CN107680080A - The Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment - Google Patents
The Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107680080A CN107680080A CN201710792838.2A CN201710792838A CN107680080A CN 107680080 A CN107680080 A CN 107680080A CN 201710792838 A CN201710792838 A CN 201710792838A CN 107680080 A CN107680080 A CN 107680080A
- Authority
- CN
- China
- Prior art keywords
- livestock
- video frame
- scene video
- sample storehouse
- sample
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides a kind of Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment, is related to artificial intelligence field.Wherein, the Sample Storehouse method for building up of the livestock includes：Obtain the scene video frame sequence in the livestock stable breeding region gathered by image capture device；By the neural network model tracked for livestock, the livestock occurred in each two scene video frame adjacent in the sequential in the scene video frame sequence is tracked；Whenever determining new livestock occur according to tracking result, and do not have the information of the new livestock in the livestock Sample Storehouse for determining to have livestock information, then the information of the new livestock is added in the livestock Sample Storehouse.By the embodiment of the present invention, the Sample Storehouse of livestock can be rapidly and accurately established, has saved substantial amounts of manpower and materials.
Description
Technical field
The present embodiments relate to artificial intelligence field, more particularly to a kind of Sample Storehouse method for building up of livestock, storage to be situated between
Matter and electronic equipment, and, a kind of counting method of livestock, storage medium and electronic equipment.
Background technology
With the rapid development of animal husbandry and the support of national policy, the livestock amount of numerous herdsman's raising significantly increases year by year
Add.The raising of livestock mainly has two ways, i.e. free range husbandry and rear livestock in pens two ways.Free range husbandry can save grass
The expenses such as material, equipment, feeding cost be low but the influence in climate and season, especially winter to herd be to lose more than gain.And drylot feeding
Stable breeding can enable livestock is balanced to develop, and efficiency of feed utilization is of a relatively high, easily form cultivation scale, improve commodity rate.
Therefore, the mode for advocating rear livestock in pens carrys out raise livestock.
However, during rear livestock in pens livestock, the problem of livestock is checked can be related to.Most area is still at present
The counting livestock by the way of manually checking.Because livestock has size difference, it can block in the presence of certain, therefore, check
It is easy to mistake occur during livestock, while this mode complexity, the efficiency of checking is low, is especially not suitable with large-scale livestock and cultivates base
Ground.The shift position further, since livestock ceaselessly walks, the work of checking of livestock number also increase difficulty.
The content of the invention
The purpose of the embodiment of the present invention is, there is provided a kind of technical scheme of Sample Storehouse foundation of livestock and checking for livestock
Technical scheme.
A kind of first aspect according to embodiments of the present invention, there is provided method for building up of livestock Sample Storehouse.Methods described bag
Include：Obtain the scene video frame sequence in the livestock stable breeding region gathered by image capture device；Pass through what is tracked for livestock
Neural network model, to the livestock occurred in each two scene video frame adjacent in the sequential in the scene video frame sequence
It is tracked；Whenever determining new livestock occur according to tracking result, and determine have in the livestock Sample Storehouse of livestock information
When not having the information of the new livestock, then the information of the new livestock is added in the livestock Sample Storehouse.
Alternatively, the livestock information includes the face image of livestock and/or the characteristic of livestock face.
Alternatively, the face image of the livestock is the face image of the livestock.
Alternatively, methods described also includes：When the quantity of the face image in the beast Sample Storehouse reaches predetermined number
When, stop carrying out the livestock occurred in each two scene video frame adjacent in the sequential in the scene video frame sequence with
Track.
Alternatively, methods described also includes：Whenever determining not occurring new livestock according to the tracking result, then continue
The livestock occurred in each two scene video frame adjacent in sequential in the scene video frame sequence is tracked.
Alternatively, when the information of the new livestock is added in the livestock Sample Storehouse, methods described also includes：To institute
State new livestock to be identified, obtain corresponding identification information；The mark of the new livestock is added in the livestock Sample Storehouse
Know information.
Alternatively, the livestock includes at least one of following：Chicken, duck, goose, ox, sheep, horse, pig.
A kind of second aspect according to embodiments of the present invention, there is provided counting method of livestock.Methods described includes：Obtain
The scene video frame sequence in the livestock stable breeding region gathered by image capture device；Will be every in the scene video frame sequence
The livestock occurred in individual scene video frame is compared with the livestock in each sample image in default livestock Sample Storehouse respectively
It is right, obtain the first comparison result；Determine the livestock according to first comparison result first checks result, wherein, it is described
Default livestock Sample Storehouse is that the method described in first aspect according to embodiments of the present invention establishes what is obtained.
Alternatively, the livestock occurred in each scene video frame by the scene video frame sequence respectively with advance
If livestock Sample Storehouse in each sample image in livestock be compared, obtain the first comparison result, including：By for
The neural network model that livestock face compares, the livestock that will occur in each scene video frame in the scene video frame sequence
Face of the face respectively with the livestock in each sample image in default livestock Sample Storehouse be compared, obtain described the
One comparison result.
Alternatively, methods described also includes：When the livestock occurred in the scene video frame in the scene video frame sequence
When being differed with the livestock in each sample image in the livestock Sample Storehouse, the domestic animal that will occur in the scene video frame
The livestock that poultry increases newly with default livestock in each scene video frame in storehouse respectively is compared, and obtains the second comparison result；
Determine that the second of the livestock checks result according to first comparison result and second comparison result.
Alternatively, the second of the livestock checks result including at least one of following：In the livestock stable breeding region
It there is currently the quantity of the livestock in the livestock Sample Storehouse, there is currently the livestock Sample Storehouse in the livestock stable breeding region
In the identification information of livestock, livestock in the livestock Sample Storehouse is currently lost in the livestock stable breeding region quantity, institute
State the identification information that the livestock in the livestock Sample Storehouse is currently lost in livestock stable breeding region, work as in the livestock stable breeding region
The preceding quantity that the new livestock is there is currently with the presence or absence of new livestock, in the livestock stable breeding region.
The third aspect according to embodiments of the present invention, there is provided a kind of computer-readable recording medium, be stored thereon with meter
Calculation machine programmed instruction, wherein, described program instruction is realized described in the first aspect of the embodiment of the present invention when being executed by processor
The step of method for building up of livestock Sample Storehouse.
Fourth aspect according to embodiments of the present invention, there is provided a kind of computer-readable recording medium, be stored thereon with meter
Calculation machine programmed instruction, wherein, described program instruction is realized described in the second aspect of the embodiment of the present invention when being executed by processor
The step of counting method of livestock.
5th aspect according to embodiments of the present invention, there is provided a kind of electronic equipment, including：First processor, first are deposited
Reservoir, the first communication device and the first communication bus, the first processor, the first memory and the first communication member
Part completes mutual communication by first communication bus；The first memory is used to deposit at least one executable finger
Order, the executable instruction make the first processor perform the livestock Sample Storehouse as described in the first aspect of the embodiment of the present invention
Method for building up the step of.
6th aspect according to embodiments of the present invention, there is provided a kind of electronic equipment, including：Second processor, second are deposited
Reservoir, the second communication device and the second communication bus, the second processor, the second memory and the second communication member
Part completes mutual communication by second communication bus；The second memory is used to deposit at least one executable finger
Order, the executable instruction make checking for livestock of the second processor execution as described in the second aspect of the embodiment of the present invention
The step of method.
The technical scheme provided according to embodiments of the present invention, obtain the livestock stable breeding region gathered by image capture device
Scene video frame sequence；And the neural network model by being tracked for livestock, in the scene video frame sequence when
The livestock occurred in sequence in adjacent each two scene video frame is tracked；Whenever according to the new domestic animal of tracking result determination appearance
When raiseeing, and not having the information of the new livestock in the livestock Sample Storehouse for determining to have livestock information, then in the livestock
The information of the new livestock is added in Sample Storehouse, thereby, it is possible to rapidly and accurately establish the Sample Storehouse of livestock, has been saved a large amount of
Manpower and materials.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described.It should be evident that drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these figures.
Fig. 1 is a kind of flow chart of the Sample Storehouse method for building up of according to embodiments of the present invention one livestock；
Fig. 2 is a kind of flow chart of the Sample Storehouse method for building up of according to embodiments of the present invention two livestock；
Fig. 3 is a kind of flow chart of the counting method of according to embodiments of the present invention three livestock；
Fig. 4 is a kind of flow chart of the counting method of according to embodiments of the present invention four livestock；
Fig. 5 is the structural representation of according to embodiments of the present invention five a kind of electronic equipment；
Fig. 6 is the structural representation of according to embodiments of the present invention six a kind of electronic equipment.
Embodiment
(identical label represents identical element in some accompanying drawings) and embodiment below in conjunction with the accompanying drawings, implement to the present invention
The embodiment of example is described in further detail.Following examples are used to illustrate the present invention, but are not limited to the present invention
Scope.
It will be understood by those skilled in the art that the term such as " first ", " second " in the embodiment of the present invention is only used for distinguishing
Different step, equipment or module etc., any particular technology implication is neither represented, also do not indicate that the inevitable logic between them is suitable
Sequence.
Embodiment one
Fig. 1 is a kind of flow chart of the Sample Storehouse method for building up of according to embodiments of the present invention one livestock.As shown in figure 1,
The Sample Storehouse method for building up for the livestock that the present embodiment provides includes：
In step S101, the scene video frame sequence in the livestock stable breeding region gathered by image capture device is obtained.
In the present embodiment, described image collecting device may include camera.It is understood that any be used to obtain domestic animal
The equipment that the scene video frame sequence in region is supported in pen is applied to this, and the present embodiment is not restricted to this.
In a particular embodiment, one image capture device can be installed in livestock stable breeding region, also can be in livestock circle
Each orientation for supporting region is installed by one image capture device.Any embodiment installation IMAQ no matter is taken to set
It is standby, as long as ensureing that each livestock in livestock stable breeding region occurs in scene sequence of frames of video.
In step s 102, by the neural network model tracked for livestock, in the scene video frame sequence
The livestock occurred in sequential in adjacent each two scene video frame is tracked.
Wherein, the neural network model can be the god of any appropriate achievable target following or recongnition of objects
Through network, including but not limited to generation network in convolutional neural networks, enhancing learning neural network, confrontation neutral net etc.
Deng.The setting of concrete structure can suitably be set according to the actual requirements by those skilled in the art in neutral net, such as convolutional layer
The number of plies, the size of convolution kernel, port number etc., the embodiment of the present invention is not restricted to this.
In a particular embodiment, the neural network model can have two inputs, an output end.Specifically
Ground, an input are used for the scene video frame inputted in the scene video frame sequence, and another input is used for defeated
Enter one scene video frame another scene video frame adjacent in sequential, the output end is used for phase on output timing
The tracking result of the livestock occurred in two adjacent scene video frames.
In step s 103, whenever determining new livestock occur according to tracking result, and determine there is livestock information
When not having the information of the new livestock in livestock Sample Storehouse, then the new livestock is added in the livestock Sample Storehouse
Information.
Wherein, the livestock that the tracking result includes occurring in two scene video frames adjacent in sequential is identical domestic animal
Raise (not occurring new livestock in rear scene frame of video), or two scene video frames adjacent in sequential in rear scene
The livestock occurred in preceding scene frame of video on the livestock occurred in frame of video and sequential in two adjacent scene video frames
Differ and (new livestock occur in rear scene frame of video).When there is new livestock in rear scene frame of video, it is described with
The characteristic information of image and/or new livestock of the track result also including new livestock.The livestock information may include the figure of livestock
Picture and/or the characteristic information of livestock.The livestock Sample Storehouse is used for the image and/or characteristic information for storing different livestocks.Specifically
Ground, the livestock Sample Storehouse cannot be only used for storing the image and/or characteristic information of different livestocks under same livestock classification, and
It can be additionally used in the image and/or characteristic information for storing different livestocks under different livestock classifications.
The Sample Storehouse method for building up of the livestock provided according to the present embodiment, obtain the livestock gathered by image capture device
The scene video frame sequence in stable breeding region；And the neural network model by being tracked for livestock, to the scene video frame sequence
The livestock occurred in sequential in row in adjacent each two scene video frame is tracked；Determined whenever according to tracking result
Now new livestock, and determine to have when not having the information of the new livestock in the livestock Sample Storehouse of livestock information, then exist
The information of the new livestock is added in the livestock Sample Storehouse, thereby, it is possible to rapidly and accurately establish the Sample Storehouse of livestock, section
About substantial amounts of manpower and materials.
The Sample Storehouse method for building up of the livestock of the present embodiment can have image or data-handling capacity by arbitrarily appropriate
Equipment perform, include but is not limited to：It is camera, terminal, mobile terminal, PC, server, mobile unit, amusement equipment, wide
Accuse equipment, personal digital assistant (PDA), tablet personal computer, notebook computer, handheld device, intelligent glasses, intelligent watch, can
Wearable device, virtual display device or display enhancing equipment (such as Google Glass, Oculus Rift, Hololens, Gear
VR) etc..
Embodiment two
Fig. 2 is a kind of flow chart of the Sample Storehouse method for building up of according to embodiments of the present invention two livestock.As shown in Fig. 2
The Sample Storehouse method for building up for the livestock that the present embodiment provides includes：
In step s 201, the scene video frame sequence in the livestock stable breeding region gathered by image capture device is obtained.
Wherein, the livestock stable breeding region may include farm house, for example, pig house, sheepfold, cattle pen etc..The scene video frame
Sequence includes the video image of all livestocks in livestock stable breeding region.Specifically, the livestock in livestock stable breeding region includes following
At least one of：Chicken, duck, goose, ox, sheep, horse, pig.
In step S202, by the neural network model tracked for livestock, in the scene video frame sequence
The livestock occurred in sequential in adjacent each two scene video frame is tracked.
In a particular embodiment, by the neural network model, in the scene video frame sequence when
The livestock occurred in sequence in adjacent each two scene video frame be tracked before, it is necessary to be instructed to neural network model
Practice.Specifically, by scene video frame sequence have identical livestock preceding scene frame of video and rear scene frame of video input
Neural network model to be trained, or by scene video frame sequence have different livestocks in preceding scene frame of video and
Neural network model to be trained is inputted in rear scene frame of video, tracking result further according to demarcation and the tracking knot currently obtained
Fruit determines difference, further according to the network parameter of neural network model described in the discrepancy adjustment.By calculating the difference, to working as
The tracking result of preceding acquisition is assessed, using the foundation as follow-up training neural network model.More specifically, can be by the difference
Different reverse transfer is to neural network model, so as to iteratively train the neural network model.The training of neural network model is one
Only a training process therein is illustrated for the process of individual iteration, the embodiment of the present invention, but those skilled in the art should
When understanding, each training to neural network model can all use the training method, until completing the training of neural network model.
In an optional embodiment of the invention, in order that tracking knot of the neural network model that must train to obtain to livestock
Fruit is more accurate, and can use has identical livestock frame of video in different scenes sequence of frames of video is carried out to the neural network model
Training, can also the frame of video that there are different livestocks in different scenes sequence of frames of video be used to be trained the neutral net.
In an optional embodiment of the invention, the neural network model is by the face of livestock to the scene video
The livestock occurred in sequential in frame sequence in adjacent each two scene video frame is tracked.Take this, it is possible to increase video
The degree of accuracy of the tracking result of livestock in frame.When training the neural network model, phase in scene video frame sequence can be used
Face's frame of video with livestock is trained to the neural network model, can also use different livestocks in scene video frame sequence
Face's frame of video the neural network model is trained.In order that the neural network model that must train to obtain is to livestock
Tracking result is more accurate, can use face's frame of video of different livestocks in different scenes sequence of frames of video to the neutral net mould
Type is trained, and can also use face's frame of video of identical livestock in different scenes sequence of frames of video to the neural network model
It is trained.
In an optional embodiment of the invention, the neural network model is by the positive face of livestock to the scene video
The livestock occurred in sequential in frame sequence in adjacent each two scene video frame is tracked.Take this, can further carry
The degree of accuracy of the tracking result of livestock in high frame of video.When training the neural network model, scene video frame sequence can be used
The positive face frame of video of identical livestock is trained to the neural network model in row, can also be used in scene video frame sequence not
Positive face frame of video with livestock is trained to the neural network model.In order that obtained neural network model pair must be trained
The tracking result of livestock is more accurate, can use the positive face frame of video of different livestocks in different scenes sequence of frames of video to the nerve
Network model is trained, and can also use the positive face frame of video of identical livestock in different scenes sequence of frames of video to the nerve net
Network model is trained.
In step S203, whenever determining new livestock occur according to tracking result, and determine there is livestock information
When not having the information of the new livestock in livestock Sample Storehouse, then the new livestock is added in the livestock Sample Storehouse
Information.
In the neural network model by the face of livestock to adjacent in the sequential in the scene video frame sequence
The livestock occurred in each two scene video frame is tracked, and in two scene video frames adjacent in sequential in back court
When occurring new livestock in scape frame of video, face image and/or new livestock of the tracking result also including new livestock
Face feature data.The livestock information may include the face image of livestock and/or the characteristic of livestock face.Take this, energy
Enough improve the degree of accuracy of the tracking result of livestock in frame of video.In the neural network model by the positive face of livestock to the field
The livestock occurred in sequential in scape sequence of frames of video in adjacent each two scene video frame is tracked, and phase in sequential
In two adjacent scene video frames when there is new livestock in rear scene frame of video, the tracking result also includes new domestic animal
The face image of poultry and/or the face feature data of new livestock.The livestock information may include livestock face image and/or
The characteristic of livestock face.Take this, can further improve the degree of accuracy of the tracking result of livestock in frame of video.
In an optional embodiment of the invention, when the information of the new livestock is added in the livestock Sample Storehouse,
Methods described also includes：The new livestock is identified, obtains corresponding identification information；Add in the livestock Sample Storehouse
Add the identification information of the new livestock.Take this, each livestock individual in livestock Sample Storehouse, which possesses, belongs to the mark of itself
Information, consequently facilitating distinguishing each livestock individual.
In step S204, whenever determining not occurring new livestock according to the tracking result, then continue to the field
The livestock occurred in sequential in scape sequence of frames of video in adjacent each two scene video frame is tracked.
In an optional embodiment of the invention, methods described also includes：Face image in the beast Sample Storehouse
Quantity when reaching predetermined number, stop to each two scene video frame adjacent in the sequential in the scene video frame sequence
The livestock of middle appearance is tracked.Take this, the foundation of livestock Sample Storehouse can be quickly completed.
In a particular embodiment, the number of livestock is certain in livestock stable breeding region.For livestock stable breeding region
Sample size in the livestock Sample Storehouse that interior livestock is established is also certain.As long as the sample size in livestock Sample Storehouse reaches
The number of livestock in livestock stable breeding region, you can complete the foundation of livestock Sample Storehouse.
In an optional embodiment of the invention, pig is being enclosed for a group, IMAQ is carried out without a first head, and
It is to carry out video record by installing camera around pigsty, as long as ensureing that every pig all occurs inside video, Ke Yitong
The method that the present embodiment offer is provided, pig is numbered automatically, IMAQ and feature extraction.Specific method is to obtain phase
After closing video recording, capture first pig A of appearance first sample image of the face image as livestock Sample Storehouse, then proceed to by
Time series obtains next pig B of appearance face image from video, and pig face is compared by neutral net, judges
Whether pig A and pig B is same head pig, if it is, continuing to look for next pig from video according to time series, if not same
One pig, then the second sample image using pig B face image as livestock Sample Storehouse.Meanwhile continue according to time series from
Next pig is looked in video, compares all sample images of pig in existing livestock Sample Storehouse, by that analogy, when livestock Sample Storehouse
After the number of the sample image of middle pig is equal to number set in advance, you can complete the foundation of livestock Sample Storehouse.This mode can
To save substantial amounts of manpower and materials, while provide fast and accurately means and establish livestock Sample Storehouse.
The Sample Storehouse method for building up of the livestock provided according to the present embodiment, obtain the livestock gathered by image capture device
The scene video frame sequence in stable breeding region；And the neural network model by being tracked for livestock, to the scene video frame sequence
The livestock occurred in sequential in row in adjacent each two scene video frame is tracked；Determined whenever according to tracking result
Now new livestock, and determine to have when not having the information of the new livestock in the livestock Sample Storehouse of livestock information, then exist
The information of the new livestock is added in the livestock Sample Storehouse, thereby, it is possible to rapidly and accurately establish the Sample Storehouse of livestock, section
About substantial amounts of manpower and materials.
The Sample Storehouse method for building up of the livestock of the present embodiment can have image or data-handling capacity by arbitrarily appropriate
Equipment perform, include but is not limited to：It is camera, terminal, mobile terminal, PC, server, mobile unit, amusement equipment, wide
Accuse equipment, personal digital assistant (PDA), tablet personal computer, notebook computer, handheld device, intelligent glasses, intelligent watch, can
Wearable device, virtual display device or display enhancing equipment (such as Google Glass, Oculus Rift, Hololens, Gear
VR) etc..
Embodiment three
Fig. 3 is a kind of flow chart of the counting method of according to embodiments of the present invention three livestock.As shown in figure 3, this implementation
The counting method for the livestock that example provides includes：
In step S301, the scene video frame sequence in the livestock stable breeding region gathered by image capture device is obtained.
Wherein, described image collecting device may include camera.It is understood that any be used to obtain livestock stable breeding area
The equipment of the scene video frame sequence in domain is applied to this, and the present embodiment is not restricted to this.Specifically, can be in livestock stable breeding area
An image capture device is installed in domain, also can install an image capture device in each orientation in livestock stable breeding region.Nothing
By any embodiment installation image capture device is taken, as long as each livestock in guarantee livestock stable breeding region is in scene visual
Occur in frequency frame sequence.
In step s 302, by the livestock occurred in each scene video frame in the scene video frame sequence respectively with
The livestock in each sample image in default livestock Sample Storehouse is compared, and obtains the first comparison result.
Wherein, the default livestock Sample Storehouse be according to embodiments of the present invention one or the embodiment of the present invention two described in side
Method establishes what is obtained.The comparison result include in scene video frame the livestock that occurs respectively with default livestock Sample Storehouse
Livestock in each sample image differs, or in the livestock occurred in scene video frame and default livestock Sample Storehouse
Livestock in one sample image is identical.
In step S303, determine the livestock according to first comparison result first checks result.
Because each livestock in livestock stable breeding region occurs in scene sequence of frames of video, according to scene video frame sequence
In each scene video frame in the livestock that occurs respectively with the livestock in each sample image in default livestock Sample Storehouse
The first comparison result can determine the livestock that there is currently in livestock stable breeding region and currently be lost in livestock stable breeding region
Livestock.
The counting method of the livestock provided according to the present embodiment, obtain the livestock stable breeding area gathered by image capture device
The scene video frame sequence in domain；And by the livestock occurred in each scene video frame in the scene video frame sequence respectively with
The livestock in each sample image in default livestock Sample Storehouse is compared, and obtains the first comparison result；Further according to described
First comparison result determines that the first of the livestock checks result, thus, not only facilitates the livestock in auto inventory stable breeding region,
And the change of livestock in stable breeding region can be monitored in real time.
The counting method of the livestock of the present embodiment can be by any appropriate equipment with image or data-handling capacity
Perform, include but is not limited to：Camera, terminal, mobile terminal, PC, server, mobile unit, amusement equipment, advertisement are set
It is standby, personal digital assistant (PDA), tablet personal computer, notebook computer, handheld device, intelligent glasses, intelligent watch, wearable
Equipment, virtual display device or display enhancing equipment (such as Google Glass, Oculus Rift, Hololens, Gear VR)
Deng.
Example IV
Fig. 4 is a kind of flow chart of the counting method of according to embodiments of the present invention four livestock.As shown in figure 4, this implementation
The counting method for the livestock that example provides includes：
In step S401, the scene video frame sequence in the livestock stable breeding region gathered by image capture device is obtained.
Wherein, the livestock stable breeding region may include farm house, for example, pig house, sheepfold, cattle pen etc..The scene video frame
Sequence includes the video image of all livestocks in livestock stable breeding region.Specifically, the livestock in livestock stable breeding region includes following
At least one of：Chicken, duck, goose, ox, sheep, horse, pig.
In step S402, by the neural network model compared for livestock face, by the scene video frame sequence
In each scene video frame in the face of livestock that occurs respectively with each sample image in default livestock Sample Storehouse
The face of livestock be compared, obtain first comparison result.
Wherein, the neural network model can be the god of any appropriate achievable target comparison or recongnition of objects
Through network, including but not limited to generation network in convolutional neural networks, enhancing learning neural network, confrontation neutral net etc.
Deng.The setting of concrete structure can suitably be set according to the actual requirements by those skilled in the art in neutral net, such as convolutional layer
The number of plies, the size of convolution kernel, port number etc., the embodiment of the present invention is not restricted to this.Wherein, the default livestock sample
This storehouse be according to embodiments of the present invention one or the embodiment of the present invention two described in method establish what is obtained.
In the present embodiment, the neural network model can have two inputs, an output end.Specifically, one
Input is used for the scene video frame inputted in the scene video frame sequence, and another input is used to input livestock sample
A sample image in this storehouse, the output end are used for face and the sample image for exporting the livestock occurred in scene frame of video
The comparison result of the face of the livestock of middle appearance.
In a particular embodiment, will be every in the scene video frame sequence by the neural network model
The face of the livestock occurred in individual scene video frame respectively with the livestock in each sample image in default livestock Sample Storehouse
Face be compared before, it is necessary to be trained to neural network model.Specifically, by identical domestic animal in scene video frame sequence
Neural network model to be trained described in face's frame of video input of poultry, or the face by different livestocks in scene video frame sequence
Portion's frame of video inputs neural network model to be trained, and comparison result further according to demarcation and the comparison result currently obtained determine
Difference, further according to the network parameter of neural network model described in the discrepancy adjustment.By calculating the difference, obtained to current
Comparison result assessed, the foundation to be used as follow-up training neural network model.More specifically, can be reverse by the difference
Neural network model is transferred to, so as to iteratively train the neural network model.The training of neural network model is an iteration
Process, only a training process therein is illustrated the embodiment of the present invention, but it should be understood by those skilled in the art that
Each training to neural network model can all use the training method, until completing the training of neural network model.
In an optional embodiment of the invention, in order that the neural network model that must train to obtain is to livestock in frame of video
Comparison result it is more accurate, can use different scenes sequence of frames of video in different livestocks face's frame of video to the neutral net
Model is trained, and can also use face's frame of video of identical livestock in different scenes sequence of frames of video to the neutral net mould
Type is trained.
In step S403, determine the livestock according to first comparison result first checks result.
Wherein, the first of the livestock checks result including at least one of following：Work as in the livestock stable breeding region
It is there is currently in the preceding quantity that the livestock in the livestock Sample Storehouse be present, the livestock stable breeding region in the livestock Sample Storehouse
The identification information of livestock, the quantity, described of livestock in the livestock Sample Storehouse is currently lost in the livestock stable breeding region
The identification information of the livestock in the livestock Sample Storehouse is currently lost in livestock stable breeding region.
Alternatively, methods described also includes：When the livestock occurred in the scene video frame in the scene video frame sequence
When being differed with the livestock in each sample image in the livestock Sample Storehouse, the domestic animal that will occur in the scene video frame
The livestock that poultry increases newly with default livestock in each scene video frame in storehouse respectively is compared, and obtains the second comparison result；
Determine that the second of the livestock checks result according to first comparison result and second comparison result.
Specifically, in each counting livestock, just establish corresponding livestock and increase storehouse newly.Checking for livestock is completed every time
When, just delete corresponding livestock and increase storehouse newly.That is, the livestock established during each counting livestock increases the scene stored in storehouse newly
Frame of video differs.Differed more specifically, livestock increases the livestock occurred in each scene video frame in storehouse newly,
And livestock increases the livestock occurred in the scene video frame in storehouse newly with going out in each sample image in the livestock Sample Storehouse
Existing livestock differs.
In a particular embodiment, when according to the domestic animal occurred in second comparison result acquisition scene video frame
When poultry differs with the livestock occurred in each scene video frame in the newly-increased storehouse of the livestock, the scene video frame is added
The livestock is added to increase newly in storehouse.When according to the livestock and institute occurred in second comparison result acquisition scene video frame
When stating livestock and increasing that the livestock that occurs is identical in a scene video frame in storehouse newly, the scene video frame is abandoned, and wait it
The scene video frame that the livestock of middle appearance differs with the livestock occurred in each sample image in the livestock Sample Storehouse.
Wherein, the second of the livestock checks result including at least one of following：Work as in the livestock stable breeding region
It is there is currently in the preceding quantity that the livestock in the livestock Sample Storehouse be present, the livestock stable breeding region in the livestock Sample Storehouse
The identification information of livestock, the quantity, described of livestock in the livestock Sample Storehouse is currently lost in the livestock stable breeding region
The identification information of the livestock in the livestock Sample Storehouse, current in the livestock stable breeding region is currently lost in livestock stable breeding region
With the presence or absence of the quantity that the new livestock is there is currently in new livestock, the livestock stable breeding region.Specifically, it is described new
Livestock differs with the livestock occurred in each sample image in the livestock Sample Storehouse.
Reality application in, the present embodiment provide livestock counting method cannot be only used for quick counting livestock
Column number, but also available for being monitored to livestock individual, to the delivering for sale of livestock, lairage situation is monitored.
The counting method of the livestock provided according to the present embodiment, obtain the livestock stable breeding area gathered by image capture device
The scene video frame sequence in domain；And by the livestock occurred in each scene video frame in the scene video frame sequence respectively with
The livestock in each sample image in default livestock Sample Storehouse is compared, and obtains the first comparison result；Further according to described
First comparison result determines that the first of the livestock checks result, thus, not only facilitates the livestock in auto inventory stable breeding region,
And the change of livestock in stable breeding region can be monitored in real time.
The counting method of the livestock of the present embodiment can be by any appropriate equipment with image or data-handling capacity
Perform, include but is not limited to：Camera, terminal, mobile terminal, PC, server, mobile unit, amusement equipment, advertisement are set
It is standby, personal digital assistant (PDA), tablet personal computer, notebook computer, handheld device, intelligent glasses, intelligent watch, wearable
Equipment, virtual display device or display enhancing equipment (such as Google Glass, Oculus Rift, Hololens, Gear VR)
Deng.
Embodiment five
The embodiment of the present invention additionally provides a kind of electronic equipment, such as can be mobile terminal, personal computer (PC), put down
Plate computer, server etc..Below with reference to Fig. 5, it illustrates suitable for for realizing the terminal device of the embodiment of the present invention or service
The structural representation of the electronic equipment 500 of device.As shown in figure 5, electronic equipment 500 includes one or more first processors, the
One communication device etc., one or more of first processors are for example：One or more CPU (CPU) 501, and/
Or one or more image processors (GPU) 513 etc., first processor can be according to being stored in read-only storage (ROM) 502
Executable instruction or performed from the storage executable instruction that is loaded into random access storage device (RAM) 503 of part 508
Various appropriate actions and processing.In the present embodiment, the first read-only storage 502 and random access storage device 503 are referred to as
One memory.First communication device includes communication component 512 and/or communication interface 509.Wherein, communication component 512 may include but
Be not limited to network interface card, the network interface card may include but be not limited to IB (Infiniband) network interface card, communication interface 509 include such as LAN card,
The communication interface of the NIC of modem etc., communication interface 509 perform mailing address via the network of such as internet
Reason.
First processor can communicate to perform executable finger with read-only storage 502 and/or random access storage device 503
Order, is connected with communication component 512 by the first communication bus 504 and is communicated through communication component 512 with other target devices, from
And complete to operate corresponding to the method for building up of livestock Sample Storehouse any one of provided in an embodiment of the present invention, pass through figure for example, obtaining
As the scene video frame sequence in the livestock stable breeding region that collecting device gathers；By the neural network model tracked for livestock,
The livestock occurred in each two scene video frame adjacent in sequential in the scene video frame sequence is tracked；Whenever
Determine new livestock occur according to tracking result, and do not have in the livestock Sample Storehouse for determining to have livestock information described new
During the information of livestock, then the information of the new livestock is added in the livestock Sample Storehouse.
In addition, in RAM 503, various programs and data needed for device operation can be also stored with.CPU501 or
GPU513, ROM502 and RAM503 are connected with each other by the first communication bus 504.In the case where there is RAM503, ROM502
For optional module.RAM503 stores executable instruction, or executable instruction is operationally write into ROM502, executable instruction
Make first processor perform corresponding to above-mentioned communication means to operate.Input/output (I/O) interface 505 is also connected to the first communication
Bus 504.Communication component 512 can with integrally disposed, it can also be provided that have multiple submodule (such as multiple IB network interface cards), and
Chained in communication bus.
I/O interfaces 505 are connected to lower component：Importation 506 including keyboard, mouse etc.；Penetrated including such as negative electrode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 508 including hard disk etc.；
And the communication interface 509 of the NIC including LAN card, modem etc..Driver 510 is also according to needing to connect
It is connected to I/O interfaces 505.Detachable media 511, such as disk, CD, magneto-optic disk, semiconductor memory etc., pacify as needed
On driver 510, in order to which the computer program read from it is mounted into storage part 508 as needed.
Need what is illustrated, framework as shown in Figure 5 is only a kind of optional implementation, can root during concrete practice
Selected, deleted, increased or replaced according to the component count amount and type being actually needed to above-mentioned Fig. 5；Set in difference in functionality part
Put, can also use the implementation such as separately positioned or integrally disposed, such as GPU and CPU is separable sets or can be by GPU collection
Into on CPU, communication device is separable to be set, can also be integrally disposed on CPU or GPU, etc..These interchangeable embodiment party
Formula 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
Include corresponding perform to instruct corresponding to method and step provided in an embodiment of the present invention, gathered for example, obtaining by image capture device
Livestock stable breeding region scene video frame sequence；By the neural network model tracked for livestock, to the scene video
The livestock occurred in sequential in frame sequence in adjacent each two scene video frame is tracked；Whenever true according to tracking result
When making now new livestock, and not having the information of the new livestock in the livestock Sample Storehouse for determining to have livestock information,
The information of the new livestock is then added in the livestock Sample Storehouse.In such embodiments, the computer program can be with
It is downloaded and installed from network by communication device, and/or is mounted from detachable media 511.In the computer program quilt
When first processor performs, the above-mentioned function of being limited in the method for the embodiment of the present invention is performed.
Embodiment six
The embodiment of the present invention additionally provides a kind of electronic equipment, such as can be mobile terminal, personal computer (PC), put down
Plate computer, server etc..Below with reference to Fig. 6, it illustrates suitable for for realizing the terminal device of the embodiment of the present invention or service
The structural representation of the electronic equipment 600 of device.As shown in fig. 6, electronic equipment 600 includes one or more second processors, the
Two communication devices etc., one or more of second processors are for example：One or more CPU (CPU) 601, and/
Or one or more image processors (GPU) 613 etc., second processor can be according to being stored in read-only storage (ROM) 602
Executable instruction or performed from the storage executable instruction that is loaded into random access storage device (RAM) 603 of part 608
Various appropriate actions and processing.In the present embodiment, the second read-only storage 602 and random access storage device 603 are referred to as
Two memories.Second communication device includes communication component 612 and/or communication interface 609.Wherein, communication component 612 may include but
Be not limited to network interface card, the network interface card may include but be not limited to IB (Infiniband) network interface card, communication interface 609 include such as LAN card,
The communication interface of the NIC of modem etc., communication interface 609 perform mailing address via the network of such as internet
Reason.
Second processor can communicate to perform executable finger with read-only storage 602 and/or random access storage device 603
Order, is connected with communication component 612 by the second communication bus 604 and is communicated through communication component 612 with other target devices, from
And complete to operate corresponding to the counting method of livestock any one of provided in an embodiment of the present invention, pass through IMAQ for example, obtaining
The scene video frame sequence in the livestock stable breeding region of equipment collection；By each scene video frame in the scene video frame sequence
The livestock of middle appearance is compared with the livestock in each sample image in default livestock Sample Storehouse respectively, obtains the first ratio
To result；Determine the livestock according to first comparison result first checks result, wherein, the default livestock sample
Storehouse be according to embodiments of the present invention one or the embodiment of the present invention two described in method establish what is obtained.
In addition, in RAM 603, various programs and data needed for device operation can be also stored with.CPU601 or
GPU613, ROM602 and RAM603 are connected with each other by the second communication bus 604.In the case where there is RAM603, ROM602
For optional module.RAM603 stores executable instruction, or executable instruction is operationally write into ROM602, executable instruction
Make second processor perform corresponding to above-mentioned communication means to operate.Input/output (I/O) interface 605 is also connected to the second communication
Bus 604.Communication component 612 can with integrally disposed, it can also be provided that have multiple submodule (such as multiple IB network interface cards), and
Chained in communication bus.
I/O interfaces 605 are connected to lower component：Importation 606 including keyboard, mouse etc.；Penetrated including such as negative electrode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 608 including hard disk etc.；
And the communication interface 609 of the NIC including LAN card, modem etc..Driver 610 is also according to needing to connect
It is connected to I/O interfaces 605.Detachable media 611, such as disk, CD, magneto-optic disk, semiconductor memory etc., pacify as needed
On driver 610, in order to which the computer program read from it is mounted into storage part 608 as needed.
Need what is illustrated, framework as shown in Figure 6 is only a kind of optional implementation, can root during concrete practice
Selected, deleted, increased or replaced according to the component count amount and type being actually needed to above-mentioned Fig. 6；Set in difference in functionality part
Put, can also use the implementation such as separately positioned or integrally disposed, such as GPU and CPU is separable sets or can be by GPU collection
Into on CPU, communication device is separable to be set, can also be integrally disposed on CPU or GPU, etc..These interchangeable embodiment party
Formula 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
Include corresponding perform to instruct corresponding to method and step provided in an embodiment of the present invention, gathered for example, obtaining by image capture device
Livestock stable breeding region scene video frame sequence；By what is occurred in each scene video frame in the scene video frame sequence
Livestock is compared with the livestock in each sample image in default livestock Sample Storehouse respectively, obtains the first comparison result；
Determine the livestock according to first comparison result first checks result, wherein, the default livestock Sample Storehouse is root
Establish what is obtained according to the method described in the embodiment of the present invention one or the embodiment of the present invention two.In such embodiments, the calculating
Machine program can be downloaded and installed by communication device from network, and/or is mounted from detachable media 611.In the meter
When calculation machine program is performed by second processor, the above-mentioned function of being limited in the method for the embodiment of the present invention is performed.
It may be noted that according to the needs of implementation, all parts/step described in the embodiment of the present invention can be split as more
Multi-part/step, the part operation of two or more components/steps or components/steps can be also combined into new part/step
Suddenly, to realize the purpose of the embodiment of the present invention.
Above-mentioned method according to embodiments of the present invention can be realized in hardware, firmware, or be implemented as being storable in note
Software or computer code in recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk), or it is implemented through net
The original storage that network is downloaded is in long-range recording medium or nonvolatile machine readable media and will be stored in local recording medium
In computer code, can be stored in using all-purpose computer, application specific processor or can compile so as to method described here
Such software processing in journey or the recording medium of specialized hardware (such as ASIC or FPGA).It is appreciated that computer, processing
Device, microprocessor controller or programmable hardware include can storing or receive software or computer code storage assembly (for example,
RAM, ROM, flash memory etc.), when the software or computer code are by computer, processor or hardware access and when performing, realize
Processing method described here.In addition, when all-purpose computer accesses the code for realizing the processing being shown in which, code
Perform special-purpose computer all-purpose computer is converted to for performing the processing being shown in which.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and method and step, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the embodiment of the present invention.
Embodiment of above is merely to illustrate the embodiment of the present invention, and is not the limitation to the embodiment of the present invention, relevant skill
The those of ordinary skill in art field, in the case where not departing from the spirit and scope of the embodiment of the present invention, it can also make various
Change and modification, therefore all equivalent technical schemes fall within the category of the embodiment of the present invention, the patent of the embodiment of the present invention
Protection domain should be defined by the claims.
Claims (15)
1. a kind of method for building up of livestock Sample Storehouse, it is characterised in that methods described includes：
Obtain the scene video frame sequence in the livestock stable breeding region gathered by image capture device；
By the neural network model tracked for livestock, to each two adjacent in the sequential in the scene video frame sequence
The livestock occurred in scene video frame is tracked；
Whenever determining new livestock occur according to tracking result, and do not have in the livestock Sample Storehouse for determining to have livestock information
During the information of the new livestock, then the information of the new livestock is added in the livestock Sample Storehouse.
2. according to the method for claim 1, it is characterised in that the face image of the livestock information including livestock and/or
The characteristic of livestock face.
3. according to the method for claim 2, it is characterised in that the face image of the livestock is the positive face figure of the livestock
Picture.
4. according to the method for claim 2, it is characterised in that methods described also includes：
When the quantity of the face image in the beast Sample Storehouse reaches predetermined number, stop to the scene video frame sequence
In sequential on the livestock that occurs in adjacent each two scene video frame be tracked.
5. according to the method for claim 1, it is characterised in that methods described also includes：
Whenever according to the tracking result determine do not occur new livestock when, then continue in the scene video frame sequence when
The livestock occurred in sequence in adjacent each two scene video frame is tracked.
6. according to the method for claim 1, it is characterised in that the new livestock is added in the livestock Sample Storehouse
During information, methods described also includes：
The new livestock is identified, obtains corresponding identification information；
The identification information of the new livestock is added in the livestock Sample Storehouse.
7. according to the method described in any one claim in claim 1~6, it is characterised in that the livestock include with
It is at least one of lower：
Chicken, duck, goose, ox, sheep, horse, pig.
8. a kind of counting method of livestock, it is characterised in that methods described includes：
Obtain the scene video frame sequence in the livestock stable breeding region gathered by image capture device；
By the livestock occurred in each scene video frame in the scene video frame sequence respectively with default livestock Sample Storehouse
In each sample image in livestock be compared, obtain the first comparison result；
Determine the livestock according to first comparison result first checks result,
Wherein, the default livestock Sample Storehouse is that the method according to any one claim in claim 1~7 is built
Stand what is obtained.
9. according to the method for claim 8, it is characterised in that each scene by the scene video frame sequence
The livestock occurred in frame of video is compared with the livestock in each sample image in default livestock Sample Storehouse respectively, obtains
First comparison result, including：
By the neural network model compared for livestock face, by each scene video frame in the scene video frame sequence
Face of the face of the livestock of middle appearance respectively with the livestock in each sample image in default livestock Sample Storehouse is compared
It is right, obtain first comparison result.
10. according to the method for claim 8, it is characterised in that methods described also includes：
When the livestock occurred in the scene video frame in the scene video frame sequence and each sample in the livestock Sample Storehouse
When livestock in this image differs, the livestock occurred in the scene video frame is increased newly in storehouse with default livestock respectively
Each scene video frame in livestock be compared, obtain the second comparison result；
Determine that the second of the livestock checks result according to first comparison result and second comparison result.
11. according to the method for claim 10, it is characterised in that the second of the livestock check result include it is following in
At least one：
The quantity of the livestock in the livestock Sample Storehouse is there is currently in the livestock stable breeding region, in the livestock stable breeding region
It there is currently the identification information of the livestock in the livestock Sample Storehouse, currently lose the livestock sample in the livestock stable breeding region
The mark letter of the livestock in the livestock Sample Storehouse is currently lost in the quantity of livestock in this storehouse, the livestock stable breeding region
It is breath, currently described new with the presence or absence of there is currently in new livestock, the livestock stable breeding region in the livestock stable breeding region
The quantity of livestock.
12. a kind of computer-readable recording medium, is stored thereon with computer program instructions, wherein, described program instruction is located
Reason device realizes the step of method for building up of the livestock Sample Storehouse in claim 1~7 described in any one claim when performing.
13. a kind of computer-readable recording medium, is stored thereon with computer program instructions, wherein, described program instruction is located
Reason device realizes the step of counting method of the livestock in claim 8~11 described in any one claim when performing.
14. a kind of electronic equipment, including：First processor, first memory, the first communication device and the first communication bus, institute
First processor, the first memory and first communication device is stated to complete each other by first communication bus
Communication；
The first memory is used to deposit an at least executable instruction, and the executable instruction performs the first processor
The step of method for building up of livestock Sample Storehouse as described in any one claim in claim 1~7.
15. a kind of electronic equipment, including：Second processor, second memory, the second communication device and the second communication bus, institute
Second processor, the second memory and second communication device is stated to complete each other by second communication bus
Communication；
The second memory is used to deposit an at least executable instruction, and the executable instruction performs the second processor
The step of counting method of livestock as described in any one claim in claim 8~11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710792838.2A CN107680080B (en) | 2017-09-05 | 2017-09-05 | Sample library establishing method and checking method for livestock, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710792838.2A CN107680080B (en) | 2017-09-05 | 2017-09-05 | Sample library establishing method and checking method for livestock, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107680080A true CN107680080A (en) | 2018-02-09 |
| CN107680080B CN107680080B (en) | 2020-02-21 |
Family
ID=61134884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710792838.2A Active CN107680080B (en) | 2017-09-05 | 2017-09-05 | Sample library establishing method and checking method for livestock, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107680080B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388877A (en) * | 2018-03-14 | 2018-08-10 | 广州影子控股股份有限公司 | The recognition methods of one boar face |
| CN109376584A (en) * | 2018-09-04 | 2019-02-22 | 湖南大学 | A kind of poultry quantity statistics system and method for animal husbandry |
| CN109461151A (en) * | 2018-11-05 | 2019-03-12 | 上海睿畜电子科技有限公司 | A kind of method, apparatus and system that livestock number is checked |
| CN109785337A (en) * | 2018-12-25 | 2019-05-21 | 哈尔滨工程大学 | Mammal counting method in a kind of column of Case-based Reasoning partitioning algorithm |
| WO2020007363A1 (en) * | 2018-07-06 | 2020-01-09 | 京东数字科技控股有限公司 | Method and apparatus for identifying number of targets, and computer-readable storage medium |
| CN110929077A (en) * | 2019-10-17 | 2020-03-27 | 北京海益同展信息科技有限公司 | Animal profiling method, device, equipment, electronic equipment and computer readable medium |
| CN111028266A (en) * | 2019-12-16 | 2020-04-17 | 洛阳语音云创新研究院 | Livestock and poultry checking method and device, electronic equipment and storage medium |
| CN111680551A (en) * | 2020-04-28 | 2020-09-18 | 平安国际智慧城市科技股份有限公司 | Method and device for monitoring livestock quantity, computer equipment and storage medium |
| CN113554644A (en) * | 2021-08-17 | 2021-10-26 | 湖南金烽信息科技有限公司 | Agricultural product identity recognition and quantity checking system based on convolutional neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070291155A1 (en) * | 2006-06-14 | 2007-12-20 | Canon Kabushiki Kaisha | Image processing apparatus, image sensing apparatus, and control method of image processing apparatus |
| US20110170749A1 (en) * | 2006-09-29 | 2011-07-14 | Pittsburgh Pattern Recognition, Inc. | Video retrieval system for human face content |
| CN106778555A (en) * | 2016-11-30 | 2017-05-31 | 石河子大学 | A kind of milk cow based on machine vision ruminates chewing, swallows number of times statistical method |
| CN107092931A (en) * | 2017-04-24 | 2017-08-25 | 河北工业大学 | A kind of method of milk cow individual identification |
-
2017
- 2017-09-05 CN CN201710792838.2A patent/CN107680080B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070291155A1 (en) * | 2006-06-14 | 2007-12-20 | Canon Kabushiki Kaisha | Image processing apparatus, image sensing apparatus, and control method of image processing apparatus |
| US20110170749A1 (en) * | 2006-09-29 | 2011-07-14 | Pittsburgh Pattern Recognition, Inc. | Video retrieval system for human face content |
| CN106778555A (en) * | 2016-11-30 | 2017-05-31 | 石河子大学 | A kind of milk cow based on machine vision ruminates chewing, swallows number of times statistical method |
| CN107092931A (en) * | 2017-04-24 | 2017-08-25 | 河北工业大学 | A kind of method of milk cow individual identification |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388877A (en) * | 2018-03-14 | 2018-08-10 | 广州影子控股股份有限公司 | The recognition methods of one boar face |
| WO2020007363A1 (en) * | 2018-07-06 | 2020-01-09 | 京东数字科技控股有限公司 | Method and apparatus for identifying number of targets, and computer-readable storage medium |
| CN109376584A (en) * | 2018-09-04 | 2019-02-22 | 湖南大学 | A kind of poultry quantity statistics system and method for animal husbandry |
| CN109461151A (en) * | 2018-11-05 | 2019-03-12 | 上海睿畜电子科技有限公司 | A kind of method, apparatus and system that livestock number is checked |
| CN109785337B (en) * | 2018-12-25 | 2021-07-06 | 哈尔滨工程大学 | In-column mammal counting method based on example segmentation algorithm |
| CN109785337A (en) * | 2018-12-25 | 2019-05-21 | 哈尔滨工程大学 | Mammal counting method in a kind of column of Case-based Reasoning partitioning algorithm |
| CN110929077A (en) * | 2019-10-17 | 2020-03-27 | 北京海益同展信息科技有限公司 | Animal profiling method, device, equipment, electronic equipment and computer readable medium |
| CN111028266A (en) * | 2019-12-16 | 2020-04-17 | 洛阳语音云创新研究院 | Livestock and poultry checking method and device, electronic equipment and storage medium |
| CN111028266B (en) * | 2019-12-16 | 2023-05-23 | 洛阳语音云创新研究院 | Livestock and poultry inventory method and device, electronic equipment and storage medium |
| CN111680551A (en) * | 2020-04-28 | 2020-09-18 | 平安国际智慧城市科技股份有限公司 | Method and device for monitoring livestock quantity, computer equipment and storage medium |
| CN111680551B (en) * | 2020-04-28 | 2024-06-11 | 平安国际智慧城市科技股份有限公司 | Method, device, computer equipment and storage medium for monitoring livestock quantity |
| CN113554644A (en) * | 2021-08-17 | 2021-10-26 | 湖南金烽信息科技有限公司 | Agricultural product identity recognition and quantity checking system based on convolutional neural network |
| CN113554644B (en) * | 2021-08-17 | 2022-08-09 | 湖南金烽信息科技有限公司 | Agricultural product identity recognition and quantity checking system based on convolutional neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107680080B (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107680080A (en) | The Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment | |
| Zhuang et al. | Detection of sick broilers by digital image processing and deep learning | |
| WO2020119659A1 (en) | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium | |
| Lin et al. | Sorghum panicle detection and counting using unmanned aerial system images and deep learning | |
| Zhou et al. | Automated counting of rice panicle by applying deep learning model to images from unmanned aerial vehicle platform | |
| BR122020015963A2 (en) | computer-implemented method of determining a number of grains from an image of a corn and non-transitory storage media | |
| CN107679183A (en) | Grader training data acquisition methods and device, server and storage medium | |
| Zang et al. | Detection method of wheat spike improved YOLOv5s based on the attention mechanism | |
| Soares et al. | Cattle counting in the wild with geolocated aerial images in large pasture areas | |
| CN105654313A (en) | Intelligent cloud scale and method for performing Internet-of-things tracing through same | |
| Wu et al. | Improved ResNet-50 deep learning algorithm for identifying chicken gender | |
| Arvind et al. | Edge computing based smart aquaponics monitoring system using deep learning in IoT environment | |
| CN107833145A (en) | The database building method and source tracing method of livestock, storage medium and electronic equipment | |
| CN116257792B (en) | Smart city carbon neutralization data analysis system | |
| US11985953B2 (en) | Poultry health benchmarking system and method | |
| Liu et al. | Field pest monitoring and forecasting system for pest control | |
| Moreira et al. | AgroLens: A low-cost and green-friendly Smart Farm Architecture to support real-time leaf disease diagnostics | |
| Rendel et al. | Optimisation of the resource of land-based livestock systems to advance sustainable agriculture: A farm-level analysis | |
| Guo et al. | Panicle Ratio Network: streamlining rice panicle measurement by deep learning with ultra-high-definition aerial images in the field | |
| Gupta et al. | Computer vision-based approach for automatic detection of dairy cow breed | |
| Gao et al. | CNN-Bi-LSTM: A complex environment-oriented cattle behavior classification network based on the fusion of CNN and Bi-LSTM | |
| Xu et al. | Automatic quantification and assessment of grouped pig movement using the XGBoost and YOLOv5s models | |
| Pavkin et al. | Development Results of a Cross-Platform Positioning System for a Robotics Feed System at a Dairy Cattle Complex | |
| Patil et al. | Cognitive intelligence of internet of things in smart agriculture applications | |
| Luo et al. | Automatic Recognition and Quantification Feeding Behaviors of Nursery Pigs Using Improved YOLOV5 and Feeding Functional Area Proposals |
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 |