein the strain information comprises male parent strain and female strain, and the basic information comprises age of day, sex, feeding amount and number of illness.
8. A seed-sowing livestock screening system based on deep learning is characterized by comprising an image acquisition module, a physical information identification module, an information acquisition module and a screening and distinguishing module,
the image acquisition module is used for acquiring multi-angle image data of the breeding livestock to be screened;
the physique information recognition module is used for constructing a multi-parameter physique recognition model based on deep learning, recognizing multi-angle image data of the breeding livestock to be screened, and obtaining physique information of the livestock to be recognized;
the information acquisition module is used for acquiring weight information, strain information and basic information of the breeding livestock to be screened;
the screening and distinguishing module is used for inputting physique information, weight information, strain information and basic information of the livestock to be identified into the distinguishing model and judging whether the livestock to be screened is high-quality livestock or non-high-quality livestock.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the deep learning based breeding stock screening method according to any one of claims 1-7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the deep learning based seeding livestock screening method according to any of claims 1-7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111568868.8A CN116343257A (en) | 2021-12-21 | 2021-12-21 | Seed-sowing livestock screening method, system, equipment and medium based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111568868.8A CN116343257A (en) | 2021-12-21 | 2021-12-21 | Seed-sowing livestock screening method, system, equipment and medium based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116343257A true CN116343257A (en) | 2023-06-27 |
Family
ID=86893478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111568868.8A Pending CN116343257A (en) | 2021-12-21 | 2021-12-21 | Seed-sowing livestock screening method, system, equipment and medium based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116343257A (en) |
-
2021
- 2021-12-21 CN CN202111568868.8A patent/CN116343257A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bao et al. | Artificial intelligence in animal farming: A systematic literature review | |
| Xiao et al. | Cow identification in free-stall barns based on an improved Mask R-CNN and an SVM | |
| CN110547210B (en) | Feed supply method and system, computer system, and storage medium | |
| Dunbar et al. | HotSpotter: Using a computer-driven photo-id application to identify sea turtles | |
| CN108664878A (en) | Pig personal identification method based on convolutional neural networks | |
| Ma et al. | Basic motion behavior recognition of single dairy cow based on improved Rexnet 3D network | |
| Nasirahmadi et al. | Pecking activity detection in group-housed turkeys using acoustic data and a deep learning technique | |
| CN111297367A (en) | Animal state monitoring method and device, electronic equipment and storage medium | |
| US20220189018A1 (en) | Human embryo evaluation using ai/ml analysis of real-time video for predicting male-sex offspring | |
| Bishop et al. | Sound analysis and detection, and the potential for precision livestock farming-a sheep vocalization case study | |
| Yurochka et al. | Technology of automatic evaluation of dairy herd fatness | |
| CN116343257A (en) | Seed-sowing livestock screening method, system, equipment and medium based on deep learning | |
| CN110414369B (en) | Cow face training method and device | |
| Watson-Haigh et al. | Proximity loggers: data handling and classification for quality control | |
| CN113516139A (en) | Data processing method, device, equipment and storage medium | |
| CN114419432B (en) | Fish group ingestion intensity assessment method and device | |
| CN115035512B (en) | Crop nutrition state diagnosis method and system based on multi-mode deep learning | |
| CN115830078A (en) | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium | |
| Guo et al. | Sheep face image dataset and DT-YOLOv5s for sheep breed recognition | |
| Yu et al. | Non‐contact detection method of pregnant sows backfat thickness based on two‐dimensional images | |
| Lee et al. | Direct–Maternal Genetic Parameters for Litter Size and Body Weight of Piglets of a New Black Breed for the Taiwan Black Hog Market | |
| Viklund et al. | Effects of long-time series of data on genetic evaluations for performance of Swedish Warmblood riding horses | |
| Owalekar et al. | An agri vigilance system based on computer vision and deep learning | |
| CN113487107B (en) | Automatic large animal weight assessment method, system and medium based on multilayer radial basis network | |
| CN116310923A (en) | Livestock eating deficiency early warning method, system, equipment and medium |
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 |