CN107992903A - Livestock personal identification method, device, storage medium and electronic equipment - Google Patents
Livestock personal identification method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107992903A CN107992903A CN201711407625.XA CN201711407625A CN107992903A CN 107992903 A CN107992903 A CN 107992903A CN 201711407625 A CN201711407625 A CN 201711407625A CN 107992903 A CN107992903 A CN 107992903A
- Authority
- CN
- China
- Prior art keywords
- livestock
- data
- identity
- identification
- identified
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention provides a kind of livestock personal identification method, device, storage medium and electronic equipment.Livestock personal identification method includes：Obtain the current behavior environmental data of livestock to be identified and image to be tested；According to the image to be tested and livestock database, the owner identification recognition result of the livestock to be identified is determined；According to the current behavior environmental data and livestock habit data, determine the identification auxiliary information of the livestock to be identified, the livestock habit data include multiple livestock identity set, and each livestock identity set includes at least one livestock identity data corresponding with behavioural environment；According to the owner identification recognition result and the identification auxiliary information, the identity of the livestock to be identified is determined.Thus, by the use of the identification auxiliary information that the livestock habit of livestock obtains as supplementary means or evidence, exact identity identification is carried out to livestock to be identified.
Description
Technical field
The present embodiments relate to identity recognizing technology, more particularly to a kind of livestock personal identification method, device, storage Jie
Matter and electronic equipment.
Background technology
When carrying out rear livestock in pens and management to livestock, it is necessary to periodically quarantine to livestock, immune processing, to prevent from sending out
The raw pestilence for influencing food security；Need to trace to the source appearing on the scene to the livestock in market, the source of every livestock is tracked, with true
Protect when food security occurs, efficiently control epidemic situation.In addition, raiser can also insure the livestock of cultivation, in the scale of generation
Property livestock death situation when, can to insure death livestock require Claims Resolution.
In the foregoing management role to captive livestock, the problem of all referring to that livestock is identified and tracks.However, domestic animal
Poultry is not the animal that intelligent interaction can be carried out with the mankind, can not ensure to protect when carrying out Image Acquisition, immune operation etc. to it
Desired posture or state are held, therefore is that the identification of livestock, tracking etc. bring difficulty.
The content of the invention
The purpose of the embodiment of the present invention is, there is provided a kind of livestock personal identification method, storage medium and electronic equipment, with
Identification effectively is carried out to livestock.
First aspect according to embodiments of the present invention, there is provided a kind of livestock personal identification method includes：Obtain domestic animal to be identified
The current behavior environmental data and image to be tested of poultry；According to the image to be tested and livestock database, the domestic animal to be identified is determined
The owner identification recognition result of poultry；According to the current behavior environmental data and livestock habit data, the livestock to be identified is determined
Identification auxiliary information, the livestock habit data include multiple livestock identity set, each livestock identity
Set includes at least one livestock identity data corresponding with behavioural environment；According to the owner identification recognition result and
The identification auxiliary information, determines the identity of the livestock to be identified.
Second aspect according to embodiments of the present invention, there is provided a kind of acquisition method of livestock habit information, including：Obtain domestic animal
Dirty swine work historical data, the livestock life history data include livestock collection image and its behavioural environment data；According to described
Livestock gathers image, obtains corresponding livestock identity data respectively；According to the behavioural environment data to the identity mark
Know data to be clustered, obtain with each respective livestock identity set of behavioural environment data as livestock habit
Property data.
The third aspect according to embodiments of the present invention, there is provided a kind of livestock querying method, including：Obtain the letter of livestock to be checked
Breath；According to livestock habit data and the information of the livestock to be checked, the behavioural environment data of the acquisition livestock to be checked, the domestic animal
Poultry habit data include multiple livestock identity set, and each livestock identity set includes corresponding respectively with behavioural environment
At least one livestock identity data；According to the behavioural environment data got, determine that the livestock to be checked is current
Behavior and position.
Fourth aspect according to embodiments of the present invention, there is provided a kind of computer-readable recording medium, is stored thereon with calculating
Machine programmed instruction, wherein, foregoing any livestock personal identification method is realized in described program instruction when being executed by processor
The step of.
5th aspect according to embodiments of the present invention, there is provided a kind of electronic equipment, including：Processor, memory, communication member
Part and communication bus, the processor, the memory and the communication device are completed each other by the communication bus
Communication；The memory is used to store an at least executable instruction, and the executable instruction makes the processor perform foregoing
The step of one livestock personal identification method.
6th aspect according to embodiments of the present invention, also provides a kind of computer program, it includes computer program and refers to
Order, described program instruction realize any livestock personal identification method provided by the embodiments of the present application when being executed by processor.
7th aspect according to embodiments of the present invention, there is provided a kind of computer program product, it is computer-readable for storing
Instruction, described instruction is performed so that computer performs the livestock identification described in any of the above-described possible implementation
Method.
Alternatively, the computer program product is specially computer-readable storage medium, in another optional embodiment,
The computer program product is specially software product, such as SDK etc..
Eighth aspect according to embodiments of the present invention, there is provided a kind of livestock identity recognition device, including：Data acquisition mould
Block, for the current behavior environmental data for obtaining livestock to be identified and image to be tested；Owner identification determining module, for according to
The image to be tested and livestock database that data acquisition module obtains, determine the owner identification recognition result of the livestock to be identified；It is auxiliary
Supplementary information determining module, for the current behavior environmental data and livestock habit data obtained according to the data acquisition module,
Determine the identification auxiliary information of the livestock to be identified, the livestock habit data include multiple livestock identity collection
Close, each livestock identity set includes at least one livestock identity data corresponding with behavioural environment；Identity
Identification module, for the owner identification recognition result determined according to the owner identification determining module and the auxiliary information determining module
Definite identification auxiliary information, determines the identity of the livestock to be identified.
Livestock identification scheme according to embodiments of the present invention, according to the image to be tested and livestock data of livestock to be identified
Storehouse, determines the owner identification recognition result of the livestock to be identified, according to the current behavior environmental data of livestock to be identified and livestock
Habit data, determine the identification auxiliary information of livestock to be identified, and according to the owner identification recognition result and the body
Part identification auxiliary information, determines the identity of the livestock to be identified.Thus, the identification obtained using the livestock habit of livestock
Auxiliary information carries out exact identity identification as supplementary means or evidence to livestock to be identified.Due to livestock continuously active or
Posture not face camera device, and in the case of the image to be tested of high quality can not be obtained, can be the identification of livestock to be identified
Auxiliary is provided, so as to improve the accuracy of livestock identification.
Brief description of the drawings
Fig. 1 is the flow chart of the acquisition method for the livestock habit information for showing according to embodiments of the present invention one；
Fig. 2 is the flow chart for the livestock personal identification method for showing according to embodiments of the present invention two；
Fig. 3 is a kind of flow chart for the exemplary process for showing the step S220 in Fig. 2；
Fig. 4 is a kind of flow chart for the exemplary process for showing the step S230 in Fig. 2；
Fig. 5 is the flow chart for the livestock querying method for showing according to embodiments of the present invention seven；
Fig. 6 is the logic diagram for the livestock identity recognition device for showing according to embodiments of the present invention eight；
Fig. 7 is the structure diagram for the electronic equipment for showing according to embodiments of the present invention ten.
Embodiment
The exemplary embodiment of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings.
In this application, " multiple " refer to two or more, " at least one " refer to one, two or more.It is right
Either component, data or the structure referred in the application, clearly limits in the case of one, it will be appreciated that for one or
It is multiple.
Embodiment one
Fig. 1 is the flow chart of the acquisition method for the livestock habit information for showing according to embodiments of the present invention one.Can be any
Such as PC, server etc. have the collection side for the livestock habit information that embodiment one is performed in the equipment of computing function
Method.
It is well known that captive livestock after training, forms habits and customs/habit of more rule.For example, pig is from cub
When, it is trained to eat food, in somewhere C stool and urines etc., their activity in somewhere A sleeps, in somewhere B
Substantially it is limited in fixed region, is consequently formed relatively fixed life habit.In addition, animal has natural group.
For example, during milk cow is fed, it is found that in food or milking, the milk bovine ear tag number by many milk cows is close,
And ear tag number is close to meaning that these milk cow places of birth are approached with the time, it is possible to from it is small just together, so as to form day
Right colony.So, these following milk cows can influence each other on the active areas, or can be mutual confirmation etc..For another example
In the feeding process of swinery, raiser is when carrying out piggy point circle, it will usually consciously by a collection of of same head sow
Piggy assigns to same circle, with this time for reducing these piggys involvement new environment etc..These life habits of livestock, social habit
Property etc., when being identified, verify, tracking to livestock, there is surcharge and meaning.
According to an embodiment of the invention one, the data that can be lived by collecting the livestock of batch are simultaneously analyzed, and obtain characterization
The data of livestock habit, so as to livestock is identified, verify, track processing when, using these livestock habit data into
Row aid in treatment.
With reference to Fig. 1, in step S110, livestock life history data are obtained, the livestock life history data include livestock
Gather image and its behavioural environment data.
During penkeeping, the livestock life data of record livestock life process can be constantly collected.According to this hair
Bright embodiment one, may be used at the livestock life history data that the livestock life data collected in a period of time are formed and carries out domestic animal
Raise the analysis of habit data.
Recorded here, livestock life history data can contain a plurality of (such as thousands of, up to ten thousand) lives, every life record
Livestock behavioural environment data when being collected including at least the livestock collection image of some livestock and the image.Here, behavior
Environmental data may include the behavioral data of livestock and the environmental data that behavior occurs.
Specifically, behavioral data may include to represent lactation, food, sleep, plays, draining, the data of the behavior such as social activity, ring
Border data may include to represent stable breeding subregion, the data of the information such as position, time occur, but be not limited to aforementioned data.For example, one
Bar behavioural environment data may indicate that livestock correlation habit, i.e. feed newborn livestock lactation, in some corner of pigsty sleep etc. by some.
In step S120, image is gathered according to the livestock, obtains corresponding livestock identity data respectively.
Specifically, image is gathered for each livestock in livestock life history data, carries out image analysis processing respectively,
The external appearance characteristic data of the livestock in image are obtained, and identification is carried out according to the external appearance characteristic data of livestock, obtain domestic animal
The identity data of poultry.Identification mentioned here refers to identify certain livestock, and identity data refers to be used for only
One ground identifies the mark data of the livestock, it can be the numbering of livestock, title etc., for example, No. 35763 pigs, circle 3-536 pigs
Deng.
Can be by any applicable personal identification method, from any livestock collection image acquisition livestock identity number
According to.For example, most simply, livestock can be gathered image and be compared with the livestock image included in livestock database, to determine
Livestock identity in livestock collection image；For another example the characteristic of image zooming-out livestock can be gathered from livestock, by the spy of extraction
Sign data are compared with each livestock characteristic included in livestock database, and livestock collection figure is determined according to comparison result
Livestock identity as in, etc..
Hereafter, in step S130, the identity data is clustered according to the behavioural environment data, obtain with
Each respective livestock identity set of the behavioural environment data is as livestock habit data.
Specifically, together with being referred to the corresponding livestock identity data of the value of identical behavioural environment data, shape
Into livestock identity set corresponding with behavior environmental data.For example, it is assumed that the behavioural environment data instruction of No. 35763 pigs
By 56384 lactation of sow, and the behavioural environment data of No. 65638 pigs are also indicated that by 56384 lactation of sow, then by No. 35763 pigs
It is added to No. 65638 pigs in the corresponding livestock identity set of behavioural environment data of instruction 56384 lactation of sow.
Aforesaid plurality of behavioural environment data and livestock identity set corresponding with each behavioural environment data are formed
Livestock habit data.
The acquisition method of according to embodiments of the present invention one livestock habit information, by using including livestock gather image and
The livestock life history data of its behavioural environment data, obtain the identity number of the livestock in each livestock collection image respectively
According to, and the identity data is clustered according to the behavioural environment data, obtain and each behavioural environment
The corresponding livestock identity set of data, to obtain livestock habit data.These livestock habit data can be used for such as livestock
The various intelligent livestock managements such as identification, livestock track, livestock is traced to the source.
Embodiment two
Fig. 2 is the flow chart for the livestock personal identification method for showing according to embodiments of the present invention two.
With reference to Fig. 2, in step S210, the current behavior environmental data of livestock to be identified and image to be tested are obtained.
The image to be tested of the livestock to be identified can be gathered by the camera device set in the feeding environment of livestock to be identified,
And the current behavior environmental data of livestock to be identified is correspondingly marked with image to be tested, can also go out work as from image recognition to be tested
Move ahead as environmental data.In the step, obtain the current behavior environmental data of the livestock to be identified obtained by aforementioned processing with
Image to be tested, is handled, i.e. step S220~S240 with carrying out follow-up identification.
As it was previously stated, current behavior environmental data includes the behavioral data of livestock to be identified and environment number corresponding with behavior
According to.Behavioral data may include to represent lactation, food, sleep, plays, draining, the data of the behavior such as social activity, and environmental data may include
Represent stable breeding subregion, the data of the information such as position, time occur, but be not limited to aforementioned data.
In step S220, according to the image to be tested and livestock database, determine that the owner identification of the livestock to be identified is known
Other result.
As it was previously stated, can be and each with being included in livestock database by the way that image to be tested is handled and analyzed
The identity characteristic data of livestock are compared, and to identify the identity of livestock to be identified, determine the owner identification identification of livestock to be identified
As a result.
The owner identification recognition result includes at least the identity data for the livestock identified or multiple domestic animals to be selected
The identity data of poultry, it can also include other data for being used to indicate identification accuracy.
For example, being compared by the characteristic of image to be tested with the identity characteristic data in livestock database, obtain
The information of preferable 3 livestocks of comparison result, then owner identification recognition result may include the identity data of this 3 livestocks.
In step S230, according to the current behavior environmental data and livestock habit data, the livestock to be identified is determined
Identification auxiliary information, the livestock habit data include multiple livestock identity set, each livestock identity
Set includes at least one livestock identity data corresponding with behavioural environment.
As it was previously stated, livestock identity corresponding with each behavioural environment data can be obtained according to livestock life history data
Logo collection is as livestock habit data.In the step, by the current behavior environmental data of livestock to be identified and livestock habit number
Behavioural environment data in are matched, and obtain the corresponding livestock identity collection of behavioural environment data that matching obtains
Close.Hereafter, the identification auxiliary information of livestock to be identified can according to matching result, be obtained.For example, it is assumed that current behavior environment
Data are indicated by 56384 lactation of sow, according to the livestock habit data previously collected, get its corresponding No. 35763 pigs
With the identification auxiliary information of No. 65638 pigs.
As can be seen that since the livestock with certain life habit usually has multiple, and livestock habit is not used to
Directly determine the identity of livestock, therefore the current behavior environmental data with livestock to be identified for the processing acquisition for passing through step S230
Corresponding livestock identity data, only can be as the auxiliary information of identification, for example, foregoing available for further confirming that
Owner identification recognition result is corrected foregoing owner identification recognition result.
Similarly, which includes at least the one or more livestock identity to be selected matched
Data, it can also include other data for being used to indicate identification accuracy.
It is appreciated that can sequentially or backward perform step S220 and step S230, or be performed in parallel this two
Step.
In step S240, according to the owner identification recognition result and the identification auxiliary information, determine described to wait to know
The identity of other livestock.
Specifically, can be determined using identification auxiliary information as supplementary means or evidence according to owner identification recognition result
The identity of livestock to be identified.If for example, by the processing of step S220, the main body of milk cow AA, milk cow BB and milk cow CC are obtained
Part recognition result, and by the processing of step S230, milk cow CC, milk cow DD, the identification auxiliary information of milk cow EE are obtained, then
It can determine that livestock to be identified is milk cow CC in step S240.Thus, by the life habit of milk cow, confirm currently by sow
The identity of the milk cow of 56384 lactations.
Being difficult to obtain quality the image to be tested of requirement is fully achieved (such as livestock is persistently bowed, face is not taken the photograph on livestock head
As device) in the case of, the livestock habit number that the current behavior environmental data of livestock to be identified can be utilized and previously collected
According to the identification for livestock to be identified provides auxiliary, so as to improve the accuracy of livestock identification.
According to embodiments of the present invention two livestock personal identification method, according to the image to be tested and livestock number of livestock to be identified
According to storehouse, the owner identification recognition result of the livestock to be identified is determined, according to the current behavior environmental data of livestock to be identified and domestic animal
Habit data are raiseeed, determine the identification auxiliary information of livestock to be identified, and according to the owner identification recognition result and described
Identification auxiliary information, determines the identity of the livestock to be identified.Thus, the identity obtained using the livestock habit of livestock is known
Other auxiliary information carries out exact identity identification as supplementary means or evidence to livestock to be identified.Due to livestock continuously active
Or posture not face camera device, and in the case of the image to be tested of high quality can not be obtained, can be the knowledge of livestock to be identified
Indescribably for auxiliary, so as to improve the accuracy of livestock identification.
Embodiment three
A kind of optional embodiment according to the present invention, the data of foregoing owner identification recognition result include at least the first identity
Mark data, the data of identification auxiliary information include at least the second identity data.Here, the first identity data
It is livestock identity data with the second identity data.
Correspondingly, according to a kind of exemplary process of step S240, if the owner identification recognition result and the identity
There are matched tiers e'tat mark data between identification auxiliary information, then according to determining the tiers e'tat mark data
The identity of livestock to be identified.That is, according to identification auxiliary information, some that step S220 is identified can be identified through
Livestock meets its common life habit, so as to confirm that livestock to be identified is the livestock body that tiers e'tat mark data indicates
Part.
For example, owner identification recognition result indicates that livestock to be identified is livestock FF, GG or HH, and aid in believing according to identification
Breath, the current behavior environment of livestock HH meets its life habit, therefore the identity of livestock to be identified is determined as livestock HH.
On the other hand, if there is no matched between the owner identification recognition result and the identification auxiliary information
Tiers e'tat mark data, then can determine the identity of the livestock to be identified according to owner identification recognition result.
Aforementioned exemplary is returned, the identity of livestock to be identified can be determined as to any one in livestock FF, GG and HH.
Example IV
According to an alternate embodiment of the invention, the data of foregoing owner identification recognition result include at least the first body
Part mark data and its identification accuracy information, the data of identification auxiliary information include at least the second identity number
According to.Here, identification accuracy information be the first identity data prediction accuracy data, the prediction accuracy data
Can be prediction probability value, forecast confidence value etc..
The data of owner identification recognition result may include that the one or more the first identity datas and its identification are accurate
Spend information.
Correspondingly, step S240 may include the operation of following 3 identity for being used to determine livestock to be identified.It may be noted that
Association without obvious order between this 4 operations, and accuracy requirement that can be according to identification or functional requirement, determine to hold
One or more of this 4 operations of row, or can also carry out other applicable behaviour for being used to determine the identity of livestock to be identified
Make.
1st, it is the same, if there are the matched 3rd between the owner identification recognition result and the identification auxiliary information
Identity data, then determine the identity of the livestock to be identified according to the tiers e'tat mark data.
If the 2nd, there are matched tiers e'tat between the owner identification recognition result and the identification auxiliary information
Mark data, and the identification accuracy information of the tiers e'tat mark data exceedes predetermined recognition accuracy threshold
Value, then determine the identity of the livestock to be identified according to the tiers e'tat mark data.
If that is, between owner identification recognition result and the identification auxiliary information, there are common livestock
(corresponding with tiers e'tat mark data), and the prediction accuracy of tiers e'tat mark data reaches expected, then will can wait to know
The identity of other livestock is determined as the corresponding livestock identity of tiers e'tat mark data, and the livestock identity thus identified is compared with subject to
Really.
3rd, it is the same, if there is no matched the between the owner identification recognition result and the identification auxiliary information
Three identity datas, then determine the identity of the livestock to be identified according to the owner identification recognition result.
If the 4th, the identification accuracy information is below predetermined recognition accuracy lower limit, it is determined that Wu Fashi
The identity of not described livestock to be identified, or determine according to the identification auxiliary information possibility body of the livestock to be identified
Part.
That is, go out the identity of livestock to be identified according to image None- identified to be tested, it may be determined that treated described in None- identified
Identify the identity of livestock；Alternatively, go out the identity of livestock to be identified according to image None- identified to be tested, it is right in indivedual investigation applications
Identification it is of less demanding in the case of, the possibility of the livestock to be identified can be determined according to the identification auxiliary information
Identity, as with reference to data.
Embodiment five
Fig. 3 is a kind of flow chart for the exemplary process for showing the step S220 in Fig. 2.
With reference to Fig. 3, in step S221, the characteristic to be tested of livestock to be identified as described in the image acquisition to be tested.
Can be by any applicable image processing techniques, from the characteristic to be tested of livestock to be identified described in image acquisition to be tested
According to for example, the character shape data at each position of livestock to be identified, color characteristic data, textural characteristics data etc..
A kind of optional embodiment according to the present invention, can pass through the nerve net for image characteristics extraction of training in advance
Network model, from the characteristic to be tested of livestock to be identified described in image acquisition to be tested.The characteristic to be tested obtained may include table
The feature vector of each external appearance characteristic of livestock is levied, finer characteristic is obtained in a manner of by machine learning.
In step S223, the reference of each archive livestock in the characteristic to be tested and livestock database is calculated respectively
Characteristic similarity value between characteristic.
Present general inventive concept according to the present invention, is each archive when filing for each livestock in livestock database
Livestock gathers archival image, and characterizes the reference feature data of its external appearance characteristic to achieve livestock generation, such as achieves livestock
The character shape data at each position, color characteristic data, textural characteristics data etc., or characterization achieve each appearance of livestock
The feature vector of feature.Hereafter, the essential information for achieving livestock, archival image, reference feature data etc. are stored in livestock number
According in storehouse.
Specifically, in the step, each archive livestock in the characteristic to be tested and livestock database is calculated respectively
Reference feature data between characteristic similarity value.For example, can by calculate the feature vector of characteristic to be tested with it is each
Euclidean distance or cosine similarity between the feature vector of reference feature data etc., obtain characteristic similarity between the two
Value, to determine which characteristic to be tested can achieve the reference feature Data Matching of livestock with.
In step S225, the highest one or more identity datas for achieving livestock of the characteristic similarity value calculated are chosen
And corresponding characteristic similarity value is as first identity data and its identification accuracy information.
Due to being usually easier to identify livestock by face feature, alternatively, the characteristic to be tested and reference
Characteristic is the face feature data of the livestock to be identified, for example, with face is wide, face is high, eye distance, nose length, ose breadth, mouth are long,
The corresponding feature vector of the features such as nozzle type, so as to be more advantageous to that the characteristic of livestock to be identified is compared and then carries out
Identification.Correspondingly, image to be tested and foregoing collection image can be the face image of livestock.
Optionally, in addition, before step S223 is performed, if it is determined that the livestock to be identified described in the image to be tested
Posture do not meet predetermined posture condition (for example, not just facing to camera device), then by the owner identification recognition result
In identification accuracy information be set below the recognition accuracy lower limit.That is, image to be tested is not met pair
Livestock carries out the requirement of identification, then owner identification recognition result is set to invalid.
It may be noted that embodiment five only provides a kind of exemplary process of step S220, other applicable domestic animals also can be used
Poultry identification performs the processing of the step, and is not limited to the exemplary process.
, can be by each in the characteristic to be tested and livestock database by livestock to be identified by the processing of embodiment five
The mode that a reference feature data for achieving livestock are compared, to determine the owner identification recognition result of livestock to be identified, so that
Identification is carried out to livestock to be identified as precisely as possible.
Embodiment six
Fig. 4 is a kind of flow chart for the exemplary process for showing the step S230 in Fig. 2.
With reference to Fig. 4, in step S231, according to the current behavior environmental data of livestock to be identified and foregoing livestock habit number
According to obtaining matched livestock identity set.
As it was previously stated, according to the acquisition method of the livestock habit information of embodiment one, livestock habit data, the domestic animal have been obtained
Raiseeing habit data includes multiple alternative livestock identity set corresponding with multiple behavioural environments.
In the step, according to the behavioural environment number in the current behavior environmental data of livestock to be identified and livestock habit data
According to being matched, the livestock identity set matched is obtained.By the processing of the step, it can obtain and be practised with similar life
The livestock information of property.
In step S233, according to the current behavior environmental data and the behavioural environment data of current recognized livestock, obtain
Take the identity data with the matched current recognized livestock of the current behavior environmental data, and from matched livestock body
The identity data of the matched current recognized livestock is removed in part logo collection.
If here, persistently carrying out identification to bull livestock, using the data for having identified livestock, obtain current
Identify the behavioural environment data of livestock, and according to the behavioural environment data of current recognized livestock to the livestock body that matches
Part logo collection is screened.For example, the identity data of current recognized livestock in livestock identity set is removed.
It is in step S235, the livestock identity set obtained by step S233 processing is auxiliary as the identification
Supplementary information.
It may be noted that embodiment six only provides a kind of exemplary process of step S230, other applicable places also can be used
Reason method performs the processing of the step, and is not limited to the exemplary process.
By the processing of embodiment six, according to livestock habit data and the information for the livestock identified, generation will be treated
Identify the identification auxiliary information of livestock, the identification of livestock to be identified is performed for auxiliary.
Embodiment seven
Fig. 5 is the flow chart for the livestock querying method for showing according to embodiments of the present invention seven.
With reference to Fig. 5, in step S510, the information of livestock to be checked is obtained.
The information of livestock to be checked can be numbering, mark, title of livestock to be checked etc..
In step S520, according to foregoing livestock habit data and the information of livestock to be checked, the row of the livestock to be checked is obtained
For environmental data.
By the way that the information of livestock to be checked is matched with foregoing livestock habit data, the life for characterizing livestock to be checked can be obtained
The behavioural environment data of habit living.
In step S530, according to the behavioural environment data got, determine the current behavior of the livestock to be checked and
Position, according to the behavior and position, to search livestock to be checked.
According to embodiments of the present invention seven livestock querying method, livestock habit data and livestock to be checked by foregoing collection
Information, obtain the behavioural environment data of livestock to be checked, further according to the behavioural environment data got, determine described to be checked
The current behavior of livestock and position, to search livestock to be checked according to the behavior and position.Thus, can be by the livestock of livestock to be checked
Habit data pointedly search livestock to be checked, and carry out livestock tracking as auxiliary.
Embodiment eight
Fig. 6 is the logic diagram for the livestock identity recognition device for showing according to embodiments of the present invention eight.
With reference to Fig. 6, according to embodiments of the present invention eight livestock identity recognition device includes data acquisition module 610, main body
Part determining module 620, auxiliary information determining module 630 and identification module 640.
Data acquisition module 610 is used to obtain the current behavior environmental data of livestock to be identified and image to be tested.
Owner identification determining module 620 is used for the image to be tested and livestock database obtained according to data acquisition module 610, really
The owner identification recognition result of the fixed livestock to be identified.
Auxiliary information determining module 630 is used for current behavior environmental data and the domestic animal obtained according to data acquisition module 610
Habit data are raiseeed, determine the identification auxiliary information of the livestock to be identified, the livestock habit data include multiple livestocks
Identity set, each livestock identity set include at least one livestock identity corresponding with behavioural environment
Data.
Identification module 640 is used for the owner identification recognition result determined according to owner identification determining module 620 and auxiliary is believed
The definite identification auxiliary information of determining module 630 is ceased, determines the identity of the livestock to be identified.
The livestock identity recognition device of the present embodiment is used for realization in preceding method embodiment corresponding livestock identification
Method, and the beneficial effect with corresponding embodiment of the method, details are not described herein.
Embodiment nine
The embodiment of the present invention eight provides a kind of computer-readable recording medium, is stored thereon with computer program instructions, its
In, the livestock personal identification method described in two~embodiment of previous embodiment six is realized in described program instruction when being executed by processor
The step of, and the beneficial effect with corresponding embodiment, details are not described herein.
The embodiment of the present invention eight also provides a kind of computer program, it includes computer program instructions, wherein, the journey
The step of sequence instruction realizes the livestock personal identification method described in two~embodiment of previous embodiment six when being executed by processor, and
Beneficial effect with corresponding embodiment, details are not described herein.
The embodiment of the present invention eight also provides a kind of computer program product, for storing computer-readable instruction, the finger
Order is performed so that computer performs the livestock personal identification method described in any of the above-described feasible implementation.
Alternatively, the computer program product is specially computer-readable storage medium, in another optional embodiment,
The computer program product is specially software product, such as SDK etc..
Embodiment ten
Fig. 7 is the structure diagram for the electronic equipment for showing according to embodiments of the present invention ten.
An embodiment of the present invention provides a kind of electronic equipment, such as can be mobile terminal, personal computer (PC), tablet
Computer, server etc..Below with reference to Fig. 7, it illustrates suitable for for realizing the terminal device of the embodiment of the present invention or server
Electronic equipment 700 structure diagram.
As shown in fig. 7, electronic equipment 700 includes one or more processors, communication device etc., one or more of places
Manage device for example：One or more central processing unit (CPU) 701, and/or one or more image processors (GPU) 713 etc.,
Processor can according to the executable instruction being stored in read-only storage (ROM) 702 or from storage part 708 be loaded into
Machine accesses the executable instruction in memory (RAM) 703 and performs various appropriate actions and processing.Communication device includes communication
Component 712 and communication interface 709.Wherein, communication component 712 may include but be not limited to network interface card, and the network interface card may include but unlimited
In IB (Infiniband) network interface card, communication interface 709 includes the communication of the network interface card of LAN card, modem etc.
Interface, communication interface 709 perform communication process via the network of such as internet.
Processor can communicate to perform executable instruction with read-only storage 702 and/or random access storage device 703,
It is connected by bus 704 with communication component 712 and is communicated through communication component 712 with other target devices, thereby completing the present invention
The corresponding operation of any one method that embodiment provides, for example, obtaining the current behavior environmental data of livestock to be identified and to be tested
Image；According to the image to be tested and livestock database, the owner identification recognition result of the livestock to be identified is determined；According to described
Current behavior environmental data and livestock habit data, determine the identification auxiliary information of the livestock to be identified, the livestock
Habit data include multiple livestock identity set, and each livestock identity set includes corresponding with behavioural environment
At least one livestock identity data；According to the owner identification recognition result and the identification auxiliary information, institute is determined
State the identity of livestock to be identified.
In a kind of optional embodiment, the data of the owner identification recognition result include at least the first identity number
According to the data of the identification auxiliary information include at least the second identity data.
In a kind of optional embodiment, executable instruction is used for so that processor further performs following operation：Such as
There are matched tiers e'tat mark data between owner identification recognition result described in fruit and the identification auxiliary information, then root
The identity of the livestock to be identified is determined according to the tiers e'tat mark data.
In a kind of optional embodiment, the data of the owner identification recognition result further include and each first identity mark
Know the corresponding identification accuracy information of data, the data of the identification auxiliary information further include and each second
Identity data.
In a kind of optional embodiment, executable instruction is used for so that processor further performs following operation：Such as
There are matched tiers e'tat mark data between owner identification recognition result described in fruit and the identification auxiliary information, then root
The identity of the livestock to be identified is determined according to the tiers e'tat mark data；If the owner identification recognition result and the body
There are matched tiers e'tat mark data between part identification auxiliary information, and the identity of the tiers e'tat mark data is known
Other accuracy information exceedes predetermined recognition accuracy threshold value, then is determined according to the tiers e'tat mark data described to be identified
The identity of livestock；And/or if between the owner identification recognition result and the identification auxiliary information there is no
The tiers e'tat mark data matched somebody with somebody, then determine the identity of the livestock to be identified according to the owner identification recognition result；And/or
Person, if the identification accuracy information is below predetermined recognition accuracy lower limit, it is determined that described in None- identified
The identity of livestock to be identified, or determine according to the identification auxiliary information possibility identity of the livestock to be identified.
In a kind of optional embodiment, executable instruction is used for so that processor further performs following operation：By
The characteristic to be tested of livestock to be identified described in the image acquisition to be tested；The characteristic to be tested and livestock number are calculated respectively
According to the characteristic similarity value between the reference feature data of each archive livestock in storehouse；Choose the characteristic similarity value calculated
Highest one or more identity datas for achieving livestock and corresponding characteristic similarity value are as first identity
Data and its identification accuracy information.
In a kind of optional embodiment, executable instruction is used for so that processor further performs following operation：Such as
Fruit posture of livestock to be identified described in the image to be tested does not meet predetermined posture condition, then identifies the owner identification
As a result the identification accuracy information in is set below the recognition accuracy lower limit.
In a kind of optional embodiment, executable instruction is used for so that processor further performs following operation：Root
According to the current behavior environmental data and the livestock habit data, matched livestock identity set is obtained；According to described
Current behavior environmental data and the behavioural environment data of current recognized livestock, acquisition are matched with the current behavior environmental data
Current recognized livestock identity data, and remove from matched livestock identity set described matched work as
The preceding identity data for having identified livestock；Using by going the livestock identity set of division operation auxiliary as the identification
Supplementary information.
In a kind of optional embodiment, the characteristic to be tested and reference feature data are the domestic animal to be identified
The face feature data of poultry.
In a kind of optional embodiment, the current behavior environmental data includes current time segment data, livestock row
For data and corresponding environmental data.
In addition, in RAM 703, various programs and data needed for device operation can be also stored with.CPU 701、ROM
702 and RAM 703 is connected with each other by bus 704.In the case where there is RAM 703, ROM 702 is optional module.RAM
703 storage executable instructions, or executable instruction is operationally write into ROM 702, executable instruction holds processor 701
The corresponding operation of the above-mentioned communication means of row.Input/output (I/O) interface 705 is also connected to bus 704.Communication component 712 can be with
It is integrally disposed, it may be set to be with multiple submodule (such as multiple IB network interface cards), and in bus link.
I/O interfaces 705 are connected to lower component：Importation 706 including keyboard, mouse etc.；Penetrated including such as cathode
The output par, c 707 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 708 including hard disk etc.；
And the communication interface 709 of the network interface card including LAN card, modem etc..Driver 710 is also according to needing to connect
It is connected to I/O interfaces 705.Detachable media 711, such as disk, CD, magneto-optic disk, semiconductor memory etc., pacify as needed
On driver 710, in order to which the computer program read from it is mounted into storage part 708 as needed.
It should be noted that framework as shown in Figure 7 is only a kind of optional implementation, can during concrete practice
The component count amount and type of above-mentioned Fig. 7 are made choice, deleted, increased or replaced according to being actually needed；In difference in functionality component
In setting, the implementation such as separately positioned or integrally disposed can be also used, such as GPU and CPU separate setting or can be by GPU
It is integrated on CPU, communication component 712 is separable to be set, can also be integrally disposed on CPU or GPU, etc..These are interchangeable
Embodiment each falls within protection scope of the present invention.
Especially, according to embodiments of the present invention, it is soft to may be implemented as computer for the process above with reference to flow chart description
Part program.For example, the embodiment of the present invention includes a kind of computer program product, it includes being tangibly embodied in machine readable media
On computer program, computer program includes the program code for being used for the method shown in execution flow chart, and program code can wrap
The corresponding instruction of corresponding execution method and step provided in an embodiment of the present invention is included, for example, for obtaining the current of livestock to be identified
The executable code of behavioural environment data and image to be tested；For according to the image to be tested and livestock database, determining described
The executable code of the owner identification recognition result of livestock to be identified；For according to the current behavior environmental data and livestock habit
Data, determine the executable code of the identification auxiliary information of the livestock to be identified, and the livestock habit data include more
A livestock identity set, each livestock identity set include at least one livestock body corresponding with behavioural environment
Part mark data；For according to the owner identification recognition result and the identification auxiliary information, determining the domestic animal to be identified
The executable code of the identity of poultry.In such embodiments, the computer program can by communication device from network quilt
Download and install, and/or be mounted from detachable media 711.Held in the computer program by central processing unit (CPU) 701
During row, the above-mentioned function of being limited in the method for the embodiment of the present invention is performed.
The electronic equipment that the embodiment of the present invention ten provides, according to the image to be tested and livestock database of livestock to be identified, really
The owner identification recognition result of the fixed livestock to be identified, according to the current behavior environmental data of livestock to be identified and livestock habit number
According to, determine the identification auxiliary information of livestock to be identified, and according to the owner identification recognition result and the identification
Auxiliary information, determines the identity of the livestock to be identified.Thus, the identification obtained using the livestock habit of livestock aids in letter
Breath is used as supplementary means or evidence, and exact identity identification is carried out to livestock to be identified.Due to livestock continuously active or posture not
Face camera device, and in the case of the image to be tested of high quality can not be obtained, it can be provided for the identification of livestock to be identified auxiliary
Help, so as to improve the accuracy of livestock identification.
It may be noted that according to the needs of implementation, all parts/step described in this application can be split as more multi-section
The part operation of two or more components/steps or components/steps, can be also combined into new components/steps by part/step,
To realize the purpose of the embodiment of the present invention.
In one or more optional embodiments, the embodiment of the present invention additionally provides a kind of computer program program production
Product, for storing computer-readable instruction, described instruction is performed so that computer is performed described in any of the above-described embodiment
Livestock personal identification method.
The computer program product can be realized especially by hardware, software or its mode combined.In an alternative embodiment
In son, the computer program product is embodied as computer-readable storage medium, in another optional example, the computer
Program product is embodied as software product, such as software development kit (Software Development Kit, SDK) etc..
In one or more optional embodiments, the embodiment of the present invention additionally provides another livestock personal identification method
And its corresponding device and electronic equipment, computer-readable storage medium, computer program and computer program product, wherein, should
Method includes：First device sends livestock identification instruction to second device, which causes second device to perform above-mentioned
Livestock personal identification method in one possible embodiment；First device receives the post processing result images that second device is sent.
In certain embodiments, livestock identification instruction can be specially call instruction, and first device can pass through
The mode of calling indicates that second device performs livestock identification, and accordingly, in response to call instruction is received, second device can
To perform step and/or flow in any embodiment in above-mentioned livestock personal identification method.
It is to be understood that the term such as " first ", " second " in the embodiment of the present invention is just for the sake of distinguishing, and it is not construed as
Restriction to the embodiment of the present invention.
It should also be understood that description of the present invention to each embodiment highlights the difference between each embodiment, its
Same or similar part can be referred to mutually, for sake of simplicity, no longer repeating one by one.
Methods and apparatus of the present invention, equipment may be achieved in many ways.For example, software, hardware, firmware can be passed through
Or any combinations of software, hardware, firmware realize the method and apparatus of the embodiment of the present invention, equipment.Step for method
Merely to illustrate, the step of method of the embodiment of the present invention, is not limited to described in detail above suitable for rapid said sequence
Sequence, unless specifically stated otherwise.In addition, in certain embodiments, the present invention can be also embodied as being recorded in record Jie
Program in matter, these programs include being used for realization machine readable instructions according to the method for the embodiment of the present invention.Thus, this hair
Bright also covering storage is used for the recording medium for performing the program of the method according to the invention.
The description of the embodiment of the present invention in order to example and description for the sake of and provide, and be not exhaustively or will
The present invention is limited to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Choosing
It is to more preferably illustrate the principle of the present invention and practical application to select and describe embodiment, and makes those of ordinary skill in the art
It will be appreciated that the present invention is so as to design the various embodiments with various modifications suitable for special-purpose.
Claims (14)
1. a kind of livestock personal identification method, including：
Obtain the current behavior environmental data of livestock to be identified and image to be tested；
According to the image to be tested and livestock database, the owner identification recognition result of the livestock to be identified is determined；
According to the current behavior environmental data and livestock habit data, determine that the identification auxiliary of the livestock to be identified is believed
Breath, the livestock habit data include multiple livestock identity set, and each livestock identity set includes and behavior ring
The corresponding at least one livestock identity data in border；
According to the owner identification recognition result and the identification auxiliary information, the identity of the livestock to be identified is determined.
2. according to the method described in claim 1, wherein, the data of the owner identification recognition result include at least the first identity mark
Know data, the data of the identification auxiliary information include at least the second identity data.
It is 3. described auxiliary according to the owner identification recognition result and the identification according to the method described in claim 2, wherein
Supplementary information, determines the identity of the livestock to be identified, including：
If there are matched tiers e'tat between the owner identification recognition result and the identification auxiliary information to identify number
According to then determining the identity of the livestock to be identified according to the tiers e'tat mark data.
4. according to the method described in claim 2, wherein, the data of the owner identification recognition result further include and each first body
The corresponding identification accuracy information of part mark data, the data of the identification auxiliary information further include with it is each
Second identity data.
It is 5. described auxiliary according to the owner identification recognition result and the identification according to the method described in claim 4, wherein
Supplementary information, determines the identity of the livestock to be identified, including：
If there are matched tiers e'tat between the owner identification recognition result and the identification auxiliary information to identify number
According to then determining the identity of the livestock to be identified according to the tiers e'tat mark data；If the owner identification recognition result
There are matched tiers e'tat mark data between the identification auxiliary information, and the tiers e'tat mark data
Identification accuracy information exceed predetermined recognition accuracy threshold value, then institute is determined according to the tiers e'tat mark data
State the identity of livestock to be identified；And/or
To be identified if there is no matched tiers e'tat between the owner identification recognition result and the identification auxiliary information
Data, then determine the identity of the livestock to be identified according to the owner identification recognition result；And/or
If the identification accuracy information is below predetermined recognition accuracy lower limit, it is determined that described in None- identified
The identity of livestock to be identified, or determine according to the identification auxiliary information possibility identity of the livestock to be identified.
6. the method according to any one of claim 4~5, wherein, it is described according to the image to be tested and livestock data
Storehouse, determines the owner identification recognition result of the livestock to be identified, including：
The characteristic to be tested of livestock to be identified as described in the image acquisition to be tested；
Between the reference feature data for calculating each archive livestock in the characteristic to be tested and livestock database respectively
Characteristic similarity value；
Choose the highest one or more identity datas for achieving livestock of the characteristic similarity value calculated and corresponding feature
Similarity value is as first identity data and its identification accuracy information.
7. it is described according to the image to be tested and livestock database according to the method described in claim 6, wherein, determine described
The owner identification recognition result of livestock to be identified, further includes：
If the posture of livestock to be identified does not meet predetermined posture condition described in the image to be tested, by the main body
Identification accuracy information in part recognition result is set below the recognition accuracy lower limit.
8. the method according to any one of claim 4~5, wherein, it is described according to the current behavior environmental data and
Livestock habit data, determine the identification auxiliary information of the livestock to be identified, including：
According to the current behavior environmental data and the livestock habit data, matched livestock identity set is obtained；
According to the current behavior environmental data and the behavioural environment data of current recognized livestock, obtain and the current behavior
The identity data of the matched current recognized livestock of environmental data, and removed from matched livestock identity set
The identity data of the matched current recognized livestock；
Using the livestock identity set by going division operation as the identification auxiliary information.
9. the method according to any one of claim 4~6, wherein, the characteristic to be tested and reference feature data
It is the face feature data of the livestock to be identified, and/or,
The current behavior environmental data includes current time segment data, livestock behavioral data and corresponding environmental data.
10. a kind of acquisition method of livestock habit information, including：
Livestock life history data are obtained, the livestock life history data include livestock collection image and its behavioural environment number
According to；
Image is gathered according to the livestock, obtains corresponding livestock identity data respectively；
The identity data is clustered according to the behavioural environment data, is obtained and each behavioural environment data
Respective livestock identity set is as livestock habit data.
11. a kind of livestock querying method, including：
Obtain the information of livestock to be checked；
According to livestock habit data and the information of the livestock to be checked, the behavioural environment data of the livestock to be checked are obtained, it is described
Livestock habit data include multiple livestock identity set, and each livestock identity set includes right respectively with behavioural environment
At least one livestock identity data answered；
According to the behavioural environment data got, the current behavior of the livestock to be checked and position are determined.
12. a kind of livestock identity recognition device, including：
Data acquisition module, for the current behavior environmental data for obtaining livestock to be identified and image to be tested；
Owner identification determining module, for the image to be tested and livestock database obtained according to the data acquisition module, determines institute
State the owner identification recognition result of livestock to be identified；
Auxiliary information determining module, for the current behavior environmental data and livestock habit obtained according to the data acquisition module
Data, determine the identification auxiliary information of the livestock to be identified, and the livestock habit data include multiple livestock identity marks
Know set, each livestock identity set includes at least one livestock identity data corresponding with behavioural environment；
Identification module, for the owner identification recognition result determined according to the owner identification determining module and the auxiliary information
The identification auxiliary information that determining module determines, determines the identity of the livestock to be identified.
13. a kind of electronic equipment, including：Processor, memory, communication device and communication bus, the processor, the storage
Device and the communication device complete mutual communication by the communication bus；
The memory is used to store an at least executable instruction, and the executable instruction makes the processor perform right such as will
Seek the livestock personal identification method any one of 1~9.
14. a kind of computer-readable recording medium, is stored thereon with computer program instructions, wherein, described program instruction is located
Reason device realizes livestock personal identification method according to any one of claims 1 to 9 when performing.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710850793 | 2017-09-20 | ||
| CN201710850793X | 2017-09-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107992903A true CN107992903A (en) | 2018-05-04 |
Family
ID=62042605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711407625.XA Pending CN107992903A (en) | 2017-09-20 | 2017-12-22 | Livestock personal identification method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107992903A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255297A (en) * | 2018-08-06 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | animal state monitoring method, terminal device, storage medium and electronic equipment |
| CN109583400A (en) * | 2018-12-05 | 2019-04-05 | 成都牧云慧视科技有限公司 | One kind is registered automatically without intervention for livestock identity and knows method for distinguishing |
| CN109948458A (en) * | 2019-02-25 | 2019-06-28 | 广东智媒云图科技股份有限公司 | Pet personal identification method, device, equipment and storage medium based on noseprint |
| CN110378953A (en) * | 2019-07-17 | 2019-10-25 | 重庆市畜牧科学院 | A kind of method of spatial distribution behavior in intelligent recognition swinery circle |
| CN110399946A (en) * | 2019-07-23 | 2019-11-01 | 日立楼宇技术（广州）有限公司 | A kind of detection method of farm, device, equipment and storage medium |
| WO2020030054A1 (en) * | 2018-08-10 | 2020-02-13 | 京东数字科技控股有限公司 | Animal identification method and apparatus, medium and electronic device |
| CN110795987A (en) * | 2019-07-30 | 2020-02-14 | 重庆小富农康农业科技服务有限公司 | Pig face identification method and device |
| CN110929650A (en) * | 2019-11-25 | 2020-03-27 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying livestock and poultry |
| CN112541432A (en) * | 2020-12-11 | 2021-03-23 | 上海品览数据科技有限公司 | Video livestock identity authentication system and method based on deep learning |
| CN112655019A (en) * | 2018-06-25 | 2021-04-13 | 农场监测公司 | Monitoring livestock in an agricultural enclosure |
| CN117745036A (en) * | 2024-02-18 | 2024-03-22 | 四川金投科技股份有限公司 | Livestock information management method and system based on feature recognition and near field communication |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933049A (en) * | 2014-03-17 | 2015-09-23 | 华为技术有限公司 | Method and system for generating digital human |
| CN105976012A (en) * | 2016-05-17 | 2016-09-28 | 内蒙古牧野昕光信息技术有限公司 | Livestock identity recognition device and system |
| WO2017001538A1 (en) * | 2015-07-01 | 2017-01-05 | Viking Genetics Fmba | System and method for identification of individual animals based on images of the back |
| CN106856015A (en) * | 2016-12-20 | 2017-06-16 | 国网山东省电力公司东明县供电公司 | A kind of Work attendance method and device |
-
2017
- 2017-12-22 CN CN201711407625.XA patent/CN107992903A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933049A (en) * | 2014-03-17 | 2015-09-23 | 华为技术有限公司 | Method and system for generating digital human |
| WO2017001538A1 (en) * | 2015-07-01 | 2017-01-05 | Viking Genetics Fmba | System and method for identification of individual animals based on images of the back |
| CN105976012A (en) * | 2016-05-17 | 2016-09-28 | 内蒙古牧野昕光信息技术有限公司 | Livestock identity recognition device and system |
| CN106856015A (en) * | 2016-12-20 | 2017-06-16 | 国网山东省电力公司东明县供电公司 | A kind of Work attendance method and device |
Non-Patent Citations (1)
| Title |
|---|
| 吴迪: "智能环境下基于视听信息多层级融合的身份识别", 《中国博士学位论文全文数据库》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112655019A (en) * | 2018-06-25 | 2021-04-13 | 农场监测公司 | Monitoring livestock in an agricultural enclosure |
| CN109255297A (en) * | 2018-08-06 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | animal state monitoring method, terminal device, storage medium and electronic equipment |
| CN109255297B (en) * | 2018-08-06 | 2022-12-13 | 百度在线网络技术（北京）有限公司 | Animal state monitoring method, terminal device, storage medium and electronic device |
| WO2020030054A1 (en) * | 2018-08-10 | 2020-02-13 | 京东数字科技控股有限公司 | Animal identification method and apparatus, medium and electronic device |
| CN109583400A (en) * | 2018-12-05 | 2019-04-05 | 成都牧云慧视科技有限公司 | One kind is registered automatically without intervention for livestock identity and knows method for distinguishing |
| CN109948458A (en) * | 2019-02-25 | 2019-06-28 | 广东智媒云图科技股份有限公司 | Pet personal identification method, device, equipment and storage medium based on noseprint |
| CN110378953A (en) * | 2019-07-17 | 2019-10-25 | 重庆市畜牧科学院 | A kind of method of spatial distribution behavior in intelligent recognition swinery circle |
| CN110399946A (en) * | 2019-07-23 | 2019-11-01 | 日立楼宇技术（广州）有限公司 | A kind of detection method of farm, device, equipment and storage medium |
| CN110399946B (en) * | 2019-07-23 | 2023-05-26 | 日立楼宇技术（广州）有限公司 | Method, device, equipment and storage medium for detecting farm |
| CN110795987A (en) * | 2019-07-30 | 2020-02-14 | 重庆小富农康农业科技服务有限公司 | Pig face identification method and device |
| CN110795987B (en) * | 2019-07-30 | 2023-12-22 | 重庆渝通合数字科技有限公司 | Pig face recognition method and device |
| CN110929650A (en) * | 2019-11-25 | 2020-03-27 | 支付宝(杭州)信息技术有限公司 | Method and device for identifying livestock and poultry |
| CN112541432A (en) * | 2020-12-11 | 2021-03-23 | 上海品览数据科技有限公司 | Video livestock identity authentication system and method based on deep learning |
| CN117745036A (en) * | 2024-02-18 | 2024-03-22 | 四川金投科技股份有限公司 | Livestock information management method and system based on feature recognition and near field communication |
| CN117745036B (en) * | 2024-02-18 | 2024-04-30 | 四川金投科技股份有限公司 | Livestock information management method and system based on feature recognition and near field communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992903A (en) | Livestock personal identification method, device, storage medium and electronic equipment | |
| Chen et al. | Recognition of feeding behaviour of pigs and determination of feeding time of each pig by a video-based deep learning method | |
| Neethirajan | The role of sensors, big data and machine learning in modern animal farming | |
| CN110929650B (en) | Method and device for identifying livestock and feed identity, computing equipment and readable storage medium | |
| CN109255297A (en) | animal state monitoring method, terminal device, storage medium and electronic equipment | |
| WO2021104007A1 (en) | Method and device for animal state monitoring, electronic device, and storage medium | |
| CN107657459A (en) | Auth method, settlement of insurance claim method, source tracing method, storage medium and the electronic equipment of livestock | |
| Lodkaew et al. | CowXNet: An automated cow estrus detection system | |
| CN108229351B (en) | Animal breeding method, animal breeding device and electronic equipment | |
| US11568530B2 (en) | System and method to analyse an animal's image for market value determination | |
| WO2021243561A1 (en) | Behaviour identification apparatus and method | |
| WO2020078114A1 (en) | Animal labour identification method, apparatus, and device | |
| JP2019010004A (en) | Information processing system and program | |
| CN109285081A (en) | Raise confirmation method, Claims Resolution method, management method and the confirmation system of animal | |
| CN115830078A (en) | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium | |
| Gan et al. | Spatiotemporal graph convolutional network for automated detection and analysis of social behaviours among pre-weaning piglets | |
| Gao et al. | CNN-Bi-LSTM: A complex environment-oriented cattle behavior classification network based on the fusion of CNN and Bi-LSTM | |
| CN113615629A (en) | Aquaculture water quality monitoring method, terminal equipment and readable storage medium | |
| Yang et al. | Automated recognition and classification of cat pain through deep learning | |
| Rohan et al. | Application of deep learning for livestock behaviour recognition: A systematic literature review | |
| Praba et al. | Smart fish farming recommendation system using k-means algorithm | |
| CN113052114A (en) | Dead shrimp identification method, terminal device and readable storage medium | |
| Shreesha et al. | Fish Tracking and Continual Behavioral Pattern Clustering Using Novel Sillago Sihama Vid (SSVid) | |
| Souza et al. | Pig aggression classification using CNN, Transformers and Recurrent Networks | |
| Mluba et al. | Pattern Mining-Based Pig Behavior Analysis for Health and Welfare Monitoring |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180504 |
|
| RJ01 | Rejection of invention patent application after publication |