CN114407051A - Livestock and poultry farm inspection method and livestock and poultry farm robot - Google Patents
Livestock and poultry farm inspection method and livestock and poultry farm robot Download PDFInfo
- Publication number
- CN114407051A CN114407051A CN202210221117.7A CN202210221117A CN114407051A CN 114407051 A CN114407051 A CN 114407051A CN 202210221117 A CN202210221117 A CN 202210221117A CN 114407051 A CN114407051 A CN 114407051A
- Authority
- CN
- China
- Prior art keywords
- livestock
- inspection
- target
- image
- poultry
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 175
- 244000144972 livestock Species 0.000 title claims abstract description 118
- 244000144977 poultry Species 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004927 fusion Effects 0.000 claims abstract description 30
- 238000001931 thermography Methods 0.000 claims abstract description 25
- 241000271566 Aves Species 0.000 claims description 17
- 241000287828 Gallus gallus Species 0.000 claims description 15
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000002146 bilateral effect Effects 0.000 claims description 2
- 230000004083 survival effect Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 13
- 230000003287 optical effect Effects 0.000 description 9
- 230000036544 posture Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 208000031295 Animal disease Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 206010048282 zoonosis Diseases 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- 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
- A01K45/00—Other aviculture appliances, e.g. devices for determining whether a bird is about to lay
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Biodiversity & Conservation Biology (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Animal Husbandry (AREA)
- Birds (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Biophysics (AREA)
- Radiation Pyrometers (AREA)
Abstract
The application provides a livestock and poultry farm inspection method and a livestock and poultry farm robot, including: simultaneously acquiring a visible light image and an infrared thermal imaging image containing an inspection target at a current inspection point position through a dual-light camera; carrying out image fusion on the collected visible light image and the infrared thermal imaging image to obtain a fusion image on the current inspection point; judging whether the current inspection target is a livestock target or not according to the visible light image information characteristics in the fusion image, and judging whether the temperature of the current inspection target is lower than a set temperature threshold or not according to the heat source information characteristics in the fusion image; and if the current polling target is a livestock target and the temperature of the current polling target is lower than a set temperature threshold value, judging the current polling target as a suspected dead livestock target, and recording corresponding position information. According to the method, the fused image of the heat source characteristic information and the visible light information is obtained through image fusion, the survival state of the livestock is judged by rejecting non-livestock targets and setting a temperature threshold, and the judgment accuracy is high.
Description
Technical Field
The application relates to the field of inspection robots, in particular to an inspection method for a livestock and poultry farm and a robot for the livestock and poultry farm.
Background
In recent years, with the rapid development and popularization of livestock and poultry industry, livestock and poultry raising standardization and cultivation facilities automation and mechanization are basically realized by cultivation enterprises. With the development of intensive cultivation, the livestock and poultry cultivation density is gradually improved, and the cultivation number in a single house is increased. Under the condition, higher requirements are provided for preventing and controlling animal diseases, once livestock and poultry die, if the livestock and poultry are not found and treated in time, the livestock and poultry in the whole house die and are killed, and great potential safety hazards and economic losses are caused. Therefore, real-time monitoring of the health status of livestock and poultry is necessary.
At present, two modes of manual visual inspection and inspection robot exist for the inspection of animal health in livestock and poultry farms. The influence of factors such as large manual labor intensity of manual visual observation, high risk of zoonosis and the like has a series of problems. On the other hand, the existing inspection robot judges whether the livestock or poultry dies by shooting high-definition images of the livestock or poultry and processing the images in a posture mode and the like, the misjudgment rate of the identification mode is extremely high, and the accuracy is greatly reduced.
Disclosure of Invention
Based on this, in order to solve above-mentioned art problem, this application provides a beasts and birds plant patrolling and examining method and beasts and birds plant robot, can promote beasts and birds survival state and judge the rate of accuracy.
The first aspect of the embodiment of this application provides a machine is patrolled and examined in beasts and birds plant, includes following step:
simultaneously acquiring a visible light image and an infrared thermal imaging image containing an inspection target at a current inspection point position through a dual-light camera;
carrying out image fusion on the collected visible light image and the infrared thermal imaging image to obtain a fusion image on the current inspection point;
judging whether the current inspection target is a livestock target or not according to the visible light image information characteristics in the fusion image, and judging whether the temperature of the current inspection target is lower than a set temperature threshold or not according to the heat source information characteristics in the fusion image;
and if the current polling target is a livestock target and the temperature of the current polling target is lower than a set temperature threshold value, judging the current polling target as a suspected dead livestock target, and recording corresponding position information.
In a specific embodiment, the temperature threshold is set according to a normal temperature value of the livestock and the temperature value of the dead livestock and the poultry.
In a specific embodiment, when the inspection target is chicken, the temperature threshold is 32-35 ℃.
In a specific embodiment, the determining whether the current inspection target is a livestock target according to the visible light image information features in the fused image includes:
preprocessing a visible light image; extracting image features; inputting a classifier; and obtaining a classification result.
In a specific embodiment, the method for inspecting livestock and poultry farms further comprises:
and displaying the relevant information of the suspected dead livestock and poultry target on a display screen, or carrying out voice broadcast in real time, or sending the information to the mobile phone of the bound worker through application program pushing and short messages.
In a specific embodiment, each inspection point is provided with a different inspection height, and the inspection method for the livestock and poultry farm further comprises the following steps:
judging whether the inspection height of the current inspection point position is finished or not;
if the current inspection point position has the inspection height which is not finished, adjusting the height of the dual-optical camera to the next inspection height, and returning to the step of simultaneously acquiring the visible light image and the infrared thermal imaging image containing the inspection target at the current inspection point position through the dual-optical camera;
and if the inspection height of the current inspection point location is all finished, the inspection robot moves to the next inspection point location.
In a specific embodiment, the method further comprises the following steps:
recording a map of a livestock and poultry farm;
planning a routing inspection path according to a map of the livestock and poultry farm, and marking and positioning each routing inspection point on the routing inspection path.
The second aspect of the embodiment of the application provides a robot is patrolled and examined in beasts and birds plant, including robot and two optical cameras, be equipped with the industrial computer in the robot, two optical cameras have visible light imaging module and infrared thermal imaging module, the industrial computer is used for controlling two optical cameras and completion as before beasts and birds plant patrol and examine the method.
In a specific embodiment, beasts and birds plant patrols and examines robot still including removing chassis and riser, the robot is installed remove on the chassis, the riser is installed on the robot, the bi-optic camera is installed on the riser, the riser includes dead lever and lifter, the lifter is movably installed along the direction of lift in the dead lever, the dead lever with the bilateral symmetry of lifter all installs the bi-optic camera.
In a specific embodiment, remove the chassis and include safety radar, navigation radar, drive wheel and battery, safety radar is used for detecting barrier or pedestrian, the navigation radar is used for discerning patrols and examines the route, patrols and examines the positional information of position, the drive wheel is used for carrying out navigation instruction, the battery is used for doing the drive wheel the riser reaches the power supply of two optical cameras.
The inspection method for the livestock and poultry farm and the robot for the livestock and poultry farm have the following beneficial effects at least: according to the livestock and poultry farm inspection method and the livestock and poultry farm robot, the physical characteristics of the thermal imaging image and the visible light image are comprehensively considered, the fused image capable of comprehensively representing the heat source characteristic information and the visible light information of livestock and poultry is obtained through image fusion, the survival state of the livestock and poultry is judged by rejecting non-livestock targets and setting the temperature threshold, and the judgment accuracy is high.
Drawings
Fig. 1 is a perspective view of a patrol robot for a livestock and poultry farm according to an embodiment of the present application;
fig. 2 is a perspective view of the inspection robot for the livestock and poultry farm in fig. 1 from another angle;
fig. 3 is a perspective view of the livestock and poultry farm inspection robot of fig. 1 after the lifter is lifted;
fig. 4 is a flowchart of a polling method of a polling robot in a livestock farm according to an embodiment of the present application;
fig. 5 is a flowchart of the specific steps of moving along a predetermined inspection path to inspect the inspection point locations in fig. 4;
FIG. 6 is a visible light image taken by a dual-optical camera;
FIG. 7 is a fused image of a visible light image and an infrared thermal image taken by a dual-optical camera;
FIG. 8 is a flowchart illustrating the specific steps of FIG. 5 for determining whether the target is a livestock or poultry target;
fig. 9 is a picture displayed on a display screen when the target of the suspect dead livestock and poultry is found in the fusion image in fig. 7.
The elements in the figures are numbered as follows: a moving chassis 10 (among them, a safety radar 11, a navigation radar 12, a collision switch 13, a driving wheel 14); a robot body 20 (among others, a housing 21, an access door 22, and a display screen 23); a lifter 30 (among them, a fixing rod 31, a lifting rod 32); a dual-light camera 40.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present application are given in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. When an element is referred to as being "coupled" to another element, it can be directly coupled to the other element or intervening elements may be present, and the term "coupled" as used herein refers to a coupling in which two elements have power transfer. As used herein, the terms "vertical," "horizontal," "left," "right," "above," "below," and the like are for illustrative purposes only and do not denote a single embodiment, it being understood that such spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures, e.g., elements or features described as "below" or "beneath" other elements or features would be oriented "above" the other elements or features if the device were turned over in the figures. Thus, the example term "below" can encompass both an orientation of above and below.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the terms "and/or" and/or "include any and all combinations of one or more of the associated listed items.
Referring to fig. 1 to 3, the inspection robot for the livestock and poultry farm according to an embodiment of the present application includes a movable chassis 10, a robot body 20, a lifter 30, and a dual-optical camera 30, wherein the robot body 20 is mounted on the movable chassis 10, the lifter 30 is mounted on the robot body 10, and the dual-optical camera 40 is mounted on the lifter 30. The mobile chassis 10 is used for driving, orienting and navigating the whole mobile lifting inspection robot; the robot body 20 is a core component of the inspection robot, and is provided with an industrial personal computer which is used as a control and data processing center of the inspection robot; the lifter 30 moves up and down and adjusts according to the instruction so that the dual cameras 40 mounted on the lifter 30 can photograph the object to be inspected.
The moving chassis 10 drives the whole inspection robot to move and comprises a safety radar 11, a navigation radar 12, a collision switch 13 and a driving wheel 14. The safety radar 11 is a navigation safety sensor of the inspection robot, and when the safety radar 11 detects an obstacle or a pedestrian and the like in the automatic walking process, the inspection robot is stopped to move so as to ensure the walking safety. The navigation radar 12 is an automatic navigation sensor of the inspection robot, and is used for identifying the inspection path of the livestock and poultry farm, planning a walking path, and automatically identifying the position information (such as a serial number) of the inspection point and the position serial number of the charging bin. The collision switch 13 is used for guaranteeing the safety of the inspection robot in the automatic walking process, and if the object accidentally invades, the collision switch 13 can guarantee the safety of the foreign object and the inspection robot. The driving wheel 14 is an operation execution component of the inspection robot, executes an instruction sent by an automatic navigation unit in an industrial personal computer of the inspection robot, and realizes the forward, backward, stop, steering and the like of an inspection route.
The mobile chassis 10 is also provided with a battery which can supply power to the driving wheels 14, the industrial personal computer, the lifter 30, the dual-optical camera 40 and the like. The batteries are arranged in the mobile chassis 10, and the bottom counter weight of the inspection robot can be added to prevent the inspection robot from tilting or turning over.
The robot body 20 contains all the electric and electronic components of the whole control part, which is the control core of the whole inspection robot. Robot body 20 has shell 21, access door 22 and display screen 23, and shell 21 and access door 22 form the accommodation space, and its inside is used for placing industrial computer, steady voltage output module, Hub etc.. The access door 22 is openable and closable with respect to the housing 21 to facilitate access and maintenance of the interior. The display screen 23 is arranged at the upper end of the shell 21 and is in signal connection with an internal industrial personal computer, and is used for visually displaying relevant information and inspection results (including frequent environment information and dead livestock position information) of the industrial personal computer.
The lifter 30 is used to adjust the position height of the dual cameras 40. Take the chicken farm as an example, the cage layer of chicken coop is 3 layers or even more than 3 layers mostly, can guarantee through riser 30 that the target on every layer can all be detected. The lifter 30 includes a fixing rod 31 and a lifting rod 32, and the lifting rod 32 is movably installed in the fixing rod 31 in a lifting direction, as shown in fig. 3. The lifting rod 32 may be driven by a linear driving member, such as an electric push rod, and when the lifting rod 32 is moved in a lifting direction within the fixing rod 31 along with the push rod. Dead lever 31, lifter 32 can adopt hollow tubular structure, and lifter 32 inlays in dead lever 31, and dead lever 31 has the guide effect and makes lifter 32 can bear certain yawing force to lifter 32, even patrol and examine the robot this moment under the scram state, also can protect the inside electric putter of riser 30 not receive the influence of yawing force, guarantee the security of operation, can satisfy various application conditions in portable over-and-under type robot.
All install two optical cameras 40 on the dead lever 31 of riser 30 and the lifter 32, a plurality of two optical cameras 40 can be simultaneously to the different target of patrolling and examining of both sides shoot, promote to patrol and examine efficiency. The position of the dual-optical camera 40 arranged on the fixed rod 31 can be finely adjusted within a certain range from top to bottom before inspection, so that the dual-optical camera can be better matched with the height of an inspection target; install the bi-optical camera 40 on lifter 32 can be along with the lifter 32 goes up and down under the control of industrial computer at the in-process of patrolling and examining, can realize shooing the target of patrolling and examining of co-altitude not.
In the illustrated embodiment, 6 dual-light cameras 40 are symmetrically disposed on both sides of the lifter 30, wherein 4 dual-light cameras 40 are mounted on both sides of the fixing rod 31, and the other 2 dual-light cameras 40 are mounted on both sides of the lifter 32. In the illustrated embodiment, the dual-light cameras 40 are distributed according to three layers, and can be used for one-time corresponding to three layers of livestock cages at different inspection heights on two sides after being lifted and lowered. Taking the inspection target as a chicken and three coops arranged at inspection point positions as an example, the first layer and the second layer of double-light cameras 40 arranged on the fixed rod 31 correspondingly shoot the lower two layers of coops with lower inspection heights of the inspection point positions below; the third layer of the double-light cameras 40 are installed at the top of the lifting rod 32, and can correspondingly shoot a third layer of coops with a higher inspection height after the height is adjusted.
If the number of different inspection heights required to be inspected on the single inspection point position is larger than the number of the single-side double-optical cameras 40, the height of the uppermost double-optical camera 40 can be adjusted to the next inspection height again through the lifting rod 32 until all inspection heights on the single inspection point position are inspected.
The dual-optical camera 40 is provided with a visible light imaging module and an infrared thermal imaging module, when the inspection is carried out, the visible light imaging module and the infrared thermal imaging module shoot an inspected target at the same time, the visible light imaging module shoots a high-definition live-action picture of the inspected target, the infrared thermal imaging module automatically identifies an infrared thermal imaging image of the inspected target, and the temperature of the inspected target can be identified.
All install two optical cameras 40 on the dead lever 31 of riser 30 and the lifter 32, a plurality of two optical cameras 40 can be simultaneously to the different target of patrolling and examining of both sides shoot, promote to patrol and examine efficiency. The position of the dual-optical camera 40 arranged on the fixed rod 31 can be finely adjusted within a certain range from top to bottom before inspection, so that the dual-optical camera can be better matched with the height of an inspection target; install the bi-optical camera 40 on lifter 32 can be along with the lifter 32 goes up and down under the control of industrial computer at the in-process of patrolling and examining, can realize shooing the target of patrolling and examining of co-altitude not. In the illustrated embodiment, 6 dual-light cameras 40 are symmetrically disposed on both sides of the lifter 30, wherein 4 dual-light cameras 40 are mounted on both sides of the fixing rod 31, and the other 2 dual-light cameras 40 are mounted on both sides of the lifter 32.
The beasts and birds plant patrols and examines the robot and start the back and patrol and examine according to the route of patrolling and examining of settlement, removes chassis 10 and takes and patrols and examines the robot and remove to patrolling and examining the position, if safe radar 11 detects barrier or pedestrian etc. at the removal in-process, will move in order to guarantee walking safety under the control of industrial computer automatic stop. When the mobile robot is moved to a detection point position, the lifter 30 can lift the dual-optical camera 40 arranged on the lifting rod 32 under the control of the industrial personal computer to a preset height, and at the moment, the dual-optical cameras 40 in different positions and different heights respectively shoot and detect routing inspection targets in different heights on two sides. The shot detection data or the processed inspection result can be displayed on the display screen 23. And after the inspection target at the current position is detected, continuously moving to the next inspection point position according to the inspection path, and repeating the inspection process until all the inspection targets on the inspection path are detected.
Referring to fig. 4, a method for polling a polling robot in a livestock and poultry farm according to an embodiment of the present application includes the following steps:
and step S10, recording a map of the livestock and poultry farm.
And step S20, planning a routing inspection path according to the map of the livestock and poultry farm. And marking and positioning each inspection point position on the inspection path.
And step S30, moving along the preset routing inspection path to inspect the routing inspection point.
And step S40, judging whether all the inspection point positions on the inspection path are inspected.
And step S50, if the inspection of the inspection point location is finished, the inspection robot returns to the charging bin for charging.
In the inspection process, if whether the livestock and poultry die or not is judged only by using the visible light image as a judgment basis, the problem of high misjudgment rate exists. Whether the livestock and poultry die is judged through the visible light image, the outlines of the livestock and poultry are generally identified through the image, so that the postures of the livestock and poultry are obtained, and the judgment is carried out according to the postures. However, the postures of the dead livestock and poultry are complex and various, so that the misjudgment rate is extremely high, and the accuracy rate is only about 30%.
Still take a chicken farm as an example, for laying hens, the body temperature is an important index for reflecting the health status of the laying hens. By utilizing rich useful information contained in the visible light image and combining the advantages of infrared thermal imaging and corresponding information of the visible light image, the accuracy of data acquisition can be improved, and the health state of the laying hens can be accurately judged.
In step S30, the process of performing inspection at each inspection site is roughly as follows:
simultaneously acquiring a visible light image and an infrared thermal imaging image containing an inspection target at a current inspection point position through a dual-light camera;
carrying out image fusion on the collected visible light image and the infrared thermal imaging image to obtain a fusion image on the current inspection point;
judging whether the current inspection target is a livestock target or not according to the visible light image information characteristics in the fusion image, and judging whether the temperature of the current inspection target is lower than a set temperature threshold or not according to the heat source information characteristics in the fusion image;
and if the current polling target is a livestock target and the temperature of the current polling target is lower than a set temperature threshold value, judging the current polling target as a suspected dead livestock target, and recording corresponding position information.
The sequence of the two judging processes is not limited uniquely, and when the specific implementation is carried out, the livestock and poultry target can be judged firstly and then the temperature can be judged, the livestock and poultry target can also be judged firstly and then the livestock and poultry target can also be judged, and the comprehensive analysis can also be carried out simultaneously.
Referring to fig. 5, step S30 further includes the following steps:
and S301, judging whether the inspection point location is reached.
And step S302, after the inspection point is reached, the industrial personal computer controls the driving wheel 14 to stop moving. At this time, the navigation radar 12 is used to input the position information of the current inspection point, and simultaneously record the time information.
And step S303, collecting a visible light image and an infrared thermal imaging image of the inspection target of the inspection point location through the dual-optical camera 40.
The visible light imaging module of the dual-light camera 40 takes a picture simultaneously with the temperature measurement of the infrared thermal imaging module, so that the consistency of a temperature measurement target and an image recognition target can be ensured.
Taking a chicken farm as an example, the visible light image captured by the dual-light camera 40 is shown in fig. 6.
And S304, carrying out image fusion on the collected visible light image and the infrared thermal imaging image to obtain a fusion image of the current inspection target.
The fused image contains the heat source information characteristic and the visible light information characteristic of the inspection target, and can be considered as a visible light image fused with temperature data. The fused image obtained by fusing the visible light image and the infrared thermography image shown in fig. 6 is shown in fig. 7.
And S305, judging whether the target is a livestock and poultry target according to the visible light image information characteristics in the fusion image.
Utilize high definition visible light imaging module to carry out target identification, can distinguish patrolling and examining target and interference target (like feeding device, equipment device), can accurately select birds poultry target, reject non-birds poultry target through artificial intelligence (AI algorithm).
The process of image recognition of the process of individual identification of livestock targets is as follows:
and step S3051, preprocessing an image. The image preprocessing mainly adopts the operations of denoising, transformation, smoothing and the like to process the visible light image, so that the important characteristics of the visible light image are improved.
And S3052, extracting image features. The recognition image has various kinds of features, and if the features of the image to be recognized are separated in a certain way, the feature extraction is also called feature extraction. In the process of image recognition by taking a chicken as a polling target, the characteristic of the chicken head/the contour (curve and volume) of the chicken body is mainly extracted as the characteristic.
And step S3053, inputting a classifier. The classifier formulates the identification rule according to training, and the main types of the features can be obtained based on the identification rule, so that the identification rate of image identification is continuously improved.
And step S3054, obtaining a classification result. And identifying special features through a classifier, and finally realizing the evaluation of the image.
The visible light image is used for identifying the livestock and poultry target, so that the non-livestock and poultry target can be removed. Compared with the method that the survival state of the livestock target is directly identified through the visible light image, the convenience and accuracy of identifying whether the livestock target is the livestock target are greatly improved, and the misjudgment rate is greatly reduced.
And if the visible light image information features judge that the target is not the livestock target, the step S308 is entered, the target is judged to be the non-livestock target and is removed.
It should be noted that, because there are relatively many non-livestock and poultry targets (such as the interference targets described above) in the visible light image, the non-livestock and poultry targets are removed first to reduce the content of irrelevant and interfering information, so that the data processing load of the industrial personal computer is reduced, the efficiency is improved, and a good foundation is laid for the subsequent processing steps. Therefore, in the embodiment corresponding to fig. 5, when identifying the suspected dead livestock and poultry target, whether the suspected dead livestock and poultry target is the livestock and poultry target is judged according to the visible light image information characteristics, and then the temperature judgment is carried out, so that the identification efficiency can be effectively improved.
And if the visible light image information features are judged to be the livestock and poultry target, the step S306 is carried out, and whether the heat source information features in the fusion image are lower than the set temperature threshold value or not is judged.
And setting a temperature threshold T after comparing the normal temperature value of the livestock and the dead temperature value of the livestock and the poultry. Extracting current inspection target temperature T when heat source information characteristicsnAnd when the temperature is lower than the set temperature threshold T, the inspection target is judged as the suspected dead livestock target.
Still taking chicken as an example, the temperature of live chicken is 40-41.5 ℃, while the temperature of dead chicken is gradually reduced until the temperature is the same as the environment temperature of the farm. The environmental temperature of the chicken farm is set to be 18-20 ℃ throughout the year, so that the temperature threshold T taking the chicken as the inspection target is set to be 32-35 ℃, and if the temperature of the inspection target is lower than 32-35 ℃, the target can be judged to be a suspected death target.
And step S307, after the current inspection target is judged to be the suspected dead livestock target, the step S309 is carried out, and the position information of the suspected dead livestock target is recorded. The position information of the suspected dead livestock and poultry target comprises the serial number of the current routing inspection point position, the number of layers of the suspected dead livestock and poultry target and the like.
At this time, in step S310, the information related to the target of the livestock suspected of dying may be displayed on the display screen 23 for the convenience of the staff to check.
As shown in fig. 9, it is a picture displayed on the display screen 23 when the target of the suspect dead livestock is found in the fusion image in fig. 7.
In addition, voice broadcasting reminding can be carried out in real time when suspected dead livestock and poultry targets are patrolled. Or if the related staff is bound by the mobile phone number, the related staff can be timely notified by means of application program push reminding, short message reminding and the like.
Different patrol heights are set on each patrol point location, so whether all patrol heights of the current patrol point location complete patrol is required to be confirmed.
Step S311, determining whether each inspection height of the current inspection point location completes inspection. If the level quantity of the inspection target of the current inspection point is greater than the level quantity of the dual-optical cameras 40 (namely, the quantity of the dual-optical cameras 40 on one side of the lifter 30), for example, the lifter 30 of the inspection robot in fig. 1 is provided with 3 dual-optical cameras 40 on one side, and corresponds to the inspection height of 3 levels, and the inspection layer number of the current inspection point is more than 3 layers, namely, more than 3 inspection heights exist, and after the inspection of 3 corresponding layers is completed by 3 dual-optical cameras 40, the upper dual-optical cameras 40 are moved to the inspection height which is not inspected yet through the lifting rod 32 of the lifter 30.
Therefore, if the inspection height of the current inspection point has not been finished, the process goes to step S312, and the height of the dual-optical camera is adjusted to the next inspection height by the lifter, and then the process returns to step S302.
If all the inspection heights of the current inspection point location are inspected, the process goes to step 313, the driving wheel 14 drives the inspection robot to move to the next inspection point location, and the steps from step 301 to step 313 are repeated.
According to the inspection method of the inspection robot for the livestock and poultry farm, the visible light image and the infrared thermal imaging image are subjected to image fusion, the survival state of livestock and poultry is judged by eliminating non-livestock targets and setting the temperature threshold, and the judgment accuracy is high. The utility model provides a physical characteristic of thermal imaging image and visible light image has been considered comprehensively to this application, obtains the heat source characteristic information that can comprehensively characterize beasts and birds and the fusion image of visible light information through image fusion to guaranteed the accuracy of testing result through the temperature threshold value, satisfied the demand of patrolling and examining of beasts and birds plant under various culture environment.
To sum up, the livestock and poultry farm inspection method and the livestock and poultry farm robot comprehensively consider the physical characteristics of the thermal imaging image and the visible light image, acquire the fusion image of the heat source characteristic information and the visible light information capable of comprehensively representing the livestock and poultry through image fusion, ensure the accuracy of the detection result through the temperature threshold value, and meet the inspection requirements of the livestock and poultry farm under various breeding environments. The utility model provides a beasts and birds plant patrols and examines method and beasts and birds plant robot, on the basis of guaranteeing to patrol and examine the result accuracy, still through setting up a plurality of two optical cameras and riser promoted the efficiency of patrolling and examining to beasts and birds plant by a wide margin, practiced thrift the breed cost, improved the economic benefits who breeds.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for patrolling a livestock and poultry farm is characterized by comprising the following steps:
simultaneously acquiring a visible light image and an infrared thermal imaging image containing an inspection target at a current inspection point position through a dual-light camera;
carrying out image fusion on the collected visible light image and the infrared thermal imaging image to obtain a fusion image on the current inspection point;
judging whether the current inspection target is a livestock target or not according to the visible light image information characteristics in the fusion image, and judging whether the temperature of the current inspection target is lower than a set temperature threshold or not according to the heat source information characteristics in the fusion image;
and if the current polling target is a livestock target and the temperature of the current polling target is lower than a set temperature threshold value, judging the current polling target as a suspected dead livestock target, and recording corresponding position information.
2. The livestock and poultry farm inspection method according to claim 1, characterized in that: the temperature threshold is set according to the temperature values of normal livestock and poultry and the temperature values of dead livestock and poultry.
3. The livestock and poultry farm inspection method according to claim 2, characterized in that: when the inspection target is chicken, the temperature threshold is 32-35 ℃.
4. The livestock and poultry farm inspection method according to claim 1, wherein the judging whether the current inspection target is the livestock and poultry target according to the visible light image information characteristics in the fusion image comprises:
preprocessing a visible light image; extracting image features; inputting a classifier; and obtaining a classification result.
5. The livestock and poultry farm inspection method according to claim 1, further comprising:
and displaying the relevant information of the suspected dead livestock and poultry target on a display screen, or carrying out voice broadcast in real time, or sending the information to the mobile phone of the bound worker through application program pushing and short messages.
6. The livestock and poultry farm inspection method according to any one of claims 1 to 5, wherein different inspection heights are set at each inspection point, and the livestock and poultry farm inspection method further comprises:
judging whether the inspection height of the current inspection point position is finished or not;
if the inspection height of the current inspection point position is not finished, adjusting the height of the dual-optical camera to the next inspection height, and returning to the step of simultaneously acquiring the visible light image and the infrared thermal imaging image containing the inspection target at the current inspection point position through the dual-optical camera;
and if the inspection height of the current inspection point location is all finished, the inspection robot moves to the next inspection point location.
7. The livestock and poultry farm inspection method according to claim 1, further comprising the steps of:
recording a map of a livestock and poultry farm;
planning a routing inspection path according to a map of the livestock and poultry farm, and marking and positioning each routing inspection point on the routing inspection path.
8. The utility model provides a robot is patrolled and examined in beasts and birds plant which characterized in that: the livestock and poultry farm inspection method comprises a robot body and a dual-light camera, wherein an industrial personal computer is arranged in the robot body, the dual-light camera is provided with a visible light imaging module and an infrared thermal imaging module, and the industrial personal computer is used for controlling the dual-light camera and completing the livestock and poultry farm inspection method according to claim 1.
9. The livestock and poultry farm inspection robot according to claim 8, characterized in that: beasts and birds plant patrols and examines robot still including removing chassis and riser, the robot is installed remove on the chassis, the riser is installed on the robot, the two-shot camera is installed on the riser, the riser includes dead lever and lifter, the lifter is movably installed along the direction of lift in the dead lever, the dead lever with the bilateral symmetry of lifter all installs two-shot camera.
10. The livestock and poultry farm inspection robot according to claim 8, characterized in that: the mobile chassis comprises a safety radar, a navigation radar, a driving wheel and a battery, wherein the safety radar is used for detecting obstacles or pedestrians, the navigation radar is used for identifying and inspecting a path and position information of an inspection point position, the driving wheel is used for executing a navigation instruction, and the battery is used for supplying power to the driving wheel, the lifter and the double-light camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210221117.7A CN114407051A (en) | 2022-03-07 | 2022-03-07 | Livestock and poultry farm inspection method and livestock and poultry farm robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210221117.7A CN114407051A (en) | 2022-03-07 | 2022-03-07 | Livestock and poultry farm inspection method and livestock and poultry farm robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114407051A true CN114407051A (en) | 2022-04-29 |
Family
ID=81263327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210221117.7A Pending CN114407051A (en) | 2022-03-07 | 2022-03-07 | Livestock and poultry farm inspection method and livestock and poultry farm robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114407051A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115147782A (en) * | 2022-08-02 | 2022-10-04 | 广州度凌科技有限公司 | Dead animal identification method and device |
| CN116447457A (en) * | 2023-04-25 | 2023-07-18 | 广东爱吉尔机器人科技有限公司 | Henhouse inspection robot |
| CN116895127A (en) * | 2023-09-11 | 2023-10-17 | 西安凌志航遥信息科技工程有限公司 | Safety monitoring alarm system with personnel positioning function for energy production |
| WO2023221170A1 (en) * | 2022-05-17 | 2023-11-23 | 浙江大学 | Sick/dead-poultry inspection apparatus and method suitable for cage-reared poultry house |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
| CN109997730A (en) * | 2019-04-28 | 2019-07-12 | 山东省农业科学院家禽研究所 | The cruise control method of cage bird intelligent inspection system and its crusing robot |
| JP2019205425A (en) * | 2018-05-24 | 2019-12-05 | 大豊産業株式会社 | Dead chicken sensing system, chicken life or death determination program, and chicken life or death determination device |
| CN111626985A (en) * | 2020-04-20 | 2020-09-04 | 北京农业信息技术研究中心 | Poultry body temperature detection method based on image fusion and poultry house inspection system |
| CN211746249U (en) * | 2020-01-02 | 2020-10-27 | 河北农业大学 | Device for identifying chickens in cage |
| CN213518003U (en) * | 2020-12-30 | 2021-06-22 | 民航成都电子技术有限责任公司 | A patrol and examine robot and system of patrolling and examining for airport pavement |
| CN113091667A (en) * | 2021-03-30 | 2021-07-09 | 中国工商银行股份有限公司 | Inspection robot and inspection method |
| EP3858142A1 (en) * | 2020-01-31 | 2021-08-04 | Farm Robotics and Automation SL | Automated removal of animal carcasses |
| CN113223035A (en) * | 2021-06-07 | 2021-08-06 | 南京农业大学 | Intelligent inspection system for cage-rearing chickens |
| KR20210107470A (en) * | 2020-02-24 | 2021-09-01 | 라온피플 주식회사 | Method and apparatus for inspecting barn environment based on ai |
| CN113903097A (en) * | 2021-09-22 | 2022-01-07 | 中国农业大学 | Laminated cage-rearing livestock house inspection device |
| CN114043493A (en) * | 2021-11-10 | 2022-02-15 | 华南农业大学 | Inspection robot and inspection method for cage chicken house |
-
2022
- 2022-03-07 CN CN202210221117.7A patent/CN114407051A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019205425A (en) * | 2018-05-24 | 2019-12-05 | 大豊産業株式会社 | Dead chicken sensing system, chicken life or death determination program, and chicken life or death determination device |
| CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
| CN109997730A (en) * | 2019-04-28 | 2019-07-12 | 山东省农业科学院家禽研究所 | The cruise control method of cage bird intelligent inspection system and its crusing robot |
| CN211746249U (en) * | 2020-01-02 | 2020-10-27 | 河北农业大学 | Device for identifying chickens in cage |
| EP3858142A1 (en) * | 2020-01-31 | 2021-08-04 | Farm Robotics and Automation SL | Automated removal of animal carcasses |
| KR20210107470A (en) * | 2020-02-24 | 2021-09-01 | 라온피플 주식회사 | Method and apparatus for inspecting barn environment based on ai |
| CN111626985A (en) * | 2020-04-20 | 2020-09-04 | 北京农业信息技术研究中心 | Poultry body temperature detection method based on image fusion and poultry house inspection system |
| CN213518003U (en) * | 2020-12-30 | 2021-06-22 | 民航成都电子技术有限责任公司 | A patrol and examine robot and system of patrolling and examining for airport pavement |
| CN113091667A (en) * | 2021-03-30 | 2021-07-09 | 中国工商银行股份有限公司 | Inspection robot and inspection method |
| CN113223035A (en) * | 2021-06-07 | 2021-08-06 | 南京农业大学 | Intelligent inspection system for cage-rearing chickens |
| CN113903097A (en) * | 2021-09-22 | 2022-01-07 | 中国农业大学 | Laminated cage-rearing livestock house inspection device |
| CN114043493A (en) * | 2021-11-10 | 2022-02-15 | 华南农业大学 | Inspection robot and inspection method for cage chicken house |
Non-Patent Citations (3)
| Title |
|---|
| 余祖俊等: "《高速铁路综合检测技术》", 30 June 2021, 北京：中国铁道出版社, pages: 371 - 372 * |
| 邓继忠等: "《数字图像处理技术》", 广州：广东科技出版, pages: 10 - 13 * |
| 陈雪松等: "司法行政信息化设计与实践", 31 December 2021, 武汉：华中科技大学出版社, pages: 73 - 74 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023221170A1 (en) * | 2022-05-17 | 2023-11-23 | 浙江大学 | Sick/dead-poultry inspection apparatus and method suitable for cage-reared poultry house |
| CN115147782A (en) * | 2022-08-02 | 2022-10-04 | 广州度凌科技有限公司 | Dead animal identification method and device |
| CN116447457A (en) * | 2023-04-25 | 2023-07-18 | 广东爱吉尔机器人科技有限公司 | Henhouse inspection robot |
| CN116447457B (en) * | 2023-04-25 | 2023-12-26 | 广东爱吉尔机器人科技有限公司 | Henhouse inspection robot |
| CN116895127A (en) * | 2023-09-11 | 2023-10-17 | 西安凌志航遥信息科技工程有限公司 | Safety monitoring alarm system with personnel positioning function for energy production |
| CN116895127B (en) * | 2023-09-11 | 2023-11-21 | 西安凌志航遥信息科技工程有限公司 | Safety monitoring alarm system with personnel positioning function for energy production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114407051A (en) | Livestock and poultry farm inspection method and livestock and poultry farm robot | |
| AU2019101786A4 (en) | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium | |
| JP7382899B2 (en) | Dead chicken detection system | |
| CN113223035B (en) | Intelligent inspection system for cage chickens | |
| CN102103663B (en) | Ward visit service robot system and target searching method thereof | |
| CN109514582B (en) | Pet teasing control device for robot and mobile robot | |
| CN109591982A (en) | A kind of no worker monitor underwater culture robot | |
| CN114037552B (en) | Method and system for polling physiological growth information of meat ducks | |
| JP6678898B2 (en) | Dead chicken detection method and dead chicken detection system | |
| CN109479746B (en) | Robot pet teasing control method and chip | |
| CN109784200A (en) | Milk cow behavior image based on binocular vision obtains and body condition intelligent monitor system | |
| CN202010257U (en) | Ward round robot system based on Bayesian theory | |
| CN113762113A (en) | Livestock parturition behavior monitoring method and device | |
| Mangaonkar et al. | Fruit harvesting robot using computer vision | |
| CN117029904A (en) | Intelligent cage-rearing poultry inspection system | |
| CN114550334A (en) | Bridge robot inspection teaching training system, method and storage medium | |
| CN108132099A (en) | A kind of fish monitoring system | |
| CN210247950U (en) | Intelligent detection device and intelligent detection system | |
| CN206370898U (en) | A kind of dead fish supervising device for aquaculture | |
| CN115481648A (en) | High-throughput plant phenotype research platform and method for field | |
| CN114982739A (en) | Intelligent laser bird repelling device and method based on deep learning | |
| CN110765930A (en) | Aquaculture inspection system, inspection method and controller | |
| CN221211696U (en) | Cage poultry house inspection robot | |
| CN115937791B (en) | Poultry counting method and device suitable for multiple cultivation modes | |
| WO2023037397A1 (en) | Dead fowl detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240130 Address after: 264006 No.11 Guiyang street, Yantai Development Zone, Yantai City, Shandong Province Applicant after: Yantai Airui Photo-Electric Technology Co.,Ltd. Country or region after: China Applicant after: BIG HERDSMAN HUSBANDRY MACHINERY Co.,Ltd. Address before: 264000 No. 11, Guiyang street, Yantai Development Zone, Yantai City, Shandong Province Applicant before: Yantai Airui Photo-Electric Technology Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right |