CN112400734A - Sow health monitoring method and monitoring system - Google Patents
Sow health monitoring method and monitoring system Download PDFInfo
- Publication number
- CN112400734A CN112400734A CN201910777209.1A CN201910777209A CN112400734A CN 112400734 A CN112400734 A CN 112400734A CN 201910777209 A CN201910777209 A CN 201910777209A CN 112400734 A CN112400734 A CN 112400734A
- Authority
- CN
- China
- Prior art keywords
- sow
- delivery
- camera
- target detection
- detection algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 230000000630 rising effect Effects 0.000 claims abstract description 32
- 230000000694 effects Effects 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims description 85
- 238000013500 data storage Methods 0.000 claims description 36
- 238000004519 manufacturing process Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 9
- 230000032696 parturition Effects 0.000 claims description 8
- 210000002826 placenta Anatomy 0.000 claims description 8
- 238000002360 preparation method Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 201000010099 disease Diseases 0.000 claims description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 6
- 230000001737 promoting effect Effects 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 abstract description 3
- 244000144972 livestock Species 0.000 abstract description 2
- 241000282887 Suidae Species 0.000 description 6
- 238000009395 breeding Methods 0.000 description 4
- 230000001488 breeding effect Effects 0.000 description 4
- 230000035606 childbirth Effects 0.000 description 4
- 241000282898 Sus scrofa Species 0.000 description 3
- 208000007407 African swine fever Diseases 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 235000021050 feed intake Nutrition 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000710778 Pestivirus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 208000010515 dystocia Diseases 0.000 description 1
- 230000012173 estrus Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000006651 lactation Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 238000003307 slaughter Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Environmental Sciences (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Biophysics (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of livestock health monitoring, in particular to a sow health monitoring method and a sow health monitoring system, which can record the complete activity state of each sow from entering to leaving, and can trace back the whole process when the abnormality is found; the delivery reminding and the farrowing early warning are carried out, so that the risks of the dead piglings and the like are reduced; the automatic alarm reminds workers of the delivery process of the sow, so that the original work is more timely and efficient while the manpower checking is reduced; the contact between the personnel and the foreign objects and the sow can be effectively reduced, the risk of infecting the epidemic situation is reduced, and the stress reaction brought to the sow by the contact of the personnel is greatly avoided; the method comprises the following steps: shooting a sow and sending a shooting signal of the sow; receiving an image pickup signal and storing the image pickup signal; displaying the data; and reading the image pickup signals, and counting the rising and lying frequency of the sow according to the image pickup signals.
Description
Technical Field
The invention relates to the technical field of livestock health monitoring, in particular to a sow health monitoring method and a sow health monitoring system.
Background
The African swine fever outbreaks in various regions throughout the country, the African swine fever epidemic situation and other factors affect the swine industry, the non-pestivirus infected areas kill pigs in a large area and the ultra-low swine price causes the serious reduction of the productivity of the live pigs, the supply gap of the live pigs is particularly prominent, the slaughtering enterprises are difficult to accept the pigs, the price is increased to accept the pigs, and the price of the pigs is increased remarkably. At present, the price of piglets is increased rapidly, and the supply of sows is not in demand. Sows are the most susceptible to epidemic situations, some pig breeders cannot bear stress, and piggeries abandoned in piggeries are continuously increased.
In the breeding process, the antenatal sow can repeatedly rise and lie at a certain specific time point and is uneasy to stand before delivery; and the frequent rising and lying of the sow after delivery can easily lead the piglets to be pressed by the sow.
The sow is mostly fed by a limit fence, the breeding process of the sow mainly comprises the stages of estrus mating, pregnancy, farrowing and postpartum lactation, and the later production activities are mainly carried out in a delivery room. The main problems of sow management at present are as follows: dystocia occurs in the production process, and the death risk of the sow is high if labor is not found and assisted in time; a large amount of manpower and material resources are consumed before and after delivery, for example, the sows are manually driven to move, and the conditions of the piglets are manually checked at regular intervals after delivery.
Meanwhile, in the field of image analysis, objects have different forms at different angles and different distances, and the difficulty in accurately detecting the target is very high. With the development of deep learning, the target detection algorithm makes great progress in terms of both accuracy and real-time performance. The object detection algorithm in the granted patents of publication numbers CN105184823B and CN105787481B is applicable to analyzing images of objects and identifying objects. Therefore, the target detection algorithm is combined with the sow breeding, the whole breeding stage of the sow can be conveniently monitored, the condition of the whole delivery room can be known at any time and any place, under the condition of no-person patrol, the activity state of the sow is automatically detected, recorded and early warned, only the sow gives an alarm when farrowing or other special conditions to remind a worker to enter a designated column for processing, and the pain point and the difficulty in the existing management are solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a sow feed-in and feed-out device which can record the complete activity state of each sow from feeding to feeding, and can trace back the abnormal condition in the whole process; the delivery reminding and the farrowing early warning are carried out, so that the risks of the dead piglings and the like are reduced; the automatic alarm reminds workers of the delivery process of the sow, so that the original work is more timely and efficient while the manpower checking is reduced; the sow health monitoring method and the monitoring system can effectively reduce the contact of personnel and foreign objects with the sow, reduce the risk of epidemic infection, and greatly avoid stress reaction brought to the sow by the contact of the personnel.
The sow health monitoring method comprises the following steps:
shooting a sow and sending a shooting signal of the sow;
receiving an image pickup signal and storing the image pickup signal;
displaying the data;
reading a camera signal, and counting the rising and lying frequency of the sow according to the camera signal; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the camera signals are analyzed through a target detection algorithm, the rising and lying frequency of the sow is counted, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user;
reading a camera signal, and identifying the piglet according to the camera signal; the method comprises the following steps that piglets are shot when born, a sow and the piglets are distinguished through a target detection algorithm, when the piglets are born, the piglets are identified in a camera signal through the target detection algorithm, the first piglet is identified in the camera signal by the target detection algorithm to land on the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified through the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified through the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted;
and reading the camera shooting signals, carrying out statistical analysis on the camera shooting signals through a target detection algorithm, detecting and recording the activity state and the production condition of the sow in real time, and displaying the estimated delivery time of the sow and the birth prompt of the piglet in real time.
The sow health monitoring method of the invention also comprises the following steps:
reading a camera signal, continuously identifying the rising and lying states of the sows through a target detection algorithm, monitoring the health states of the sows, simultaneously comparing state curves of the sows in the same physiological period in the delivery room, judging whether the sows are abnormal, if so, not informing a user to check, and if so, informing the user to check.
The sow health monitoring method of the invention also comprises the following steps:
reading a camera signal, continuously identifying the prone state of the sow through a target detection algorithm, not reminding a user to check and driving the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminding the user to check and driving the sow to stand if the sow continuously lies prone after delivery is finished.
The sow health monitoring method of the invention also comprises the following steps:
reading a camera signal, continuously identifying the rising and lying states of the sow through a target detection algorithm, reminding a technician to arrive at the site and drive the sow if the sow does not frequently rise and lie postpartum, promoting the postpartum recovery of the sow, and informing the technician to perform disease early warning when the sow lies prone for a long time.
The sow health monitoring system of the invention comprises:
the camera is used for shooting the sow and sending a shooting signal of the sow;
the data storage module is used for receiving the camera shooting signal of the camera and storing the camera shooting signal;
the data display platform is used for displaying data;
the processing module is used for reading the camera signals stored by the data storage module, performing statistical analysis on the camera signals through a target detection algorithm, detecting and recording the activity state and the production condition of the sow in real time, and displaying the result on the data display platform in real time;
wherein, processing module includes: the delivery early warning module and the delivery reminding module;
the delivery early warning module is used for reading the camera signals stored by the data storage module and counting the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user;
the delivery reminding module is used for reading the camera signals stored by the data storage module and identifying the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; and the target detection algorithm assists in counting the landing time of the first piglet and the last piglet, and the total number born of the sow is counted.
The sow health monitoring system of the invention further comprises:
and the postpartum sow health monitoring module is used for reading the camera signals stored by the data storage module, continuously identifying the rising and lying states of the sows through a target detection algorithm, monitoring the health states of the sows, simultaneously comparing state curves of the sows in the same physiological period in the delivery room, judging whether the sows are abnormal, if so, informing the user to check, and if so, informing the user to check.
The sow health monitoring system of the invention further comprises:
the postpartum sow movement reminding module is used for reading the camera signals stored by the data storage module, continuously identifying the prone state of the sow through a target detection algorithm, not reminding a user to check and driving the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminding the user to check and driving the sow to stand if the sow continuously lies prone after delivery is finished.
The sow health monitoring system of the invention further comprises:
the sow lying-up reminding module is used for reading the camera signals stored by the data storage module, continuously identifying the lying-up state of the sow through a target detection algorithm, reminding a technician to drive to the site and drive the sow if the sow does not lie up frequently after delivery, promoting the postpartum recovery of the sow, and informing the technician to perform disease early warning when the sow lies prone for a long time.
The invention has the beneficial effects that: the complete activity state of each sow from entering to leaving can be recorded, and the whole course tracing can be realized when the abnormality is found; the delivery reminding and the farrowing early warning are carried out, so that the risks of the dead piglings and the like are reduced; the automatic alarm reminds workers of the delivery process of the sow, so that the original work is more timely and efficient while the manpower checking is reduced; can effectively reduce the contact of personnel and foreign objects with the sow, reduce the risk of infecting the epidemic situation, and greatly avoid the stress reaction brought to the sow by the contact of the personnel.
Drawings
FIG. 1 is a schematic view of the present invention;
fig. 2 is a schematic diagram of modules such as a data storage module and a birth warning module;
FIG. 3 is a schematic diagram of an application scenario of the present invention;
in the drawings, the reference numbers: 1. a sow; 2. a camera is provided.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Common algorithms for the target detection algorithm include, but are not limited to, SSD algorithm and YOLO algorithm.
The YOLO algorithm: the whole process of target detection is simplified, a video frame image is zoomed into an image with a uniform size and is divided into S multiplied by S grids, information of B rectangular frames containing objects and attribution probability values of C categories need to be predicted for each grid, each rectangular frame contains 4-dimensional coordinate information and 1-dimensional target confidence, and each grid outputs a 5 multiplied by B + C-dimensional vector. YOLO integrates target determination and recognition.
SSD algorithm: the rough division of the S multiplied by S grid of the YOLO network causes a large target position error of regression, the SSD improves by taking the idea of region nomination as a reference, an RPN network similar to the fast R-CNN is used, and the difference is that the SSD performs classification and frame regression after using the RPN on a plurality of characteristic layers of the CNN, so that the detection of small objects on an original image can also have a more accurate detection result.
Example 1
The camera shoots the sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the delivery early warning module reads the camera signals stored by the data storage module and counts the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user; the childbirth reminding module reads the camera signals stored in the data storage module and identifies the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted; the processing module integrates the camera signal, the delivery early warning module and the delivery reminding module, detects and records the activity state and the production condition of the sow in real time, and displays the result on the data display platform in real time; the complete activity state of each sow from entering to leaving can be recorded, and the whole course tracing can be realized when the abnormality is found; the delivery reminding and the farrowing early warning are carried out, so that the risks of the dead piglings and the like are reduced; the automatic alarm reminds workers of the delivery process of the sow, so that the original work is more timely and efficient while the manpower checking is reduced; can effectively reduce the contact of personnel and foreign objects with the sow, reduce the risk of infecting the epidemic situation, and greatly avoid the stress reaction brought to the sow by the contact of the personnel.
Example 2
The camera shoots the sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the postpartum sow health monitoring module reads the camera signals stored by the data storage module, continuously identifies the rising and lying states of the sows through a target detection algorithm, monitors the health states of the sows, simultaneously compares state curves of the sows in the same other physiological periods in the delivery room, judges whether the sows are abnormal, if so, does not inform the user to check, and if not, informs the user to check; reduce the death rate and elimination rate of postpartum sows.
As a preferred technical scheme, a camera shoots a sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the delivery early warning module reads the camera signals stored by the data storage module and counts the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user; the childbirth reminding module reads the camera signals stored in the data storage module and identifies the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted; the processing module integrates the camera signal, the delivery early warning module and the delivery reminding module, detects and records the activity state and the production condition of the sow in real time, and displays the result on the data display platform in real time; the postpartum sow health monitoring module reads the camera signals stored by the data storage module, continuously identifies the rising and lying states of the sows through a target detection algorithm, monitors the health states of the sows, simultaneously compares state curves of the sows in the same other physiological periods in the delivery room, judges whether the sows are abnormal, if so, does not inform the user to check, and if not, informs the user to check; reduce the death rate and elimination rate of postpartum sows.
Example 3
The camera shoots the sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the postpartum sow movement reminding module reads the camera signals stored by the data storage module, continuously identifies the prone position of the sow through a target detection algorithm, does not remind a user to check and drive the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminds the user to check and drive the sow to stand if the sow continuously lies prone after delivery is finished; on one hand, the feed intake of the sow can be improved, on the other hand, the postpartum exercise of the sow can be increased, and the postpartum paralysis probability of the sow is reduced.
As a preferred technical scheme, a camera shoots a sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the delivery early warning module reads the camera signals stored by the data storage module and counts the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user; the childbirth reminding module reads the camera signals stored in the data storage module and identifies the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted; the processing module integrates the camera signal, the delivery early warning module and the delivery reminding module, detects and records the activity state and the production condition of the sow in real time, and displays the result on the data display platform in real time; the postpartum sow movement reminding module reads the camera signals stored by the data storage module, continuously identifies the prone position of the sow through a target detection algorithm, does not remind a user to check and drive the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminds the user to check and drive the sow to stand if the sow continuously lies prone after delivery is finished; on one hand, the feed intake of the sow can be improved, on the other hand, the postpartum exercise of the sow can be increased, and the postpartum paralysis probability of the sow is reduced.
Example 4
The camera shoots the sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the postpartum sow rising and lying reminding module reads the camera signals stored by the data storage module, continuously identifies the rising and lying states of the sows through a target detection algorithm, reminds technicians to arrive at the site and drive the sows if the sows do not frequently rise and lie postpartum, promotes postpartum recovery of the sows, and informs the technicians to perform disease early warning when the sows lie prone for a long time; the occurrence of the situation that the piglets are pressed due to frequent rising and lying of the sows is reduced.
As a preferred technical scheme, a camera shoots a sow and sends a shooting signal of the sow; the data storage module receives a camera signal of the camera and stores the camera signal; the delivery early warning module reads the camera signals stored by the data storage module and counts the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user; the childbirth reminding module reads the camera signals stored in the data storage module and identifies the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted; the processing module integrates the camera signal, the delivery early warning module and the delivery reminding module, detects and records the activity state and the production condition of the sow in real time, and displays the result on the data display platform in real time; the postpartum sow rising and lying reminding module reads the camera signals stored by the data storage module, continuously identifies the rising and lying states of the sows through a target detection algorithm, reminds technicians to arrive at the site and drive the sows if the sows do not frequently rise and lie postpartum, promotes postpartum recovery of the sows, and informs the technicians to perform disease early warning when the sows lie prone for a long time; the occurrence of the situation that the piglets are pressed due to frequent rising and lying of the sows is reduced.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A sow health monitoring method is characterized by comprising the following steps:
shooting a sow and sending a shooting signal of the sow;
receiving an image pickup signal and storing the image pickup signal;
displaying the data;
reading a camera signal, and counting the rising and lying frequency of the sow according to the camera signal; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the camera signals are analyzed through a target detection algorithm, the rising and lying frequency of the sow is counted, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user;
reading a camera signal, and identifying the piglet according to the camera signal; the method comprises the following steps that piglets are shot when born, a sow and the piglets are distinguished through a target detection algorithm, when the piglets are born, the piglets are identified in a camera signal through the target detection algorithm, the first piglet is identified in the camera signal by the target detection algorithm to land on the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified through the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified through the target detection algorithm until a placenta is identified; the target detection algorithm assists in counting landing time of the first piglet and the last piglet, and total number born of the sow is counted;
and reading the camera shooting signals, carrying out statistical analysis on the camera shooting signals through a target detection algorithm, detecting and recording the activity state and the production condition of the sow in real time, and displaying the estimated delivery time of the sow and the birth prompt of the piglet in real time.
2. The sow health monitoring method of claim 1, further comprising:
reading a camera signal, continuously identifying the rising and lying states of the sows through a target detection algorithm, monitoring the health states of the sows, simultaneously comparing state curves of the sows in the same physiological period in the delivery room, judging whether the sows are abnormal, if so, not informing a user to check, and if so, informing the user to check.
3. The sow health monitoring method of claim 2, further comprising:
reading a camera signal, continuously identifying the prone state of the sow through a target detection algorithm, not reminding a user to check and driving the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminding the user to check and driving the sow to stand if the sow continuously lies prone after delivery is finished.
4. The sow health monitoring method of claim 3, further comprising:
reading a camera signal, continuously identifying the rising and lying states of the sow through a target detection algorithm, reminding a technician to arrive at the site and drive the sow if the sow does not frequently rise and lie postpartum, promoting the postpartum recovery of the sow, and informing the technician to perform disease early warning when the sow lies prone for a long time.
5. Sow health monitoring system, its characterized in that includes:
the camera is used for shooting the sow and sending a shooting signal of the sow;
the data storage module is used for receiving the camera shooting signal of the camera and storing the camera shooting signal;
the data display platform is used for displaying data;
the processing module is used for reading the camera signals stored by the data storage module, performing statistical analysis on the camera signals through a target detection algorithm, detecting and recording the activity state and the production condition of the sow in real time, and displaying the result on the data display platform in real time;
wherein, processing module includes: the delivery early warning module and the delivery reminding module;
the delivery early warning module is used for reading the camera signals stored by the data storage module and counting the rising and lying frequencies of the sows according to the camera signals; before parturition of the antenatal sow, the antenatal sow can repeatedly rise and lie at a certain specific time point, and the antenatal sow is uneasy to stand; the delivery early warning module analyzes the camera signals through a target detection algorithm and counts the rising and lying frequency of the sow, the delivery time of the sow is estimated in advance, and delivery preparation is conveniently carried out before delivery of the sow by a user;
the delivery reminding module is used for reading the camera signals stored by the data storage module and identifying the piglets according to the camera signals; the method comprises the following steps that piglets are shot by a camera when being born, a sow and the piglets are distinguished by a target detection algorithm, when the piglets are born, the piglets are identified by the target detection algorithm in a shooting signal, the first piglet is identified by the target detection algorithm in the shooting signal to fall to the ground and prompt a user that the sow starts to give birth, the delivery process of the sow is continuously identified by the target detection algorithm, if the production time of two adjacent piglets exceeds 15 minutes, the user is reminded to give birth to the sow, and the delivery process of the sow is continuously identified by the target detection algorithm until a placenta is identified; and the target detection algorithm assists in counting the landing time of the first piglet and the last piglet, and the total number born of the sow is counted.
6. The sow health monitoring system of claim 5, further comprising:
and the postpartum sow health monitoring module is used for reading the camera signals stored by the data storage module, continuously identifying the rising and lying states of the sows through a target detection algorithm, monitoring the health states of the sows, simultaneously comparing state curves of the sows in the same physiological period in the delivery room, judging whether the sows are abnormal, if so, informing the user to check, and if so, informing the user to check.
7. The sow health monitoring system of claim 6, further comprising:
the postpartum sow movement reminding module is used for reading the camera signals stored by the data storage module, continuously identifying the prone state of the sow through a target detection algorithm, not reminding a user to check and driving the sow to stand if the sow does not continuously lie prone after delivery is finished, and reminding the user to check and driving the sow to stand if the sow continuously lies prone after delivery is finished.
8. The sow health monitoring system of claim 7, further comprising:
the sow lying-up reminding module is used for reading the camera signals stored by the data storage module, continuously identifying the lying-up state of the sow through a target detection algorithm, reminding a technician to drive to the site and drive the sow if the sow does not lie up frequently after delivery, promoting the postpartum recovery of the sow, and informing the technician to perform disease early warning when the sow lies prone for a long time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910777209.1A CN112400734A (en) | 2019-08-21 | 2019-08-21 | Sow health monitoring method and monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910777209.1A CN112400734A (en) | 2019-08-21 | 2019-08-21 | Sow health monitoring method and monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112400734A true CN112400734A (en) | 2021-02-26 |
Family
ID=74779582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910777209.1A Pending CN112400734A (en) | 2019-08-21 | 2019-08-21 | Sow health monitoring method and monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112400734A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113115722A (en) * | 2021-04-19 | 2021-07-16 | 青岛得八兄弟机械有限公司 | Intelligent sow parturition monitoring and feeding management system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009074153A1 (en) * | 2007-12-10 | 2009-06-18 | Skov A/S | Method for prediction of time of birth, climate control and warning in animal houses and application hereof |
| CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
| CN205389948U (en) * | 2016-03-11 | 2016-07-27 | 陕西科技大学 | Wireless monitoring devices of antenatal sow action based on acceleration sensor |
| US20180071069A1 (en) * | 2015-03-03 | 2018-03-15 | Farrowtech Aps | System, device and method for observing piglet birth |
| CN109816072A (en) * | 2019-03-14 | 2019-05-28 | 安徽鲜森绿色食品有限公司 | A kind of animal health intelligent management and its system based on RFID |
| CN109964845A (en) * | 2019-04-26 | 2019-07-05 | 中国农业科学院农业信息研究所 | Piglet safety apparatus |
| CN110047009A (en) * | 2019-03-01 | 2019-07-23 | 广州影子科技有限公司 | Cultivate task management method and device, cultivation task management equipment and system |
| CN110147771A (en) * | 2019-05-23 | 2019-08-20 | 南京农业大学 | Sow side-lying position real-time detecting system based on sow key position Yu environment joint partition |
-
2019
- 2019-08-21 CN CN201910777209.1A patent/CN112400734A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009074153A1 (en) * | 2007-12-10 | 2009-06-18 | Skov A/S | Method for prediction of time of birth, climate control and warning in animal houses and application hereof |
| CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
| US20180071069A1 (en) * | 2015-03-03 | 2018-03-15 | Farrowtech Aps | System, device and method for observing piglet birth |
| CN205389948U (en) * | 2016-03-11 | 2016-07-27 | 陕西科技大学 | Wireless monitoring devices of antenatal sow action based on acceleration sensor |
| CN110047009A (en) * | 2019-03-01 | 2019-07-23 | 广州影子科技有限公司 | Cultivate task management method and device, cultivation task management equipment and system |
| CN109816072A (en) * | 2019-03-14 | 2019-05-28 | 安徽鲜森绿色食品有限公司 | A kind of animal health intelligent management and its system based on RFID |
| CN109964845A (en) * | 2019-04-26 | 2019-07-05 | 中国农业科学院农业信息研究所 | Piglet safety apparatus |
| CN110147771A (en) * | 2019-05-23 | 2019-08-20 | 南京农业大学 | Sow side-lying position real-time detecting system based on sow key position Yu environment joint partition |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113115722A (en) * | 2021-04-19 | 2021-07-16 | 青岛得八兄弟机械有限公司 | Intelligent sow parturition monitoring and feeding management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102296501B1 (en) | System to determine sows' estrus and the right time to fertilize sows using depth image camera and sound sensor | |
| CN110839557A (en) | Sow oestrus monitoring method, device and system, electronic equipment and storage medium | |
| US20230276773A1 (en) | Systems and methods for automatic and noninvasive livestock health analysis | |
| CN113662530B (en) | Pig physiological growth state monitoring and early warning method | |
| CN113711944B (en) | Sow estrus identification method, device and system | |
| CN112400734A (en) | Sow health monitoring method and monitoring system | |
| CN112101291B (en) | Livestock nursing method, device, medium and electronic equipment | |
| WO2018143889A1 (en) | Systems and methods for determining likelihood of states in cattle animal | |
| CN113673472A (en) | Intelligent pig information acquisition system | |
| US20230413786A1 (en) | Pig rearing support apparatus, pig rearing support method, and non-volatile storage medium storing pig rearing support program | |
| CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
| WO2022247500A1 (en) | Piglet anti-crushing early warning method and apparatus, device, and storage medium | |
| WO2023106993A1 (en) | Parturition surveillance and alerting | |
| CN115777560A (en) | Intelligent sow feeding system based on machine vision analysis technology | |
| TWI785729B (en) | Monitoring system and method of intelligent on estrus in sow | |
| TWI789598B (en) | Livestock abnormality monitoring system, method, computer program product, and computer readable recording medium | |
| CN114022302A (en) | Pregnant goat intelligent management system and management method based on video monitoring | |
| Wang et al. | Automatic identification and analysis of multi-object cattle rumination based on computer vision | |
| Nabenishi et al. | Predicting the start of calving in Japanese Black cattle using camera image analysis | |
| KR20230026006A (en) | Monitoring system and method for mounting behavior in livestock barn | |
| CN113743261A (en) | Pig body trauma detection method and device and readable storage medium | |
| CN112399151A (en) | Sow obstetric table monitoring and early warning device, method and system | |
| WO2023235735A2 (en) | Method and system for detecting sow estrus utilizing machine vision | |
| CN111904653A (en) | Target object childbirth monitoring method, device and system, and monitoring system and method | |
| CN116530465A (en) | Prediction method of live pig disease, live pig monitoring device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |
|
| RJ01 | Rejection of invention patent application after publication |