CN114092687A - Animal feeding device and method based on visual identification and readable storage medium - Google Patents
Animal feeding device and method based on visual identification and readable storage medium Download PDFInfo
- Publication number
- CN114092687A CN114092687A CN202210057084.7A CN202210057084A CN114092687A CN 114092687 A CN114092687 A CN 114092687A CN 202210057084 A CN202210057084 A CN 202210057084A CN 114092687 A CN114092687 A CN 114092687A
- Authority
- CN
- China
- Prior art keywords
- feeding
- feeding device
- image information
- animals
- target image
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Feeding And Watering For Cattle Raising And Animal Husbandry (AREA)
Abstract
The invention relates to a visual identification based animal feeding device, method and readable storage medium, the device comprising: the feeding device comprises two cameras, a camera controller and a feeding device; the camera is used for collecting target image information and transmitting the target image information to the camera controller; the target image information is image information of animal feeding in a target area; and the camera controller is used for acquiring the identification result according to the target image information and sending the identification result to the controller of the feeding device so that the controller of the feeding device controls the feeding device to feed according to the identification result. The technical scheme that this application provided has realized differentiation, the automatic feeding of multiple type animal, not only reduces the waste of animal feed, has still reduced the manpower burden, has reduced the probability of false detection, misidentification.
Description
Technical Field
The invention belongs to the technical field of animal feeding, and particularly relates to an animal feeding device and method based on visual identification and a readable storage medium.
Background
Traditional animal feeding mode is generally for artifical timing feeding to the feeding device who uses is simple, not intelligent enough, exposes multiple problem gradually in the feeding process. Such as: 1. labor force cannot be liberated, the labor load is increased, and particularly in the large-scale cultivation and feeding process; 2. the timeliness is not enough, and the uninterrupted feeding in 24 hours cannot be realized by manpower; 3. customized feeding can not be realized for different types of animals, so that different requirements are met; 4. the intelligent and information-based feeding system cannot realize intellectualization and informatization, cannot trace the source of the individual feeding data of the animals, and the like. Along with the development of times and technologies, breeding practitioners hope to realize intellectualization and informatization of feeding processes, and finally achieve unmanned feeding.
Conventional feeders typically employ a common sensor for detecting the quantity of water, feed, and feed animals, such as: 1. the water detection usually adopts a carbon rod or other sensors are added at the rear end of an electromagnetic valve for detection, the defects are that the detection depends seriously on the existence of water, and when the water pressure is unstable, impurities in water are excessive or the water is abnormal, the abnormality of false detection and undetected detection exists; 2. the material level sensor is usually adopted for detecting the material, and the defects are that the sensitivity is not well adjusted, and the interference of surrounding conducting media is easy to cause the condition of false detection; 3. the identification of the number of animals generally adopts an ultrahigh frequency scheme, and has the defects of unstable ultrahigh frequency signals, difficulty in mastering detection distance, occurrence of phenomena of false identification and the like. Due to the characteristics of the universal sensor, factors such as water resistance, dust resistance, impact resistance and the like of the sensor need to be considered in many occasions (particularly in a farm with a severe environment), so that the complexity of the mechanical structure design is increased, the probability of false detection and false identification of the sensor is increased, and finally, a lot of troubles are brought to the highly integrated and intelligent design of the feeding device.
Disclosure of Invention
In view of the above, the present invention is to overcome the disadvantages of the prior art, and provide a visual recognition-based animal feeding device, method and readable storage medium, so as to solve the problems of false detection and false recognition in the prior art.
According to a first aspect of embodiments herein there is provided a visual identification based animal feeding device, the device comprising: the feeding device comprises two cameras, a camera controller and a feeding device;
the camera is used for collecting target image information and transmitting the target image information to the camera controller;
the target image information is image information of animal feeding in a target area;
the camera controller is used for acquiring an identification result according to the target image information and sending the identification result to the controller of the feeding device so that the controller of the feeding device controls the feeding device to feed according to the identification result;
wherein the recognition result comprises: identifying the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device;
the device further comprises: an H-shaped bracket and a camera bracket; two ends of the camera support are respectively connected with a camera;
the vertical bars on two sides of the H-shaped support are respectively fixed on two sides of the feeding device, and the horizontal bar in the H-shaped support is positioned above the feeding device;
the center of the horizontal bar in the H-shaped support is connected with the center of the camera support.
Further, the obtaining a recognition result according to the target image information includes:
and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device by taking the target image information as the input of a preset machine vision identification algorithm.
Further, the controlling a feeding device to feed according to the identification result comprises:
when the feeding device is provided with leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to stop feeding until the feeding device has no leftovers, and controlling the blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding;
when the feeding device has no leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has no residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding.
Further, the process of establishing the preset machine vision recognition algorithm includes:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain the preset machine vision recognition algorithm.
According to a second aspect of embodiments herein there is provided a visual identification based animal feeding method comprising:
acquiring target image information, wherein the target image information is image information of animal feeding in a target area;
acquiring an identification result according to the target image information; wherein the recognition result comprises: identifying the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device;
and controlling a feeding device to feed according to the identification result.
Further, the obtaining a recognition result according to the target image information includes:
and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device by taking the target image information as the input of a preset machine vision identification algorithm.
Further, the controlling a feeding device to feed according to the identification result comprises:
when the feeding device is provided with leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to stop feeding until the feeding device has no leftovers, and controlling the blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding;
when the feeding device has no leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has no residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding.
Further, the process of establishing the preset machine vision recognition algorithm includes:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain the preset machine vision recognition algorithm.
According to a third aspect of embodiments of the present application, there is provided a readable storage medium having stored thereon an executable program which, when executed by a processor, performs the steps of the visual identification based animal feeding method of the above-described technical solution.
By adopting the technical scheme, the invention can achieve the following beneficial effects: gather target image information through the camera to convey target image information to camera controller, acquire the identification result according to target image information through camera controller, and send the identification result to feeding device's controller, so that feeding device's controller controls feeding device according to the identification result and feeds, realized the differentiation of multiple type animal, automatic feeding, not only reduce the waste of animal feed, still reduced the manpower burden, reduced the probability of false retrieval, misidentification.
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, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a visual identification based animal feeding device shown in accordance with an exemplary embodiment;
FIG. 2 is a schematic diagram of a visual identification based animal feeding device shown in accordance with an exemplary embodiment;
fig. 3 is a flow diagram illustrating a visual identification based animal feeding method according to an exemplary embodiment;
in the figure, 1-camera, 2-camera controller, 3-feeding device, 4-feeding device controller, 5-feeding device blanking mechanism, 6-H type support, 7-camera support.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
FIG. 1 is a schematic diagram illustrating the construction of a visual identification based animal feeding device according to an exemplary embodiment, as shown in FIG. 1, the device comprising: the feeding device comprises two cameras 1, a camera controller 2 and a feeding device 3;
the camera 1 is used for collecting target image information and transmitting the target image information to the camera controller 2; the target image information is image information of animal feeding in a target area;
the camera controller 2 is used for acquiring an identification result according to the target image information and sending the identification result to the controller 4 of the feeding device, so that the controller 4 of the feeding device controls the feeding device 3 to feed according to the identification result;
wherein, the recognition result includes: the type of feeding animal, the number of feeding animals and the remaining material information of the feeding device 3 are identified.
According to the animal feeding device based on visual identification, the target image information is collected through the camera 1 and is transmitted to the camera controller 2, the identification result is obtained through the camera controller 2 according to the target image information and is sent to the controller 4 of the feeding device, so that the controller 4 of the feeding device controls the feeding device 3 to feed according to the identification result, differentiation and automatic feeding of various types of animals are achieved, waste of animal feed is reduced, labor burden is reduced, and probability of false detection and false identification is reduced.
Further, as shown in fig. 2, the apparatus further includes: an H-shaped bracket 6 and a camera bracket 7; two ends of the camera bracket 7 are respectively connected with a camera 1;
the vertical bars at two sides of the H-shaped support 6 are respectively fixed at two sides of the feeding device 3, and the horizontal bar in the H-shaped support 6 is positioned above the feeding device 3;
the center of the horizontal bar in the H-shaped bracket 6 is connected with the center of the camera bracket 7.
It should be noted that the vertical bars on both sides of the H-shaped frame 6 should be fixed on both sides of the feeding device 3 which does not affect the feeding of the animals. The camera support 7 should be fixedly connected with the center of the cross bar in the H-shaped support 6, and the camera support cannot rock, so that the animal is prevented from mistakenly colliding with the camera 1, the shooting angle of the camera 1 is passively adjusted, and the acquisition of target image information is affected. However, on the premise that the camera support 7 is fixed, when the camera 1 is connected with the two ends of the camera support 7, the connecting structure in the prior art can be used for adjusting the camera, namely the camera 1 is fixed after being adjusted, so that the camera angle is kept.
Further, acquiring the recognition result according to the target image information includes:
and (3) taking the target image information as the input of a preset machine vision identification algorithm, and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device 3.
It should be noted that the target image information collected by the two cameras 1 may capture the same animal, and therefore, when the target image information is identified by using the machine vision identification algorithm, the same number of animals is not subjected to the repetition base. For example, it is assumed that the target image information acquired by the two cameras 1 includes one animal a, one animal B, and two identical animals C, and although there are two animals C, the number of feeding animals in the target image information is still 3.
It can be appreciated that, since the animal can feed on both sides of the feeding device 3, if the camera is mounted on only one side, there can be a case of missed shots. Therefore, the two cameras are used for shooting target image information, so that animals which are fed can be shot completely, and the accuracy and the reliability of the recognition result are improved.
Further, controlling the feeding device 3 to feed according to the recognition result, comprising:
when the feeding device 3 has leftovers and the number of the feeding animals is more than zero, controlling the blanking mechanism 5 of the feeding device to stop feeding until the feeding device 3 has no leftovers, and controlling the blanking mechanism 5 of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device 3 has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism 5 of the feeding device to stop feeding;
when the feeding device 3 has no leftovers and the number of the feeding animals is more than zero, the feeding device controls the blanking mechanism 5 of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device 3 has no residual materials and the number of the feeding animals is equal to zero, the feeding device is controlled to stop feeding by the blanking mechanism 5.
In some embodiments, the controller 4 of the feeding device can control, but is not limited to, a motor component in the feeding mechanism 5 of the feeding device according to the recognition result, and the motor is driven by the controller 4 of the feeding device, so as to finally realize the adjustment of the feeding speed. Generally, the number of animals fed is large, and the feeding speed is high; the number of animals fed is small, and the feeding speed is slow.
It should be noted that the manner of "controlling the feeding device by the controller 4 of the feeding device to feed by the feeding device according to the type of the feeding animal, the number of the feeding animals, and the remaining material information of the feeding device 3" according to the embodiment of the present invention is not limited, and may be implemented by, but not limited to, a machine learning algorithm after training, and other types of algorithms or models that can implement this manner may also be used.
In particular, the types of feeding animals may include, but are not limited to: chicken, duck, goose, dog, pig, cat, etc. It will be appreciated that the feeding pattern will vary from animal to animal.
For example, pigs in the fattening stage need to be fed continuously for 24 hours a day; the pigs in the gestation period need to be fed once a day; the pigs in the mating stage need to be fed 2-3 times a day.
For another example, when the number of the feeding animals is 5, about 1KG of feed is fed under the feeding mechanism 5 of the feeding device.
Further, the process of establishing the preset machine vision recognition algorithm comprises:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain a preset machine vision recognition algorithm.
In some embodiments, the image information of the animal feeding process can be collected through the camera 1, the information is picture information, and then data filtering, searching, comparing and other processing are performed by a machine vision recognition algorithm model which is pre-loaded in the camera controller 2, the algorithm model is obtained by collecting a large amount of picture information to calibrate and train, and finally, the identification of the types of the feeding animals, the number of the feeding animals and the residual condition of the feeding device 3 in the image information of the animal feeding process is realized.
According to the animal feeding device based on visual identification, the target image information is collected through the camera 1 and is transmitted to the camera controller 2, the identification result is obtained through the camera controller 2 according to the target image information and is sent to the controller 4 of the feeding device, so that the controller 4 of the feeding device controls the feeding device 3 to feed according to the identification result, the animal feeding device is compatible with most of animal feeding devices 3 in the current market, differentiation and automatic feeding of various types of animals are achieved, waste of animal feed is reduced, labor burden is reduced, and probability of false detection and false identification is reduced.
According to the animal feeding device based on visual identification, provided by the embodiment of the invention, a machine visual identification technology is added on the feeding device 3 to replace a general sensor detection technology, so that the use of sensor types is reduced, the probability of false detection and false identification is reduced, the design of a mechanical structure is facilitated, the feeding device 3 is more integrated and intelligent, and the maintenance is convenient; the type of the feeding animal is intelligently identified through the feeding image information acquired by the camera 1, and different feeding is performed according to different types of animals; meanwhile, the feeding speed of the feeding device 3 is determined by the number of the recognized animals; the situation of the residual materials of the feeding device 3 can be identified and fed back to the feeding device 3, so that the situation of wasting the feed in the feeding process is avoided as much as possible. Finally, the method for differential automatic feeding of various animals is realized by combining the feeding device 3 and a machine vision identification technology.
The embodiment of the invention also provides a method for feeding animals based on visual identification, which can be used for a terminal but not limited to, as shown in fig. 3, and comprises the following steps:
step 101: acquiring target image information, wherein the target image information is image information of animal feeding in a target area;
step 102: acquiring an identification result according to the target image information; wherein, the recognition result includes: identifying the type of feeding animal, the number of feeding animals and the remainder information of the feeding device 3;
step 103: and controlling the feeding device 3 to feed according to the recognition result.
According to the animal feeding method based on visual identification, provided by the embodiment of the invention, the target image information is collected, the identification result is obtained according to the target image information, and the feeding device 3 is controlled to feed according to the identification result, so that the differentiated and automatic feeding of various animals is realized, the waste of animal feed is reduced, the labor burden is reduced, and the probability of false detection and false identification is reduced.
Further, step 102, obtaining a recognition result according to the target image information, including:
and (3) taking the target image information as the input of a preset machine vision identification algorithm, and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device 3.
Further, step 103 of controlling the feeding device 3 to feed according to the recognition result includes:
when the feeding device 3 has leftovers and the number of the feeding animals is more than zero, controlling the blanking mechanism 5 of the feeding device to stop feeding until the feeding device 3 has no leftovers, and controlling the blanking mechanism 5 of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device 3 has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism 5 of the feeding device to stop feeding;
when the feeding device 3 has no leftovers and the number of the feeding animals is more than zero, the feeding device controls the blanking mechanism 5 of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device 3 has no residual materials and the number of the feeding animals is equal to zero, the feeding device is controlled to stop feeding by the blanking mechanism 5.
Further, the process of establishing the preset machine vision recognition algorithm comprises:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain a preset machine vision recognition algorithm.
According to the animal feeding method based on visual identification, provided by the embodiment of the invention, the target image information is collected, the identification result is obtained according to the target image information, and the feeding device 3 is controlled to feed according to the identification result, so that the differentiated and automatic feeding of various animals is realized, the waste of animal feed is reduced, the labor burden is reduced, and the probability of false detection and false identification is reduced.
It is to be understood that the embodiments of the method provided above correspond to the embodiments of the apparatus described above, and the corresponding specific contents may be referred to each other, which is not described herein again.
Embodiments of the present invention also provide a readable storage medium, on which an executable program is stored, and the executable program, when executed by a processor, implements the steps of a vision recognition-based animal feeding method in the above embodiments.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (9)
1. An animal feeding device based on visual identification, the device comprising: the feeding device comprises two cameras, a camera controller and a feeding device;
the camera is used for collecting target image information and transmitting the target image information to the camera controller; the target image information is image information of animal feeding in a target area;
the camera controller is used for acquiring an identification result according to the target image information and sending the identification result to the controller of the feeding device so that the controller of the feeding device controls the feeding device to feed according to the identification result;
wherein the recognition result comprises: identifying the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device;
the device further comprises: an H-shaped bracket and a camera bracket; two ends of the camera support are respectively connected with a camera;
the vertical bars on two sides of the H-shaped support are respectively fixed on two sides of the feeding device, and the horizontal bar in the H-shaped support is positioned above the feeding device;
the center of the horizontal bar in the H-shaped support is connected with the center of the camera support.
2. The apparatus according to claim 1, wherein the obtaining of the recognition result according to the target image information comprises:
and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device by taking the target image information as the input of a preset machine vision identification algorithm.
3. The device of claim 1, wherein controlling the feeding device to feed based on the identification comprises:
when the feeding device is provided with leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to stop feeding until the feeding device has no leftovers, and controlling the blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding;
when the feeding device has no leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has no residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding.
4. The apparatus of claim 2, wherein the process of establishing the preset machine vision recognition algorithm comprises:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain the preset machine vision recognition algorithm.
5. A visual identification based animal feeding method, comprising:
acquiring target image information, wherein the target image information is image information of animal feeding in a target area;
acquiring an identification result according to the target image information; wherein the recognition result comprises: identifying the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device;
and controlling a feeding device to feed according to the identification result.
6. The method according to claim 5, wherein the obtaining of the recognition result according to the target image information comprises:
and acquiring the type of the feeding animals, the number of the feeding animals and the residual material information of the feeding device by taking the target image information as the input of a preset machine vision identification algorithm.
7. The method of claim 5, wherein controlling the feeding device to feed based on the identification comprises:
when the feeding device is provided with leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to stop feeding until the feeding device has no leftovers, and controlling the blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding;
when the feeding device has no leftovers and the number of the feeding animals is more than zero, controlling a blanking mechanism of the feeding device to feed according to the types of the feeding animals and the number of the feeding animals of different types;
when the feeding device has no residual materials and the number of the feeding animals is equal to zero, controlling a blanking mechanism of the feeding device to stop feeding.
8. The method of claim 6, wherein the establishing of the preset machine vision recognition algorithm comprises:
and training by taking historical target image information as an input layer training sample of the machine vision recognition algorithm and taking a historical recognition result corresponding to the historical target image information as an output layer training sample of the machine vision recognition algorithm to obtain the preset machine vision recognition algorithm.
9. A readable storage medium having stored thereon an executable program, wherein the executable program when executed by a processor implements the steps of the visual identification based animal feeding method of any one of claims 5-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210057084.7A CN114092687A (en) | 2022-01-19 | 2022-01-19 | Animal feeding device and method based on visual identification and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210057084.7A CN114092687A (en) | 2022-01-19 | 2022-01-19 | Animal feeding device and method based on visual identification and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114092687A true CN114092687A (en) | 2022-02-25 |
Family
ID=80308726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210057084.7A Pending CN114092687A (en) | 2022-01-19 | 2022-01-19 | Animal feeding device and method based on visual identification and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114092687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116076382A (en) * | 2023-02-23 | 2023-05-09 | 江苏华丽智能科技股份有限公司 | Automatic induction-based feeding regulation control method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107182909A (en) * | 2017-05-08 | 2017-09-22 | 北京农业信息技术研究中心 | A kind of pig feeding method, server, feeder and system |
| CN109548672A (en) * | 2019-01-08 | 2019-04-02 | 北京探感科技股份有限公司 | A kind of feeding systems and method |
| CN109618961A (en) * | 2018-12-12 | 2019-04-16 | 北京京东金融科技控股有限公司 | A kind of intelligence of domestic animal feeds system and method |
| CN110495399A (en) * | 2019-08-16 | 2019-11-26 | 斯威方德(深圳)智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of automatic feeding |
| CN110796043A (en) * | 2019-10-16 | 2020-02-14 | 北京海益同展信息科技有限公司 | Container detection and feeding detection method and device and feeding system |
| CN111264405A (en) * | 2020-02-19 | 2020-06-12 | 北京海益同展信息科技有限公司 | Feeding method, system, device, equipment and computer readable storage medium |
-
2022
- 2022-01-19 CN CN202210057084.7A patent/CN114092687A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107182909A (en) * | 2017-05-08 | 2017-09-22 | 北京农业信息技术研究中心 | A kind of pig feeding method, server, feeder and system |
| CN109618961A (en) * | 2018-12-12 | 2019-04-16 | 北京京东金融科技控股有限公司 | A kind of intelligence of domestic animal feeds system and method |
| CN109548672A (en) * | 2019-01-08 | 2019-04-02 | 北京探感科技股份有限公司 | A kind of feeding systems and method |
| CN110495399A (en) * | 2019-08-16 | 2019-11-26 | 斯威方德(深圳)智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of automatic feeding |
| CN110796043A (en) * | 2019-10-16 | 2020-02-14 | 北京海益同展信息科技有限公司 | Container detection and feeding detection method and device and feeding system |
| CN111264405A (en) * | 2020-02-19 | 2020-06-12 | 北京海益同展信息科技有限公司 | Feeding method, system, device, equipment and computer readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116076382A (en) * | 2023-02-23 | 2023-05-09 | 江苏华丽智能科技股份有限公司 | Automatic induction-based feeding regulation control method and system |
| CN116076382B (en) * | 2023-02-23 | 2024-03-22 | 江苏华丽智能科技股份有限公司 | Automatic induction-based feeding regulation control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389161B (en) | Garbage identification evolutionary learning method, device, system and medium based on deep learning | |
| CN109618961B (en) | Intelligent feeding system and method for livestock | |
| CN109717120A (en) | A kind of fish culture monitoring feeding system and method based on Internet of Things | |
| CN105957354A (en) | Road side parking management system based on terrestrial magnetism and camera array linkage and method thereof | |
| CN116019023A (en) | Electronic information management system and management method | |
| CN114092687A (en) | Animal feeding device and method based on visual identification and readable storage medium | |
| CN114980011B (en) | Livestock and poultry body temperature monitoring method with cooperation of wearable sensor and infrared camera | |
| CN107590467A (en) | A kind of intelligence based on machine vision feeds system | |
| CN109380146A (en) | Live pig self-operated measuring unit and method | |
| CN115613128A (en) | Intelligent control system for crystal growth | |
| CN111354011A (en) | Multi-moving-target information capturing and tracking system and method | |
| CN116125840A (en) | Intelligent feeding system | |
| CN113219964A (en) | Poultry house environment inspection and regulation method, equipment and medium | |
| EP4344539A1 (en) | Device and method for automatically marking a linen of a pig | |
| KR20100012614A (en) | System for detecting estrus using image recognition | |
| CN117029904A (en) | Intelligent cage-rearing poultry inspection system | |
| CN114375158A (en) | Sow estrus judgment device, sow estrus judgment method, and sow estrus judgment program | |
| CN112257489A (en) | Automatic detection system and method for garbage bag throwing | |
| CN110286625A (en) | A kind of raising Object Management System and management method | |
| CN106094700A (en) | Control method shed by a kind of feedstuff for pond culture | |
| CN115760904A (en) | Livestock and poultry statistical method, device, electronic equipment and medium | |
| CN114022302A (en) | Pregnant goat intelligent management system and management method based on video monitoring | |
| CN112885045A (en) | Fault alarm system for remotely monitoring abnormal conditions of breeding place | |
| CN113052074B (en) | Method, apparatus, electronic device and medium for recording livestock feeding information | |
| TW202133717A (en) | Smart bamboo shoot cultivation harvest monitoring system and method transmit image data back to server end through image determination module to replace and update image depth learning model |
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: 20220225 |
|
| RJ01 | Rejection of invention patent application after publication |