CN108175389A - A kind of Multi-source Information Fusion milk cow behavior monitoring system and method - Google Patents
A kind of Multi-source Information Fusion milk cow behavior monitoring system and method Download PDFInfo
- Publication number
- CN108175389A CN108175389A CN201711405688.1A CN201711405688A CN108175389A CN 108175389 A CN108175389 A CN 108175389A CN 201711405688 A CN201711405688 A CN 201711405688A CN 108175389 A CN108175389 A CN 108175389A
- Authority
- CN
- China
- Prior art keywords
- data
- pulse
- cow
- parameter
- body temperature
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 60
- 230000004927 fusion Effects 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 36
- 235000013336 milk Nutrition 0.000 title claims abstract description 11
- 239000008267 milk Substances 0.000 title claims abstract description 11
- 210000004080 milk Anatomy 0.000 title claims abstract description 11
- 230000036760 body temperature Effects 0.000 claims abstract description 81
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 238000006243 chemical reaction Methods 0.000 claims abstract description 17
- 241000283690 Bos taurus Species 0.000 claims description 109
- 208000030175 lameness Diseases 0.000 claims description 25
- 235000013365 dairy product Nutrition 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 14
- 230000012173 estrus Effects 0.000 claims description 13
- 238000005452 bending Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 8
- 206010022562 Intermittent claudication Diseases 0.000 claims description 6
- 208000024980 claudication Diseases 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 39
- 238000009395 breeding Methods 0.000 description 7
- 230000001488 breeding effect Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003750 conditioning effect Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 235000020185 raw untreated milk Nutrition 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61D—VETERINARY INSTRUMENTS, IMPLEMENTS, TOOLS, OR METHODS
- A61D17/00—Devices for indicating trouble during labour of animals ; Methods or instruments for detecting pregnancy-related states of animals
- A61D17/002—Devices for indicating trouble during labour of animals ; Methods or instruments for detecting pregnancy-related states of animals for detecting period of heat of animals, i.e. for detecting oestrus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/40—Animals
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Physiology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Cardiology (AREA)
- Animal Husbandry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Environmental Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Dentistry (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Biodiversity & Conservation Biology (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Pulmonology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Pregnancy & Childbirth (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
Abstract
The present invention provides a kind of Multi-source Information Fusion milk cow behavior monitoring system and methods.Method includes：Data fusion is carried out to the body temperature parameter of acquisition, Pulse-Parameters and amount of exercise parameter respectively, obtains temperature data, pulse data and amount of exercise data；The video frame in milk cow monitoring video is acquired, conversion is normalized to the video frame of the acquisition, obtains image data；Based on the temperature data, the pulse data, the amount of exercise data and described image data, sample data matrix is built；Based on the sample matrix, outlier is determined whether there is using density clustering algorithm；Show that outlier corresponds to the moment if there are outlier, milk cow is in heat state.The present invention is avoided the poor anti jamming capability problem of single data, is realized the accurate judgement to milk cow behavior state, and the effect with reliability height, zmodem using the complementarity between different dimensions data.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a multi-source information fusion cow behavior monitoring system and method.
Background
With the progress and development of the times, the living standard of people is gradually improved, and the demand of dairy products in daily life is increasingly increased. The key factor for the development of the dairy industry is the yield and quality of raw milk, and the health and oestrus of cows are the key elements determining the quality and yield of milk. The physical sign parameters of the dairy cows comprise body temperature, pulse, exercise amount and the like, and are important indexes for evaluating the health condition and physiological state of the dairy cows. Normally, the physical parameters of cows only slightly change within a relatively constant range, but increase or decrease to different degrees during pathological processes and oestrus. Therefore, monitoring of cow behavioral states is very important in the dairy industry.
The existing cow behavior state monitoring adopts a digital monitoring method, introduces a digital technology into cow breeding, monitors the behavior state of cows by an electronic sensor, and collects and records the physical parameters of individual cows on site. For the farm, the labor force can be saved, the diseases of the dairy cows can be timely found and correctly diagnosed, the prevention and the control of the infectious diseases of the dairy cows are facilitated, the estrus of the dairy cows can be identified, the milk production period of the dairy cows can be prolonged, and the milk yield can be improved. In addition, due to the fact that the system is provided with a background data backup system, management personnel can conduct operation management on historical data, and valuable data materials are reserved for long-term development of farms. However, the existing digital monitoring method is a single signal preprocessing technology, and only has good information response to a certain signal, so that a certain judgment error is generated, the robustness is poor, and the problems of high false alarm rate and high false alarm rate are caused.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a multi-source information fusion cow behavior monitoring system and method, which realize real-time monitoring and improve the monitoring accuracy through mutual fusion of multi-source information.
In order to achieve the purpose, the invention provides the following technical scheme:
in one aspect, the invention provides a multi-source information fusion cow behavior monitoring method, which comprises the following steps:
acquiring body temperature parameters, pulse parameters and exercise quantity parameters of the cows, and respectively carrying out data fusion on the acquired body temperature parameters, pulse parameters and exercise quantity parameters to obtain body temperature data, pulse data and exercise quantity data;
collecting video frames in the cow surveillance videos, and performing normalization conversion on the collected video frames to obtain image data;
constructing a sample data matrix based on the body temperature data, the pulse data, the motion amount data and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
determining whether outliers exist by adopting a density clustering algorithm based on the sample matrix;
and if the outlier exists, determining that the cow is in an oestrous state at the moment corresponding to the outlier.
Further, the monitoring method further comprises:
calculating and acquiring a bending angle of the back of the cow according to the video frame;
calculating a claudication parameter according to the bending angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
if the calculated lameness parameter is larger than a preset lameness parameter, the cow is indicated to be in a lameness state.
Further, the monitoring method further comprises:
and when the cow is in an oestrus state or a lameness state, early warning is carried out.
Furthermore, a temperature sensor, a pulse sensor and a vibration sensor are respectively adopted to respectively obtain the body temperature parameter, the pulse parameter and the exercise quantity parameter of the cow.
Further, the data fusion is carried out on the collected body temperature parameter, the collected pulse parameter and the collected exercise amount parameter respectively to obtain body temperature data, pulse data and exercise amount data, and the method comprises the following steps:
carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
performing density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and performing clustering feature extraction on the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain clustering feature extraction fused motion quantity data.
On the other hand, the invention also provides a multi-source information fusion cow behavior monitoring system, which comprises:
the characteristic parameter monitoring unit is used for acquiring body temperature parameters, pulse parameters and motion parameters of the cows, and respectively carrying out data fusion on the acquired body temperature parameters, pulse parameters and motion parameters to obtain body temperature data, pulse data and motion data;
the behavior characteristic monitoring unit is used for acquiring video frames in the cow monitoring video and carrying out normalization conversion on the acquired video frames to obtain image data;
the processing unit is used for constructing a sample data matrix based on the body temperature data, the pulse data, the motion amount data and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
the judging unit is used for determining whether outliers exist by adopting a density clustering algorithm based on the sample matrix;
and if the outlier exists, determining that the cow is in an oestrous state at the moment corresponding to the outlier.
Further, the monitoring system further comprises:
the acquisition unit is used for calculating and acquiring the bending angle of the back of the cow according to the video frame;
a calculating unit for calculating a claudication parameter according to the bending angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
a determination unit for indicating that the cow is in a lameness state if the calculated lameness parameter is greater than a preset lameness parameter.
Further, the monitoring system further comprises:
and the early warning unit is used for early warning when the cow is in an oestrus state or a lameness state.
Furthermore, a temperature sensor, a pulse sensor and a vibration sensor are respectively adopted to respectively obtain the body temperature parameter, the pulse parameter and the exercise quantity parameter of the cow.
Further, the characteristic parameter monitoring unit includes:
the first conversion module is used for carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
the second conversion module is used for carrying out density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and the third conversion module is used for extracting the clustering characteristics of the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain the motion quantity data after the clustering characteristics are extracted and fused.
According to the technical scheme, the multi-source information fusion cow behavior monitoring system and method provided by the invention have the advantages that the cow state is monitored by adopting the image behavior recognition and physiological data characteristic extraction modes, the complementarity among different dimensional data is effectively utilized, the problem of poor anti-interference capability of single data is avoided, the cow behavior state is accurately judged, and the effects of high reliability and good fault tolerance are realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a multi-source information fusion cow behavior monitoring method provided by an embodiment of the invention;
fig. 2 is a schematic flowchart of a specific implementation of step S101 in a multi-source information fusion cow behavior monitoring method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a multisource information fusion cow behavior monitoring system provided by an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a multi-source information fusion cow behavior monitoring method, and particularly comprises the following steps of:
s101: acquiring body temperature parameters, pulse parameters and exercise quantity parameters of the cows, and respectively carrying out data fusion on the acquired body temperature parameters, pulse parameters and exercise quantity parameters to obtain body temperature data, pulse data and exercise quantity data;
in the step, physical sign parameter data of the cow are represented by body temperature parameters, pulse parameters and motion parameters of the cow, wherein the body temperature parameters, the pulse parameters and the motion parameters of the cow are respectively obtained by adopting a temperature sensor, a pulse sensor and a vibration sensor.
Carry out data fusion respectively through body temperature parameter, pulse parameter and the amount of exercise parameter to the characteristic parameter data of sign milk cow, specifically include:
carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
performing density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and performing clustering feature extraction on the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain clustering feature extraction fused motion quantity data.
S102: collecting video frames in the cow surveillance videos, and performing normalization conversion on the collected video frames to obtain image data;
in the step, a monitoring video of the cow is acquired, video frames are extracted, monitoring information of cow behavior characteristics is acquired, and background removal and noise elimination are performed on the extracted video frames in order to improve the pertinence to the target cow and the display definition of the video frames. And carrying out normalization conversion on the video frames subjected to background removal and noise elimination by adopting a method based on the regional correlation coefficient to form image data representing the cow behaviors.
Setting a minimum bounding box on the video frame, wherein the minimum bounding box takes the cow as a target object, and the area of the minimum bounding box can be as follows:
wherein, I (x, y) is any pixel point in the minimum bounding box, and x and y are horizontal and vertical coordinate values of the pixel point. L and W are the length and width of the minimum bounding box;
the center coordinate of the minimum bounding box is (x)c，yc) Wherein the abscissa xcAnd ordinate ycThe calculation can be made using the following formula:
the image data of cow behavior may be expressed as:
wherein (x)1,y1)，(xj,yj) And the coordinate of the center point of the minimum bounding box of the target object when the time serial number is 1 and the time serial number is j is shown.
S103: constructing a sample data matrix based on the body temperature data, the pulse data, the motion amount data and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
in this step, performing space-time registration on the body temperature data, the pulse data, the exercise amount data and the image data, acquiring the body temperature data, the pulse data, the exercise amount data and the image data at the same time, calculating euclidean distances between any two data of the body temperature data, the pulse data, the exercise amount data and the image data at the same time, taking the calculated euclidean distances as a row of elements in a sample data matrix, acquiring the euclidean distances of each time sequence according to the above manner, and taking the euclidean distances of each time sequence as a row of elements in the sample data matrix, wherein the total length of the time sequence is n, each column in the sample data matrix has n elements, the sample data matrix has n rows of elements, and the sample data matrix can be represented by a following matrix D:
wherein k1, k2, k3 and k4 respectively represent body temperature data, pulse data, motion amount data and image data, dqefDenotes an euclidean distance between a parameter e and a parameter f at a time sequence number q, where q is 1,2,3 … n, n is a total length of the time series and determines a maximum time range for behavior recognition, the parameter e and the parameter f are respectively expressed as any one of k1, k2, k3, and k4, and d is dqef＝||eq-fq||2。
S104: determining whether outliers exist by adopting a density clustering algorithm based on the sample matrix; and if the outlier exists, indicating that the outlier corresponds to the moment, and the cow is in an oestrus state.
In this step, the average value of each row of data in the matrix D is calculated according to the matrix D in the above step S103, wherein the average value of the 1 st row isThe average value of the n-th row isThe average value of each row of data is brought into the density clustering algorithm in turn, and when the category number and the outlier number formed in the clustering result tend to be stable, the minimum average value of the stable result is keptIs the neighborhood radius in the density clustering algorithm.
And determining any core point according to the neighborhood radius and the minimum sample number MinPts, and expanding the core point. The method of expansion starts with the core point and determines all data points connected to the core point density. All core points within a neighborhood of a neighborhood radius with the core point as the origin are traversed and data points connected to these data point densities are determined until there are no data points that can be expanded. The data points on the boundary of the last clustered cluster are all non-core data points. The core points that are not clustered are re-found and extended until there are no new core points in the dataset. Data points in the dataset that are not contained in any cluster constitute outliers. The abnormal outliers can judge that the cow is in oestrus. The core object is data including at least MinPts samples in a neighborhood with a neighborhood radius as a radius.
From the above description, it can be seen that the method for monitoring the behavior of the multi-source information fusion cow provided by the embodiment of the invention monitors the state of the cow by adopting the image behavior recognition and physiological data feature extraction modes, effectively utilizes the complementarity among different dimensional data, avoids the problem of poor anti-interference capability of single data, realizes accurate judgment on the behavior state of the cow, and has the effects of high reliability and good fault tolerance.
On the basis of the above embodiment, the monitoring method further includes:
s201: calculating and acquiring a bending angle of the back of the cow according to the video frame;
in the present step, the first step is carried out,
where h is the vertical distance from the horizontal tangent to the back curve to the long side of the minimum bounding box, x0Is the perpendicular distance from the tangent point of the back curve to the long side of the minimum bounding box to the line of the width side of the minimum bounding box.
S202: calculating a claudication parameter according to the bending angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
wherein, a>1,b>0. When L isimpGreater than a threshold value Limp0And judging the lameness of the cow.
S203: if the calculated lameness parameter is larger than a preset lameness parameter, the cow is indicated to be in a lameness state.
Further, when the cow is in an oestrus state or a lameness state, early warning is carried out.
According to the description, the early warning prompt is carried out according to the abnormal behaviors occurring in the cow breeding process, so that the time of breeding personnel is effectively saved, and the large-scale breeding management efficiency is improved.
In an alternative embodiment, a specific implementation of step S101 is provided. Referring to fig. 2, the step S101 specifically includes the following steps:
s1011: carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
in this step, a time series T based on body temperature parameters for the cowi(i ═ 1, 2.. times, n) by optimal factor weighting, resulting in
Wherein,the body temperature data after the optimal factor weighted fusion. w is aiIs a weighting factor of the temperature data of the time series i and meetsn is the total length of the time sequence and determines the maximum time range of behavior recognition.
S1012: performing density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
in this step, a time sequence P based on pulse parameters for the cowl(1, 2.., n) using a kernel density estimation function for density deviation estimation:
wherein,is the fused pulse data of the kernel density estimate, wlIs an environmental impact weighting factor and satisfies The average pulse of the cow under normal conditions (normal conditions means that the cow is not in heat at 25 ℃ in the environment and has no other interference).Is shown asThe time value is 1. And l is a time sequence serial number, and n is the total length of the time sequence, and determines the maximum time range of behavior recognition.
S1013: performing clustering feature extraction on the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain clustering feature extraction fused motion quantity data;
in this step, the amount of exercise of the cow is Ak(K1, 2.., n) clustering feature extraction is carried out based on a time sequence, wherein the clustering feature extraction method can be a hierarchical clustering method or a K-means clustering method, and an outlier set A in the motion quantity parameters is extractedkAnd for the set of outliers AkCalculating the difference result of the motion amount before and after the normalization processing;
wherein,is the amount of exercise after the clustering feature extraction method is fused. w is akIs an environment-dependent motion quantity weighting factor and satisfies Which represents the average value of the amount of motion,and the distance between the outlier and the motion quantity mean value is shown, k is a time sequence number, and n is the total length of the time sequence, so that the maximum time range of behavior recognition is determined.
According to the description, by adopting a multi-source information fusion method, the behavior characteristics of the dairy cows are respectively mined from the data of different dimensions, and extracted according to the characteristic change of a specific behavior, so that the complementarity among the data of different dimensions is effectively utilized, and the problem of poor anti-interference capability of single data is avoided; the feature fusion method based on the structured data and the unstructured data can effectively improve the accuracy of cow behavior identification.
The embodiment of the invention provides a multisource information fusion cow behavior monitoring system, and referring to fig. 3, the system specifically comprises:
the characteristic parameter monitoring unit 10 is used for acquiring body temperature parameters, pulse parameters and motion parameters of the cows, and performing data fusion on the acquired body temperature parameters, pulse parameters and motion parameters respectively to obtain body temperature data, pulse data and motion data;
when the sensor is adopted to collect data:
the body temperature acquisition module comprises a body temperature sensor, a signal amplifier, a buffer and a digital display screen. The signal amplifier amplifies the temperature data collected by the body temperature sensor, and the amplified temperature signal is temporarily stored in the buffer and can be displayed on the digital display screen.
The pulse acquisition module comprises a pulse sensor, a signal conditioning circuit and a control display element. The signal conditioning circuit outputs the pulse rate data analog signal acquired by the pulse sensor in real time, and outputs a pulse signal synchronous with pulse fluctuation on the control display element.
The motion quantity acquisition module comprises a vibration sensor, a signal processing unit and an A/D converter. The signal processing unit adjusts the weak current signal output by the vibration sensor to a voltage signal required by the A/D converter without distortion. The signal processing unit specifically comprises a signal amplifying circuit, a filter circuit, a precise voltage reference circuit and the like, and mainly realizes the functions of amplifying, shaping, filtering and the like of signals.
The behavior feature monitoring unit 20 is configured to collect video frames in the cow surveillance video, and perform normalization conversion on the collected video frames to obtain image data;
the method comprises the following steps of acquiring a monitoring video of a cow at a video acquisition module, extracting image information of cow behavior characteristic video monitoring through a video frame extraction module, wherein an image processing module comprises: the device comprises a background removing module for removing the background of a video frame and an image denoising module for denoising an image, wherein the background removing module is used for removing the image interference background of the cow behavior characteristic video monitoring, and the denoising module is used for performing noise elimination processing on the image information after the background removal based on wavelet analysis. The video frames processed by the processing module are sent to the behavior feature fusion module, and the behavior feature fusion module performs data fusion on the cow behavior feature video monitoring image data processed by the image processing module based on the feature vectors.
The processing unit 30 is configured to construct a sample data matrix based on the body temperature data, the pulse data, the motion amount data, and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
the judging unit 40 is configured to determine whether an outlier exists by using a density clustering algorithm based on the sample matrix;
and if the outlier exists, indicating that the outlier corresponds to the moment, and the cow is in an oestrus state.
Further, the monitoring system further comprises:
the acquisition unit 50 is used for calculating and acquiring the bending angle of the back of the cow according to the video frame;
a calculating unit 60 for calculating a claudication parameter based on the flexion angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
a determination unit 70 for indicating that the cow is in a lameness state if the calculated lameness parameter is greater than a preset lameness parameter.
Further, the monitoring system further comprises:
and the early warning unit 80 is used for early warning when the cows are in an oestrus state or a lameness state.
Furthermore, a temperature sensor, a pulse sensor and a vibration sensor are respectively adopted to respectively obtain the body temperature parameter, the pulse parameter and the exercise quantity parameter of the cow.
Further, the characteristic parameter monitoring unit includes:
the first conversion module is used for carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
the second conversion module is used for carrying out density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and the third conversion module is used for extracting the clustering characteristics of the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain the motion quantity data after the clustering characteristics are extracted and fused.
From the above description, it can be known that the multisource information fusion cow behavior monitoring system provided by the embodiment of the invention realizes accurate judgment of the cow behavior state by fusing the information obtained by the body temperature acquisition module, the pulse acquisition module, the exercise amount acquisition module and the video monitoring cow behavior characteristics. Is helpful for preventing, controlling, finding and correctly diagnosing and treating the diseases of the dairy cows, finds the problems timely and accurately and ensures the improvement of the milk yield of the dairy cows. According to the monitoring device, early warning prompt is carried out on abnormal behaviors occurring in the cow breeding process, the time of breeding personnel is effectively saved, and the large-scale breeding management efficiency is improved. The method has the beneficial effects of low cost, high reliability and good fault tolerance, and the aim of accurately judging the health state and the oestrus behavior of the dairy cows is fulfilled.
In the description of the present invention, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention is not limited to any single aspect, nor is it limited to any single embodiment, nor is it limited to any combination and/or permutation of these aspects and/or embodiments. Moreover, each aspect and/or embodiment of the present invention may be utilized alone or in combination with one or more other aspects and/or embodiments thereof.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A multi-source information fusion cow behavior monitoring method is characterized by comprising the following steps:
acquiring body temperature parameters, pulse parameters and exercise quantity parameters of the cows, and respectively carrying out data fusion on the acquired body temperature parameters, pulse parameters and exercise quantity parameters to obtain body temperature data, pulse data and exercise quantity data;
collecting video frames in the cow surveillance videos, and performing normalization conversion on the collected video frames to obtain image data;
constructing a sample data matrix based on the body temperature data, the pulse data, the motion amount data and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
determining whether outliers exist by adopting a density clustering algorithm based on the sample matrix;
and if the outlier exists, determining that the cow is in an oestrous state at the moment corresponding to the outlier.
2. The method for monitoring behavior of a multi-source information-fused cow according to claim 1, wherein the method further comprises:
calculating and acquiring a bending angle of the back of the cow according to the video frame;
calculating a claudication parameter according to the bending angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
if the calculated lameness parameter is larger than a preset lameness parameter, the cow is indicated to be in a lameness state.
3. The method for monitoring the behavior of the multi-source information fusion cow according to claim 1 or 2, wherein the method further comprises:
and when the cow is in an oestrus state or a lameness state, early warning is carried out.
4. The method for monitoring the behavior of the multi-source information fusion cow according to claim 1, wherein a temperature sensor, a pulse sensor and a vibration sensor are respectively adopted to respectively obtain the body temperature parameter, the pulse parameter and the motion quantity parameter of the cow.
5. The method for monitoring the behavior of the dairy cow with the multi-source information fusion function according to claim 1, wherein the step of performing data fusion on the collected body temperature parameter, the collected pulse parameter and the collected motion parameter to obtain body temperature data, pulse data and motion data comprises the steps of:
carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
performing density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and performing clustering feature extraction on the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain clustering feature extraction fused motion quantity data.
6. The utility model provides a multisource information fusion milk cow behavior monitoring system which characterized in that includes:
the characteristic parameter monitoring unit is used for acquiring body temperature parameters, pulse parameters and motion parameters of the cows, and respectively carrying out data fusion on the acquired body temperature parameters, pulse parameters and motion parameters to obtain body temperature data, pulse data and motion data;
the behavior characteristic monitoring unit is used for acquiring video frames in the cow monitoring video and carrying out normalization conversion on the acquired video frames to obtain image data;
the processing unit is used for constructing a sample data matrix based on the body temperature data, the pulse data, the motion amount data and the image data; wherein, the elements of the sample data matrix are Euclidean distances between any two data of the body temperature data, the pulse data, the motion amount data and the image data at the same time;
the judging unit is used for determining whether outliers exist by adopting a density clustering algorithm based on the sample matrix;
and if the outlier exists, determining that the cow is in an oestrous state at the moment corresponding to the outlier.
7. The multi-source information fusion cow behavior monitoring system of claim 6, wherein the monitoring system further comprises:
the acquisition unit is used for calculating and acquiring the bending angle of the back of the cow according to the video frame;
a calculating unit for calculating a claudication parameter according to the bending angle, the body temperature parameter, the pulse parameter and the exercise amount parameter,
a determination unit for indicating that the cow is in a lameness state if the calculated lameness parameter is greater than a preset lameness parameter.
8. The multi-source information fusion cow behavior monitoring system according to claim 6 or 7, wherein the monitoring system further comprises:
and the early warning unit is used for early warning when the cow is in an oestrus state or a lameness state.
9. The multi-source information fusion cow behavior monitoring system according to claim 6, wherein a temperature sensor, a pulse sensor and a vibration sensor are respectively adopted to respectively obtain a body temperature parameter, a pulse parameter and an exercise amount parameter of the cow.
10. The multi-source information fusion cow behavior monitoring system according to claim 6, wherein the characteristic parameter monitoring unit comprises:
the first conversion module is used for carrying out optimal factor weighting on the body temperature parameters based on the time sequence of the body temperature parameters to obtain body temperature data after optimal factor weighting fusion;
the second conversion module is used for carrying out density offset estimation on the pulse parameters based on the time sequence of the pulse parameters to obtain pulse data after density estimation fusion;
and the third conversion module is used for extracting the clustering characteristics of the motion quantity parameters based on the time sequence of the motion quantity parameters to obtain the motion quantity data after the clustering characteristics are extracted and fused.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711405688.1A CN108175389B (en) | 2017-12-22 | 2017-12-22 | Multi-source information fusion cow behavior monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711405688.1A CN108175389B (en) | 2017-12-22 | 2017-12-22 | Multi-source information fusion cow behavior monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108175389A true CN108175389A (en) | 2018-06-19 |
| CN108175389B CN108175389B (en) | 2020-12-29 |
Family
ID=62546765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711405688.1A Active CN108175389B (en) | 2017-12-22 | 2017-12-22 | Multi-source information fusion cow behavior monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108175389B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070051A (en) * | 2019-04-24 | 2019-07-30 | 卿胜奎 | Ox heat monitoring method and system based on computer vision technique |
| CN112450118A (en) * | 2020-01-07 | 2021-03-09 | 丰疆智能科技股份有限公司 | Wearing device, detection system and detection method for detecting estrus |
| CN112528772A (en) * | 2020-11-27 | 2021-03-19 | 中国农业大学 | Cow lameness movement characteristic detection method and device based on thermal infrared |
| CN113628182A (en) * | 2021-08-03 | 2021-11-09 | 中国农业大学 | Fish weight automatic estimation method and device, electronic equipment and storage medium |
| CN114765658A (en) * | 2022-04-20 | 2022-07-19 | 内蒙古农业大学 | Cow hoof disease real-time monitoring method and device, electronic equipment and readable storage medium |
| CN114896441A (en) * | 2022-06-07 | 2022-08-12 | 连云港东旺奶牛养殖有限公司 | Intelligent cow informatization breeding method and system |
| CN117115754A (en) * | 2023-10-23 | 2023-11-24 | 贵州省种畜禽种质测定中心 | Intelligent duck shed monitoring method based on computer vision |
| CN117216722A (en) * | 2023-11-09 | 2023-12-12 | 山东农业大学 | Sensor time sequence data-based multi-source heterogeneous data fusion system |
| CN117379016A (en) * | 2023-12-11 | 2024-01-12 | 吉林省牛人网络科技股份有限公司 | Remote monitoring system and method for beef cattle cultivation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012177792A9 (en) * | 2011-06-24 | 2013-06-06 | Sequenom, Inc. | Methods and processes for non-invasive assessment of a genetic variation |
| CN103248703A (en) * | 2013-05-16 | 2013-08-14 | 中国农业大学 | Automatic monitoring system and method for live pig action |
| CN103475736A (en) * | 2013-09-26 | 2013-12-25 | 河北烽联信息技术有限公司 | Sensor communication system and method for conducting monitoring through same |
| CN103690150A (en) * | 2013-12-30 | 2014-04-02 | 东北农业大学 | Multi-source sensing equipment for physical sign parameters of dairy cows |
| CN104320618A (en) * | 2014-10-23 | 2015-01-28 | 西北农林科技大学 | Calf state monitoring device and method based on behavior characteristics spectrum linkage |
| CN105091938A (en) * | 2015-07-09 | 2015-11-25 | 北京农业信息技术研究中心 | Poultry health monitoring method and system |
| CN105784083A (en) * | 2016-04-05 | 2016-07-20 | 北京农业信息技术研究中心 | Cow shape measuring method and cow shape measuring system based on stereo vision technology |
| CN205694933U (en) * | 2016-04-11 | 2016-11-23 | 内蒙古牧野昕光信息技术有限公司 | A kind of device gathering milk cow activity and system |
| CN106818532A (en) * | 2017-01-23 | 2017-06-13 | 中国农业大学 | A kind of cow oestrus identification systems and authentication method |
-
2017
- 2017-12-22 CN CN201711405688.1A patent/CN108175389B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012177792A9 (en) * | 2011-06-24 | 2013-06-06 | Sequenom, Inc. | Methods and processes for non-invasive assessment of a genetic variation |
| CN103248703A (en) * | 2013-05-16 | 2013-08-14 | 中国农业大学 | Automatic monitoring system and method for live pig action |
| CN103475736A (en) * | 2013-09-26 | 2013-12-25 | 河北烽联信息技术有限公司 | Sensor communication system and method for conducting monitoring through same |
| CN103690150A (en) * | 2013-12-30 | 2014-04-02 | 东北农业大学 | Multi-source sensing equipment for physical sign parameters of dairy cows |
| CN104320618A (en) * | 2014-10-23 | 2015-01-28 | 西北农林科技大学 | Calf state monitoring device and method based on behavior characteristics spectrum linkage |
| CN105091938A (en) * | 2015-07-09 | 2015-11-25 | 北京农业信息技术研究中心 | Poultry health monitoring method and system |
| CN105784083A (en) * | 2016-04-05 | 2016-07-20 | 北京农业信息技术研究中心 | Cow shape measuring method and cow shape measuring system based on stereo vision technology |
| CN205694933U (en) * | 2016-04-11 | 2016-11-23 | 内蒙古牧野昕光信息技术有限公司 | A kind of device gathering milk cow activity and system |
| CN106818532A (en) * | 2017-01-23 | 2017-06-13 | 中国农业大学 | A kind of cow oestrus identification systems and authentication method |
Non-Patent Citations (5)
| Title |
|---|
| JAN BROUCEK，等: "Robotic Milking and Dairy Cows Behaviour", 《2017 INTERNATIONAL CONFERENCE ON CONTROL, ARTIFICIAL INTELLIGENCE, ROBOTICS & OPTIMIZATION》 * |
| KRZYSZTOFADAMCZYK，等: "The application of cluster analysis methods in assessment of daily physical activity of dairy cows milked in the Voluntary Milking System", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| MARYAMTEIMOURI，等: "A method to detect inactive periods in animal movement using density-based clustering", 《APPLIED GEOGRAPHY》 * |
| 尹令等: "基于无线传感器网络的奶牛行为特征监测系统设计", 《农业工程学报》 * |
| 顾静秋等: "基于融合图像与运动量的奶牛行为识别方法", 《农业机械学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070051A (en) * | 2019-04-24 | 2019-07-30 | 卿胜奎 | Ox heat monitoring method and system based on computer vision technique |
| CN112450118A (en) * | 2020-01-07 | 2021-03-09 | 丰疆智能科技股份有限公司 | Wearing device, detection system and detection method for detecting estrus |
| CN112528772A (en) * | 2020-11-27 | 2021-03-19 | 中国农业大学 | Cow lameness movement characteristic detection method and device based on thermal infrared |
| CN113628182A (en) * | 2021-08-03 | 2021-11-09 | 中国农业大学 | Fish weight automatic estimation method and device, electronic equipment and storage medium |
| CN113628182B (en) * | 2021-08-03 | 2024-04-26 | 中国农业大学 | Automatic fish weight estimation method and device, electronic equipment and storage medium |
| CN114765658B (en) * | 2022-04-20 | 2023-05-16 | 内蒙古农业大学 | Real-time monitoring method and device for cow hoof diseases, electronic equipment and readable storage medium |
| CN114765658A (en) * | 2022-04-20 | 2022-07-19 | 内蒙古农业大学 | Cow hoof disease real-time monitoring method and device, electronic equipment and readable storage medium |
| CN114896441A (en) * | 2022-06-07 | 2022-08-12 | 连云港东旺奶牛养殖有限公司 | Intelligent cow informatization breeding method and system |
| CN117115754A (en) * | 2023-10-23 | 2023-11-24 | 贵州省种畜禽种质测定中心 | Intelligent duck shed monitoring method based on computer vision |
| CN117115754B (en) * | 2023-10-23 | 2023-12-26 | 贵州省种畜禽种质测定中心 | Intelligent duck shed monitoring method based on computer vision |
| CN117216722A (en) * | 2023-11-09 | 2023-12-12 | 山东农业大学 | Sensor time sequence data-based multi-source heterogeneous data fusion system |
| CN117216722B (en) * | 2023-11-09 | 2024-02-27 | 山东农业大学 | Sensor time sequence data-based multi-source heterogeneous data fusion system |
| CN117379016A (en) * | 2023-12-11 | 2024-01-12 | 吉林省牛人网络科技股份有限公司 | Remote monitoring system and method for beef cattle cultivation |
| CN117379016B (en) * | 2023-12-11 | 2024-02-23 | 吉林省牛人网络科技股份有限公司 | Remote monitoring system and method for beef cattle cultivation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108175389B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108175389B (en) | Multi-source information fusion cow behavior monitoring system and method | |
| WO2022151819A1 (en) | Clustering analysis-based battery system online fault diagnosis method and system | |
| CN108216252B (en) | Subway driver vehicle-mounted driving behavior analysis method, vehicle-mounted terminal and system | |
| CN103517042B (en) | A kind of nursing house old man's hazardous act monitoring method | |
| CN114596448A (en) | Meat duck health management method and management system thereof | |
| CN112587153B (en) | End-to-end non-contact atrial fibrillation automatic detection system and method based on vPPG signal | |
| CN114999629B (en) | AD early prediction method, system and device based on multi-feature fusion | |
| CN101627905B (en) | Noninvasive integrative monitoring analytical method and noninvasive integrative monitoring analytic device for intracranial pressure | |
| WO2014082480A1 (en) | Method and device for calculating number of pedestrians and crowd movement directions | |
| CN111985445B (en) | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing | |
| WO2023216609A1 (en) | Target behavior recognition method and apparatus based on visual-audio feature fusion, and application | |
| CN107767874A (en) | A kind of baby crying sound identification reminding method and system | |
| CN115830490A (en) | Multi-target tracking and behavior statistical method for herd health pigs | |
| CN112257608A (en) | Yak breeding health state monitoring method | |
| CN117671396A (en) | Intelligent monitoring and early warning system and method for construction progress | |
| CN114093501A (en) | Intelligent auxiliary analysis method for children's motor epilepsy based on synchronous video and electroencephalogram | |
| CN110633680A (en) | Video-based people number abnormity detection method | |
| CN118038548A (en) | Abnormal behavior detection method, device, electronic equipment and storage medium | |
| CN117064333B (en) | Primary screening device for obstructive sleep apnea hypopnea syndrome | |
| CN113569656A (en) | Examination room monitoring method based on deep learning | |
| CN117475482A (en) | Tongue picture feature extraction method and device | |
| EP3679787B1 (en) | Method and system for monitoring epidemic disease in piggery | |
| CN117503107A (en) | Method and device for measuring bovine respiratory frequency based on differential pressure sensor | |
| CN110363247B (en) | Intelligent monitoring method and system for abnormal diet of live pigs | |
| CN108670256A (en) | A kind of milk cow respiratory rate monitoring system and 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 |