CN117745036A - Livestock information management method and system based on feature recognition and near field communication - Google Patents
Livestock information management method and system based on feature recognition and near field communication Download PDFInfo
- Publication number
- CN117745036A CN117745036A CN202410179254.8A CN202410179254A CN117745036A CN 117745036 A CN117745036 A CN 117745036A CN 202410179254 A CN202410179254 A CN 202410179254A CN 117745036 A CN117745036 A CN 117745036A
- Authority
- CN
- China
- Prior art keywords
- livestock
- information
- identified
- cluster
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 244000144972 livestock Species 0.000 title claims abstract description 465
- 238000004891 communication Methods 0.000 title claims abstract description 38
- 238000007726 management method Methods 0.000 title claims abstract description 26
- 238000009395 breeding Methods 0.000 claims abstract description 33
- 230000001488 breeding effect Effects 0.000 claims abstract description 33
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 241001465754 Metazoa Species 0.000 claims description 50
- 230000001815 facial effect Effects 0.000 claims description 39
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 19
- 230000037213 diet Effects 0.000 claims description 15
- 235000005911 diet Nutrition 0.000 claims description 15
- 239000003651 drinking water Substances 0.000 claims description 14
- 235000020188 drinking water Nutrition 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 8
- 239000007788 liquid Substances 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 28
- 230000035622 drinking Effects 0.000 description 16
- 238000000034 method Methods 0.000 description 13
- 241000283690 Bos taurus Species 0.000 description 12
- 210000001015 abdomen Anatomy 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000036760 body temperature Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 241000894007 species Species 0.000 description 1
Classifications
-
- 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 provides a livestock information management method and system based on feature recognition and near field communication, and relates to the field of data processing, wherein the system comprises the following components: the information acquisition module is used for acquiring the breeding information of the livestock and establishing a livestock information database; the livestock identification module is used for acquiring image information of the livestock to be identified based on the identification request, identifying first identity information of the livestock to be identified, and acquiring second identity information of the livestock to be identified by interacting with the ear tag of the livestock to be identified through a near field communication technology; the information interaction module is used for determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to the user terminal when the authenticity is determined to be possessed, and sending the warning information to the user terminal when the authenticity is determined not to be possessed.
Description
Technical Field
The invention relates to the field of data processing, in particular to a livestock information management method and system based on feature identification and near field communication.
Background
Livestock individual identification is of great importance for the accurate livestock industry, as it is a prerequisite for modern livestock management and automated behavioral analysis. At present, the variety, source, production performance, immune condition, health condition, animal owners and other information of livestock individuals need to be recorded in various breeding bases and farms due to the needs of seed selection, matching, immunity and the like. Individual numbering and identification are carried out on different species and their progeny.
The existing cattle individual identification method mainly comprises the steps of adding identification marks such as brands, ear marks and earmarks on cattle bodies, and then identifying the marks in a manual mode, so that the cattle individuals are identified, and the identification efficiency is low, the accuracy is low, a large amount of manpower and material resources are required, and the method is not suitable for modern requirements. Meanwhile, a worker needs to hold a printed work list to record data, the data recording speed is slow, the recognition and recording workload is large, and data entry errors are easy to occur.
Therefore, it is desirable to provide a method and a system for livestock information management based on feature recognition and near field communication for improving the level of intellectualization of livestock information management.
Disclosure of Invention
The invention provides a livestock information management system based on feature recognition and near field communication, which comprises: the information acquisition module is used for acquiring the breeding information of the livestock and establishing a livestock information database for storing the breeding information of the livestock; the livestock identification module is used for acquiring image information of livestock to be identified based on the identification request, acquiring first identity information of the livestock to be identified based on the image information of the livestock to be identified, and acquiring second identity information of the livestock to be identified by interacting with the ear tag of the livestock to be identified through a near field communication technology based on the identification request; the information interaction module is used for determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information of the livestock to be recognized, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to the user terminal when the identity recognition result of the livestock to be recognized is determined to have authenticity, and sending warning information to the user terminal when the identity recognition result of the livestock to be recognized is determined to have no authenticity.
Further, the livestock identification module obtains image information of the livestock to be identified, and obtains first identity information of the livestock to be identified based on the image information of the livestock to be identified, including: for each breed of livestock, acquiring facial comparison images of a plurality of livestock of the breed, clustering the plurality of livestock of the breed based on the facial comparison images of the plurality of livestock of the breed, determining a plurality of livestock clusters of the breed, for each livestock cluster of the breed, acquiring body comparison images of each livestock included in the livestock cluster, and determining body characteristics of each livestock included in the livestock cluster based on the body comparison images of each livestock included in the livestock cluster; acquiring face image information of the livestock to be identified, determining variety information of the livestock to be identified based on the face image information of the livestock to be identified, determining a plurality of candidate livestock cluster clusters based on the variety information of the livestock to be identified, determining a target candidate livestock cluster from the plurality of candidate livestock cluster based on the face image information of the livestock to be identified and face comparison images of the cluster centers of each candidate livestock cluster, acquiring body image information of the livestock to be identified, and acquiring first body information of the livestock to be identified based on the body image information of the livestock to be identified and body characteristics of each livestock included in the target candidate livestock cluster.
Further, the animal identification module clusters the plurality of animals of the breed based on facial contrast images of the plurality of animals of the breed, comprising: establishing a variety characteristic association map, wherein the variety characteristic association map is used for recording the corresponding target characteristic type of each variety; determining a target feature type corresponding to the variety based on the variety feature association map; extracting feature information of each livestock of the breed in a target feature type based on face comparison images of a plurality of livestock of the breed; calculating the feature similarity of any two animals of the breed based on the feature information of the two animals in the target feature type; and clustering the plurality of livestock of the breed based on the feature similarity of any two livestock of the breed.
Further, the animal recognition module determines a target candidate animal cluster from the plurality of candidate animal clusters based on the facial image information of the animal to be recognized and the facial contrast image of the cluster center of each of the candidate animal clusters, including: determining the current growth period of the livestock to be identified based on the second identity information of the livestock to be identified; generating a current face comparison image of the clustering center of each candidate livestock cluster corresponding to the current growth period based on the current growth period of the livestock to be identified and the face comparison image of the clustering center of each candidate livestock cluster through a feature prediction model corresponding to the variety; for each candidate livestock cluster, extracting characteristic information of the target characteristic type of the cluster center of the candidate livestock cluster corresponding to the current growth period based on the current face comparison image of the cluster center of the candidate livestock cluster corresponding to the current growth period; extracting feature information of the livestock to be identified in a target feature type based on the facial image information of the livestock to be identified; for each candidate livestock cluster, calculating a matching value of the candidate livestock cluster based on the characteristic information of the target characteristic type of the clustering center of the candidate livestock cluster corresponding to the current growth period and the characteristic information of the target characteristic type of the livestock to be identified; a target candidate livestock cluster is determined from the plurality of candidate livestock clusters based on the matching value of each of the candidate livestock clusters.
Further, the information acquisition module acquires body image information of the livestock to be identified, including: determining a plurality of image acquisition positions based on physical characteristics of each animal included in the target candidate livestock cluster; and acquiring body image information of the livestock to be identified based on the plurality of image acquisition positions.
Further, the information acquisition module acquires body image information of the livestock to be identified based on the plurality of image acquisition positions, including: generating a plurality of candidate image acquisition tracks based on the plurality of image acquisition positions; screening the candidate image acquisition tracks based on a plurality of track screening indexes to determine a target image acquisition track; and acquiring body image information of the livestock to be identified at each image acquisition position based on the target image acquisition track.
Further, the livestock identification module extracts feature information of the livestock to be identified in a target feature type based on the facial image information of the livestock to be identified, and the method comprises the following steps: extracting color information of the livestock to be identified in a target feature type based on the facial image information of the livestock to be identified; acquiring facial point cloud characteristics of the livestock to be identified based on the facial image information of the livestock to be identified, carrying out facial modeling on the livestock to be identified based on the facial point cloud characteristics of the livestock to be identified, and extracting size information of the livestock to be identified in a target characteristic type.
Further, the information acquisition module includes: a physiological information acquisition unit for acquiring health status information of livestock; a diet information acquisition unit for acquiring diet information of livestock; and the exercise information acquisition unit is used for acquiring exercise information of the livestock.
Further, the diet information acquisition unit comprises a diet information acquisition component and a drinking water information acquisition component; the feeding information acquisition component comprises a feeding trough area image acquisition device arranged in a feeding trough; the drinking water information acquisition component comprises a liquid level sensor arranged in the water tank.
The invention provides a livestock information management method based on feature identification and near field communication, which comprises the following steps: acquiring livestock breeding information, and establishing an livestock information database for storing the livestock breeding information; acquiring image information of livestock to be identified based on an identity identification request, and acquiring first identity information of the livestock to be identified based on the image information of the livestock to be identified; based on the identity recognition request, interacting with the ear tag of the livestock to be recognized through a near field communication technology to acquire second identity information of the livestock to be recognized; determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information of the livestock to be recognized; when the identity recognition result of the livestock to be recognized is determined to be true, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to a user terminal; and when the identity recognition result of the livestock to be recognized is determined to be not true, sending warning information to the user terminal.
Compared with the prior art, the livestock information management method and system based on feature identification and near field communication provided by the invention have the following beneficial effects:
1. the method comprises the steps of automatically obtaining and storing the breeding information of the livestock, obtaining the first identity information of the livestock to be identified based on the image information of the livestock to be identified, interacting with the ear tag of the livestock to be identified through a near field communication technology, obtaining the second identity information of the livestock to be identified, determining whether the identity recognition result of the livestock to be identified has authenticity based on the first identity information and the second identity information of the livestock to be identified, and sending warning information to a user terminal when the identity recognition result of the livestock to be identified is determined to not have authenticity.
2. The method comprises the steps of clustering a plurality of livestock of a variety based on facial comparison images of the plurality of livestock of the variety, acquiring body comparison images of each livestock included in the livestock cluster, and determining unique body characteristics of each livestock included in the livestock cluster based on the body comparison images of each livestock included in the livestock cluster, so that efficiency and accuracy of subsequently determining first identity information of the livestock to be identified are improved.
3. Based on the facial image information of the livestock to be identified, the color information and the size information of the livestock to be identified in the target feature type are extracted, and the efficiency and the accuracy of determining the first identity information of the livestock to be identified are improved.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a block diagram of a livestock information management system based on feature identification and near field communication according to some embodiments of the present disclosure;
FIG. 2 is a schematic flow chart of clustering a plurality of animals of a breed based on facial contrast images of the plurality of animals of the breed according to some embodiments of the present description;
FIG. 3 is a schematic flow chart of determining a target candidate livestock cluster from a plurality of candidate livestock clusters, according to some embodiments of the present disclosure;
fig. 4 is a flow chart of a method for livestock information management based on feature recognition and near field communication according to some embodiments of the present disclosure.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
Fig. 1 is a schematic block diagram of an animal information management system based on feature recognition and near field communication according to some embodiments of the present disclosure, and as shown in fig. 1, an animal information management system based on feature recognition and near field communication may include an information acquisition module, an animal recognition module, and an information interaction module.
The information acquisition module may be configured to acquire breeding information of the livestock and establish a livestock information database for storing the breeding information of the livestock.
The livestock breeding information may include at least a livestock listing date, a livestock individual identification, a livestock variety, a livestock listing channel, a livestock rail identification, a livestock listing date, a livestock listing weight, a livestock sales channel, epidemic disease information, treatment information, and the like.
In some embodiments, the information acquisition module comprises:
the system comprises a physiological information acquisition unit, a pulse detection unit and a pulse detection unit, wherein the physiological information acquisition unit is used for acquiring health state information of livestock, and specifically can comprise a body temperature detection component, a respiration detection component, a pulse detection component and the like, wherein the body temperature detection component can be used for acquiring body temperature of the livestock, the respiration detection component can be used for acquiring respiratory rate of the livestock, and the pulse detection component can be used for acquiring pulse rate of the livestock;
a diet information acquisition unit for acquiring diet information of livestock;
the motion information acquisition unit is used for acquiring motion information of the livestock, and particularly, a positioning component can be arranged in an ear tag of the livestock and used for acquiring the real-time position of the livestock so as to generate the motion information of the livestock.
In some embodiments, the diet information acquisition unit comprises a diet information acquisition component and a drinking water information acquisition component, wherein the diet information acquisition component comprises a diet groove area image acquisition device arranged in a diet groove, and the drinking water information acquisition component comprises a liquid level sensor arranged in the water groove.
Specifically, at least one infrared pyroelectric sensor can be further arranged in the trough, when the at least one infrared pyroelectric sensor outputs a high level, the trough area image acquisition device is started, whether livestock feed exists or not is identified according to the image of the trough area acquired by the trough area image acquisition device, when the livestock feed exists is identified, coding information on the ear tag of the livestock is identified according to the image of the trough area acquired by the trough area image acquisition device, the identity of the livestock is determined based on the coding information on the ear tag of the livestock, the feeding time of the livestock is determined according to the image of the trough area acquired by the trough area image acquisition device, and the feeding time of the acquired livestock is stored according to the identity of the livestock.
The water tank area can be further provided with a water tank area image acquisition device, whether livestock drinking water occurs can be judged according to an output signal of a water tank liquid level sensor in a detection period, when the livestock drinking water occurs, the water tank area image acquisition device is started, coding information on an ear tag of the livestock is identified according to an image of the water tank area acquired by the water tank area image acquisition device, the identity of the livestock is determined based on the coding information on the ear tag of the livestock, the drinking water amount of the livestock is determined according to the liquid level information before and after drinking water is completed by the livestock, and the drinking water amount of the collected livestock is stored according to the identity of the livestock.
And determining a water level fluctuation parameter in a detection period (for example, 30S) according to an output signal of a liquid level sensor of the water tank, and judging that livestock drinking water occurs when the water level fluctuation parameter is larger than a preset water level fluctuation parameter threshold value. For example, the water level fluctuation parameter for one detection period may be calculated based on the following formula:
wherein,for the water level fluctuation parameter of the ith detection period, is->The (th) of the (i) th detection period>Water level at each time point>For the average water level of the history detection period, for which the water level fluctuation parameter nearest to the ith detection period is less than or equal to the preset water level fluctuation parameter threshold value,/v>Is the time length of the ith detection period.
In some embodiments, the information obtaining module may determine the abnormal eating condition of the livestock according to the eating information and drinking information of the livestock in one cultivation detection period (for example, 3 days, 5 days, etc.), where the eating information of the livestock in one cultivation detection period may include at least an average eating interval, a single average eating time length, an eating interval fluctuation parameter, and a single eating time length fluctuation parameter of the livestock in one cultivation detection period, and the drinking information of the livestock in one cultivation detection period may include at least an average drinking time length, a single average drinking time length, a drinking time interval fluctuation parameter, and a single drinking time length fluctuation parameter of the livestock in one cultivation detection period.
For example, the eating interval fluctuation parameter may be calculated based on the following formula:
wherein,for the feeding interval fluctuation parameter of the livestock in the j-th cultivation detection period,/>For the time interval between the nth feeding and the N-1 th feeding of the livestock in the jth cultivation detection period, N is the total number of feeding of the livestock in the jth cultivation detection period.
The single meal length fluctuation parameter may be calculated based on the following formula:
wherein,for the single food duration fluctuation parameter of the livestock in the j-th cultivation detection period,/for the livestock>For the length of a single meal taken by the livestock at the nth meal of the jth cultivation detection period.
The calculation mode of the drinking water interval fluctuation parameter is similar to the calculation mode of the feeding interval fluctuation parameter, the calculation mode of the single feeding duration fluctuation parameter is similar to the calculation mode of the single drinking water duration fluctuation parameter, and the details are not repeated here.
In some embodiments, the information acquisition module may determine the eating anomalies of the livestock based on the following procedure:
basic information of livestock, such as variety, breeding environment, breeding food and the like, is acquired;
acquiring basic information of a sample livestock;
determining a sample animal similar to the basic information of the animal as a target sample animal;
obtaining average feeding interval, single average feeding time length, feeding interval fluctuation parameter, single feeding time length fluctuation parameter, average drinking time interval, single average drinking time length, drinking time interval fluctuation parameter and single drinking time length fluctuation parameter of a target sample livestock in a current growth period of the livestock in which a breeding detection period of the livestock belongs;
calculating average feeding interval, single average feeding time length, feeding interval fluctuation parameter, single feeding time length fluctuation parameter, average drinking time interval, single average drinking time length, drinking time interval fluctuation parameter, single drinking time length fluctuation parameter and average feeding time length, single average feeding time length, feeding interval fluctuation parameter, single feeding time length fluctuation parameter, average drinking time length fluctuation parameter, single drinking time length fluctuation parameter of the current growth period of the livestock in the livestock breeding detection period, determining abnormal eating conditions of the livestock, and generating warning information to a user terminal of a manager of the livestock when abnormal eating of the livestock is judged.
The livestock identification module can be used for interacting with the earmarks of the livestock to be identified through a near field communication technology based on the identification request to acquire second identity information of the livestock to be identified.
Specifically, be provided with NFC (Near Field Communication) label in the ear tag of waiting to discern the livestock, the livestock identification module can include the card reader, and this NFC label can carry out data interaction with the card reader of livestock identification module based on near field communication technique, and the card reader of livestock identification module can read the second identity information of waiting to discern the livestock of the NFC label record of the ear tag of livestock. The second identity information of the livestock to be identified, which is recorded by the NFC tag of the earmark of the livestock, may at least include a unique individual livestock identification of the livestock to be identified.
The livestock identification module can be further used for acquiring image information of the livestock to be identified based on the identification request and acquiring first identity information of the livestock to be identified based on the image information of the livestock to be identified.
In some embodiments, the animal identification module obtains image information of the animal to be identified and obtains first identity information of the animal to be identified based on the image information of the animal to be identified, including:
for each breed of livestock, acquiring facial comparison images of a plurality of livestock of the breed, clustering the plurality of livestock of the breed based on the facial comparison images of the plurality of livestock of the breed, determining a plurality of livestock clusters of the breed, for each breed of livestock cluster, acquiring body comparison images of each livestock included in the livestock cluster, and determining body characteristics of each livestock included in the livestock cluster based on the body comparison images of each livestock included in the livestock cluster, wherein the body characteristics of each livestock included in the livestock cluster are characteristics of the livestock different from any other livestock included in the livestock cluster;
acquiring face image information of the livestock to be identified, determining variety information of the livestock to be identified based on the face image information of the livestock to be identified, determining a plurality of candidate livestock cluster clusters based on the variety information of the livestock to be identified, determining target candidate livestock cluster from the plurality of candidate livestock cluster based on the face image information of the livestock to be identified and the face contrast image of the cluster center of each candidate livestock cluster, acquiring body image information of the livestock to be identified, acquiring first identity information of the livestock to be identified based on the body image information of the livestock to be identified and the body characteristics of each livestock included in the target candidate livestock cluster, and specifically, acquiring identity information of the livestock in the target candidate livestock cluster, which is consistent with the body characteristics of the livestock to be identified, as the first identity information of the livestock to be identified.
Fig. 2 is a schematic flow diagram of clustering animals of a breed based on facial contrast images of animals of the breed according to some embodiments of the present description, as shown in fig. 2, in some embodiments, the animal identification module clusters animals of the breed based on facial contrast images of animals of the breed, including:
establishing a variety feature association graph, wherein the variety feature association graph is used for recording target feature types corresponding to each variety, specifically, the target feature types can be features which are convenient for identifying different livestock of a certain variety, the target feature types corresponding to the livestock of different varieties can be different, for example, the target feature types corresponding to the cattle at least comprise the distribution, the position and the like of the swirls, the eye marks, the hair and the texture on the cattle face, and the target feature types corresponding to the pigs at least comprise the distance between eyes, the position of the mouth, the width of the skull and the like;
determining a target feature type corresponding to the variety based on the variety feature association graph;
extracting feature information of each livestock of the variety in a target feature type based on face comparison images of a plurality of livestock of the variety;
for any two animals of the breed, calculating the feature similarity of the two animals based on the feature information of the two animals in the target feature type;
based on the feature similarity of any two animals of the breed, a plurality of animals of the breed are clustered.
Specifically, the livestock identification module can calculate cosine similarity of feature information of two livestock in a target feature type as the feature similarity of the two livestock, and then cluster a plurality of livestock of the variety based on the feature similarity of any two livestock according to a k-means clustering algorithm (k-means clustering algorithm). When the feature similarity of two animals is greater than a preset feature similarity threshold, the two animals may be clustered into one animal cluster.
Fig. 3 is a schematic flow chart of determining a target candidate livestock cluster from a plurality of candidate livestock clusters according to some embodiments of the present specification, as shown in fig. 3, in some embodiments, the livestock recognition module determines the target candidate livestock cluster from the plurality of candidate livestock clusters based on facial image information of the livestock to be recognized and a facial contrast image of a cluster center of each candidate livestock cluster, including:
determining a current growing period of the livestock to be identified based on the second identity information of the livestock to be identified, specifically, determining the time of entering the fence and the growing period of the livestock when entering the fence corresponding to the second identity information of the livestock to be identified based on the second identity information of the livestock to be identified, calculating a time difference value between the current time and the time of entering the fence, and determining the current growing period of the livestock to be identified based on the time difference value and the growing period of the livestock when entering the fence;
generating a current face comparison image of the clustering center of each candidate livestock cluster corresponding to the current growth period based on the current growth period of the livestock to be identified and the face comparison image of the clustering center of each candidate livestock cluster through a feature prediction model corresponding to the variety, wherein the feature prediction model can comprise a GAN (Generative Adversarial Network) model;
for each candidate livestock cluster, extracting feature information of the target feature type of the candidate livestock cluster corresponding to the current growth period based on a current face comparison image of the candidate livestock cluster, wherein the feature information of the target feature type of the candidate livestock cluster corresponding to the current growth period can be extracted based on a feature extraction model corresponding to the variety, the feature extraction model can be a CNN (Convolutional Neural Network) model, and the feature information of the target feature type of the candidate livestock cluster corresponding to the current growth period at least comprises color information and size information of the target feature type;
extracting feature information of the livestock to be identified in the target feature type based on the face image information of the livestock to be identified, specifically, extracting feature information of the livestock to be identified in the target feature type based on a feature extraction model corresponding to the variety;
for each candidate livestock cluster, calculating a matching value of the candidate livestock cluster based on the characteristic information of the target characteristic type of the clustering center of the candidate livestock cluster corresponding to the current growth period and the characteristic information of the target characteristic type of the livestock to be identified;
a target candidate livestock cluster is determined from the plurality of candidate livestock clusters based on the match value for each candidate livestock cluster.
Specifically, the livestock identification module may calculate a matching value of the candidate livestock cluster based on the characteristic information of the target characteristic type corresponding to the current growth cycle of the clustering center of the candidate livestock cluster and the characteristic information of the target characteristic type of the livestock to be identified through the matching value determination model, wherein the matching value determination model may be an artificial neural network (Artificial Neural Network, ANN). The target candidate livestock cluster is the candidate livestock cluster with the largest matching value.
In some embodiments, the information acquisition module acquires body image information of the livestock to be identified, comprising:
determining a plurality of image acquisition positions based on the physical characteristics of each animal included in the target candidate animal cluster, for example, a third candidate animal cluster of the breed of cattle is a target candidate animal cluster corresponding to the animal to be identified, the target candidate animal cluster including cattle 1, cattle 2 and cattle 3, wherein the physical characteristics of cattle 1 are that the backs have round spots, the physical characteristics of cattle 2 are that the left side abdomen has irregular spots, and the physical characteristics of cattle 3 are that the right side abdomen has irregular spots, and the plurality of image acquisition positions include the backs, the left side abdomen and the right side abdomen of the animal to be identified;
based on a plurality of image acquisition positions, acquiring body image information of the livestock to be identified, and specifically, acquiring body image information of one livestock to be identified at each image acquisition position.
In some embodiments, the information acquisition module acquires body image information of the livestock to be identified based on the plurality of image acquisition positions, including:
generating a plurality of candidate image acquisition tracks based on the plurality of image acquisition positions, specifically, generating a plurality of candidate image acquisition tracks based on the plurality of image acquisition positions and the volume information of the livestock to be identified through a track generation model, wherein the track generation model can be a GAN (Generative Adversarial Network) model;
screening a plurality of candidate image acquisition tracks based on a plurality of track screening indexes to determine a target image acquisition track, wherein the plurality of track screening indexes at least comprise track length indexes, track required time indexes, position transition indexes and the like, wherein the position transition indexes can represent the position change condition between two adjacent track points in the track, the more similar the position between the two adjacent track points in the candidate image acquisition track is, the higher the score of the candidate image acquisition track in the position transition indexes is, the score of the candidate image acquisition track in the plurality of track screening indexes can be calculated, the priority value of the candidate image acquisition track is determined, the candidate image acquisition track with the largest priority value is taken as the target image acquisition track, the shorter the length of the candidate image acquisition track is, the higher the score of the candidate image acquisition track in the track length indexes is, the shorter the time required for executing the candidate image acquisition track in the image acquisition position is, and the score of the candidate image acquisition track in the track required time index is higher;
and acquiring body image information of the livestock to be identified at each image acquisition position based on the target image acquisition track.
In some embodiments, the animal identification module extracts feature information of the animal to be identified in the target feature type based on facial image information of the animal to be identified, including:
extracting color information of the livestock to be identified in the target feature type based on the facial image information of the livestock to be identified;
based on the facial image information of the livestock to be identified, facial point cloud characteristics of the livestock to be identified are obtained, facial modeling is carried out on the livestock to be identified based on the facial point cloud characteristics of the livestock to be identified, and size information of the livestock to be identified in the target characteristic type is extracted.
The information interaction module may be configured to determine whether the identity recognition result of the livestock to be recognized has authenticity based on the first identity information and the second identity information of the livestock to be recognized.
When the identity recognition result of the livestock to be recognized is determined to be true, the breeding information of the livestock is obtained from the livestock information database and is sent to the user terminal, and when the identity recognition result of the livestock to be recognized is determined to be not true, warning information is sent to the user terminal.
Specifically, when the livestock corresponding to the first identity information and the second identity information of the livestock to be identified are the same livestock, the identity identification result of the livestock to be identified is determined to have authenticity.
Fig. 4 is a schematic flow chart of a method for managing livestock information based on feature recognition and near field communication according to some embodiments of the present disclosure, as shown in fig. 4, the method for managing livestock information based on feature recognition and near field communication may include the following steps:
step 410, acquiring breeding information of livestock, and establishing a livestock information database for storing the breeding information of the livestock;
step 420, based on the identification request, acquiring image information of the livestock to be identified, and based on the image information of the livestock to be identified, acquiring first identity information of the livestock to be identified;
step 430, based on the identification request, interacting with the ear tag of the livestock to be identified through a near field communication technology to obtain second identity information of the livestock to be identified;
step 440, determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information of the livestock to be recognized;
step 450, when the identity recognition result of the livestock to be recognized is determined to be true, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to the user terminal;
and step 460, when the identity recognition result of the livestock to be recognized is determined to be not true, warning information is sent to the user terminal.
In some embodiments, a method for managing livestock information based on feature identification and near field communication may be performed by a livestock information management system based on feature identification and near field communication, and further description of a method for managing livestock information based on feature identification and near field communication may be referred to as related description of a livestock information management system based on feature identification and near field communication, which is not repeated herein.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (10)
1. A livestock information management system based on feature identification and near field communication, comprising:
the information acquisition module is used for acquiring the breeding information of the livestock and establishing a livestock information database for storing the breeding information of the livestock;
the livestock identification module is used for acquiring image information of livestock to be identified based on the identification request, acquiring first identity information of the livestock to be identified based on the image information of the livestock to be identified, and acquiring second identity information of the livestock to be identified by interacting with the ear tag of the livestock to be identified through a near field communication technology based on the identification request;
the information interaction module is used for determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information of the livestock to be recognized, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to the user terminal when the identity recognition result of the livestock to be recognized is determined to have authenticity, and sending warning information to the user terminal when the identity recognition result of the livestock to be recognized is determined to have no authenticity.
2. The livestock information management system based on feature recognition and near field communication as set forth in claim 1, wherein said livestock identification module obtains image information of the livestock to be identified, and obtains first identity information of the livestock to be identified based on the image information of the livestock to be identified, comprising:
for each breed of livestock, acquiring facial comparison images of a plurality of livestock of the breed, clustering the plurality of livestock of the breed based on the facial comparison images of the plurality of livestock of the breed, determining a plurality of livestock clusters of the breed, for each livestock cluster of the breed, acquiring body comparison images of each livestock included in the livestock cluster, and determining body characteristics of each livestock included in the livestock cluster based on the body comparison images of each livestock included in the livestock cluster;
acquiring face image information of the livestock to be identified, determining variety information of the livestock to be identified based on the face image information of the livestock to be identified, determining a plurality of candidate livestock cluster clusters based on the variety information of the livestock to be identified, determining a target candidate livestock cluster from the plurality of candidate livestock cluster based on the face image information of the livestock to be identified and face comparison images of the cluster centers of each candidate livestock cluster, acquiring body image information of the livestock to be identified, and acquiring first body information of the livestock to be identified based on the body image information of the livestock to be identified and body characteristics of each livestock included in the target candidate livestock cluster.
3. The livestock information management system based on feature recognition and near field communication of claim 2, wherein said livestock recognition module clusters said plurality of livestock of said breed based on facial contrast images of said plurality of livestock of said breed, comprising:
establishing a variety characteristic association map, wherein the variety characteristic association map is used for recording the corresponding target characteristic type of each variety;
determining a target feature type corresponding to the variety based on the variety feature association map;
extracting feature information of each livestock of the breed in a target feature type based on face comparison images of a plurality of livestock of the breed;
calculating the feature similarity of any two animals of the breed based on the feature information of the two animals in the target feature type;
and clustering the plurality of livestock of the breed based on the feature similarity of any two livestock of the breed.
4. The livestock information management system based on feature recognition and near field communication of claim 3, wherein said livestock recognition module determines a target candidate livestock cluster from said plurality of candidate livestock clusters based on facial image information of said livestock to be recognized and a facial contrast image of a cluster center of each of said candidate livestock clusters, comprising:
determining the current growth period of the livestock to be identified based on the second identity information of the livestock to be identified;
generating a current face comparison image of the clustering center of each candidate livestock cluster corresponding to the current growth period based on the current growth period of the livestock to be identified and the face comparison image of the clustering center of each candidate livestock cluster through a feature prediction model corresponding to the variety;
for each candidate livestock cluster, extracting characteristic information of the target characteristic type of the cluster center of the candidate livestock cluster corresponding to the current growth period based on the current face comparison image of the cluster center of the candidate livestock cluster corresponding to the current growth period;
extracting feature information of the livestock to be identified in a target feature type based on the facial image information of the livestock to be identified;
for each candidate livestock cluster, calculating a matching value of the candidate livestock cluster based on the characteristic information of the target characteristic type of the clustering center of the candidate livestock cluster corresponding to the current growth period and the characteristic information of the target characteristic type of the livestock to be identified;
a target candidate livestock cluster is determined from the plurality of candidate livestock clusters based on the matching value of each of the candidate livestock clusters.
5. The livestock information management system based on feature identification and near field communication as claimed in any one of claims 2 to 4, wherein said information acquisition module acquires body image information of said livestock to be identified, comprising:
determining a plurality of image acquisition positions based on physical characteristics of each animal included in the target candidate livestock cluster;
and acquiring body image information of the livestock to be identified based on the plurality of image acquisition positions.
6. The livestock information management system based on feature identification and near field communication as set forth in claim 5, wherein said information acquisition module acquires body image information of said livestock to be identified based on said plurality of image acquisition positions, comprising:
generating a plurality of candidate image acquisition tracks based on the plurality of image acquisition positions;
screening the candidate image acquisition tracks based on a plurality of track screening indexes to determine a target image acquisition track;
and acquiring body image information of the livestock to be identified at each image acquisition position based on the target image acquisition track.
7. The livestock information management system based on feature recognition and near field communication as set forth in claim 5, wherein said livestock recognition module extracts feature information of said livestock to be recognized in a target feature type based on facial image information of said livestock to be recognized, comprising:
extracting color information of the livestock to be identified in a target feature type based on the facial image information of the livestock to be identified;
acquiring facial point cloud characteristics of the livestock to be identified based on the facial image information of the livestock to be identified, carrying out facial modeling on the livestock to be identified based on the facial point cloud characteristics of the livestock to be identified, and extracting size information of the livestock to be identified in a target characteristic type.
8. The livestock information management system based on feature identification and near field communication as set forth in any one of claims 1 to 4, wherein said information acquisition module includes:
a physiological information acquisition unit for acquiring health status information of livestock;
a diet information acquisition unit for acquiring diet information of livestock;
and the exercise information acquisition unit is used for acquiring exercise information of the livestock.
9. The livestock information management system based on feature recognition and near field communication as recited in claim 8, wherein said diet information acquisition unit comprises a diet information acquisition component and a drinking water information acquisition component;
the feeding information acquisition component comprises a feeding trough area image acquisition device arranged in a feeding trough;
the drinking water information acquisition component comprises a liquid level sensor arranged in the water tank.
10. A livestock information management method based on feature recognition and near field communication, comprising:
acquiring livestock breeding information, and establishing an livestock information database for storing the livestock breeding information;
acquiring image information of livestock to be identified based on an identity identification request, and acquiring first identity information of the livestock to be identified based on the image information of the livestock to be identified;
based on the identity recognition request, interacting with the ear tag of the livestock to be recognized through a near field communication technology to acquire second identity information of the livestock to be recognized;
determining whether the identity recognition result of the livestock to be recognized has authenticity or not based on the first identity information and the second identity information of the livestock to be recognized;
when the identity recognition result of the livestock to be recognized is determined to be true, acquiring the breeding information of the livestock from the livestock information database and sending the breeding information to a user terminal;
and when the identity recognition result of the livestock to be recognized is determined to be not true, sending warning information to the user terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179254.8A CN117745036B (en) | 2024-02-18 | 2024-02-18 | Livestock information management method and system based on feature recognition and near field communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179254.8A CN117745036B (en) | 2024-02-18 | 2024-02-18 | Livestock information management method and system based on feature recognition and near field communication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117745036A true CN117745036A (en) | 2024-03-22 |
| CN117745036B CN117745036B (en) | 2024-04-30 |
Family
ID=90283516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410179254.8A Active CN117745036B (en) | 2024-02-18 | 2024-02-18 | Livestock information management method and system based on feature recognition and near field communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117745036B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503194A (en) * | 2002-11-26 | 2004-06-09 | 中国科学院计算技术研究所 | Status identification method by using body information matched human face information |
| US20140226896A1 (en) * | 2011-07-07 | 2014-08-14 | Kao Corporation | Face impression analyzing method, aesthetic counseling method, and face image generating method |
| CN107229947A (en) * | 2017-05-15 | 2017-10-03 | 邓昌顺 | A kind of banking and insurance business method and system based on animal identification |
| CN107992903A (en) * | 2017-09-20 | 2018-05-04 | 翔创科技（北京）有限公司 | Livestock personal identification method, device, storage medium and electronic equipment |
| JPWO2017069231A1 (en) * | 2015-10-23 | 2018-10-04 | 国立大学法人大阪大学 | Method and system for predicting morphology after treatment in human body |
| CN108717464A (en) * | 2018-05-31 | 2018-10-30 | 中国联合网络通信集团有限公司 | photo processing method, device and terminal device |
| CN111243005A (en) * | 2020-01-07 | 2020-06-05 | 洛阳语音云创新研究院 | Livestock weight estimation method, device, equipment and computer readable storage medium |
| US20210067684A1 (en) * | 2019-08-27 | 2021-03-04 | Lg Electronics Inc. | Equipment utilizing human recognition and method for utilizing the same |
| CN113128529A (en) * | 2019-12-30 | 2021-07-16 | 中移(成都)信息通信科技有限公司 | Livestock identity recognition model training method, recognition method, system and device |
| CN113569895A (en) * | 2021-02-20 | 2021-10-29 | 腾讯科技（北京）有限公司 | Image processing model training method, processing method, device, equipment and medium |
| CN114092809A (en) * | 2021-11-17 | 2022-02-25 | 杭州海康威视数字技术股份有限公司 | Object identification method and device and electronic equipment |
| CN114581948A (en) * | 2022-03-04 | 2022-06-03 | 吉林大学 | Animal face identification method |
| CN114627505A (en) * | 2022-03-18 | 2022-06-14 | 中国农业大学 | Automatic milk cow cleanliness scoring method and system, storage medium and equipment |
| CN114638536A (en) * | 2022-03-31 | 2022-06-17 | 北京农业职业学院(中国共产党北京市委员会农村工作委员会党校) | Animal health monitoring method and system based on artificial intelligence |
| CN116258881A (en) * | 2022-12-12 | 2023-06-13 | 浙江大华技术股份有限公司 | Image clustering method, device, terminal and computer readable storage medium |
| CN116563040A (en) * | 2023-07-07 | 2023-08-08 | 中国平安财产保险股份有限公司 | Farm risk exploration method, device, equipment and storage medium based on livestock identification |
| CN117377988A (en) * | 2021-05-14 | 2024-01-09 | 苹果公司 | Identification using facial-related physical features |
-
2024
- 2024-02-18 CN CN202410179254.8A patent/CN117745036B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503194A (en) * | 2002-11-26 | 2004-06-09 | 中国科学院计算技术研究所 | Status identification method by using body information matched human face information |
| US20140226896A1 (en) * | 2011-07-07 | 2014-08-14 | Kao Corporation | Face impression analyzing method, aesthetic counseling method, and face image generating method |
| JPWO2017069231A1 (en) * | 2015-10-23 | 2018-10-04 | 国立大学法人大阪大学 | Method and system for predicting morphology after treatment in human body |
| CN107229947A (en) * | 2017-05-15 | 2017-10-03 | 邓昌顺 | A kind of banking and insurance business method and system based on animal identification |
| CN107992903A (en) * | 2017-09-20 | 2018-05-04 | 翔创科技（北京）有限公司 | Livestock personal identification method, device, storage medium and electronic equipment |
| CN108717464A (en) * | 2018-05-31 | 2018-10-30 | 中国联合网络通信集团有限公司 | photo processing method, device and terminal device |
| US20210067684A1 (en) * | 2019-08-27 | 2021-03-04 | Lg Electronics Inc. | Equipment utilizing human recognition and method for utilizing the same |
| CN113128529A (en) * | 2019-12-30 | 2021-07-16 | 中移(成都)信息通信科技有限公司 | Livestock identity recognition model training method, recognition method, system and device |
| CN111243005A (en) * | 2020-01-07 | 2020-06-05 | 洛阳语音云创新研究院 | Livestock weight estimation method, device, equipment and computer readable storage medium |
| CN113569895A (en) * | 2021-02-20 | 2021-10-29 | 腾讯科技（北京）有限公司 | Image processing model training method, processing method, device, equipment and medium |
| CN117377988A (en) * | 2021-05-14 | 2024-01-09 | 苹果公司 | Identification using facial-related physical features |
| CN114092809A (en) * | 2021-11-17 | 2022-02-25 | 杭州海康威视数字技术股份有限公司 | Object identification method and device and electronic equipment |
| CN114581948A (en) * | 2022-03-04 | 2022-06-03 | 吉林大学 | Animal face identification method |
| CN114627505A (en) * | 2022-03-18 | 2022-06-14 | 中国农业大学 | Automatic milk cow cleanliness scoring method and system, storage medium and equipment |
| CN114638536A (en) * | 2022-03-31 | 2022-06-17 | 北京农业职业学院(中国共产党北京市委员会农村工作委员会党校) | Animal health monitoring method and system based on artificial intelligence |
| CN116258881A (en) * | 2022-12-12 | 2023-06-13 | 浙江大华技术股份有限公司 | Image clustering method, device, terminal and computer readable storage medium |
| CN116563040A (en) * | 2023-07-07 | 2023-08-08 | 中国平安财产保险股份有限公司 | Farm risk exploration method, device, equipment and storage medium based on livestock identification |
Non-Patent Citations (5)
| Title |
|---|
| ABHINAV SHARMA等: "Machine Learning Applications for Precision Agriculture: A Comprehensive Review", IEEE, vol. 9, 31 December 2020 (2020-12-31), pages 4843, XP011831332, DOI: 10.1109/ACCESS.2020.3048415 * |
| 沈明霞等: "生猪自动化养殖装备与技术研究进展与展望", 农业机械学报, vol. 53, no. 12, 25 December 2022 (2022-12-25), pages 1 * |
| 郭阳阳等: "基于坐标注意力机制和YOLO v5s模型的山羊脸部检测方法", 农业机械学报, vol. 54, no. 7, 22 May 2023 (2023-05-22), pages 313 * |
| 黄玳;蔡晓东;胡月琳;曹艺;刘玉柱;: "基于特征融合的目标动态身份识别方法", 电视技术, vol. 44, no. 06, 15 June 2020 (2020-06-15), pages 6 * |
| 齐咏生等: "基于自适应注意力机制的复杂场景下牛脸检测算法", 农业工程学报, vol. 39, no. 14, 16 August 2023 (2023-08-16), pages 173 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117745036B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Behaviour recognition of pigs and cattle: Journey from computer vision to deep learning | |
| Bao et al. | Artificial intelligence in animal farming: A systematic literature review | |
| CN110583550B (en) | Accurate feeding system and device are bred to fish shrimp sea cucumber based on target detection and tracking | |
| Jingqiu et al. | Cow behavior recognition based on image analysis and activities | |
| CN110929650B (en) | Method and device for identifying livestock and feed identity, computing equipment and readable storage medium | |
| KR102307327B1 (en) | Electronic Sow Management Apparatus | |
| CN111507302B (en) | Image recognition-based pet searching method and device | |
| CN111274975A (en) | Pig feeding behavior prediction method and device | |
| Tscharke et al. | Review of methods to determine weight and size of livestock from images | |
| CN113159244B (en) | Poultry farming management system based on thing networking | |
| CN113420709A (en) | Cattle face feature extraction model training method and system and cattle insurance method and system | |
| CN117745036B (en) | Livestock information management method and system based on feature recognition and near field communication | |
| CN113516139A (en) | Data processing method, device, equipment and storage medium | |
| CN115830078A (en) | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium | |
| CN114065801B (en) | Soil monitoring method and system based on neural network model and readable storage medium | |
| CN113068657B (en) | Intelligent efficient pig raising method and system | |
| Bello et al. | Smart animal husbandry: A review of its data, applications, techniques, challenges and opportunities | |
| KR20230033068A (en) | Smart farm management system based on behavior pattern and method thereof | |
| Bastiaansen et al. | Continuous real-time cow identification by reading ear tags from live-stream video | |
| CN113971227B (en) | Big data based livestock monitoring method, system and readable storage medium | |
| Harris et al. | Improving the power of activity-based heat detection using additional automatically captured data | |
| Yeşil et al. | Recognition of Hereford and Simmental cattle breeds via computer vision. | |
| SAITOH et al. | A Static Video Summarization Approach for the Analysis of Cattle's Movement | |
| CN116579508B (en) | Fish prediction method, device, equipment and storage medium | |
| Trezubov et al. | Analysis of Technologies for Visual Tracking of Physiological Condition of Cattle |
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 |