CN112167074A - Automatic feeding device based on pet face recognition - Google Patents
Automatic feeding device based on pet face recognition Download PDFInfo
- Publication number
- CN112167074A CN112167074A CN202011098907.8A CN202011098907A CN112167074A CN 112167074 A CN112167074 A CN 112167074A CN 202011098907 A CN202011098907 A CN 202011098907A CN 112167074 A CN112167074 A CN 112167074A
- Authority
- CN
- China
- Prior art keywords
- pet
- feeding
- server
- controller
- pet face
- 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
- 235000013305 food Nutrition 0.000 claims abstract description 57
- 230000007246 mechanism Effects 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 235000005686 eating Nutrition 0.000 claims abstract description 10
- 238000003860 storage Methods 0.000 claims description 34
- 238000004891 communication Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 235000012054 meals Nutrition 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 235000008242 dietary patterns Nutrition 0.000 claims description 2
- 238000013459 approach Methods 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000037406 food intake Effects 0.000 description 4
- 235000012631 food intake Nutrition 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 235000004251 balanced diet Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000010794 food waste Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000282472 Canis lupus familiaris Species 0.000 description 1
- 241000282326 Felis catus Species 0.000 description 1
- 206010020710 Hyperphagia Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000020830 overeating Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K5/00—Feeding devices for stock or game ; Feeding wagons; Feeding stacks
- A01K5/02—Automatic devices
- A01K5/0275—Automatic devices with mechanisms for delivery of measured doses
-
- 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
- A01K5/00—Feeding devices for stock or game ; Feeding wagons; Feeding stacks
- A01K5/02—Automatic devices
- A01K5/0291—Automatic devices with timing mechanisms, e.g. pet feeders
-
- 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
- A01K7/00—Watering equipment for stock or game
- A01K7/02—Automatic devices ; Medication dispensers
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Birds (AREA)
- Biophysics (AREA)
- Feeding And Watering For Cattle Raising And Animal Husbandry (AREA)
Abstract
The invention discloses an automatic feeding device based on pet face recognition, which comprises: the system comprises a feeder, a server and a user side; wherein, the feeder is provided with a sensor, a camera and a feeding controller; the user side is used for setting a pet face image database and a pet eating mode; the sensor is used for detecting whether a pet approaches, and when the pet approaches, the face of the current pet is shot by the camera and uploaded to the server; the server identifies the pet face image according to the pet face image database based on an image identification algorithm, judges the feeding mode of the current pet according to the identification result and the pet feeding mode set by the user, sends a feeding instruction to the feeding controller according to the judgment result, and controls the opening and closing state of the corresponding valve mechanism according to the feeding instruction by the feeding controller. The invention can automatically feed different kinds and quantities of food for different pets.
Description
Technical Field
The invention relates to the technical field of smart homes, in particular to an automatic feeding device based on pet face recognition.
Background
With the development of social economy and the application of intelligent products, people seek spiritual satisfaction, and are fond of companion pets such as cats, dogs and the like, so that the pet demand quantity is increasingly increased, and the market scale of pet products is larger. Meanwhile, people's scientific pet-raising consciousness is gradually improved, healthy and reasonable pet-raising life is sought, and the problems of irregular feeding and the like of pets caused by insufficient time and energy are avoided. The change of the cultivation consciousness is transferred to a production end, and new industrial opportunity is brought to scientific and intelligent feeding products.
On the large technical background, the automatic feeding problem of pets has been studied at home and abroad, and the current related research has made great progress in the aspects of intellectualization and automation, but the problems of large equipment volume, complex structure, high price, incapability of bearing by ordinary pet breeders and the like exist.
On a small technical background, the existing automatic pet feeding device is close to the intellectualization aspect, for example, people like anzhi, Zhao Juan and the like propose an intelligent pet feeder based on the control of a T89S52 single-chip microcomputer in 2019, and the system of the automatic pet feeding device consists of a single-chip microcomputer main control system, a loudspeaker, a stepping motor simulation feeding module, an alarm clock module, a perpetual calendar and a photoswitch. The functions which can be realized are as follows: the pet food throwing device has the advantages that food is placed in the storage box of the food throwing device in advance, when the set food throwing time is up, the alarm signal is automatically sent out to attract the attention of a pet, and then the food is automatically thrown to the pet. The intelligent pet feeder exchanges data between the mobile phone and the feeder through a network through a Wi-Fi module, sends an instruction through the mobile phone to control the single chip microcomputer to send the instruction and control the motor to rotate, and feeding is achieved. However, most of pet feeders are simple in structure, can only feed regularly according to set time or remotely through smart devices such as mobile phones, and are difficult to meet the requirements of pet owners on physical health, mental health and the like of pets.
Disclosure of Invention
The invention provides an automatic feeding device based on pet face recognition, which aims to solve the technical problem that the existing pet feeder can only feed regularly according to set time or realize feeding through remote control of intelligent equipment such as a mobile phone and the like, and is difficult to meet the requirements of pet owners on the aspects of physical health, mental health and the like of pets.
In order to solve the technical problems, the invention provides the following technical scheme:
an automatic feeding device based on pet face recognition, the automatic feeding device based on pet face recognition includes: the system comprises a feeder, a server and a user side; wherein,
the feeder comprises a base, wherein a shell is arranged on the base, a food storage box is arranged on the shell, and a cover body is arranged on the food storage box; a plurality of food storage barrels are arranged in the food storage box; an opening is formed in the bottom end of one side of the shell, and a food groove is formed in the position, corresponding to the opening, of one side of the shell; the bottom end of each food storage barrel is respectively provided with a pipeline, and each pipeline is respectively provided with a valve mechanism; the inlet end of the pipeline is communicated with the corresponding food storage barrel, and the outlet end of the pipeline extends out of the opening and extends to the trough;
the feeding device is provided with a sensor and a camera, a feeding controller is arranged in the feeding device, the sensor, the camera and a valve mechanism are all electrically connected with the feeding controller, the feeding controller is respectively in communication connection with the server and the user side, and the server is in communication connection with the user side;
the user side is used for setting a pet face image database and a pet eating mode; the feeding controller is used for controlling the camera to shoot the face of the pet which is close to the trough at present and uploading the shot pet face image to the server; the server is used for identifying the pet face images uploaded by the feeding controller based on a preset image identification algorithm according to a pet face image database set by the user side, judging the feeding mode of the current pet according to an identification result and a pet feeding mode set by the user side, sending a feeding instruction to the feeding controller according to a judgment result, and controlling the opening and closing state of the corresponding valve mechanism according to the feeding instruction by the feeding controller.
The sensor is arranged on the outer side wall of the shell, and the camera is arranged on the outer side wall of the food storage box and is positioned on the same side of the feeder as the sensor; the feeding controller is arranged in the shell.
Wherein the sensor is an infrared sensor; the shell is also provided with a display screen electrically connected with the feeding controller.
Wherein, the controller of throwing something and feeding control the camera is close at present the pet of trough face shoots, includes:
the feeding controller controls the camera to continuously shoot the face of the pet which is close to the trough at present so as to collect ten face images of the pet at present; wherein the shooting interval is 0.8 seconds.
Wherein, the server is based on preset image recognition algorithm, according to the pet face image database that the user terminal set for, to the pet face image that controller uploaded throws something and feeds identifies, includes:
and carrying out image preprocessing on the pet face image uploaded by the feeding controller, sending the preprocessed pet face image to a recognition algorithm based on a convolutional neural network for pet face recognition, and finishing the recognition if three or more pet face images can correspond to the same pet in the pet face image database.
Wherein the image preprocessing comprises: image denoising, fuzzy restoration and pet face detection and correction.
The image denoising is realized by Gaussian filtering, the fuzzy restoration is realized by wiener filtering, and the pet face detection and correction are realized by means of a Dlib library.
Wherein, the number of the food storage barrels is three; the eating pattern includes the duration of the interval between meals and the amount of a single meal.
Wherein, the server combines the pet mode of eating that the user set for according to the recognition result, judges the feeding mode of current pet to according to the judgement result to throw the feeding controller and send and throw the feeding instruction, by throw the feeding controller according to throw the feeding instruction, control corresponding valve mechanism's the state that opens and shuts, include:
if the server determines that the current pet has eaten within the feeding interval time, the server controls the corresponding valve mechanism to be kept closed through the feeding controller;
if the server determines that the current pet does not eat within the feeding interval time, the opening time of the corresponding valve mechanism is calculated according to the single feeding amount corresponding to the current pet, the corresponding valve mechanism is controlled to be opened through the feeding controller, quantitative feeding is completed, and the feeding is recorded in the server.
The valve mechanism comprises a valve and a stepping motor, the stepping motor is electrically connected with the feeding controller, and the valve is in transmission connection with the stepping motor so as to control the opening and closing of the valve through the stepping motor.
The technical scheme provided by the invention has the beneficial effects that at least:
1. the invention realizes the automatic feeding of the specific food intake, and can intelligently and accurately judge whether the pet is hungry at the moment through the capture of the sensor and the camera and the calculation of the distance between the sensor and the last feeding time. According to the knowledge of the master on the pet, the system can automatically throw the specific amount of the food taken by the pet at one time only by setting the amount of the food thrown at each time at the user end, so that the phenomenon that the food of the pet is not eaten enough or the food is too much stored to drink the food too violently when the pet is not watched by the master is effectively reduced.
2. The pet balanced diet is realized, the research on the existing automatic pet feeding device in the market shows that almost only one food storage barrel is provided, and if customers have the requirements for automatic water feeding of pets, the customers need to additionally purchase an automatic water dispenser, so that the cost performance is not high. The feeder is internally provided with a plurality of food storage barrels and a plurality of corresponding valve mechanisms, so that different types of foods can be stored respectively, namely, different foods can be fed to different types of pets in a home or a pet store by one device. Meanwhile, the food storage barrels can also conveniently make a special recipe for the pets, different types of food are put in different proportions when the pets are fed every time, the phenomenon of single food is effectively avoided, and the balanced diet of the pets is guaranteed.
3. The invention combines the automatic feeding device of the pet with the face recognition algorithm, and compares the pet face picture shot by the infrared camera with the existing pet face in the database through the convolution neural network face recognition algorithm. The system can immediately identify a specific pet after detecting that a certain pet is close to the device, and then realizes 'special feeding' according to the type and the quantity of the put-in food which is set in advance by the background management system to finish different feeding functions of different pets.
4. The automatic feeding device records the feeding time of each time to the background, and ensures that the time difference between two adjacent times of feeding is greater than the set time length, so that the excessive feeding and food waste of the pet caused by frequent detection of the face are effectively avoided, the phenomenon of overeating of the pet due to incapability of controlling the pet is reduced, and meanwhile, the master or manager can inquire the feeding condition of the pet in time.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic external structure diagram of an automatic feeding device based on pet face identification provided by the invention;
fig. 2 is a schematic diagram of the internal structure of the automatic feeding device based on pet face recognition provided by the invention.
Description of reference numerals:
1. a base; 2. a housing; 3. a food storage box; 4. a cover body; 5. a food storage barrel; 6. a trough; 7. a pipeline;
8. a valve mechanism; 9. a sensor; 10. a camera; 11. a display screen.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Referring to fig. 1 and 2, the present embodiment provides an automatic feeding device based on pet face recognition, which includes: the system comprises a feeder, a server and a user side; wherein,
the feeder comprises a base 1, wherein a shell 2 is arranged on the base 1, a food storage box 3 is arranged on the shell 2, and a cover body 4 capable of being opened and closed is arranged on the food storage box 3; the shell 2 can play a role of supporting installation so as to install the food storage box 3 on the base 1; a plurality of food storage barrels 5 are arranged in the food storage box 3; an opening is formed in the bottom end of one side of the shell 2, and a feeding trough 6 is arranged on one side of the shell 2 corresponding to the opening; the bottom end of each food storage barrel 5 is respectively provided with a pipeline 7, and each pipeline 7 is respectively provided with a valve mechanism 8; the inlet end of the pipeline 7 is communicated with the corresponding food storage barrel 5, and the outlet end of the pipeline extends out of the opening and extends to the trough 6; when the valve mechanism 8 is opened, the food or water stored in the corresponding food storage barrel 5 can flow into the food groove 6 through the corresponding pipeline 7 for the pet to eat.
The feeding device is provided with a sensor 9 and a camera 10, a feeding controller (not shown in the figure) is arranged in the feeding device, the sensor 9, the camera 10 and the valve mechanism 8 are all electrically connected with the feeding controller, and the feeding controller can be externally connected with a power supply or powered by a built-in power supply; the feeding controller is in communication connection with the server and the user side respectively, and the server is in communication connection with the user side;
the user side is used for setting the pet face image database and the pet eating modes, wherein the pet face image database and the pet eating modes comprise eating interval duration and single food intake; the sensor 9 is used for detecting whether a pet approaches the trough 6, when the sensor 9 detects that the pet approaches the trough 6, the feeding controller controls the camera 10 to shoot the face of the pet which currently approaches the trough 6, and uploads the shot pet face image to the server; the server is used for identifying the pet face images uploaded by the feeding controller based on a preset image identification algorithm according to a pet face image database set by the user side, judging the feeding mode of the current pet according to an identification result and a pet feeding mode set by the user side, sending a feeding instruction to the feeding controller according to a judgment result, and controlling the opening and closing states of the corresponding valve mechanisms 8 by the feeding controller according to the feeding instruction so as to realize feeding of different types and quantities of food for different pets.
Specifically, in this embodiment, considering the temperature of the pet and the proximity of human beings, the sensor 9 of the present device uses a human body pyroelectric infrared sensor HC-SR501 to achieve full-automatic sensing, and outputs a high level once it detects that a pet enters its sensing range. The sensor 9 may be arranged on an outer side wall of the housing 2; meanwhile, the camera 10 is arranged on the outer side wall of the food storage box 3 and is positioned on the same side of the feeder as the sensor 9; the feeding controller is arranged inside the shell 2.
Further, the shell 2 is further provided with a display screen 11 and a control key which are electrically connected with the feeding controller, and the automatic feeding device of the embodiment can be set through the display screen 11 and the control key.
The communication implementation mode among the feeding controller, the server and the user side is as follows: the most basic socket connection and data receiving and sending are realized by driving a network module such as W5100 through a single chip microcomputer. After being activated by the sensor 9, the real-time pet face image is uploaded to the server for face comparison, and an instruction is sent to the corresponding valve mechanism 8 according to the recognition result returned by the server so as to control the opening and closing of the valve and the corresponding opening time.
The feeding controller uses an STM32 microcontroller as a core and mainly comprises a power supply and a motor driving module. The valve mechanism 8 comprises a valve and a stepping motor, the stepping motor is electrically connected with the feeding controller, and the valve is in transmission connection with the stepping motor so as to control the opening and closing of the valve through the stepping motor. The stepping motor rotates forwards to open the valve and rotates backwards to close the valve, so that the function of quantitatively putting food is completed. Of course, it is understood that the valve mechanism 8 may also be implemented by a solenoid valve, which is not limited in this embodiment.
The master and the manager can perform operations such as adding, deleting, changing and the like on the pet face image database through a background management system arranged on the user side, and monitor and manage the food intake data of the pet.
The number of the food storage barrels 5 is three (different foods can be respectively placed in the food storage barrels); of course, it is understood that the number of the food storage barrels 5 can be set according to actual requirements, and this embodiment is not particularly limited thereto.
The feeding controller controls the camera 10 to shoot the face of the pet which is close to the feeding trough 6 at present in the following modes: the feeding controller controls the camera 10 to continuously shoot the face of the pet which is close to the feeding trough 6 so as to collect ten face images of the current pet; wherein the shooting interval is 0.8 seconds. The server is based on preset image recognition algorithm, according to the pet face image database that the user terminal set for, to the pet face image that the controller uploaded throws something and feeds and discern, include:
and carrying out image preprocessing on the pet face image uploaded by the feeding controller, sending the preprocessed pet face image to a recognition algorithm based on a convolutional neural network for pet face recognition, and finishing the recognition if three or more pet face images can correspond to the same pet in the pet face image database.
Wherein the image preprocessing comprises: denoising, fuzzy restoration and detecting and correcting the pet face; the image denoising is realized by adopting Gaussian filtering, and different pixels in a neighborhood are endowed with different weights when the image is averaged in the Gaussian smoothing of the image. In this embodiment, the operation is directly implemented by calling a gaussianblu function in opencv. The fuzzy restoration is realized by adopting wiener filtering, and under the condition that the camera 10 is still, pets can rapidly move, so that the shot pictures can blur the faces which are not clearly seen, and the subsequent face recognition is influenced. The pet face detection and correction method comprises the following steps: the face detection and the cutting correction are carried out by means of a Dlib library which is mature in the field of deep learning face recognition.
The pet face image processed in the above way is input into a neural network recognition model based on Faster R-CNN. And (3) finding the optimal parameters by adjusting step and learning _ rate values at different stages, and determining the structure and parameters of the neural network. The neural network is used for converting an input pet face image into a 1024-dimensional vector, and comparing the 1024-dimensional vector with various known vectors in the same dimension in the database. And matching with the most similar pet face in the database by calculating the complexity-invariant distance, thereby completing the identification.
Wherein, the server combines the pet mode of eating that the user set for according to the recognition result, judges the feeding mode of current pet to according to the judgement result to throw the feeding controller and send and throw the feeding instruction, by throw the feeding controller according to throw the feeding instruction, control corresponding valve mechanism's the state that opens and shuts, include:
and sending an instruction to the feeding controller according to the returned identification result, and sending three instructions of opening the valve, keeping the valve closed and abnormally retrying to the feeding controller for execution according to different identification results.
If the server determines that the current pet has eaten within the eating interval (for example, 6 hours), controlling the corresponding valve mechanism to be kept closed through the feeding controller (so as to avoid food waste caused by frequent feeding of a certain pet when the owner is not at home);
if the server determines that the current pet does not eat within the eating interval time (for example, 6 hours), the server automatically calculates the opening time of the corresponding valve mechanism according to the single food intake corresponding to the current pet, controls the corresponding valve mechanism to open through the feeding controller, completes quantitative feeding, and records the feeding in the server so as to judge whether feeding is performed or not according to the next calculation time.
In summary, the present embodiment combines the automatic pet feeding device with image recognition in the field of computer vision. Combine neural network image recognition algorithm through the introduction, detect through infrared sensor, the camera absorbs pet face image to upload and carry out face's discernment on the cloud ware, so not only can improve the inconvenient of traditional device regularly throwing something and feeding, also through face's discernment simultaneously, accomplish the affirmation of pet, can realize throwing something and feeding different types, weight's food to the pet of difference, thereby make the automatic device of throwing something and feeding of pet more intelligent.
Further, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
It should be noted that the above describes only a preferred embodiment of the invention and that, although a preferred embodiment of the invention has been described, it will be apparent to those skilled in the art that, once having the benefit of the teachings of the present invention, numerous modifications and adaptations can be made without departing from the principles of the invention and are intended to be within the scope of the invention. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Claims (10)
1. The utility model provides an automatic feeding device based on pet face discernment which characterized in that, automatic feeding device based on pet face discernment includes: the system comprises a feeder, a server and a user side; wherein,
the feeder comprises a base, wherein a shell is arranged on the base, a food storage box is arranged on the shell, and a cover body is arranged on the food storage box; a plurality of food storage barrels are arranged in the food storage box; an opening is formed in the bottom end of one side of the shell, and a food groove is formed in the position, corresponding to the opening, of one side of the shell; the bottom end of each food storage barrel is respectively provided with a pipeline, and each pipeline is respectively provided with a valve mechanism; the inlet end of the pipeline is communicated with the corresponding food storage barrel, and the outlet end of the pipeline extends out of the opening and extends to the trough;
the feeding device is provided with a sensor and a camera, a feeding controller is arranged in the feeding device, the sensor, the camera and a valve mechanism are all electrically connected with the feeding controller, the feeding controller is respectively in communication connection with the server and the user side, and the server is in communication connection with the user side;
the user side is used for setting a pet face image database and a pet eating mode; the feeding controller is used for controlling the camera to shoot the face of the pet which is close to the trough at present and uploading the shot pet face image to the server; the server is used for identifying the pet face images uploaded by the feeding controller based on a preset image identification algorithm according to a pet face image database set by the user side, judging the feeding mode of the current pet according to an identification result and a pet feeding mode set by the user side, sending a feeding instruction to the feeding controller according to a judgment result, and controlling the opening and closing state of the corresponding valve mechanism according to the feeding instruction by the feeding controller.
2. The automatic feeding device based on pet face recognition is characterized in that the sensor is arranged on the outer side wall of the shell, the camera is arranged on the outer side wall of the food storage box and is positioned on the same side of the feeder as the sensor; the feeding controller is arranged in the shell.
3. An automatic feeding device based on pet face recognition as claimed in claim 1, characterized in that the sensor is an infrared sensor; the shell is also provided with a display screen electrically connected with the feeding controller.
4. An automatic feeding device based on pet face recognition as claimed in claim 1, wherein the feeding controller controls the camera to photograph the face of the pet currently approaching the trough, including:
the feeding controller controls the camera to continuously shoot the face of the pet which is close to the trough at present so as to collect ten face images of the pet at present; wherein the shooting interval is 0.8 seconds.
5. An automatic feeding device based on pet face recognition according to claim 1, wherein the server recognizes the pet face image uploaded by the feeding controller according to the pet face image database set by the user side based on a preset image recognition algorithm, and the automatic feeding device comprises:
and carrying out image preprocessing on the pet face image uploaded by the feeding controller, sending the preprocessed pet face image to a recognition algorithm based on a convolutional neural network for pet face recognition, and finishing the recognition if three or more pet face images can correspond to the same pet in the pet face image database.
6. An automatic feeding device based on pet face recognition as claimed in claim 5 wherein the image pre-processing comprises: image denoising, fuzzy restoration and pet face detection and correction.
7. The automatic feeding device based on pet face recognition as claimed in claim 6, wherein the image denoising is implemented by Gaussian filtering, the blur restoration is implemented by wiener filtering, and the pet face detection and correction is implemented by means of a Dlib library.
8. An automatic feeding device based on pet face recognition as claimed in claim 1, wherein the number of said food storage barrels is three; the eating pattern includes a length of an interval between meals and a single meal size.
9. An automatic feeding device based on pet face recognition according to claim 8, wherein the server determines the current feeding mode of the pet according to the recognition result and the pet feeding mode set by the user terminal, and sends a feeding instruction to the feeding controller according to the determination result, and the feeding controller controls the open/close state of the corresponding valve mechanism according to the feeding instruction, including:
if the server determines that the current pet has eaten within the feeding interval time, the server controls the corresponding valve mechanism to be kept closed through the feeding controller;
if the server determines that the current pet does not eat within the feeding interval time, the opening time of the corresponding valve mechanism is calculated according to the single feeding amount corresponding to the current pet, the corresponding valve mechanism is controlled to be opened through the feeding controller, quantitative feeding is completed, and the feeding is recorded in the server.
10. An automatic feeding device based on pet face recognition as claimed in claim 1, wherein the valve mechanism comprises a valve and a stepping motor, the stepping motor is electrically connected with the feeding controller, and the valve is in transmission connection with the stepping motor to control the opening and closing of the valve through the stepping motor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011098907.8A CN112167074A (en) | 2020-10-14 | 2020-10-14 | Automatic feeding device based on pet face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011098907.8A CN112167074A (en) | 2020-10-14 | 2020-10-14 | Automatic feeding device based on pet face recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112167074A true CN112167074A (en) | 2021-01-05 |
Family
ID=73950096
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011098907.8A Pending CN112167074A (en) | 2020-10-14 | 2020-10-14 | Automatic feeding device based on pet face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112167074A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113439675A (en) * | 2021-07-26 | 2021-09-28 | 连城县丰海竹木业有限公司 | Intelligent pet house capable of automatically feeding and storing water and implementation method thereof |
CN114446443A (en) * | 2021-12-23 | 2022-05-06 | 新瑞鹏宠物医疗集团有限公司 | Pet food material pushing method and device, electronic equipment and storage medium |
CN114464294A (en) * | 2021-12-22 | 2022-05-10 | 新瑞鹏宠物医疗集团有限公司 | Pet recipe generation method based on image recognition and related device |
CN114467782A (en) * | 2022-01-07 | 2022-05-13 | 珠海一微半导体股份有限公司 | Intelligent feeding method for pet robot, chip and robot |
CN114793929A (en) * | 2022-04-27 | 2022-07-29 | 东南大学 | Multi-species pet feeding system based on visual identification and feeding method thereof |
WO2024169785A1 (en) * | 2023-02-15 | 2024-08-22 | 上海哈啰普惠科技有限公司 | Animal feeding device and animal feeding system |
Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030091627A (en) * | 2002-08-08 | 2003-12-03 | 주식회사 쓰리비 시스템 | household pet internet food feeder of an integrated type and an internet food supply system using it |
CN101889453A (en) * | 2008-06-18 | 2010-11-17 | 松下电器产业株式会社 | Image processing device, imaging device, method, and program |
CN102006484A (en) * | 2009-08-31 | 2011-04-06 | 索尼公司 | Image processing device, image processing method, and program |
CN103329813A (en) * | 2013-06-27 | 2013-10-02 | 无锡商业职业技术学院 | Remote pet feeder based on GPRS (general packet radio service) |
CN205052470U (en) * | 2015-10-28 | 2016-03-02 | 卢苗苗 | Automatic feeder |
CN105961213A (en) * | 2016-05-05 | 2016-09-28 | 江西智能无限物联科技有限公司 | Intelligent pet feeder and intelligent feeding system |
CN107182820A (en) * | 2017-06-27 | 2017-09-22 | 苏州见真物联科技有限公司 | A kind of automatic feeding apparatus for pets |
CN107318680A (en) * | 2017-08-02 | 2017-11-07 | 深圳市广和通无线股份有限公司 | Pet feeding control method and device |
CN107563280A (en) * | 2017-07-24 | 2018-01-09 | 南京道熵信息技术有限公司 | Face identification method and device based on multi-model |
CN108112488A (en) * | 2016-11-28 | 2018-06-05 | 邻水县生产力促进中心 | A kind of pet food dispensing device |
CN108171722A (en) * | 2017-12-26 | 2018-06-15 | 广东美的厨房电器制造有限公司 | Image extraction method, device and cooking apparatus |
CN108197546A (en) * | 2017-12-26 | 2018-06-22 | 深圳市友信长丰科技有限公司 | Photo-irradiation treatment method, apparatus, computer equipment and storage medium in recognition of face |
CN108207686A (en) * | 2018-04-09 | 2018-06-29 | 安徽理工大学 | A kind of automatic food thrower for pet |
CN108460334A (en) * | 2018-01-23 | 2018-08-28 | 北京易智能科技有限公司 | A kind of age forecasting system and method based on vocal print and facial image Fusion Features |
CN108921132A (en) * | 2018-07-27 | 2018-11-30 | 广东电网有限责任公司 | Unmanned aerial vehicle onboard cable detection system |
CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
CN109874688A (en) * | 2018-12-27 | 2019-06-14 | 香港民生大数据有限公司 | Feeding system |
CN109976417A (en) * | 2018-12-26 | 2019-07-05 | 香港民生大数据有限公司 | The control method of feeding system and feeding system |
CN110896871A (en) * | 2019-09-30 | 2020-03-24 | 珠海格力电器股份有限公司 | Method and device for putting food and intelligent food throwing machine |
CN111149718A (en) * | 2020-01-20 | 2020-05-15 | 华侨大学 | Automatic feeding method and device for pets |
CN111292504A (en) * | 2020-01-23 | 2020-06-16 | 深圳市大拿科技有限公司 | Method and system for carrying out safety alarm through image identification |
CN111567427A (en) * | 2020-05-27 | 2020-08-25 | 北京科技大学 | Automatic feeder, system and method based on pig face recognition technology |
-
2020
- 2020-10-14 CN CN202011098907.8A patent/CN112167074A/en active Pending
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030091627A (en) * | 2002-08-08 | 2003-12-03 | 주식회사 쓰리비 시스템 | household pet internet food feeder of an integrated type and an internet food supply system using it |
CN101889453A (en) * | 2008-06-18 | 2010-11-17 | 松下电器产业株式会社 | Image processing device, imaging device, method, and program |
CN102006484A (en) * | 2009-08-31 | 2011-04-06 | 索尼公司 | Image processing device, image processing method, and program |
CN103329813A (en) * | 2013-06-27 | 2013-10-02 | 无锡商业职业技术学院 | Remote pet feeder based on GPRS (general packet radio service) |
CN205052470U (en) * | 2015-10-28 | 2016-03-02 | 卢苗苗 | Automatic feeder |
CN105961213A (en) * | 2016-05-05 | 2016-09-28 | 江西智能无限物联科技有限公司 | Intelligent pet feeder and intelligent feeding system |
CN108112488A (en) * | 2016-11-28 | 2018-06-05 | 邻水县生产力促进中心 | A kind of pet food dispensing device |
CN107182820A (en) * | 2017-06-27 | 2017-09-22 | 苏州见真物联科技有限公司 | A kind of automatic feeding apparatus for pets |
CN107563280A (en) * | 2017-07-24 | 2018-01-09 | 南京道熵信息技术有限公司 | Face identification method and device based on multi-model |
CN107318680A (en) * | 2017-08-02 | 2017-11-07 | 深圳市广和通无线股份有限公司 | Pet feeding control method and device |
CN108171722A (en) * | 2017-12-26 | 2018-06-15 | 广东美的厨房电器制造有限公司 | Image extraction method, device and cooking apparatus |
CN108197546A (en) * | 2017-12-26 | 2018-06-22 | 深圳市友信长丰科技有限公司 | Photo-irradiation treatment method, apparatus, computer equipment and storage medium in recognition of face |
CN108460334A (en) * | 2018-01-23 | 2018-08-28 | 北京易智能科技有限公司 | A kind of age forecasting system and method based on vocal print and facial image Fusion Features |
CN108207686A (en) * | 2018-04-09 | 2018-06-29 | 安徽理工大学 | A kind of automatic food thrower for pet |
CN108921132A (en) * | 2018-07-27 | 2018-11-30 | 广东电网有限责任公司 | Unmanned aerial vehicle onboard cable detection system |
CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
CN109976417A (en) * | 2018-12-26 | 2019-07-05 | 香港民生大数据有限公司 | The control method of feeding system and feeding system |
CN109874688A (en) * | 2018-12-27 | 2019-06-14 | 香港民生大数据有限公司 | Feeding system |
CN110896871A (en) * | 2019-09-30 | 2020-03-24 | 珠海格力电器股份有限公司 | Method and device for putting food and intelligent food throwing machine |
CN111149718A (en) * | 2020-01-20 | 2020-05-15 | 华侨大学 | Automatic feeding method and device for pets |
CN111292504A (en) * | 2020-01-23 | 2020-06-16 | 深圳市大拿科技有限公司 | Method and system for carrying out safety alarm through image identification |
CN111567427A (en) * | 2020-05-27 | 2020-08-25 | 北京科技大学 | Automatic feeder, system and method based on pig face recognition technology |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113439675A (en) * | 2021-07-26 | 2021-09-28 | 连城县丰海竹木业有限公司 | Intelligent pet house capable of automatically feeding and storing water and implementation method thereof |
CN114464294A (en) * | 2021-12-22 | 2022-05-10 | 新瑞鹏宠物医疗集团有限公司 | Pet recipe generation method based on image recognition and related device |
CN114446443A (en) * | 2021-12-23 | 2022-05-06 | 新瑞鹏宠物医疗集团有限公司 | Pet food material pushing method and device, electronic equipment and storage medium |
CN114467782A (en) * | 2022-01-07 | 2022-05-13 | 珠海一微半导体股份有限公司 | Intelligent feeding method for pet robot, chip and robot |
CN114467782B (en) * | 2022-01-07 | 2023-10-24 | 珠海一微半导体股份有限公司 | Intelligent feeding method of pet robot, chip and robot |
CN114793929A (en) * | 2022-04-27 | 2022-07-29 | 东南大学 | Multi-species pet feeding system based on visual identification and feeding method thereof |
WO2024169785A1 (en) * | 2023-02-15 | 2024-08-22 | 上海哈啰普惠科技有限公司 | Animal feeding device and animal feeding system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112167074A (en) | Automatic feeding device based on pet face recognition | |
JP6739049B2 (en) | Automatic feeding method for farmed fish and automatic feeding system | |
TWI736950B (en) | System and method for smart aquaculture | |
CN106577345B (en) | Intelligent pet interaction system | |
CN107821284A (en) | A kind of intelligent fish breeding system based on cloud database | |
WO2019174082A1 (en) | Feeding method and feeding device | |
WO2019056856A1 (en) | Automatic pet feeding device | |
GB2454658A (en) | Automatic pet feeder | |
CN106383537A (en) | Intelligence livestock culturing system | |
CN114467824B (en) | Intelligent bait casting boat | |
CN109460097A (en) | A kind of fish jar intelligent monitor system | |
CN206641180U (en) | Feeding device for pets | |
CN106538448A (en) | Network fish tank control system | |
CN208047700U (en) | A kind of intelligent pet drinking trough | |
CN213695268U (en) | Pet feeding device | |
CN111149718A (en) | Automatic feeding method and device for pets | |
CN110250027A (en) | A kind of intelligent pet feeding system and method | |
CN110333748A (en) | It is a kind of for monitoring the customer query system and method for plant growth | |
CN106577336A (en) | Smart control pet automatic feeding system | |
CN112036248A (en) | Intelligent fishpond management system based on scene recognition | |
CN207369849U (en) | A kind of livestock breed aquatics workshop with monitoring function | |
CN109976417A (en) | The control method of feeding system and feeding system | |
CN115443936A (en) | Intelligent aquatic organism feeding control system and method, electronic equipment and storage medium | |
CN109610584A (en) | A kind of intellectual water closet and its intelligent adjusting method with face identification functions | |
CN211322522U (en) | Automatic feeding device for pets |
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 |