CN110612921A - Monitoring system and method for positioning gilts - Google Patents
Monitoring system and method for positioning gilts Download PDFInfo
- Publication number
- CN110612921A CN110612921A CN201910913980.7A CN201910913980A CN110612921A CN 110612921 A CN110612921 A CN 110612921A CN 201910913980 A CN201910913980 A CN 201910913980A CN 110612921 A CN110612921 A CN 110612921A
- Authority
- CN
- China
- Prior art keywords
- sow
- data
- image
- condition
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000036760 body temperature Effects 0.000 claims abstract description 51
- 238000009826 distribution Methods 0.000 claims abstract description 41
- 230000036541 health Effects 0.000 claims abstract description 32
- 230000007613 environmental effect Effects 0.000 claims abstract description 31
- 238000009395 breeding Methods 0.000 claims abstract description 27
- 230000001488 breeding effect Effects 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000001931 thermography Methods 0.000 claims abstract description 6
- 230000037396 body weight Effects 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 230000003862 health status Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 7
- 241001465754 Metazoa Species 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 241000282887 Suidae Species 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 244000144972 livestock Species 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001850 reproductive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- 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
- A01K67/00—Rearing or breeding animals, not otherwise provided for; New or modified breeds of animals
- A01K67/02—Breeding vertebrates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Zoology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the invention provides a monitoring system and a monitoring method for positioning a gilt, which are characterized in that a data acquisition device is used for acquiring a color image, a depth image and a heat distribution image of the gilt, the body size, the weight and the body temperature of the gilt are acquired according to the color image, the depth image and the heat distribution image of the gilt, and the growth health condition score of the gilt is acquired according to the body size, the weight and the body temperature of the gilt. The embodiment of the invention integrates the technologies of machine vision, a depth sensor, a thermal imaging sensor, the Internet of things, signal processing, three-dimensional scanning, intelligent information processing and the like, comprises the monitoring of physiological signs of sows, the monitoring of body size parameters, the monitoring of health conditions, the evaluation of breeding environments and the like, and can realize the timely, accurate, rapid, automatic and intelligent information acquisition and monitoring of the body condition information and the environmental information of the positioning fence sows.
Description
Technical Field
The invention relates to the technical field of livestock raising, in particular to a monitoring system and method for positioning a gilt.
Background
The production of live pigs is an important component of animal husbandry, and sows in large-scale pig farms and commercial pig breeding processes in China usually adopt a positioning fence feeding mode. In the breeding production of sows in a positioning fence, the body condition, physiological indexes and breeding environment parameters of sows are important factors influencing the production performance and the reproductive performance, and the method has important practical significance for timely finding and making evaluation and early warning when the body condition or environment of the sows is abnormal, and in addition, the daily production file record of the growth condition of the sows has important value for fine breed breeding and breed tracing.
At present, the inspection method for health conditions and breeding conditions of sows in a positioning fence mainly comprises manual observation, environmental sensor, video monitoring and the like, and also comprises an inspection platform mode using a self-navigation mobile platform. The manual inspection method is limited by factors such as personnel, field and population quantity, the aim of accurate, quick and timely monitoring is often difficult to achieve, the labor cost is high, the requirement on observers is high, the working intensity is high, real-time uninterrupted inspection cannot be realized, abnormal conditions are not found timely, and the labor cost investment in the large-scale cultivation management process is large; the sensor mode can only collect environmental indexes generally and can not directly reflect the physiological and body condition information of the breeding pigs in real time; video monitoring is passive shooting generally, is limited by shooting position and angle, is difficult to realize accurate monitoring of all-round coverage, generally needs manual video monitoring, is difficult to meet the requirements of monitoring comprehensiveness and accuracy, and is difficult to obtain better monitoring precision and monitoring effect. At present, because beasts and birds breed intelligence inspection device from navigation moving platform (AGV) generally need rely on system map, navigation, keep away the barrier etc. need carry on laser radar, navigation device module, and is relatively poor to the complex environment adaptability of plant on the one hand, and moving platform adopts the mode of charging, and the daily use of system and maintenance face increase pressure, and on the other hand moving platform cost is higher. In addition, the existing mobile platform inspection system does not provide an intelligent model of body conditions, physiological indexes and inspection decisions, only realizes a platform device, and still has a plurality of limitations in the practical application of intelligent inspection.
Therefore, at present, the monitoring modes of the sows in the positioning fences have the problems that the labor or capital cost investment is overlarge, the complex environment adaptability of a farm is poor, the integration level is not high, and the requirements of higher and higher intelligent routing inspection cannot be met.
Disclosure of Invention
In order to solve the problems that the labor cost or capital cost investment is overlarge, the adaptability to the complex environment of a farm is poor, the integration level is not high, and the higher and higher intelligent routing inspection requirements cannot be met in the conventional monitoring mode of the positioning fence sows, the embodiment of the invention provides a monitoring system and a monitoring method of the positioning fence sows.
In a first aspect, an embodiment of the present invention provides a monitoring system for positioning a gilt, including: the sow positioning fence comprises a data acquisition device and a closed-loop guide rail, wherein the closed-loop guide rail is erected right above the sow positioning fence, and the data acquisition device is connected with the closed-loop guide rail and moves along the closed-loop guide rail; the data acquisition device is used for acquiring environmental information of a monitoring area, a color image, a depth image and a heat distribution image of the sow, acquiring the body size and body condition, the weight and the body temperature of the sow according to the color image, the depth image and the heat distribution image of the sow, and acquiring the growth health condition score of the sow according to the environmental information, the body size and body condition, the weight and the body temperature of the sow.
Preferably, the data acquisition device comprises a data processing module, and an environmental information acquisition module, a color image acquisition module, a depth image acquisition module and a thermal distribution image acquisition module which are respectively connected with the data processing module; the system comprises an environment information acquisition module, a color image acquisition module, a depth image acquisition module and a heat distribution image acquisition module, wherein the environment information acquisition module is used for acquiring environment information of a monitoring area, and the color image acquisition module, the depth image acquisition module and the heat distribution image acquisition module are respectively used for acquiring a color image, a depth image and a heat distribution image of a sow; the data processing module is respectively used for acquiring three-dimensional point cloud data of the sow according to the color image and the depth image, acquiring the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data, extracting feature points and contour lines of the sow according to the body size and body condition and the three-dimensional point cloud data, estimating the weight of the sow according to the feature points and contour lines and the three-dimensional point cloud data, and estimating the body temperature of the sow according to the color image and the heat distribution image.
Preferably, the environmental information includes temperature, humidity, CO2Content and NH3And the depth image acquisition module adopts a Kinect sensor, and the thermal distribution image acquisition module adopts a Flir thermal imaging sensor.
Preferably, the data acquisition device further comprises a wireless module, and the data processing module is connected with the server through the wireless module.
Preferably, the system further comprises two pairs of U-shaped groove pulleys and a motor, wherein one pair of U-shaped groove pulleys is fixedly arranged on one side of the data acquisition device, and the other pair of U-shaped groove pulleys is fixedly arranged on the other side of the data acquisition device; one of the two pairs of U-shaped groove pulleys is a driving wheel, the other pair is a driven wheel, and the driving wheel is driven by a motor.
Preferably, the system further comprises a power supply sliding contact line and a power supply sliding block electric brush, the power supply sliding contact line is arranged right above the closed-loop guide rail, the power supply sliding block electric brush is fixedly connected with the data acquisition device, and the power supply sliding block electric brush slides along the power supply sliding contact line to supply power to the data acquisition device.
Preferably, the system further comprises a cleaning device and a resetting and calibrating device, the cleaning device and the resetting and calibrating device are respectively arranged at two different fixing positions of the closed-loop guide rail, the resetting and calibrating device is used for stopping the data acquisition device, and the cleaning device is used for cleaning the data acquisition device.
In a second aspect, an embodiment of the present invention further provides a monitoring method for positioning a gilt, including: collecting environmental information of a monitoring area, a color image, a depth image and a heat distribution image of a sow; and acquiring the body size body condition, the body weight and the body temperature of the sow according to the color image, the depth image and the heat distribution image of the sow, and acquiring the growth health condition score of the sow according to the environmental information, the body size body condition, the body weight and the body temperature of the sow.
Preferably, the body size and body condition, the body weight and the body temperature of the sow are obtained according to the color image, the depth image and the heat distribution image of the sow, and the method specifically comprises the following steps: acquiring three-dimensional point cloud data of the sow by utilizing the color image and the depth image; calculating the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data; carrying out point cloud layering on the three-dimensional point cloud data according to the body size body condition, extracting a layer curve, and extracting body type feature points of the sow according to the layer curve; acquiring the weight of the sow according to the three-dimensional point cloud data and the body size and body condition; and acquiring the body temperature of the sow according to the color image and the heat distribution image.
Preferably, the obtaining of the score of the growth health condition of the sow according to the environmental information, the body size and body condition, the body weight and the body temperature of the sow specifically comprises the following steps: inputting feeding data of the sow into a sow breeding growth model, and outputting body size body conditions, body weight and body temperature corresponding to the feeding data, wherein the feeding data comprises feeding time, feeding amount and environment data of a monitoring area; wherein the sow breeding growth model is obtained after training according to the first sample feeding data, the first sample body size condition, the weight and the body temperature; inputting the body size and body condition, the weight and the body temperature of the sow into a physiological health intelligent analysis model of the sow, and outputting a growth health condition score corresponding to the body size and body condition, the weight and the body temperature; and the intelligent analysis model of the physiological health of the sow is obtained according to the body size and body condition of the second sample, the weight and the body temperature and the grading training of the growth health condition of the second sample.
According to the monitoring system and method for the sow in the positioning fence, provided by the embodiment of the invention, the data acquisition device is used for acquiring the color image, the depth image and the heat distribution image of the sow, the body size body condition, the weight and the body temperature of the sow are acquired according to the color image, the depth image and the heat distribution image of the sow, and the growth health condition score of the sow is acquired according to the body size body condition, the weight and the body temperature of the sow. The embodiment of the invention integrates the technologies of machine vision, a depth sensor, a thermal imaging sensor, the Internet of things, signal processing, three-dimensional scanning, intelligent information processing and the like, comprises the monitoring of physiological signs of sows, the monitoring of body size parameters, the monitoring of health conditions, the evaluation of breeding environments and the like, and can realize the timely, accurate, rapid, automatic and intelligent information acquisition and monitoring of the body condition information and the environmental information of the positioning fence sows.
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 described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a general schematic diagram of a monitoring system for localizing gilts in accordance with an embodiment of the present invention;
fig. 2 is a detailed schematic diagram of a monitoring system for positioning gilts according to an embodiment of the invention;
FIG. 3 is a schematic structural diagram of a data acquisition device according to an embodiment of the present invention;
fig. 4 is a schematic general flow chart of a monitoring method for positioning gilts according to an embodiment of the present invention;
fig. 5 is a schematic flow chart of a monitoring method for positioning gilts according to an embodiment of the present invention;
wherein:
1. guide rail bracket 2, U-shaped groove pulley 3 and driving pulley support
4. Synchronous belt 5, closed loop guide rail 6 and power supply sliding contact line
7. Power supply sliding block electric brush 8, driven pulley support 9 and data acquisition device
10. Numbered indication board 11, sow positioning column 12 and pigsty
13. Wireless module 14, belt cleaning device 15, calibration equipment resets.
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.
With the development of modern informatization and automation technical means, particularly the deep application of sensors, the Internet of things and computer technology in the agricultural field, brand new technical means and practical tools are brought to the fields of traditional livestock and poultry animal character parameter acquisition, measurement and analysis, animal behavior, vital sign monitoring and the like, accurate, efficient, rapid and timely monitoring of vital signs of breeding sows in a location fence is realized by constructing an autonomous inspection monitoring system and device based on machine vision, various sensors and the Internet of things, real-time and accurate data support is provided for the production of breeding pigs, so that the high-yield and stable-yield capacity of the breeding pig industry and even the animal husbandry is improved, and the system has great practical significance for promoting the rapid development of modern agriculture.
Fig. 1 is a general schematic diagram of a gilt positioning monitoring system according to an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a gilt positioning monitoring system, including: the sow positioning device comprises a data acquisition device 9 and a closed-loop guide rail 5, wherein the closed-loop guide rail 5 is erected right above a sow positioning fence 11, and the data acquisition device 9 is connected with the closed-loop guide rail 5 and moves along the closed-loop guide rail 5; the data acquisition device 9 is used for acquiring environmental information of a monitoring area, a color image, a depth image and a heat distribution image of the sow, acquiring the body size and body condition, the weight and the body temperature of the sow according to the color image, the depth image and the heat distribution image of the sow, and acquiring the growth health condition score of the sow according to the environmental information, the body size and body condition, the weight and the body temperature of the sow.
Specifically, the closed-loop guide rail 5 is erected right above the sow positioning fence 11, and the data acquisition device 9 is mounted on the closed-loop guide rail 5 and can move along the closed-loop guide rail 5, so that the sow is monitored by the data acquisition device 9. The data acquisition device 9 can collect the color image, the depth image and the heat distribution image of the sow from the position right above the sow, and through analyzing the color image, the depth image and the heat distribution image of the sow, the body size body condition of the sow including the body length, the body width and the body height of the sow and the body weight and the body temperature of the sow are obtained, meanwhile, the growth health condition of the sow is scored according to the environmental information, the body size body condition, the body weight and the body temperature of the sow, and therefore the growth health condition of the sow is quantitatively evaluated and analyzed.
The embodiment of the invention integrates the technologies of machine vision, a depth sensor, a thermal imaging sensor, the Internet of things, signal processing, three-dimensional scanning, intelligent information processing and the like, comprises the monitoring of physiological signs of sows, the monitoring of body size parameters, the monitoring of health conditions, the evaluation of breeding environments and the like, and can realize the timely, accurate, rapid, automatic and intelligent information acquisition and monitoring of the body condition information and the environmental information of the positioning fence sows.
Fig. 2 is a specific schematic view of a monitoring system for a gilt positioning fence according to an embodiment of the present invention, and as shown in fig. 2, a closed-loop guide 5 is mounted above a gilt positioning fence 11 through a guide rail bracket 1.
Fig. 3 is a schematic structural diagram of a data acquisition device according to an embodiment of the present invention, and as shown in fig. 3, the data acquisition device 9 includes a data processing module, and an environmental information acquisition module, a color image acquisition module, a depth image acquisition module, and a thermal distribution image acquisition module, which are respectively connected to the data processing module; the system comprises an environment information acquisition module, a color image acquisition module, a depth image acquisition module and a heat distribution image acquisition module, wherein the environment information acquisition module is used for acquiring environment information of a monitoring area; the data processing module is respectively used for acquiring three-dimensional point cloud data of the sow according to the color image and the depth image, acquiring the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data, extracting feature points and contour lines of the sow according to the body size and body condition and the three-dimensional point cloud data, estimating the weight of the sow according to the feature points and contour lines and the three-dimensional point cloud data, and estimating the body temperature of the sow according to the color image and the heat distribution image.
Specifically, the environment information acquisition module is used for acquiring the environment information of a monitoring area, the color image acquisition module is used for acquiring a color image of the sow, the depth image acquisition module is used for acquiring a depth image of the sow, and the heat distribution image acquisition module is used for acquiring a heat distribution image of the sow.
Further, a data processing module is used for reconstructing a three-dimensional model of the sow in the designated range positioning fence according to the depth image, extracting three-dimensional point cloud data of the sow in the designated range positioning fence according to the sow profile of the color image, then calculating the body size body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data, wherein the body size body condition comprises the body length, the body width and the body height of the sow, extracting a layer curve from the three-dimensional point cloud data according to main parameters of the body size body condition, calculating the curvature of the layer curve, extracting characteristic points of the body shape of the sow, including a head point, a front shoulder point, a back hip point and a tail point, extracting contour lines of the sow, including a back ridge line, a front shoulder contour line and a back hip contour line, estimating the body weight of the sow according to the characteristic points, the contour lines and the three-dimensional point cloud data, and estimating the.
It should be noted that the environmental information includes temperature, humidity, and CO2Content and NH3And the depth image acquisition module adopts a Kinect sensor, and the thermal distribution image acquisition module adopts a Flir thermal imaging sensor.
Further, as shown in fig. 2, each pigsty 12 is provided with a numbering sign 10, and the data acquisition device 9 further comprises a character recognition module, wherein the character recognition module is used for extracting the numbering sign 10 according to the color image, correcting error codes by adopting a front context and a back context which are continuous, and taking the extracted numbering as current positioning information and a unique identification code.
Further, the data acquisition device 9 further comprises an abnormity alarm module, and the abnormity alarm module is used for determining an abnormity condition and sending out an early warning signal according to the body size, body condition, weight and body temperature of the sow and the growth health condition score of the sow, so as to respond in time and reduce the breeding risk.
Further, as shown in fig. 1, the data acquisition device 9 further includes a wireless module 13, the data processing module is connected to the server through the wireless module 13, and the server exchanges data with the data processing module through the wireless module 13.
As shown in fig. 2, the system further includes two pairs of U-shaped grooved pulleys 2 and a motor, one pair of U-shaped grooved pulleys 2 is fixedly disposed on one side of the data acquisition device 9, and the other pair of U-shaped grooved pulleys 2 is fixedly disposed on the other side of the data acquisition device 9; one of the two pairs of U-shaped groove pulleys 2 is a driving wheel, the other pair is a driven wheel, and the driving wheel is driven by a motor.
Specifically, two pairs of U-shaped groove pulleys 2 are respectively disposed on two sides of the data acquisition device 9, and one pair of the U-shaped groove pulleys is used as a driving wheel and is fixedly connected with the closed-loop guide rail 5 through the driving pulley support 3. The other pair of driven wheels are connected with the closed-loop guide rail 5 in a sliding mode through the driven pulley support 8, the driven wheel support is connected with the closed-loop guide rail 5 through the linear sliding block through the rotating bearing, and therefore the driven wheels can rotate and move within a certain range, and the data acquisition device 9 is guaranteed to be suitable for sliding at the arc of turning on the closed-loop guide rail 5.
Therefore, one of each pair of U-shaped groove pulleys 2 is connected with the data acquisition device 9 through a synchronous belt 4, one pair of U-shaped groove pulleys 2 serving as driving wheels drives the other pair of U-shaped groove pulleys 2 serving as driven wheels to move along the closed-loop guide rail 5, and the data acquisition device 9 is driven to move along the closed-loop guide rail 5.
Further, as shown in fig. 2, the system further includes a power supply trolley line 6 and a power supply slider brush 7, the data acquisition device 9 uses a trolley power supply mode, the power supply trolley line 6 is arranged right above the closed-loop guide rail 5, the power supply slider brush 7 is fixedly connected with the data acquisition device 9, and the power supply slider brush 7 slides along the power supply trolley line 6, so as to supply power to the data acquisition device 9.
Further, as shown in fig. 1, the system further includes a cleaning device 14 and a resetting and calibrating device 15, the cleaning device 14 and the resetting and calibrating device 15 are respectively disposed at two different fixing positions of the closed-loop guide rail 5, the resetting and calibrating device 15 is used for daily parking of the data acquisition device 9, and the cleaning device 14 is used for cleaning the data acquisition device 9.
Fig. 4 is a schematic general flow chart of a monitoring method of a gilt positioning apparatus according to an embodiment of the present invention, and as shown in fig. 4, an embodiment of the present invention further provides a monitoring method of a gilt positioning apparatus, the method including: s1, collecting environmental information of a monitoring area, a color image, a depth image and a heat distribution image of the sow; s2, obtaining the body size and body condition, weight and body temperature of the sow according to the color image, the depth image and the heat distribution image of the sow, and obtaining the growth health condition score of the sow according to the environmental information, the body size and body condition, the weight and the body temperature of the sow.
Based on the above embodiment, fig. 5 is a specific flowchart of the monitoring method for a gilt of a gilt according to an embodiment of the present invention, and as shown in fig. 5, the method for acquiring the body size, body weight and body temperature of a sow according to a color image, a depth image and a heat distribution image of the sow specifically includes: acquiring three-dimensional point cloud data of the sow by utilizing the color image and the depth image; calculating the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data; carrying out point cloud layering on the three-dimensional point cloud data according to the body size body condition, extracting a layer curve, and extracting body type feature points of the sow according to the layer curve; acquiring the weight of the sow according to the three-dimensional point cloud data and the body size and body condition; and acquiring the body temperature of the sow according to the color image and the heat distribution image.
Based on the above embodiment, as shown in fig. 5, obtaining a health status score of the sow according to the environmental information, the body size and body temperature of the sow specifically includes: inputting feeding data of the sow into a sow breeding growth model, and outputting body size body conditions, body weight and body temperature corresponding to the feeding data, wherein the feeding data comprises feeding time, feeding amount and environment data of a monitoring area; wherein the sow breeding growth model is obtained after training according to the first sample feeding data, the first sample body size condition, the weight and the body temperature; inputting the environment information and the body size and body condition, weight and body temperature of the sow into an intelligent physiological health analysis model, and outputting a growth health condition score corresponding to the body size and body condition, the weight and the body temperature; the intelligent analysis model of the physiological health of the sow is obtained according to the environmental information, the body size and body condition, the weight and the body temperature of the second sample and the grading training of the growth health condition of the second sample.
Specifically, based on multi-factor intelligent analysis neural network knowledge, a sow breeding growth model is obtained by utilizing first sample breeding data and first sample body size condition, weight and body temperature training, then the breeding data of the sow is input into the sow breeding growth model, and the body size condition, the weight and the body temperature corresponding to the breeding data are output.
Similarly, the second sample environmental information, the body size body condition, the weight and the body temperature and the second sample growth health condition score are used for training to obtain the sow physiological health intelligent analysis model, and then the environmental information, the body size body condition, the weight and the body temperature of the sow are input into the sow physiological health intelligent analysis model, so that the growth health condition score corresponding to the body size body condition, the weight and the body temperature is output.
The system and the method for monitoring the sow on the positioning fence can realize timely, accurate, rapid, automatic and intelligent information acquisition and monitoring of the body condition information and the environmental information of the sow on the positioning fence, integrate the software and hardware environment of an Internet of things data platform, realize remote transmission and management of data, upload the data to a data server, realize non-contact, automatic and intelligent inspection and monitoring of the sow on the positioning fence, timely send out early warning aiming at the body condition abnormity and the environmental abnormity, provide comprehensive, accurate and timely all-round monitoring data for the breeding management of the sow, and further provide technical support and auxiliary tools for production management decision, thereby improving the informatization and intelligent level of breeding of the sow in animal husbandry production.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A monitoring system for positioning gilts, comprising: the sow positioning device comprises a data acquisition device and a closed-loop guide rail, wherein the closed-loop guide rail is erected right above a sow positioning fence, and the data acquisition device is connected with the closed-loop guide rail and moves along the closed-loop guide rail;
the data acquisition device is used for acquiring environmental information of a monitoring area, a color image, a depth image and a heat distribution image of the sow, acquiring the body size and body condition, the weight and the body temperature of the sow according to the color image, the depth image and the heat distribution image, and acquiring the growth health condition score of the sow according to the body size and body condition, the weight and the body temperature of the sow and the environmental information.
2. The system for monitoring a gilt of claim 1, wherein the data acquisition device comprises a data processing module, and an environmental information acquisition module, a color image acquisition module, a depth image acquisition module, a thermal distribution image acquisition module, each of which is connected to the data processing module;
the environment information acquisition module is used for acquiring environment information of a monitoring area, and the color image acquisition module, the depth image acquisition module and the thermal distribution image acquisition module are respectively used for acquiring the color image, the depth image and the thermal distribution image of the sow;
the data processing module is used for acquiring three-dimensional point cloud data of a sow according to the color image and the depth image, acquiring the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data, extracting feature points and contour lines of the sow according to the body size and body condition and the three-dimensional point cloud data, estimating the weight of the sow according to the feature points and contour lines and the three-dimensional point cloud data, and estimating the body temperature of the sow according to the color image and the heat distribution image.
3. The gilt monitoring system of claim 2 wherein the environmental information includes temperature, humidity, CO2Content and NH3And the depth image acquisition module adopts a depth sensor, and the thermal distribution image acquisition module adopts a thermal imaging sensor.
4. The system as recited in claim 2, wherein said data acquisition device further comprises a wireless module, said data processing module being connected to a server via said wireless module.
5. The system as set forth in claim 1, further comprising two pairs of U-grooved pulleys and a motor, one pair of said U-grooved pulleys being fixedly mounted on one side of said data acquisition device and the other pair of said U-grooved pulleys being fixedly mounted on the other side of said data acquisition device; one of the two pairs of U-shaped groove pulleys is a driving wheel, the other pair of U-shaped groove pulleys is a driven wheel, and the driving wheel is driven by the motor.
6. The system as recited in claim 1, further comprising a power supply trolley line and a power supply slider brush, wherein said power supply trolley line is disposed directly above said closed loop guide rail, said power supply slider brush is fixedly connected to said data acquisition device, and said power supply slider brush slides along said power supply trolley line to power said data acquisition device.
7. The system as recited in claim 1, further comprising a cleaning device and a resetting and calibrating device, wherein said cleaning device and said resetting and calibrating device are respectively disposed at two different fixed positions of said closed-loop rail, said resetting and calibrating device is used for parking said data acquisition device, and said cleaning device is used for cleaning said data acquisition device.
8. A monitoring method for positioning a gilt is characterized by comprising
Collecting environmental information of a monitoring area, a color image, a depth image and a heat distribution image of a sow;
according to the color image, the depth image and the heat distribution image of the sow, the body size and body condition, the weight and the body temperature of the sow are obtained, and according to the environment information, the body size and body condition, the weight and the body temperature of the sow, the growth health condition score of the sow is obtained.
9. The method for monitoring gilt according to claim 8, wherein said obtaining the body size, body weight and body temperature of the sow based on said color image, said depth image and said heat distribution image of the sow comprises:
acquiring three-dimensional point cloud data of the sow by using the color image and the depth image;
calculating the body size and body condition of the sow according to the color image or the depth image and the three-dimensional point cloud data;
carrying out point cloud layering on the three-dimensional point cloud data according to the body size and the body condition, extracting a layer curve, and extracting body type feature points of the sow according to the layer curve;
acquiring the weight of the sow according to the three-dimensional point cloud data and the body size and body condition;
and acquiring the body temperature of the sow according to the color image and the heat distribution image.
10. The method for monitoring gilts of claim 8, wherein obtaining a health status score for the sow based on the environmental information, the body size, body weight and body temperature of the sow comprises:
inputting feeding data of the sow into a sow breeding growth model, and outputting the body size body condition, the body weight and the body temperature corresponding to the feeding data, wherein the feeding data comprises feeding time, feeding amount and environment data of a monitoring area; the sow breeding growth model is obtained after training according to first sample breeding data, first sample body size conditions, body weight and body temperature;
inputting the body size body condition, the body weight and the body temperature of the sow into a sow physiological health intelligent analysis model, and outputting the growth health condition score corresponding to the body size body condition, the body weight and the body temperature; and the intelligent analysis model for the physiological health of the sow is obtained according to the body size and body condition of the second sample, the weight and the body temperature and the growth health condition scoring training of the second sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913980.7A CN110612921A (en) | 2019-09-25 | 2019-09-25 | Monitoring system and method for positioning gilts |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913980.7A CN110612921A (en) | 2019-09-25 | 2019-09-25 | Monitoring system and method for positioning gilts |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110612921A true CN110612921A (en) | 2019-12-27 |
Family
ID=68924178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910913980.7A Pending CN110612921A (en) | 2019-09-25 | 2019-09-25 | Monitoring system and method for positioning gilts |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110612921A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111418509A (en) * | 2020-01-16 | 2020-07-17 | 秒针信息技术有限公司 | Method and device for feeding livestock, storage medium and electronic device |
| CN112150498A (en) * | 2020-11-09 | 2020-12-29 | 浙江大华技术股份有限公司 | Method and device for determining posture information, storage medium and electronic device |
| CN112257991A (en) * | 2020-09-30 | 2021-01-22 | 内蒙古农业大学 | Automatic scoring device and method for sheep body condition |
| CN112945395A (en) * | 2021-03-17 | 2021-06-11 | 西藏新好科技有限公司 | Livestock and poultry animal body temperature evaluation method based on target detection |
| CN112970621A (en) * | 2021-03-26 | 2021-06-18 | 中国农业大学 | Sow heat conduction monitoring device and method |
| CN113068657A (en) * | 2021-03-31 | 2021-07-06 | 重庆市畜牧技术推广总站 | Intelligent efficient pig raising method and system |
| CN113080095A (en) * | 2021-04-02 | 2021-07-09 | 重庆市畜牧技术推广总站 | Sow post-pregnancy intelligent monitoring and nursing system |
| CN113662530A (en) * | 2021-07-02 | 2021-11-19 | 华南农业大学 | Pig physiological growth state monitoring and early warning method |
| CN113785783A (en) * | 2021-08-26 | 2021-12-14 | 北京市农林科学院智能装备技术研究中心 | Livestock grouping system and method |
| KR102372107B1 (en) * | 2021-09-16 | 2022-03-10 | 주식회사 일루베이션 | Image-based sow farrowing notification system |
| CN114304057A (en) * | 2021-12-23 | 2022-04-12 | 深圳市金新农科技股份有限公司 | Molecular breeding method aiming at body size characters and application thereof |
| CN114931112A (en) * | 2022-04-08 | 2022-08-23 | 南京农业大学 | Sow body ruler detection system based on intelligent inspection robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205233080U (en) * | 2015-12-31 | 2016-05-18 | 无锡职业技术学院 | But pig farm of rapid survey live pig body temperature |
| CN106529006A (en) * | 2016-11-04 | 2017-03-22 | 北京农业信息技术研究中心 | Depth image-based broiler growth model fitting method and apparatus |
| KR101729443B1 (en) * | 2016-06-15 | 2017-04-24 | 김국현 | Animal Monitoring System |
| CN206795819U (en) * | 2017-05-31 | 2017-12-26 | 上海谱盟光电科技有限公司 | Rail mounted electric inspection process robot |
| CN108606783A (en) * | 2018-05-24 | 2018-10-02 | 池州市池越农业科技有限公司 | A kind of live pig remote health monitoring system |
| CN109636826A (en) * | 2018-11-13 | 2019-04-16 | 平安科技（深圳）有限公司 | Live pig weight method for measurement, server and computer readable storage medium |
| CN109632058A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of intelligent group rearing method for measuring weight, device, electronic equipment and storage medium of raising pigs |
| CN209170424U (en) * | 2019-02-13 | 2019-07-26 | 鞍山星奥肉禽有限公司 | Disease surveillance prior-warning device in a kind of cultivation of scale poultry |
-
2019
- 2019-09-25 CN CN201910913980.7A patent/CN110612921A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205233080U (en) * | 2015-12-31 | 2016-05-18 | 无锡职业技术学院 | But pig farm of rapid survey live pig body temperature |
| KR101729443B1 (en) * | 2016-06-15 | 2017-04-24 | 김국현 | Animal Monitoring System |
| CN106529006A (en) * | 2016-11-04 | 2017-03-22 | 北京农业信息技术研究中心 | Depth image-based broiler growth model fitting method and apparatus |
| CN206795819U (en) * | 2017-05-31 | 2017-12-26 | 上海谱盟光电科技有限公司 | Rail mounted electric inspection process robot |
| CN108606783A (en) * | 2018-05-24 | 2018-10-02 | 池州市池越农业科技有限公司 | A kind of live pig remote health monitoring system |
| CN109636826A (en) * | 2018-11-13 | 2019-04-16 | 平安科技（深圳）有限公司 | Live pig weight method for measurement, server and computer readable storage medium |
| CN109632058A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of intelligent group rearing method for measuring weight, device, electronic equipment and storage medium of raising pigs |
| CN209170424U (en) * | 2019-02-13 | 2019-07-26 | 鞍山星奥肉禽有限公司 | Disease surveillance prior-warning device in a kind of cultivation of scale poultry |
Non-Patent Citations (8)
| Title |
|---|
| 印遇龙 等: "《改革开放40年中国猪业发展与进步 猪营养与饲料科学》", 31 October 2018, 吉林科学技术出版社 * |
| 樊福好: "猪健康状态的数学评价 ", 《养猪》 * |
| 樊福好: "通过数学模型和血液样本获知猪群健康状态 ", 《今日养猪业》 * |
| 江晓庆等: "基于Kinect的农作物长势深度图像实时获取算法 ", 《广东农业科学》 * |
| 潘家荣 等: "《食品及食品污染溯源技术与应用》", 31 May 2014, 中国质检出版社 * |
| 范同顺 等: "《建筑供配电与照明》", 30 April 2012, 中国建材工业出版社 * |
| 谭志国等: "多特征组合的深度图像分割算法 ", 《计算机工程与科学》 * |
| 韩洁 等: "《物联网RFID技术与应用》", 30 April 2019, 华中科技大学出版社 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111418509A (en) * | 2020-01-16 | 2020-07-17 | 秒针信息技术有限公司 | Method and device for feeding livestock, storage medium and electronic device |
| CN112257991A (en) * | 2020-09-30 | 2021-01-22 | 内蒙古农业大学 | Automatic scoring device and method for sheep body condition |
| CN112150498A (en) * | 2020-11-09 | 2020-12-29 | 浙江大华技术股份有限公司 | Method and device for determining posture information, storage medium and electronic device |
| CN112945395A (en) * | 2021-03-17 | 2021-06-11 | 西藏新好科技有限公司 | Livestock and poultry animal body temperature evaluation method based on target detection |
| CN112970621A (en) * | 2021-03-26 | 2021-06-18 | 中国农业大学 | Sow heat conduction monitoring device and method |
| CN113068657B (en) * | 2021-03-31 | 2022-04-08 | 重庆市畜牧技术推广总站 | Intelligent efficient pig raising method and system |
| CN113068657A (en) * | 2021-03-31 | 2021-07-06 | 重庆市畜牧技术推广总站 | Intelligent efficient pig raising method and system |
| CN113080095A (en) * | 2021-04-02 | 2021-07-09 | 重庆市畜牧技术推广总站 | Sow post-pregnancy intelligent monitoring and nursing system |
| CN113662530A (en) * | 2021-07-02 | 2021-11-19 | 华南农业大学 | Pig physiological growth state monitoring and early warning method |
| CN113662530B (en) * | 2021-07-02 | 2023-02-07 | 华南农业大学 | Pig physiological growth state monitoring and early warning method |
| CN113785783A (en) * | 2021-08-26 | 2021-12-14 | 北京市农林科学院智能装备技术研究中心 | Livestock grouping system and method |
| KR102372107B1 (en) * | 2021-09-16 | 2022-03-10 | 주식회사 일루베이션 | Image-based sow farrowing notification system |
| CN114304057A (en) * | 2021-12-23 | 2022-04-12 | 深圳市金新农科技股份有限公司 | Molecular breeding method aiming at body size characters and application thereof |
| CN114931112A (en) * | 2022-04-08 | 2022-08-23 | 南京农业大学 | Sow body ruler detection system based on intelligent inspection robot |
| CN114931112B (en) * | 2022-04-08 | 2024-01-26 | 南京农业大学 | Sow body ruler detection system based on intelligent inspection robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110612921A (en) | Monitoring system and method for positioning gilts | |
| CN108875647B (en) | Moving track monitoring method and system based on livestock identity | |
| CN109900280B (en) | Autonomous navigation-based livestock and poultry information perception robot and map construction method | |
| CN110260789B (en) | System and method for monitoring phenotype of field high-throughput crops | |
| CN114037552B (en) | Method and system for polling physiological growth information of meat ducks | |
| CN105784083A (en) | Cow shape measuring method and cow shape measuring system based on stereo vision technology | |
| KR20150025333A (en) | Management control system for growing plants using moving robot based on image processing | |
| CN104463688A (en) | Free-ranging beef cattle positioning and early warning system | |
| CN110849264A (en) | Multi-row track based field crop phenotype monitoring system and method | |
| CN109380146B (en) | Automatic measurement device and method for live pigs | |
| CN113662530B (en) | Pig physiological growth state monitoring and early warning method | |
| CN114980011B (en) | Livestock and poultry body temperature monitoring method with cooperation of wearable sensor and infrared camera | |
| CN113947734A (en) | Pig physical sign information acquisition method and system | |
| CN108120473A (en) | Chamber crop three-dimensional configuration monitoring device and monitoring method based on depth camera | |
| CN211532340U (en) | Monitoring system for positioning fence sows | |
| CN108670256B (en) | Cow respiratory rate monitoring system and method | |
| CN114847196B (en) | Intelligent beehive and bee identification tracking counting system based on deep learning | |
| CN103983798A (en) | Crop detecting system | |
| CN113569971A (en) | Image recognition-based catch target classification detection method and system | |
| CN117029904A (en) | Intelligent cage-rearing poultry inspection system | |
| CN210247950U (en) | Intelligent detection device and intelligent detection system | |
| CN114931112B (en) | Sow body ruler detection system based on intelligent inspection robot | |
| CN111105518A (en) | Breeding inspection system | |
| KR20190084154A (en) | 3D Depth Camera based fruit crop yield prediction system and method | |
| CN115756037A (en) | Greenhouse vegetable management and control method and system |
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: 20191227 |
|
| RJ01 | Rejection of invention patent application after publication |