CN109255297A - animal state monitoring method, terminal device, storage medium and electronic equipment - Google Patents
animal state monitoring method, terminal device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109255297A CN109255297A CN201810887644.5A CN201810887644A CN109255297A CN 109255297 A CN109255297 A CN 109255297A CN 201810887644 A CN201810887644 A CN 201810887644A CN 109255297 A CN109255297 A CN 109255297A
- Authority
- CN
- China
- Prior art keywords
- animal
- video
- monitored
- virtual
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/446—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering using Haar-like filters, e.g. using integral image techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The present invention provides a kind of animal state monitoring method, terminal device, storage medium and electronic equipment.Animal state monitoring method provided by the invention, it include: the real video for obtaining animal to be monitored, and facial feature extraction is carried out to real video by preset neural network model, to obtain the corresponding facial image features of animal to be monitored, then the identity identification information of animal to be monitored is determined according to facial image features and default animal identification identification model, the corresponding status information of animal to be monitored is obtained further according to identity identification information and default animal state library, and the first virtual video is generated, finally by the first virtual video Overlapping display in real video.Animal state monitoring method provided by the invention, the status information is shown in the real video of animal to be monitored by way of augmented reality, so that poultry raiser can get the status information of every animal quickly and intuitively to improve the efficiency of management in large-scale plant that raises for animal population.
Description
Technical field
The present invention relates to technical field of computer vision more particularly to a kind of animal state monitoring method, terminal device, deposit
Storage media and electronic equipment.
Background technique
With the continuous development of livestock cultural technique, the scale trend of current livestock aquaculture is more and more obvious.And
It can only when user needs to monitor the related cultivation information such as health and fitness information, the feed information of the livestock of cultivation in animal husbandry field
By the way of manually monitoring.
In order to distinguish the difference between animal individual in existing feed lot, be usually all by animal (such as: pig, ox,
Sheep etc.) it wears ear tag or is subcutaneously implanted the mode of electronic mark and carry out identity marks.Especially quarantining to animal or
When immune processing, animal doctor would generally be identified the uniqueness of livestock using the form for wearing ear tag to livestock.But it is right
Livestock carries out ear tag wearing and mark, needs professional equipment, professional just to can be carried out, operating cost is higher.Moreover, livestock is worn
The ear tag worn has the problems such as certain repeatability, there is easily fraud, is easy to be lost, not easily passs through ear tag to accurately identify livestock
Uniqueness.
As it can be seen that poultry raiser is if necessary to carry out status inquiry to specific animal individual after carrying out mark to animal
When, then need first to obtain the identity information on ear tag, and carry out status inquiry using the identity information, to confirm each animal
The corresponding particular state of body, operating process is complicated, and inefficiency, needs to expend a large amount of man power and material, it is difficult to adapt to
The management of large-scale plant that raises.
Summary of the invention
The present invention provides a kind of animal state monitoring method, terminal device, storage medium and electronic equipment, efficient to realize
Ground is monitored the state of the animal in feed lot.
In a first aspect, the present invention provides a kind of animal state monitoring method, comprising:
The real video of animal to be monitored is obtained, and face is carried out to the real video by preset neural network model
Portion's feature extraction, to obtain the corresponding facial image features of the animal to be monitored, wherein include described in the reality video
The facial image information of animal to be monitored；
The identity of the animal to be monitored is determined according to the facial image features and default animal identification identification model
Identification information；
The corresponding state letter of the animal to be monitored is obtained according to the identity identification information and default animal state library
Breath, and the first virtual video is generated according to the state information；
By the first virtual video Overlapping display in the real video.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video, tool
Body includes:
Determine the first position of the corresponding facial image information of animal to be monitored described in the real video；
According to the first position by the first virtual video Overlapping display in the real video so that the void
Quasi- video indicates the particular state of the animal to be monitored.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video it
Afterwards, further includes:
The corresponding detailed status information of the status information is obtained according to the state expansion instruction of user's input, and according to institute
State detailed status information generate the second virtual video, wherein the status details include: the identity identification information and
Health status information；
Cancel and show first virtual video, and by the second virtual video Overlapping display in the real video
In.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video it
Afterwards, further includes:
Judge whether the animal to be monitored is health status according to the health status information；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if sentencing
Disconnected result be it is yes, then Overlapping display third virtual video, the third virtual video are used to characterize institute in the real video
Stating animal to be monitored is health status, if judging result is no, the 4th virtual video of Overlapping display in the real video,
4th virtual video is unhealthy status for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: vaccine inoculation status information.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video it
Afterwards, further includes:
Judge whether the animal to be monitored is to vaccinate according to the vaccine inoculation status information；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if sentencing
Disconnected result be it is yes, then the 4th virtual video of Overlapping display, the 4th virtual video are used to characterize institute in the real video
State animal to be monitored and injected the vaccine, if judging result be it is no, Overlapping display the 5th is virtual in the real video
Video, the 5th virtual video do not inject the vaccine for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: the current pricing information of animal.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video it
Afterwards, further includes:
Judge whether the animal to be monitored is that can sell with default pricing information according to the current pricing information of the animal
Object；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if sentencing
Disconnected result be it is yes, then the 6th virtual video of Overlapping display, the 6th virtual video are used to characterize institute in the real video
Stating animal to be monitored is that can sell animal, if judging result is no, the 7th virtual video of Overlapping display in the real video,
7th virtual video is that can not sell animal for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: Animal Sex information.
In a kind of possible design, it is described by the first virtual video Overlapping display in the real video it
Afterwards, further includes:
According to the Animal Sex information in the real video the corresponding virtual video content of Overlapping display, wherein
If the Animal Sex information is male, the 8th virtual video of Overlapping display in the real video, if the animality
Other information is female, then the 9th virtual video of Overlapping display in the real video, if the Animal Sex information is sterilization,
Then the tenth virtual video of Overlapping display in the real video.
In a kind of possible design, the facial image features include at least following one: eye feature, mouth are special
Sign, ear feature and nose feature.
Second aspect, the present invention also provides a kind of terminal devices, comprising:
Module is obtained, for obtaining the real video of animal to be monitored, and by preset neural network model to described
Real video carries out facial feature extraction, to obtain the corresponding facial image features of the animal to be monitored, wherein the reality
It include the facial image information of the animal to be monitored in video；
Identification module, it is described wait supervise for being determined according to the facial image features and default animal identification identification model
Survey the identity identification information of animal；
Generation module, for obtaining the animal to be monitored according to the identity identification information and default animal state library
Corresponding status information, and the first virtual video is generated according to the state information；
Display module is used for the first virtual video Overlapping display in the real video.
In a kind of possible design, the display module is specifically used for:
Determine the first position of the corresponding facial image information of animal to be monitored described in the real video；
According to the first position by the first virtual video Overlapping display in the real video so that the void
Quasi- video indicates the particular state of the animal to be monitored.
In a kind of possible design, the acquisition module, the state expansion instruction for being also used to be inputted according to user is obtained
The corresponding detailed status information of the status information, and the second virtual video is generated according to the detailed status information, wherein institute
Stating status details includes: the identity identification information and health status information；
The display module is also used to cancel display first virtual video, and second virtual video is superimposed
It is shown in the real video.
In a kind of possible design, the terminal device, further includes:
Judgment module, for judging whether the animal to be monitored is health status according to the health status information；
The display module, is also used to that Overlapping display is corresponding virtual in the real video according to the judging result
Video content, wherein if the determination result is YES, then Overlapping display third virtual video, the third in the real video
Virtual video is health status for characterizing the animal to be monitored, if judging result be it is no, it is folded in the real video
Add the 4th virtual video of display, the 4th virtual video is unhealthy status for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: vaccine inoculation status information.
In a kind of possible design, the terminal device, further includes:
Judgment module, for judging whether the animal to be monitored is injection epidemic disease according to the vaccine inoculation status information
Seedling；
The display module, for according to the judging result in the real video the corresponding virtual view of Overlapping display
Frequency content, wherein if the determination result is YES, then the 4th virtual video of Overlapping display in the real video, the described 4th is empty
Quasi- video has injected the vaccine for characterizing the animal to be monitored, if judging result be it is no, in the reality video
The 5th virtual video of Overlapping display, the 5th virtual video do not inject the vaccine for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: the current pricing information of animal.
In a kind of possible design, the terminal device, further includes:
Judgment module, for judging the animal to be monitored according to the current pricing information of the animal and default pricing information
It whether is that can sell animal；
The display module, for according to the judging result in the real video the corresponding virtual view of Overlapping display
Frequency content, wherein if the determination result is YES, then the 6th virtual video of Overlapping display in the real video, the described 6th is empty
Quasi- video for characterize the animal to be monitored be can sell animal, if judging result be it is no, be superimposed in the reality video
Show that the 7th virtual video, the 7th virtual video are that can not sell animal for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: Animal Sex information.
In a kind of possible design, the display module is also used to according to the Animal Sex information in the reality
The corresponding virtual video content of Overlapping display in video, wherein if the Animal Sex information is male, in the reality view
The 8th virtual video of Overlapping display in frequency, if the Animal Sex information is female, the Overlapping display in the real video
9th virtual video, if the Animal Sex information is sterilization, the tenth virtual video of Overlapping display in the real video.
In a kind of possible design, the facial image features include at least following one: eye feature, mouth are special
Sign, ear feature and nose feature.
The third aspect, the present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the journey
Any one possible animal state monitoring method in first aspect is realized when sequence is executed by processor.
Fourth aspect, the present invention also provides a kind of electronic equipment, comprising:
Camera, processor, memory and display；
The camera and the display are connected with the processor respectively；
The camera, for obtaining the real video of animal to be monitored；
The memory, for storing the executable instruction of the processor；
Wherein, be configured to execute any one in first aspect via the executable instruction is executed can for the processor
The animal state monitoring method of energy；
The display, for showing the real video and virtual video.
A kind of animal state monitoring method, device, storage medium and electronic equipment provided by the invention, by from getting
Animal to be monitored real video in extract facial image features, then pass through facial image features and preset animal identification
Identification model determines the corresponding identity identification information of the animal, moves followed by the identity identification information identified from default
The corresponding status information of the animal is obtained in object state repository, then by way of augmented reality by the status information show to
In the real video for monitoring animal, so that poultry raiser can quickly and intuitively get the status information of every animal, it is seen then that
The acquisition process operating process is complicated, high-efficient, is very suitable to the management in large-scale plant that raises for animal population.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the application scenario diagram of animal state monitoring method shown according to an exemplary embodiment；
Fig. 2 is the schematic diagram of interface display of terminal device in Fig. 1；
Fig. 3 is the application scenario diagram of the animal state monitoring method shown according to another exemplary embodiment；
Fig. 4 is the schematic diagram of interface display of terminal device in Fig. 3；
Fig. 5 is the flow chart of animal state monitoring method shown according to an exemplary embodiment；
Fig. 6 is the flow chart of the animal state monitoring method shown according to a further exemplary embodiment；
Fig. 7 is a kind of schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6；
Fig. 8 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6；
Fig. 9 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6；
Figure 10 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6；
Figure 11 is the structural schematic diagram of terminal device shown according to an exemplary embodiment；
Figure 12 is the structural schematic diagram of the terminal device shown according to another exemplary embodiment；
Figure 13 is the structural schematic diagram of present invention electronic equipment shown according to an exemplary embodiment.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the application scenario diagram of animal state monitoring method shown according to an exemplary embodiment, and Fig. 2 is in Fig. 1
The schematic diagram of interface display of terminal device.As Figure 1-Figure 2, animal state monitoring method provided in this embodiment is being applied
When, the real video of animal to be monitored is obtained by the camera on terminal device, wherein the terminal device can be intelligent hand
Machine, tablet computer, personal computer, AR glasses etc. have the electronics of real video image acquisition, data processing and display function
Equipment.Wherein, in the present embodiment can be using smart phone as terminal device, and application scenarios can be lifted for pig farm
Example.For example, raiser has known the health status information of every pig after checking UP to all live pigs in pig farm,
And the health and fitness information of every pig is entered into default animal state library.In the later period, raiser is in order in time to sick pig
Carry out drug therapy, so that it may obtain the real video of pig to be monitored by AR glasses, then pass through the processing built in AR glasses
Server of the device either with the communication connection of AR glasses carries out facial characteristics identification to the pig in real video, to obtain every
Identity identification information corresponding to pig determines whether the pig is sick pig further according to identity identification information.It, then can be with referring to Fig. 2
It is shown in by way of augmented reality on the screen of smart phone, such as " I am very healthy for display near the pig of health！"
Animated video, and near sick pig display " I am sick！" animated video so that poultry raiser can quickly and intuitively obtain
Get the health status of every pig.
Fig. 3 is the application scenario diagram of the animal state monitoring method shown according to another exemplary embodiment, and Fig. 4 is Fig. 3
The schematic diagram of interface display of middle terminal device.As Figure 3-Figure 4, it can also be set in the present embodiment using AR glasses as terminal
It is standby, and application scenarios can illustrate for pig farm.For example, raiser is checking it UP to all live pigs in pig farm
Afterwards, the health status information of every pig has been known, and the health and fitness information of every pig has been entered into default animal state library.Afterwards
Phase, raiser is in order in time to sick pig progress drug therapy, so that it may obtain pig to be monitored by wearing AR glasses
Real video, then the server by the processor built in AR glasses either with the communication connection of AR glasses is to real video
In pig carry out facial characteristics identification, so that identity identification information corresponding to every pig is obtained, further according to identity identification information
Determine whether the pig is sick pig.Referring to Fig. 4, the mode that may then pass through augmented reality is shown on the screen of AR glasses, example
" I am very healthy for display such as near the pig of health！" animated video, and near sick pig display " I am sick！" it is dynamic
Video is drawn, so that poultry raiser can quickly and intuitively get the health status of every pig.
Fig. 5 is the flow chart of animal state monitoring method shown according to an exemplary embodiment.As shown in figure 5, this reality
The animal state monitoring method of example offer is provided, comprising:
Step 101, the real video for obtaining animal to be monitored, and by preset neural network model to real video into
Row facial feature extraction, to obtain the corresponding facial image features of the animal to be monitored.
Specifically, the real video of animal to be monitored can be obtained by the camera on terminal device, and by default
Neural network model facial feature extraction is carried out to real video, it is special to obtain the corresponding face-image of the animal to be monitored
Sign, wherein include the facial image information of animal to be monitored in real video.
Wherein, any suitable achievable feature extraction can be for the above-mentioned neural network model for state-detection
Or the neural network of recongnition of objects, including but not limited to convolutional neural networks, enhancing learning neural network, confrontation nerve net
Generation network in network etc..The setting of specific structure can be fitted according to actual needs by those skilled in the art in neural network
Work as setting, such as the number of plies, the size of convolution kernel, port number of convolutional layer, the embodiment of the present invention to this with no restriction.
In a kind of optional embodiment, in the training process of neural network model, it can use containing to be monitored dynamic
The video sample data of the corresponding facial image features of object are trained neural network model.Wherein, animal to be monitored is corresponding
Facial image features can include but is not limited to: eye feature, mouth feature, ear feature and nose feature etc..
It, not only can be to including animal according to neural network model, mathematical model or algorithm in addition, in the embodiment of the present invention
Still image carry out characteristic extraction, can also to the dynamic video comprising animal face carry out behavioural analysis.
Step 102, the identity that animal to be monitored is determined according to facial image features and default animal identification identification model
Identification information.
Specifically, the facial characteristics that animal face can be studied by Eigenface recycles these characteristic quantities to establish
Animal face model finally obtains animal identification identification model.
It, can be by establishing the machine of animal face in order to improve the recognition accuracy of above-mentioned default animal identification identification model
Automatic recognition system obtains a large amount of pig face training sample from network, and sample is inputted above-mentioned default animal identification and identifies mould
Type is trained.It wherein, can be with for the machine automatic recognition system of the machine automatic recognition system of animal face, such as pig face
It is realized by the following method:
Firstly, it is necessary to define the facial characteristics of pig, the eyes, nose and mouth of pig can be extracted as being identified
Three facial image features.Here it can be studied using the method for Haar-like feature.By edge feature, linear character, in
Heart feature and diagonal line feature, are combined into feature templates.Wherein, there are white and two kinds of rectangles of black in feature templates, and define
The characteristic value of the template be white rectangle pixel and subtract black rectangle pixel and.And Haar characteristic value reflects the gray scale of image
Situation of change.Then again by changing the size and location of feature templates, exhaustion a large amount of feature can be gone out in image child window.
It image is arrived to each point is from the off formed by the sum of rectangular area pixel as the element of an array and be stored in memory
In, and the characteristic value of all child windows is calculated, it is hereby achieved that the feature of eye feature, mouth feature and nose feature
Vector.
Then, it for the machine automatic recognition system of above-mentioned pig face, can be established using the method for principal component analysis
The machine automatic recognition system of the pig face of animal.Sample can be first read, gray processing processing is then carried out and then obtains grayscale image,
Unified dimension of picture is then proceeded to, finally every figure is converted into the column vector of N*N dimension, and all column vectors are put into a collection
In conjunction.Then, average value is calculated, the average image (average face) is obtained, and calculates the difference of every figure and the average image, then count
Thus its diagonalization is obtained each feature vector by the covariance matrix for calculating it, also just obtained each feature face image.
And the solution under this group of characteristic solution system is to belong to pig face, also just completes the model of the pig face.
Finally, identified using the model of the pig face of above-mentioned foundation to online animal painting, specifically identification process
It is a secondary new image projection to eigenface subspace, and passes through the position and projection line of its subpoint in subspace
Length is determined and is identified.The foundation of the machine automatic recognition system of pig face can use eigenface method, pass through foundation
Simple classification device simultaneously cascades, and then exploitation tool loads classifier carries out the detection identification of pig face.
Step 103 obtains the corresponding state letter of animal to be monitored according to identity identification information and default animal state library
Breath, and the first virtual video is generated according to status information.
Specifically, the corresponding state of animal to be monitored is obtained by identity identification information and default animal state library to believe
Breath, wherein the identity identification information can be a string encoding, such as pig1000001, and include in default animal state library
The mapping relations of the coding and particular state information, by by the coding input into default animal state library, so that it may
The corresponding status information of the coding is retrieved, and corresponds to different virtual videos for different status informations.
For example, raiser has known the health status of every pig after checking UP to all live pigs in pig farm
Information, and the health and fitness information of every pig has been entered into default animal state library, if the health status of the pig is become
Change, then can preset animal state library at this its health status information is updated.In addition, default animal state library can be
It is arranged in terminal device, is also possible to setting in the server, if setting is in the server, need to guarantees terminal device and service
It is communicatively coupled.
Referring to Fig. 2 or Fig. 4, later period, raiser is in order in time to sick pig progress drug therapy, so that it may pass through
Smart phone or AR glasses obtain the real video of pig to be monitored, then raw according to the health status information of every pig to be monitored
At the first virtual video, wherein if the health status information of the pig is " health ", corresponding is that " I am very healthy！" animation
Video, and if the health status information of the pig be " non-health ", corresponding the first virtual video is that " I am sick！" animation
Video.
Step 104, by the first virtual video Overlapping display in real video.
Specifically, the first position of the corresponding facial image information of animal to be monitored in real video can be first determined, so
Afterwards according to first position by the first virtual video Overlapping display in real video so that virtual video indicates animal to be monitored
Particular state.Referring to Fig. 2 or Fig. 4, the facial positions of every pig of real video can be first determined, then according to the position, existing
The facial text of every pig draws corresponding bubble dialog box in such a way that bubble connects in real video, and can open up in frame
The now corresponding particular state information of every pig.
In the present embodiment, by extracting facial image features from the real video of the animal to be monitored got, so
The corresponding identity identification information of the animal is determined by facial image features and preset animal identification identification model afterwards, it is then sharp
The corresponding status information of the animal is obtained from default animal state library with the identity identification information identified, is then passed through
The mode of augmented reality shows the status information in the real video of animal to be monitored, so that poultry raiser can be quickly and straight
Get the status information of every animal with seeing, it is seen then that the acquisition process operating process is complicated, high-efficient, is very suitable to large size
For the management of animal population in farm.
Fig. 6 is the flow chart of the animal state monitoring method shown according to a further exemplary embodiment.As shown in fig. 6, this
The animal state monitoring method that embodiment provides, comprising:
Step 201, the real video for obtaining animal to be monitored, and by preset neural network model to real video into
Row facial feature extraction, to obtain the corresponding facial image features of the animal to be monitored.
Step 202, the identity that animal to be monitored is determined according to facial image features and default animal identification identification model
Identification information.
Step 203 obtains the corresponding state letter of animal to be monitored according to identity identification information and default animal state library
Breath, and the first virtual video is generated according to status information.
Step 204, by the first virtual video Overlapping display in real video.
It is worth explanatorily, the specific implementation of step 201-204 step in embodiment referring to Figure 5 in the present embodiment
The description of 101-104, which is not described herein again.
Step 205 obtains the corresponding detailed status information of status information, and root according to the state expansion instruction of user's input
The second virtual video is generated according to detailed status information.
Specifically, the corresponding detailed status information of status information, and root are obtained according to the state expansion instruction of user's input
The second virtual video is generated according to detailed status information, wherein status details include: identity identification information and health status
Information.
Wherein, raiser can be by clicking the first virtual video corresponding position in the display and pass through it
He sees triggering input state expansion instruction, and user can carry out detailed in status information of the needs to some specific animal individual
The instruction is triggered when solution.
Fig. 7 is a kind of schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6.As shown in fig. 7, when raiser touches
State expansion instruction has been sent out, more detailed status details, such as specific weight letter can be shown to the pig of health
Breath and body fat information.
Step 206 cancels the first virtual video of display, and by the second virtual video Overlapping display in real video.
Specifically, it can first cancel the first virtual video of display, then determine that animal to be monitored is corresponding in real video
The first position of facial image information, then further according to first position by the first virtual video Overlapping display in real video,
So that virtual video indicates the particular state of animal to be monitored.Referring to Fig. 7, the facial position of every pig of real video can be first determined
It sets, then according to the position, the facial text of every pig draws corresponding gas in such a way that bubble connects in real video
Dialog box is steeped, and the corresponding particular state information of every pig can be showed in frame, such as specific weight information and body fat
Information.
In a specific application scenarios, poultry raiser after having injected vaccine to the Some Animals in farm, by
There is motility in animal, after mutually mixing, be difficult telling which specific animal injected vaccine, and it is specific which
Animal did not injected vaccine.
It, can be by updating default animal state library after having injected vaccine to every animal for above-mentioned scene
The information vaccinated is added in the status details of the animal by mode.Then poultry raiser can be according to epidemic disease
Seedling inoculation status information judges whether animal to be monitored is to vaccinate, also, be superimposed in real video according to judging result
Show corresponding virtual video content, wherein if the determination result is YES, then Overlapping display the 4th virtually regards in real video
Frequently, the 4th virtual video has been vaccinated for characterizing animal to be monitored, if judging result be it is no, be superimposed in real video
Show that the 5th virtual video, the 5th virtual video do not vaccinate for characterizing animal to be monitored.
By taking pig farm as an example, Fig. 8 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6.Such as Fig. 8
Shown, raiser can pass through smart phone or AR in order to carry out vaccine injection to the pig not vaccinated in time
Glasses obtain the real video of pig to be monitored, then generate the 4th or the according to the vaccine inoculation status information of every pig to be monitored
Five virtual videos, wherein if the vaccine inoculation status information of the pig is inoculated vaccine, the 4th virtual video is corresponding to be
" I has been inoculated with！" animated video, and if the vaccine inoculation status information of the pig be not inoculated vaccine, the 5th virtual video
Corresponding is that " I is not inoculated with！" animated video.Vaccine inoculation status information is shown wait supervise by way of augmented reality
It surveys in the real video of animal, so that poultry raiser can quickly and intuitively get the vaccine inoculation state letter of every animal
Breath, so that poultry raiser can efficiently complete inoculation work.
In another specific application scenarios, poultry raiser needs first to inquire the same day when selecting animal to sell
Animal pricing information, then select suitable animal and sold, and the animal of a variety of kinds may be raised in each feed lot,
And the price of each kind is also that can be fluctuated with market sale situation, the process need user to the animal in feed lot into
Row screens one by one, quite time-consuming effort.
For above-mentioned scene, the current pricing information of animal can be obtained by terminal device, and by updating default animal
The corresponding current pricing information of every animal is added in the status details of the animal by the mode of state repository.Then again
Judge whether animal to be monitored is that can sell animal according to the current pricing information of animal and default pricing information, is existed according to judging result
The corresponding virtual video content of Overlapping display in real video, wherein if the determination result is YES, be then superimposed in real video aobvious
Show the 6th virtual video, the 6th virtual video for characterize animal to be monitored be can sell animal, if judging result be it is no, showing
The 7th virtual video of Overlapping display in real video, the 7th virtual video are that can not sell animal for characterizing animal to be monitored.
By taking pig farm as an example, Fig. 9 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6.Such as Fig. 9
Shown, raiser can sell in order to quickly filter out which pig, can so that pig for sale is isolated in advance
To obtain the real video of pig to be monitored by smart phone or AR glasses, then the animal according to every pig to be monitored is current
Pricing information generates the 6th or the 7th virtual video, wherein if the current pricing information of the animal of the pig is more than or default sell that maintain an equal level
Valence information, then it is that " I can sell that the 6th virtual video is corresponding！" animated video, and if the current pricing information of the animal of the pig is low
In default pricing information, then it is that " I can not sell that the 7th virtual video is corresponding！" animated video.By way of augmented reality
The information whether every pig can sell is shown in the real video of animal to be monitored, so that poultry raiser can quickly and intuitively
Judge that group can be sold, to be isolated in advance, to improve efficiency.
In another specific application scenarios, in the season of animals into heat, poultry raiser needs the animal to different sexes
Isolation or specific aim collocation are carried out, to improve the gene quality of animal offspring.
For above-mentioned scene, Animal Sex letter can all inputted in advance for every animal in default animal state library
Breath, so that it may according to Animal Sex information in real video the corresponding virtual video content of Overlapping display, wherein if animality
Other information is male, then the 8th virtual video of Overlapping display in real video, if Animal Sex information is female, in reality
The 9th virtual video of Overlapping display in video, if Animal Sex information is sterilization, Overlapping display the tenth is empty in real video
Quasi- video.
By taking pig farm as an example, Figure 10 is another schematic diagram of interface display of terminal device in embodiment illustrated in fig. 6.Such as figure
Shown in 10, raiser recombinates in order to the pig to different sexes, can be obtained by smart phone or AR glasses to
The real video of pig is monitored, the eight, the nine or the tenth virtual video is then generated according to the Animal Sex information of every pig to be monitored,
Wherein, if Animal Sex information is male, corresponding the 8th virtual video is that " I is male！" animated video, if animal
Gender information is female, then it is that " I is female that the 8th virtual video is corresponding！" animated video, if Animal Sex information is exhausted
It educates, then it is " my sterilization that the 8th virtual video is corresponding！" animated video.Animal Sex is believed by way of augmented reality
Breath is shown in the real video of animal to be monitored, so that poultry raiser can quickly and intuitively get the animal of every animal
Gender information, so that poultry raiser can efficiently complete breeding work.
Figure 11 is the structural schematic diagram of terminal device shown according to an exemplary embodiment.Terminal provided in this embodiment
Equipment, comprising:
Module 301 is obtained, for obtaining the real video of animal to be monitored, and by preset neural network model to institute
It states real video and carries out facial feature extraction, to obtain the corresponding facial image features of the animal to be monitored, wherein described existing
It include the facial image information of the animal to be monitored in real video；
Identification module 302, for according to the facial image features and the determination of default animal identification identification model
The identity identification information of animal to be monitored；
Generation module 303, it is described to be monitored for being obtained according to the identity identification information and default animal state library
The corresponding status information of animal, and the first virtual video is generated according to the state information；
Display module 304 is used for the first virtual video Overlapping display in the real video.
In a kind of possible design, the display module 304 is specifically used for:
Determine the first position of the corresponding facial image information of animal to be monitored described in the real video；
According to the first position by the first virtual video Overlapping display in the real video so that the void
Quasi- video indicates the particular state of the animal to be monitored.
In a kind of possible design, the acquisition module 301, the state expansion instruction for being also used to be inputted according to user is obtained
The corresponding detailed status information of the status information is taken, and the second virtual video is generated according to the detailed status information, wherein
The status details include: the identity identification information and health status information；
The display module 304 is also used to cancel display first virtual video, and second virtual video is folded
Add and is shown in the real video.
On the basis of embodiment illustrated in fig. 11, Figure 12 is the knot of the terminal device shown according to another exemplary embodiment
Structure schematic diagram.As shown in figure 12, terminal device provided in this embodiment, further includes:
Judgment module 305, for judging whether the animal to be monitored is health status according to the health status information；
The display module 304, is also used to that Overlapping display is corresponding in the real video according to the judging result
Virtual video content, wherein if the determination result is YES, then the Overlapping display third virtual video in the real video, described
Third virtual video for characterize the animal to be monitored be health status, if judging result be it is no, it is described reality video
Middle the 4th virtual video of Overlapping display, the 4th virtual video are unhealthy status for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: vaccine inoculation status information.
In a kind of possible design, judgment module 305, for according to vaccine inoculation status information judgement it is described to
Monitor whether animal is to vaccinate；
The display module 304, for according to the judging result in the real video the corresponding void of Overlapping display
Quasi- video content, wherein if the determination result is YES, then the 4th virtual video of Overlapping display in the real video, described the
Four virtual videos have injected the vaccine for characterizing the animal to be monitored, if judging result be it is no, regarded in the reality
The 5th virtual video of Overlapping display in frequency, the 5th virtual video do not inject the epidemic disease for characterizing the animal to be monitored
Seedling.
In a kind of possible design, the status details further include: the current pricing information of animal.
In a kind of possible design, judgment module 305, for according to the current pricing information of the animal and default price
Information judges whether the animal to be monitored is that can sell animal；
The display module 304, for according to the judging result in the real video the corresponding void of Overlapping display
Quasi- video content, wherein if the determination result is YES, then the 6th virtual video of Overlapping display in the real video, described the
Six virtual videos for characterize the animal to be monitored be can sell animal, if judging result be it is no, it is described reality video in
The 7th virtual video of Overlapping display, the 7th virtual video are that can not sell animal for characterizing the animal to be monitored.
In a kind of possible design, the status details further include: Animal Sex information.
In a kind of possible design, the display module 304 is also used to according to the Animal Sex information described existing
The corresponding virtual video content of Overlapping display in real video, wherein if the Animal Sex information is male, in the reality
The 8th virtual video of Overlapping display in video, if the Animal Sex information is female, superposition is aobvious in the real video
Show the 9th virtual video, if the Animal Sex information is sterilization, Overlapping display the tenth is virtually regarded in the real video
Frequently.
In a kind of possible design, the facial image features include at least following one: eye feature, mouth are special
Sign, ear feature and nose feature.
It is worth explanatorily, the terminal device in Figure 11 and embodiment illustrated in fig. 12 can be used for executing shown in above-mentioned Fig. 3-Fig. 9
Method in embodiment, specific implementation is similar with technical effect, and which is not described herein again.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, and the program is processed
Device realizes the technical solution of any one of aforementioned embodiment of the method when executing, it is similar that the realization principle and technical effect are similar, herein no longer
It repeats.
Figure 13 is the structural schematic diagram of present invention electronic equipment shown according to an exemplary embodiment.As shown in figure 13,
Electronic equipment provided in this embodiment, comprising:
Camera 401, processor 402, memory 403 and display 404；
The camera 401 and the display 404 are connected with the processor 402 respectively；
The camera 401, for obtaining the real video of animal to be monitored；
The memory 403, for storing the executable instruction of the processor；
The display 404, for showing the real video and virtual video；
Wherein, processor 404 is configured to execute the skill of any one of aforementioned embodiment of the method via executable instruction is executed
Art scheme, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Also, the function of each module in above equipment can be realized by processor 401.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or part of or all technical features are carried out etc.
With replacement；And these modifications or substitutions, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
Range.
Claims (24)
1. a kind of animal state monitoring method characterized by comprising
The real video of animal to be monitored is obtained, and face spy is carried out to the real video by preset neural network model
Sign is extracted, to obtain the corresponding facial image features of the animal to be monitored, wherein includes described wait supervise in the reality video
Survey the facial image information of animal；
The identification of the animal to be monitored is determined according to the facial image features and default animal identification identification model
Information；
The corresponding status information of the animal to be monitored is obtained according to the identity identification information and default animal state library, and
The first virtual video is generated according to the state information；
By the first virtual video Overlapping display in the real video.
2. animal state monitoring method according to claim 1, which is characterized in that described to fold first virtual video
Add and be shown in the real video, specifically includes:
Determine the first position of the corresponding facial image information of animal to be monitored described in the real video；
According to the first position by the first virtual video Overlapping display in the real video so that the virtual view
Frequency indicates the particular state of the animal to be monitored.
3. animal state monitoring method according to claim 1, which is characterized in that described by first virtual video
After Overlapping display is in the real video, further includes:
The corresponding detailed status information of the status information is obtained according to the state expansion instruction of user's input, and according to described detailed
Thin status information generates the second virtual video, wherein the status details include: the identity identification information and health
Status information；
Cancel and show first virtual video, and by the second virtual video Overlapping display in the real video.
4. animal state monitoring method according to claim 3, which is characterized in that described by first virtual video
After Overlapping display is in the real video, further includes:
Judge whether the animal to be monitored is health status according to the health status information；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if judgement knot
Fruit is yes, the then Overlapping display third virtual video in the real video, the third virtual video for characterize it is described to
Monitoring animal is health status, described if judging result is no, the 4th virtual video of Overlapping display in the real video
4th virtual video is unhealthy status for characterizing the animal to be monitored.
5. animal state monitoring method according to claim 3, which is characterized in that the status details further include:
Vaccine inoculation status information.
6. animal state monitoring method according to claim 5, which is characterized in that described by first virtual video
After Overlapping display is in the real video, further includes:
Judge whether the animal to be monitored is to vaccinate according to the vaccine inoculation status information；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if judgement knot
Fruit is yes, then the 4th virtual video of Overlapping display in the real video, the 4th virtual video for characterize it is described to
Monitoring animal has injected the vaccine, if judging result is no, the 5th virtual video of Overlapping display in the real video,
5th virtual video does not inject the vaccine for characterizing the animal to be monitored.
7. animal state monitoring method according to claim 3, which is characterized in that the status details further include:
The current pricing information of animal.
8. animal state monitoring method according to claim 7, which is characterized in that described by first virtual video
After Overlapping display is in the real video, further includes:
Judge whether the animal to be monitored is that can sell animal according to the current pricing information of the animal and default pricing information；
According to the judging result in the real video the corresponding virtual video content of Overlapping display, wherein if judgement knot
Fruit is yes, then the 6th virtual video of Overlapping display in the real video, the 6th virtual video for characterize it is described to
Monitoring animal is that can sell animal, described if judging result is no, the 7th virtual video of Overlapping display in the real video
7th virtual video is that can not sell animal for characterizing the animal to be monitored.
9. animal state monitoring method according to claim 3, which is characterized in that the status details further include:
Animal Sex information.
10. animal state monitoring method according to claim 9, which is characterized in that described by the described first virtual view
After frequency Overlapping display is in the real video, further includes:
According to the Animal Sex information in the real video the corresponding virtual video content of Overlapping display, wherein if institute
Stating Animal Sex information is male, then the 8th virtual video of Overlapping display in the real video, if the Animal Sex is believed
Breath is female, then the 9th virtual video of Overlapping display in the real video, if the Animal Sex information is sterilization,
The tenth virtual video of Overlapping display in the reality video.
11. animal state monitoring method described in any one of -10 according to claim 1, which is characterized in that the face figure
As feature includes at least following one: eye feature, mouth feature, ear feature and nose feature.
12. a kind of terminal device characterized by comprising
Module is obtained, for obtaining the real video of animal to be monitored, and by preset neural network model to the reality
Video carries out facial feature extraction, to obtain the corresponding facial image features of the animal to be monitored, wherein the reality video
In include the animal to be monitored facial image information；
Identification module, it is described to be monitored dynamic for being determined according to the facial image features and default animal identification identification model
The identity identification information of object；
Generation module, it is corresponding for obtaining the animal to be monitored according to the identity identification information and default animal state library
Status information, and generate the first virtual video according to the state information；
Display module is used for the first virtual video Overlapping display in the real video.
13. terminal device according to claim 12, which is characterized in that the display module is specifically used for:
Determine the first position of the corresponding facial image information of animal to be monitored described in the real video；
According to the first position by the first virtual video Overlapping display in the real video so that the virtual view
Frequency indicates the particular state of the animal to be monitored.
14. terminal device according to claim 13, which is characterized in that the acquisition module is also used to defeated according to user
The state expansion instruction entered obtains the corresponding detailed status information of the status information, and is generated according to the detailed status information
Second virtual video, wherein the status details include: the identity identification information and health status information；
The display module, is also used to cancel display first virtual video, and by the second virtual video Overlapping display
In the real video.
15. terminal device according to claim 14, which is characterized in that further include:
Judgment module, for judging whether the animal to be monitored is health status according to the health status information；
The display module is also used to according to the judging result the corresponding virtual video of Overlapping display in the real video
Content, wherein if the determination result is YES, then Overlapping display third virtual video, the third are virtual in the real video
Video is health status for characterizing the animal to be monitored, if judging result be it is no, superposition is shown in the real video
Show that the 4th virtual video, the 4th virtual video are unhealthy status for characterizing the animal to be monitored.
16. terminal device according to claim 14, which is characterized in that the status details further include: vaccine connects
Kind status information.
17. terminal device according to claim 16, which is characterized in that further include:
Judgment module, for judging whether the animal to be monitored is to vaccinate according to the vaccine inoculation status information；
The display module, for according to the judging result in the real video in the corresponding virtual video of Overlapping display
Hold, wherein if the determination result is YES, then the 4th virtual video of Overlapping display in the real video, the described 4th virtual view
Frequency has injected the vaccine for characterizing the animal to be monitored, if judging result be it is no, be superimposed in the reality video
Show that the 5th virtual video, the 5th virtual video do not inject the vaccine for characterizing the animal to be monitored.
18. terminal device according to claim 14, which is characterized in that the status details further include: animal is worked as
Preceding pricing information.
19. terminal device according to claim 18, which is characterized in that further include:
Judgment module, for whether judging the animal to be monitored according to the current pricing information of the animal and default pricing information
For animal can be sold；
The display module, for according to the judging result in the real video in the corresponding virtual video of Overlapping display
Hold, wherein if the determination result is YES, then the 6th virtual video of Overlapping display in the real video, the described 6th virtual view
Frequency is that can sell animal for characterizing the animal to be monitored, if judging result is no, the Overlapping display in the real video
7th virtual video, the 7th virtual video are that can not sell animal for characterizing the animal to be monitored.
20. terminal device according to claim 14, which is characterized in that the status details further include: animality
Other information.
21. terminal device according to claim 20, which is characterized in that the display module is also used to according to described dynamic
Object gender information corresponding virtual video content of Overlapping display in the real video, wherein if the Animal Sex information
For male, then the 8th virtual video of Overlapping display in the real video, if the Animal Sex information is female, in institute
The 9th virtual video of Overlapping display in real video is stated, if the Animal Sex information is sterilization, in the real video
The tenth virtual video of Overlapping display.
22. terminal device described in any one of 2-21 according to claim 1, which is characterized in that the facial image features
Including at least following one: eye feature, mouth feature, ear feature and nose feature.
23. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Claim 1-11 described in any item animal state monitoring methods are realized when execution.
24. a kind of electronic equipment characterized by comprising
Camera, processor, memory and display；
The camera and the display are connected with the processor respectively；
The camera, for obtaining the real video of animal to be monitored；
The memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to require 1-11 described in any item via executing the executable instruction and carry out perform claim
Animal state monitoring method；
The display, for showing the real video and virtual video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887644.5A CN109255297B (en) | 2018-08-06 | 2018-08-06 | Animal state monitoring method, terminal device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810887644.5A CN109255297B (en) | 2018-08-06 | 2018-08-06 | Animal state monitoring method, terminal device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109255297A true CN109255297A (en) | 2019-01-22 |
| CN109255297B CN109255297B (en) | 2022-12-13 |
Family
ID=65049722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810887644.5A Active CN109255297B (en) | 2018-08-06 | 2018-08-06 | Animal state monitoring method, terminal device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109255297B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919445A (en) * | 2019-02-01 | 2019-06-21 | 广州影子科技有限公司 | Cultivate task management method and device, cultivation task management equipment and system |
| CN110222725A (en) * | 2019-05-15 | 2019-09-10 | 广州影子科技有限公司 | Pig checking method, pig veritify device and pig verifying system |
| CN110741963A (en) * | 2019-10-16 | 2020-02-04 | 北京海益同展信息科技有限公司 | Object state monitoring and sow oestrus monitoring method, device and system |
| 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 |
| CN110837299A (en) * | 2019-11-11 | 2020-02-25 | 上海萃钛智能科技有限公司 | Activity management intelligent device, system and method |
| 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 |
| CN111199535A (en) * | 2019-11-28 | 2020-05-26 | 北京海益同展信息科技有限公司 | Animal state monitoring method and device, electronic equipment and storage medium |
| CN111429296A (en) * | 2020-04-07 | 2020-07-17 | 北京海益同展信息科技有限公司 | Target biological monitoring method, device, electronic equipment and computer readable medium |
| CN112215105A (en) * | 2020-09-28 | 2021-01-12 | 北京海益同展信息科技有限公司 | Method and device for monitoring body abnormality of target animal, equipment and storage medium |
| CN113283340A (en) * | 2021-05-25 | 2021-08-20 | 复旦大学 | Method, device and system for detecting vaccination condition based on ocular surface characteristics |
| CN114403047A (en) * | 2022-02-09 | 2022-04-29 | 上海依蕴宠物用品有限公司 | Aged animal health intervention method and system based on image analysis technology |
| CN115250950A (en) * | 2022-08-02 | 2022-11-01 | 苏州数智赋农信息科技有限公司 | Artificial intelligence-based livestock and poultry pig farm inspection method and system |
| CN115361526A (en) * | 2022-08-16 | 2022-11-18 | 苏州数智赋农信息科技有限公司 | Pig farm inspection system and method based on image processing |
| TWI820870B (en) * | 2022-08-17 | 2023-11-01 | 探極生物科技有限公司 | Methods and devices for biological monitoring by automated systems based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160180590A1 (en) * | 2014-12-23 | 2016-06-23 | Lntel Corporation | Systems and methods for contextually augmented video creation and sharing |
| CN106961595A (en) * | 2017-03-21 | 2017-07-18 | 深圳市科漫达智能管理科技有限公司 | A kind of video frequency monitoring method and video monitoring system based on augmented reality |
| CN107067474A (en) * | 2017-03-07 | 2017-08-18 | 深圳市吉美文化科技有限公司 | A kind of augmented reality processing method and processing device |
| CN107833145A (en) * | 2017-09-19 | 2018-03-23 | 翔创科技（北京）有限公司 | The database building method and source tracing method of livestock, storage medium and electronic equipment |
| 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 |
| CN108052964A (en) * | 2017-12-05 | 2018-05-18 | 翔创科技（北京）有限公司 | Livestock condition detection method, computer program, storage medium and electronic equipment |
| CN108363990A (en) * | 2018-03-14 | 2018-08-03 | 广州影子控股股份有限公司 | One boar face identifying system and method |
-
2018
- 2018-08-06 CN CN201810887644.5A patent/CN109255297B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160180590A1 (en) * | 2014-12-23 | 2016-06-23 | Lntel Corporation | Systems and methods for contextually augmented video creation and sharing |
| CN107067474A (en) * | 2017-03-07 | 2017-08-18 | 深圳市吉美文化科技有限公司 | A kind of augmented reality processing method and processing device |
| CN106961595A (en) * | 2017-03-21 | 2017-07-18 | 深圳市科漫达智能管理科技有限公司 | A kind of video frequency monitoring method and video monitoring system based on augmented reality |
| CN107833145A (en) * | 2017-09-19 | 2018-03-23 | 翔创科技（北京）有限公司 | The database building method and source tracing method of livestock, storage medium and electronic equipment |
| 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 |
| CN108052964A (en) * | 2017-12-05 | 2018-05-18 | 翔创科技（北京）有限公司 | Livestock condition detection method, computer program, storage medium and electronic equipment |
| CN108363990A (en) * | 2018-03-14 | 2018-08-03 | 广州影子控股股份有限公司 | One boar face identifying system and method |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919445A (en) * | 2019-02-01 | 2019-06-21 | 广州影子科技有限公司 | Cultivate task management method and device, cultivation task management equipment and system |
| CN110222725A (en) * | 2019-05-15 | 2019-09-10 | 广州影子科技有限公司 | Pig checking method, pig veritify device and pig verifying system |
| CN110222725B (en) * | 2019-05-15 | 2022-01-04 | 广州影子科技有限公司 | Pig checking method, pig checking device and pig checking system |
| 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 |
| CN110741963B (en) * | 2019-10-16 | 2021-11-02 | 北京海益同展信息科技有限公司 | Object state monitoring and sow oestrus monitoring method, device and system |
| CN110741963A (en) * | 2019-10-16 | 2020-02-04 | 北京海益同展信息科技有限公司 | Object state monitoring and sow oestrus monitoring method, device and system |
| CN110837299A (en) * | 2019-11-11 | 2020-02-25 | 上海萃钛智能科技有限公司 | Activity management intelligent device, system and method |
| 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 |
| CN111199535B (en) * | 2019-11-28 | 2023-11-03 | 京东科技信息技术有限公司 | Animal state monitoring method and device, electronic equipment and storage medium |
| CN111199535A (en) * | 2019-11-28 | 2020-05-26 | 北京海益同展信息科技有限公司 | Animal state monitoring method and device, electronic equipment and storage medium |
| CN111429296A (en) * | 2020-04-07 | 2020-07-17 | 北京海益同展信息科技有限公司 | Target biological monitoring method, device, electronic equipment and computer readable medium |
| CN112215105A (en) * | 2020-09-28 | 2021-01-12 | 北京海益同展信息科技有限公司 | Method and device for monitoring body abnormality of target animal, equipment and storage medium |
| CN113283340A (en) * | 2021-05-25 | 2021-08-20 | 复旦大学 | Method, device and system for detecting vaccination condition based on ocular surface characteristics |
| CN113283340B (en) * | 2021-05-25 | 2022-06-14 | 复旦大学 | Method, device and system for detecting vaccination condition based on ocular surface characteristics |
| CN114403047A (en) * | 2022-02-09 | 2022-04-29 | 上海依蕴宠物用品有限公司 | Aged animal health intervention method and system based on image analysis technology |
| CN114403047B (en) * | 2022-02-09 | 2023-01-06 | 上海依蕴宠物用品有限公司 | Aged animal health intervention method and system based on image analysis technology |
| CN115250950A (en) * | 2022-08-02 | 2022-11-01 | 苏州数智赋农信息科技有限公司 | Artificial intelligence-based livestock and poultry pig farm inspection method and system |
| CN115250950B (en) * | 2022-08-02 | 2024-01-19 | 苏州数智赋农信息科技有限公司 | Method and system for inspecting livestock and poultry pig farm based on artificial intelligence |
| CN115361526A (en) * | 2022-08-16 | 2022-11-18 | 苏州数智赋农信息科技有限公司 | Pig farm inspection system and method based on image processing |
| TWI820870B (en) * | 2022-08-17 | 2023-11-01 | 探極生物科技有限公司 | Methods and devices for biological monitoring by automated systems based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109255297B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255297A (en) | animal state monitoring method, terminal device, storage medium and electronic equipment | |
| US20190164012A1 (en) | State detection using machine-learning model trained on simulated image data | |
| US20190206546A1 (en) | Modeling and learning character traits and medical condition based on 3d facial features | |
| US9846845B2 (en) | Hierarchical model for human activity recognition | |
| Branson et al. | Visual recognition with humans in the loop | |
| CN108229268A (en) | Expression Recognition and convolutional neural networks model training method, device and electronic equipment | |
| CN108388876A (en) | A kind of image-recognizing method, device and relevant device | |
| CN108460356A (en) | A kind of facial image automated processing system based on monitoring system | |
| KR20220066366A (en) | Predictive individual 3D body model | |
| CN107679546A (en) | Face image data acquisition method, device, terminal device and storage medium | |
| CN107992903A (en) | Livestock personal identification method, device, storage medium and electronic equipment | |
| CN105740780A (en) | Method and device for human face in-vivo detection | |
| CN106897659A (en) | The recognition methods of blink motion and device | |
| CN107657459A (en) | Auth method, settlement of insurance claim method, source tracing method, storage medium and the electronic equipment of livestock | |
| CN107784678B (en) | Cartoon face image generation method and device and terminal | |
| CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
| CN107833145A (en) | The database building method and source tracing method of livestock, storage medium and electronic equipment | |
| CN113449704B (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| WO2021243561A1 (en) | Behaviour identification apparatus and method | |
| CN110728242A (en) | Image matching method and device based on portrait recognition, storage medium and application | |
| CN110008922A (en) | Image processing method, unit, medium for terminal device | |
| Perez et al. | Cnn-based action recognition and pose estimation for classifying animal behavior from videos: a survey | |
| KR102247481B1 (en) | Device and method for generating job image having face to which age transformation is applied | |
| CN109192314B (en) | Cervical vertebra health scoring device based on multi-example learning and application thereof | |
| CN117133014A (en) | Live pig face key point detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |