CN111310596A - Animal diseased state monitoring system and method - Google Patents
Animal diseased state monitoring system and method Download PDFInfo
- Publication number
- CN111310596A CN111310596A CN202010066390.8A CN202010066390A CN111310596A CN 111310596 A CN111310596 A CN 111310596A CN 202010066390 A CN202010066390 A CN 202010066390A CN 111310596 A CN111310596 A CN 111310596A
- Authority
- CN
- China
- Prior art keywords
- animal
- feeding area
- gateway
- information
- images
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Abstract
The application relates to a system and a method for monitoring the diseased state of an animal, wherein the system comprises: the system comprises an image acquisition module, a gateway and an image analysis module; the image acquisition module is used for acquiring images of the feeding area; the gateway is in communication connection with the image acquisition module and is used for controlling the image acquisition module to acquire the images of the feeding area; the image analysis module is in communication connection with the gateway and is used for receiving the feeding area image sent by the gateway, determining the ill information of the animals in the corresponding feeding area according to the feeding area image and sending the ill information to the gateway. The system in the embodiment can realize the state of the unmanned monitoring animal, and compared with the traditional animal sick state monitoring method, the monitoring efficiency is effectively improved; meanwhile, the obtaining efficiency of the abnormal state can be improved through the obtained illness information, and the economic benefit of the breeding enterprise is guaranteed.
Description
Technical Field
The application relates to the technical field of intelligent breeding, in particular to a system and a method for monitoring the diseased state of an animal.
Background
As a traditional farming and animal husbandry kingdom, the pig breeding industry in China also develops along with the increase of consumption demand. The pig breeding process needs to formulate a scientific feeding method to improve the growth speed of animals, meanwhile, disease prevention and control are also key technologies in the breeding process, and the disease prevention and control easily cause troubles for pig farmers. The common diseases in the pig breeding process are more, the breeding cost is increased slightly, and huge economic loss is caused seriously, so that the state of the pig breeding process needs to be monitored.
At present, in the related art, a method for monitoring an animal disease state is generally performed by adopting an artificial inspection mode, and the following method for monitoring an animal disease is taken as an example:
because the farms in China are widely distributed and have large south-north east-west differences, the discovery of animal diseases is generally carried out by adopting a manual inspection mode. The most common diseases in pig farms are generally accompanied by symptoms of cough, asthma, diarrhea, etc. in animals. Generally, when a breeder patrols a breeding area, the manual patrolling is used for observing whether animals have symptoms such as cough, asthma, abnormal morphological body surface, diarrhea and the like so as to find animals with diseases and carry out subsequent related treatment.
However, the related art has disadvantages as follows:
(1) the manual patrol is generally carried out regularly and is fixed for several times every day, but the site with diarrhea of animals is easily damaged by the animals, so that diseases cannot be found in time.
(2) Manual inspection of the health of the animal cannot be monitored continuously and manual inspection may miss the diseased animal, thereby missing the optimal period of treatment and management and delaying treatment.
(3) Diarrhea data can not be recorded and counted in time, which is not beneficial to epidemic prevention, statistics and alarm of diseases.
(4) The cost of manually inspecting the diarrhea frequency of the animals is high, the virus transmission risk is increased, the health condition of the animals is influenced, and the epidemic situation is caused.
(5) The manual patrol increases the stress response of animals and is not beneficial to the health of the animals.
In view of the technical problems in the related art, no effective solution is provided at present.
Disclosure of Invention
In order to solve the above technical problem or at least partially solve the above technical problem, the present application provides an animal diseased state monitoring system and method.
In a first aspect, the present application provides an animal diseased state monitoring system comprising: the system comprises an image acquisition module, a gateway and an image analysis module;
the image acquisition module is used for acquiring images of the feeding area;
the gateway is in communication connection with the image acquisition module and is used for controlling the image acquisition module to acquire the images of the feeding area;
the image analysis module is in communication connection with the gateway and is used for receiving the feeding area image sent by the gateway, determining the ill information of the animals in the corresponding feeding area according to the feeding area image and sending the ill information to the gateway.
Optionally, the system for monitoring the diseased state of the animal as described above further comprises: inspecting the vehicle; the gateway is an edge computing gateway;
the image acquisition module is arranged on the inspection vehicle and used for acquiring images of the feeding areas corresponding to different feeding areas along with the movement of the inspection vehicle;
the patrol car is in communication connection with the gateway and is used for moving in the feeding area under the control of the gateway.
Optionally, the system for monitoring the diseased state of the animal as described above further comprises: an internet of things platform and a SAAS platform;
the Internet of things platform is in communication connection with the gateway and is used for receiving and storing the data uploaded by the gateway;
the SAAS platform is in communication connection with the Internet of things platform and is used for receiving the data uploaded by the gateway transferred by the Internet of things platform and displaying the data uploaded by the gateway.
Optionally, the system for monitoring the diseased state of the animal as described above further comprises: a big data platform;
the big data platform is in communication connection with the Internet of things platform and is used for receiving the data uploaded by the gateway and transferred by the Internet of things platform and storing the data uploaded by the gateway.
In a second aspect, the present application provides a method of monitoring a diseased state in an animal comprising:
acquiring an image of a feeding area;
analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to animal excrement, wherein the animal diarrhea information comprises a plurality of diarrhea grades;
analyzing the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animals;
and determining monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
Optionally, as the aforementioned animal diseased state monitoring method, the establishment method of the stool detection model includes:
obtaining pre-collected feeding area sample images, wherein different feeding area sample images correspond to different diarrhea grades, and the feeding area sample images comprise animal wastes;
determining labeling information corresponding to the feeding area sample image, wherein the labeling information comprises: a marking frame corresponding to the animal excrement;
and inputting the feeding area sample image into a first preset neural network for training, and learning the corresponding relation between the animal excrement and the diarrhea grade to obtain the excrement detection model.
Optionally, as in the foregoing method for monitoring an animal diseased state, the method for establishing an animal posture detection model includes:
acquiring pre-collected feeding area sample images, wherein the feeding area sample images comprise a first sample image with abnormal animal health condition information and a second sample image with normal animal health condition information;
determining animal pose information in the feeding area sample image;
inputting the feeding area sample image into a second preset neural network for training, and learning the corresponding relation between the animal posture information and the animal health condition information to obtain the animal posture detection model.
In a third aspect, the present application provides an animal diseased state monitoring device comprising:
the acquisition module is used for acquiring images of the feeding area;
the excrement detection module is used for analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to the animal excrement, and the animal diarrhea information comprises a plurality of diarrhea grades;
the posture detection module is used for analyzing the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animals;
and the monitoring information module is used for determining the monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
In a fourth aspect, the present application provides an electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, is configured to implement the monitoring method according to any of the preceding claims.
In a fifth aspect, the present application provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the monitoring method according to any one of the preceding claims.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
the embodiment of the application provides a system and a method for monitoring the diseased state of an animal, wherein the system comprises: the system comprises an image acquisition module, a gateway and an image analysis module; the image acquisition module is used for acquiring images of the feeding area; the gateway is in communication connection with the image acquisition module and is used for controlling the image acquisition module to acquire the images of the feeding area; the image analysis module is in communication connection with the gateway and is used for receiving the feeding area image sent by the gateway, determining the ill information of the animals in the corresponding feeding area according to the feeding area image and sending the ill information to the gateway. The system in the embodiment can realize the state of the unmanned monitoring animal, and compared with the traditional animal sick state monitoring method, the monitoring efficiency is effectively improved; meanwhile, the obtaining efficiency of the abnormal state can be improved through the obtained illness information, and the economic benefit of the breeding enterprise is guaranteed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a block diagram of an animal diseased state monitoring system provided by an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for monitoring a diseased state of an animal according to an embodiment of the present application;
fig. 3 is a block diagram of an animal diseased state monitoring device provided by an embodiment of the application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a system for monitoring a diseased state of an animal according to an embodiment of the present application, including: the system comprises an image acquisition module 1, a gateway 2 and an image analysis module 7;
the image acquisition module 1 is used for acquiring images of a feeding area;
specifically, the image acquisition module 1 may be a camera for video recording or photo shooting, and in order to make the shot image have high definition and achieve a better recognition effect, optionally, the pixels of the camera are 1000 ten thousand or more; the feeding area image is an image obtained by carrying out image acquisition on a feeding area through the image acquisition module 1; furthermore, a storage device, such as a TF card, may be provided, and the feeding area image may be stored on the local side.
The gateway 2 is in communication connection with the image acquisition module 1 and is used for controlling the image acquisition module 1 to acquire images of the feeding area;
specifically, the gateway 2 and the image acquisition module 1 can perform information interaction in a wired communication or wireless communication mode; the gateway 2 in this embodiment has a certain data processing capability, and thus can manage and control different hardware; besides the image acquisition module 1, in the embodiment of the present application, a device for controlling the environmental parameters of the feeding area or a sensor for acquiring the environmental parameters may be further provided, for example, the device for controlling the environmental parameters may include: a ventilation system, a temperature regulation system, a humidity regulation system and the like; the sensors for environmental parameter acquisition may include: carbon dioxide concentration sensors, temperature and humidity sensors, and the like; meanwhile, the above-mentioned device for controlling the environmental parameters and the sensor for collecting the environmental parameters may be in communication connection with the gateway 2, so as to receive the control of the gateway 2 and upload the collected data to the gateway 2.
The image analysis module 7 is in communication connection with the gateway 2, and is configured to receive the feeding area image sent by the gateway 2, determine diseased information of animals in the corresponding feeding area according to the feeding area image, and send the diseased information to the gateway 2.
Specifically, the image analysis module 7 may be deployed on a certain server, or may be deployed on the gateway 2; when the system is deployed on a server, the gateway 2 sends the images of the feeding area to the corresponding server, and returns the images to the gateway after the server obtains the identification result; furthermore, the server can send the ill information to the gateway only when the ill information is ill (for example, the animal has diarrhea, etc.), and does not send the ill information to the gateway when the ill information is normal.
The invention can reduce the polling times of the animal breeders, solve the problems of untimely and inaccurate monitoring of the diseased states of the animals when the breeders perform on-site polling, and improve the monitoring efficiency; the invention can utilize the image recognition device (the image acquisition module 1, the gateway 2 and the image analysis module 7) to match with the data wireless transmission rule to realize remote monitoring of the animal state, and can also check the images of the feeding area including the animal state in real time by a mobile phone.
In some embodiments, the animal diseased state monitoring system as described above, further comprising: a patrol car 3; the gateway 2 is an edge computing gateway;
specifically, the gateway 2 is an edge computing gateway, and an open platform integrating network, computing, storage and application core capabilities can be used on one side close to a data source to provide nearest-end services nearby. And then, a faster network service response can be generated, and the basic requirements of the breeding industry in the aspects of real-time business, application intelligence, safety, privacy protection and the like are met.
The image acquisition module 1 is arranged on the inspection vehicle 3 and used for acquiring feeding area images corresponding to different feeding areas along with the movement of the inspection vehicle 3;
for example, a farm has a plurality of feeding areas in which rails may be provided for the inspection vehicles 3 to travel along; optionally, in order to collect images of the feeding area as comprehensive as possible, the track may be arranged above the feeding area, and the camera device on the inspection vehicle captures the inspection area below the rail to obtain inspection images or images, so as to reduce the shielding of the shielding objects (such as door fences and columns) on the target objects (such as animals and excrement).
The patrol car generally operates and shoots according to a certain sequence, each feeding area can have corresponding area identification to acquire position information, and the acquired position information can be the position information of the patrol car, further can be the position information of the patrol car on an operation track, and can also be the geographic position information of the patrol car (such as the position obtained through GPS positioning). Therefore, after the patrol car reaches a position corresponding to the acquisition position information, the feeding area image corresponding to the acquisition position information can be acquired, and further, the feeding area image can be uploaded to an SAAS (Software-as-a-Service) or a gateway, and further, identification information of the feeding area is included during uploading, so that the feeding area can be corresponding to the feeding area image. Therefore, the images of the feeding areas can be displayed through SAAS, and the condition of animal excrement can be detected from the images corresponding to each feeding area through a computer vision mode, so that whether the animal has epidemic situations such as diarrhea or not is determined.
The patrol car 3 is in communication connection with the gateway 2 and is used for moving in the feeding area under the control of the gateway 2.
Specifically, the gateway 2 and the image analysis module 7 can be arranged on the inspection vehicle 3, and can control and connect the action mechanism of the inspection vehicle 3, so that the movement of the inspection vehicle 3 can be controlled, the inspection vehicle can move to a specific position, or move at a specific speed, or perform image acquisition at a specific frequency.
Further, above-mentioned device structure wholly can adopt waterproof dustproof anticorrosion, the structural design of being convenient for to install and dismantle, reduces personnel's business turn over and raises the region (for example pig house), promotes the alarm efficiency of sick information, reduces the outbreak of disease risk, guarantees the economic benefits of breeding the enterprise.
In some embodiments, the animal diseased state monitoring system as described above, further comprising: an internet of things platform 4 and a SAAS platform 5;
the Internet of things platform 4 is in communication connection with the gateway 2 and is used for receiving and storing data uploaded by the gateway 2;
the SAAS platform 5 is in communication connection with the Internet of things platform 4 and is used for receiving data uploaded by the gateway 2 transferred by the Internet of things platform 4 and displaying the data uploaded by the gateway 2.
Specifically, the Internet of things platform 4 (i.e., the Internet of things platform) may provide a unified service for the entire system, and on one hand, the diseased information (e.g., diarrhea data) reported by the gateway 2 may be received based on the MQTT protocol (Message Queuing technical Transport protocol) and uploaded to the SAAS platform through the rule engine. The platform 4 of the internet of things can abstract the diarrhea data into time series indexes, and automatic data circulation and automatic system diagnosis are achieved.
The SAAS platform 5 may be a platform integrating hardware and rule management, data viewing, and statistical analysis, and the supported contents may include: the system is responsible for binding the relationship among the patrol car 3, the gateway 2 and the feeding areas of the animals; further, the data uploaded by the internet of things platform 4 may be displayed after being processed and analyzed, wherein an optional manner is as follows: graphically presenting data to a user; in addition, the user can be supported to set corresponding parameters so as to meet specific control requirements required by the user. Finally, the user can learn about all the conditions of the animals in the feeding area through the SAAS platform 5, and can take an adapted treatment regime.
In some embodiments, the animal diseased state monitoring system as described above, further comprising: a big data platform 6;
the big data platform 6 is in communication connection with the internet of things platform 4 and is used for receiving data uploaded by the gateway 2 transferred by the internet of things platform 4 and storing the data uploaded by the gateway 2.
Specifically, the internet of things platform 4 can provide an interface for storing data in the big data platform 6, and then can store the images uploaded by the gateway 2 in the feeding area on the big data platform completely, so that the images and the data can be checked anytime and anywhere.
According to an embodiment of another aspect of the present application, there is provided a method for monitoring a diseased state of an animal, comprising the steps S1 to S3 as follows:
s1, acquiring a feeding area image;
specifically, the images of the feeding area can be photos or videos corresponding to the feeding area acquired by the image acquisition module; and the number of feeding areas included in the same feeding area image may be one or more;
s2, analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to the animal excrement, wherein the animal diarrhea information comprises a plurality of diarrhea grades;
wherein: the establishment method of the stool detection model can comprise the following steps A1-A3:
a1, obtaining pre-collected feeding area sample images, wherein the feeding area sample images can be obtained by periodically shooting different feeding areas in a farm; the sample images of different feeding areas correspond to different diarrhea grades, and the sample images of the feeding areas comprise animal excrement.
Specifically, each diarrhea grade corresponds to a plurality of feeding area sample images, and the diarrhea grade is obtained by analyzing animal wastes in the feeding area sample images; generally, the larger the area of diarrhea, the higher the diarrhea grade (the more severe the diarrhea); the thinner the stool consistency, the higher the diarrhea grade (the more severe the diarrhea); the severity is divided into any number of levels, optionally: four grades of none, mild, severe and dangerous.
Step A2, determining annotation information corresponding to the sample image of the feeding area, wherein the annotation information comprises: and marking frames corresponding to the animal wastes.
Optionally, the animal feces in the image can be selected by using a software LabelMe box, the feces are manually marked as abnormal or normal according to the color and the quantity of the feces, and the abnormal state can be further classified into different abnormal grades, such as none, slight, serious, dangerous and the like.
And step A3, inputting the sample image of the feeding area into a first preset neural network for training, and learning the corresponding relation between the animal excrement and the diarrhea grade to obtain an excrement detection model.
During training, a plurality of sample images can be obtained in advance and input into the first preset neural network for training, and after each training, parameters of the first preset neural network are adjusted until the range of the excrement can be accurately identified when the verification image of the feeding area is input, and then the range of the excrement can be used as an excrement detection model. And then the user can carry out corresponding disease diagnosis according to the diarrhea disease information of the animal. According to the method in the embodiment, the monitoring efficiency of diseases such as diarrhea can be improved through an intelligent image recognition technology, and the overall economic benefit of a pig farm is improved.
The first preset neural network may be a convolutional neural network such as ENet (image semantic segmentation model), MobileNet-YOLO, MobileNet-YOLOv1, MobileNet-YOLOv2, MobileNet-YOLOv3, Faster R-CNN, R-FCN, and the like.
The training process of the model will be described in detail by taking ENet as an example.
(1) Inputting the feeding area sample image and the labeling information into an ENet network for training; the ENet can identify the fecal region in the resulting feeding area sample image and obtain the diarrhea grade.
(2) After the ENet network is trained through a large number of feeding area sample images, and when the ENet network is judged to meet the preset performance through the verification images, the ENet network is used as a feces detection model.
Alternatively, the confidence level of each bounding box can be determined by calculating the intersection and comparison (IOU) of the bounding box of the stool selected by the ENet network box and the labeled box, and comparing the detected categories (e.g., severe, moderate, and mild) with the pre-labeled animal status to obtain the category error.
Calculating a loss function through the obtained confidence coefficient, position error and classification error of each bounding box, and continuously and reversely propagating the loss function to optimize the network until the network converges to obtain the excrement detection model.
When each image acquisition module respectively and correspondingly acquires an image in one feeding area, no distinction is needed; when the images of all the feeding areas in the farm are acquired through the same image acquisition module, the feeding areas corresponding to the images of all the feeding areas need to be determined, and then the diseased information of the animals corresponding to each feeding area and the diseased state of the animals in which feeding area is abnormal can be accurately analyzed and obtained.
Specifically, the algorithm for analyzing the images of the feeding area may be deployed on a certain server, or may be deployed on a gateway; when the system is deployed on a server, the gateway sends the images of the feeding area to the corresponding server, and the server returns the images to the gateway after obtaining the identification result; furthermore, the server can send the ill information to the gateway only when the animal has diarrhea and the like, and does not send the ill information to the gateway when the ill information is normal.
S3, analyzing the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animals;
in some embodiments, as the aforesaid animal diseased state monitoring method, the animal posture detection model establishing method includes the following steps B1 to B3:
b1, obtaining pre-collected feeding area sample images, wherein the feeding area sample images comprise a first sample image with abnormal animal health condition information and a second sample image with normal animal health condition information;
b2, determining animal posture information in the sample image of the feeding area;
and B3, inputting the sample image of the feeding area into a second preset neural network for training, and learning the corresponding relation between the animal posture information and the animal health condition information to obtain an animal posture detection model.
Optionally, the feeding area sample image may be obtained by periodically shooting different feeding areas in the farm. The animals in the images can be selected using a software LabelMe box and manually labeled as diseased or healthy depending on their pose and detection.
The training process of the animal posture detection model is explained in detail by taking MobileNet-YOLO as an example.
(1) The animals and their corresponding poses may be framed in the feeding area sample image.
(2) And inputting the feeding area sample image and the labeling information into a MobileNet-YOLO network for training.
(3) After the mobileNet-YOLO network is trained through a large number of feeding area sample images, and when the mobileNet-YOLO network is judged to be capable of accurately framing and selecting animals and obtaining corresponding postures through verification images, the animals are used as animal posture detection models.
And S4, determining monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
Since animal postures are usually changed correspondingly when the animal is in epidemic situation, after the animal diarrhea information and the animal health condition information are obtained through the steps S2 and S3, comprehensive disease diagnosis can be performed according to the animal diarrhea information and the animal health condition information to obtain reliable analysis results, and the specific diagnosis method can be judged by adopting methods such as weighted analysis. The specific decision logic can be selected according to specific breeding conditions. For example: when the animal is slightly diarrhea and the pig is in a standing state, the monitoring information of the pig can be judged to be in good condition; when the animal is in severe diarrhea and the pig is in a lying state, the monitoring information of the pig can be judged to be serious.
By adopting the method in the embodiment, the monitoring efficiency of diseases such as diarrhea and the like can be effectively improved, and the overall economic benefit of a pig farm is improved.
In addition, the method can also be used for detecting the crib in a pre-trained mode, and comprises the following steps: acquiring an image to be detected of the crib; identifying feed information in the image to be detected according to the trough detection model; and generating a label corresponding to the trough according to the feed information.
In this embodiment, through carrying out image recognition to the trough, confirm the fodder information in the trough, generate the label that this trough corresponds according to the fodder information, whether follow-up can be based on this label and confirm whether to put in the fodder in this trough. Like this, need not the manual work and monitor the fodder in the trough, but feed balance and the animal condition of eating in the real time monitoring trough have improved the efficiency and the degree of accuracy that the animal fed, and avoid the waste of fodder, reduce the cost of labor.
Specifically, the determination of the feeding area is mainly for classifying the animals by lot, and since the present embodiment is intended for determining monitoring information of the animals, the analysis object is the animals themselves or objects (feces) related to the animals. By way of example: when the obtained detection information judges that the excrement in a certain feeding area indicates that the animal has diarrhea, a corresponding veterinarian needs to be informed to go to the feeding area (for example, a No. 01 pigsty) to carry out drug administration treatment on the animal (for example, pigs).
In summary, by the method in the embodiment, the information of the animals in each feeding area can be accurately obtained, and corresponding countermeasures can be taken in time to improve the survival rate, the health rate and the like of the breeding.
As shown in fig. 2, in some embodiments, the animal diseased state monitoring method as described above, step S1 acquires the feeding area image, including steps S21 and S22 as follows:
s21, determining acquisition position information corresponding to the acquired images of the feeding area according to a preset image acquisition position relation;
and S22, when the inspection vehicle reaches the position corresponding to the acquisition position information according to the preset running track, an image acquisition module arranged on the inspection vehicle acquires images of the feeding area.
In this embodiment, shoot each feeding area through an image acquisition module, can be equipped with the track above feeding area, and the patrol and examine car goes on the track, and the image acquisition module on the patrol and examine car simultaneously shoots the below and patrol and examine the region, obtains and patrols and examines the image.
The image acquisition position relation is the corresponding relation between the acquisition position information and the feeding area images of all feeding areas; for example, when there is the collecting position information I, it may correspond to the feeding area a, and thus: when the inspection vehicle is positioned at the position I, images of the feeding area at the position A can be collected; in addition, the collected position information may be a position point or a position range.
The patrol car generally operates and shoots according to a certain sequence, and each feeding area has corresponding acquisition position information, and the acquisition position information can be the position information of the patrol car, further can be the position information of the patrol car on an operation track, and also can be the geographical position information of the patrol car (such as the position obtained by GPS positioning). Therefore, after the patrol car reaches a position corresponding to the acquisition position information, the feeding area image corresponding to the acquisition position information can be acquired, and further, the feeding area image can be uploaded to the SAAS or the gateway. Therefore, the images of the feeding areas can be displayed by the SAAS, and the disease information of the animals can be detected from the images corresponding to each feeding area in a computer vision mode, for example, the excrement condition of the animals can be determined, so that whether the animals have epidemic situations such as diarrhea or not can be determined.
In some embodiments, the method for monitoring the diseased state of the animal as described above, analyzing the images of the feeding area to determine the diseased information of the animal in the corresponding feeding area, includes:
and analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea illness information corresponding to the animal excrement, wherein the animal diarrhea illness information comprises a plurality of grades.
As shown in fig. 3, according to an embodiment of another aspect of the present application, there is provided an animal diseased state monitoring device comprising:
an obtaining module 21, configured to obtain a feeding area image;
the excrement detection module 22 is configured to analyze the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to animal excrement, where the animal diarrhea information includes a plurality of diarrhea grades;
the posture detection module 23 is configured to analyze the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animal;
and the monitoring information module 24 is used for determining the monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
According to another embodiment of the present application, there is also provided an electronic apparatus including: as shown in fig. 4, the electronic device may include: the system comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 complete communication with each other through the communication bus 1504.
A memory 1503 for storing a computer program;
the processor 1501 is configured to implement the steps of the above-described method embodiments when executing the program stored in the memory 1503.
The bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the steps of the above-described method embodiments.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An animal diseased state monitoring system, comprising: the system comprises an image acquisition module (1), a gateway (2) and an image analysis module (7);
the image acquisition module (1) is used for acquiring images of a feeding area;
the gateway (2) is in communication connection with the image acquisition module (1) and is used for controlling the image acquisition module (1) to acquire images of the feeding area;
the image analysis module (7) is in communication connection with the gateway (2) and is used for receiving the feeding area image sent by the gateway (2), determining the illness information of the animals in the corresponding feeding area according to the feeding area image, and sending the illness information to the gateway (2).
2. The animal diseased state monitoring system of claim 1 further comprising: a patrol car (3); the gateway (2) is an edge computing gateway;
the image acquisition module (1) is arranged on the inspection vehicle (3) and is used for acquiring the images of the feeding areas corresponding to different feeding areas along with the movement of the inspection vehicle (3);
the patrol car (3) is in communication connection with the gateway (2) and is used for moving in the feeding area under the control of the gateway (2).
3. The animal diseased state monitoring system of claim 1 further comprising: an Internet of things platform (4) and an SAAS platform (5);
the Internet of things platform (4) is in communication connection with the gateway (2) and is used for receiving and storing data uploaded by the gateway (2);
the SAAS platform (5) is in communication connection with the Internet of things platform (4) and is used for receiving data uploaded by the gateway (2) transferred by the Internet of things platform (4) and displaying the data uploaded by the gateway (2).
4. The animal diseased state monitoring system of claim 3 further comprising: a big data platform (6);
the big data platform (6) is in communication connection with the Internet of things platform (4) and used for receiving data uploaded by the gateway (2) and transferred by the Internet of things platform (4) and storing the data uploaded by the gateway (2).
5. A method for monitoring the diseased state of an animal comprising:
acquiring an image of a feeding area;
analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to animal excrement, wherein the animal diarrhea information comprises a plurality of diarrhea grades;
analyzing the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animals;
and determining monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
6. The method for monitoring the diseased state of an animal according to claim 5, wherein the establishment method of the stool detection model comprises the following steps:
obtaining pre-collected feeding area sample images, wherein different feeding area sample images correspond to different diarrhea grades, and the feeding area sample images comprise animal wastes;
determining labeling information corresponding to the feeding area sample image, wherein the labeling information comprises: a marking frame corresponding to the animal excrement;
and inputting the feeding area sample image into a first preset neural network for training, and learning the corresponding relation between the animal excrement and the diarrhea grade to obtain the excrement detection model.
7. The method for monitoring the diseased state of the animal according to claim 5, wherein the method for establishing the animal posture detection model comprises the following steps:
acquiring pre-collected feeding area sample images, wherein the feeding area sample images comprise a first sample image with abnormal animal health condition information and a second sample image with normal animal health condition information;
determining animal pose information in the feeding area sample image;
inputting the feeding area sample image into a second preset neural network for training, and learning the corresponding relation between the animal posture information and the animal health condition information to obtain the animal posture detection model.
8. An animal diseased state monitoring device, comprising:
the acquisition module is used for acquiring images of the feeding area;
the excrement detection module is used for analyzing the images of the feeding area according to a pre-trained excrement detection model to obtain animal diarrhea information corresponding to the animal excrement, and the animal diarrhea information comprises a plurality of diarrhea grades;
the posture detection module is used for analyzing the images of the feeding area according to a pre-trained animal posture detection model to obtain animal health condition information corresponding to the animals;
and the monitoring information module is used for determining the monitoring information of the animal according to the animal diarrhea information and the animal health condition information.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, implementing the monitoring method of any one of claims 5-7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the monitoring method of any one of claims 5-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010066390.8A CN111310596A (en) | 2020-01-20 | 2020-01-20 | Animal diseased state monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010066390.8A CN111310596A (en) | 2020-01-20 | 2020-01-20 | Animal diseased state monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111310596A true CN111310596A (en) | 2020-06-19 |
Family
ID=71160795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010066390.8A Pending CN111310596A (en) | 2020-01-20 | 2020-01-20 | Animal diseased state monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310596A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052075A (en) * | 2021-03-25 | 2021-06-29 | 京东数科海益信息科技有限公司 | Environment monitoring method, device, terminal and medium for pasture |
| CN113393937A (en) * | 2021-07-12 | 2021-09-14 | 长沙瑞和数码科技有限公司 | Method, device, equipment and computer storage medium for preventing pig infectious diseases |
| CN113505795A (en) * | 2021-07-16 | 2021-10-15 | 河南牧原智能科技有限公司 | Method and system for detecting diarrhea of herd of pigs |
| CN113671892A (en) * | 2021-08-18 | 2021-11-19 | 迟明海 | Animal management method and animal management system based on cloud platform |
| CN114449701A (en) * | 2021-12-29 | 2022-05-06 | 新瑞鹏宠物医疗集团有限公司 | Medical record information-based light type regulation and control method and device and electronic equipment |
| CN115147837A (en) * | 2022-08-16 | 2022-10-04 | 河北省农林科学院植物保护研究所 | Athetis lepigone breeding method and system based on optical image recognition |
| CN116267695A (en) * | 2023-05-10 | 2023-06-23 | 厦门农芯数字科技有限公司 | Sow health monitoring method, system and storage medium based on big data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574899A (en) * | 2015-12-15 | 2016-05-11 | 浙江大学 | Feces monitoring method and system for cage chicken |
| CN105850773A (en) * | 2016-03-29 | 2016-08-17 | 西北农林科技大学 | Device and method for monitoring of pig attitudes based on micro-inertial sensor |
| CN107480651A (en) * | 2017-08-25 | 2017-12-15 | 清华大学深圳研究生院 | Abnormal gait detection method and abnormal gait detecting system |
| WO2018000215A1 (en) * | 2016-06-29 | 2018-01-04 | 宋英楠 | Pet health monitoring method and device |
| CN109243003A (en) * | 2018-08-24 | 2019-01-18 | 北京京东金融科技控股有限公司 | Method for inspecting and device for inspection car |
| CN109496123A (en) * | 2016-07-20 | 2019-03-19 | 农场机器人和自动化有限公司 | The robot of domestic animal assists monitoring |
| CN109902558A (en) * | 2019-01-15 | 2019-06-18 | 安徽理工大学 | A kind of human health deep learning prediction technique based on CNN-LSTM |
| US20190244350A1 (en) * | 2016-07-07 | 2019-08-08 | Cowmatix S.R.L. | Method of and apparatus for diagnosing leg pathologies in quadrupeds |
| CN110521670A (en) * | 2019-09-29 | 2019-12-03 | 佛山科学技术学院 | A kind of automation chicken-raising method and control system |
| CN110706219A (en) * | 2019-09-27 | 2020-01-17 | 北京海益同展信息科技有限公司 | Animal waste monitoring method, monitoring device, inspection equipment and inspection system |
-
2020
- 2020-01-20 CN CN202010066390.8A patent/CN111310596A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574899A (en) * | 2015-12-15 | 2016-05-11 | 浙江大学 | Feces monitoring method and system for cage chicken |
| CN105850773A (en) * | 2016-03-29 | 2016-08-17 | 西北农林科技大学 | Device and method for monitoring of pig attitudes based on micro-inertial sensor |
| WO2018000215A1 (en) * | 2016-06-29 | 2018-01-04 | 宋英楠 | Pet health monitoring method and device |
| US20190244350A1 (en) * | 2016-07-07 | 2019-08-08 | Cowmatix S.R.L. | Method of and apparatus for diagnosing leg pathologies in quadrupeds |
| CN109496123A (en) * | 2016-07-20 | 2019-03-19 | 农场机器人和自动化有限公司 | The robot of domestic animal assists monitoring |
| CN107480651A (en) * | 2017-08-25 | 2017-12-15 | 清华大学深圳研究生院 | Abnormal gait detection method and abnormal gait detecting system |
| CN109243003A (en) * | 2018-08-24 | 2019-01-18 | 北京京东金融科技控股有限公司 | Method for inspecting and device for inspection car |
| CN109902558A (en) * | 2019-01-15 | 2019-06-18 | 安徽理工大学 | A kind of human health deep learning prediction technique based on CNN-LSTM |
| CN110706219A (en) * | 2019-09-27 | 2020-01-17 | 北京海益同展信息科技有限公司 | Animal waste monitoring method, monitoring device, inspection equipment and inspection system |
| CN110521670A (en) * | 2019-09-29 | 2019-12-03 | 佛山科学技术学院 | A kind of automation chicken-raising method and control system |
Non-Patent Citations (1)
| Title |
|---|
| 胡肄农等: "母猪精细养殖管理物联网平台的建立" * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052075A (en) * | 2021-03-25 | 2021-06-29 | 京东数科海益信息科技有限公司 | Environment monitoring method, device, terminal and medium for pasture |
| CN113393937A (en) * | 2021-07-12 | 2021-09-14 | 长沙瑞和数码科技有限公司 | Method, device, equipment and computer storage medium for preventing pig infectious diseases |
| CN113505795A (en) * | 2021-07-16 | 2021-10-15 | 河南牧原智能科技有限公司 | Method and system for detecting diarrhea of herd of pigs |
| CN113671892A (en) * | 2021-08-18 | 2021-11-19 | 迟明海 | Animal management method and animal management system based on cloud platform |
| CN113671892B (en) * | 2021-08-18 | 2024-03-12 | 迟明海 | Animal management method and animal management system based on cloud platform |
| CN114449701A (en) * | 2021-12-29 | 2022-05-06 | 新瑞鹏宠物医疗集团有限公司 | Medical record information-based light type regulation and control method and device and electronic equipment |
| CN114449701B (en) * | 2021-12-29 | 2023-08-08 | 新瑞鹏宠物医疗集团有限公司 | Light type regulation and control method and device based on medical record information and electronic equipment |
| CN115147837A (en) * | 2022-08-16 | 2022-10-04 | 河北省农林科学院植物保护研究所 | Athetis lepigone breeding method and system based on optical image recognition |
| CN115147837B (en) * | 2022-08-16 | 2023-10-27 | 河北省农林科学院植物保护研究所 | Athetis lepigone feeding method and system based on optical image recognition |
| CN116267695A (en) * | 2023-05-10 | 2023-06-23 | 厦门农芯数字科技有限公司 | Sow health monitoring method, system and storage medium based on big data |
| CN116267695B (en) * | 2023-05-10 | 2023-08-15 | 厦门农芯数字科技有限公司 | Sow health monitoring method, system and storage medium based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310596A (en) | Animal diseased state monitoring system and method | |
| Wu et al. | Using a CNN-LSTM for basic behaviors detection of a single dairy cow in a complex environment | |
| CN110839557B (en) | Sow oestrus monitoring method, device and system, electronic equipment and storage medium | |
| CN111183917B (en) | Animal abnormity monitoring and image processing method and device | |
| Forsyth et al. | Methodology matters when estimating deer abundance: a global systematic review and recommendations for improvements | |
| Guzhva et al. | Now you see me: Convolutional neural network based tracker for dairy cows | |
| US11967154B2 (en) | Video analytics to detect instances of possible animal abuse based on mathematical stick figure models | |
| CN110991222B (en) | Object state monitoring and sow oestrus monitoring method, device and system | |
| CN110022379A (en) | A kind of livestock monitoring system and method | |
| KR102584357B1 (en) | Apparatus for identifying a livestock using a pattern, and system for classifying livestock behavior pattern based on images using the apparatus and method thereof | |
| CN108874910B (en) | Vision-based small target recognition system | |
| KR102425522B1 (en) | Method for Establishing Prevention Boundary of Epidemics of Livestock Based On Image Information Analysis | |
| CN111797831A (en) | BIM and artificial intelligence based parallel abnormality detection method for poultry feeding | |
| Kuan et al. | An imaging system based on deep learning for monitoring the feeding behavior of dairy cows | |
| Mücher et al. | Detection, identification and posture recognition of cattle with satellites, aerial photography and UAVs using deep learning techniques | |
| CN111325181A (en) | State monitoring method and device, electronic equipment and storage medium | |
| KR20200115317A (en) | Method and appartus for checking symptom of pig and managing cloud service | |
| CN114494965A (en) | Method and system for detecting wandering pets based on vision | |
| González et al. | Real-time monitoring of poultry activity in breeding farms | |
| KR20210116183A (en) | System and method for diarrhea signs dection of animals and diarrhea risk prediction | |
| KR102341715B1 (en) | Apparatus and method for livestock monitoring | |
| CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
| CN112734730B (en) | Livestock quantity identification method, device, equipment and storage medium | |
| KR102332252B1 (en) | Apparatus and method for analyzing oestrus behavior pattern of ruminant animal based on image analysis | |
| KR102328981B1 (en) | System for providing pet information sharing service using harness camera |
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 | ||
| CB02 | Change of applicant information |
Address after: 601, 6 / F, building 2, No. 18, Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Technology Information Technology Co.,Ltd. Address before: 601, 6 / F, building 2, No. 18, Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant before: Jingdong Shuke Haiyi Information Technology Co.,Ltd. Address after: 601, 6 / F, building 2, No. 18, Kechuang 11th Street, Daxing District, Beijing, 100176 Applicant after: Jingdong Shuke Haiyi Information Technology Co.,Ltd. Address before: 601, 6 / F, building 2, No. 18, Kechuang 11th Street, Beijing Economic and Technological Development Zone, Beijing 100176 Applicant before: BEIJING HAIYI TONGZHAN INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information |