CN112036206A

CN112036206A - Monitoring method, device and system based on identification code type pig ear tag

Info

Publication number: CN112036206A
Application number: CN202010864494.3A
Authority: CN
Inventors: 鞠铁柱; 张兴福; 陈春雨; 黄平
Original assignee: Beijing Xiaolongqianxing Technology Co ltd
Current assignee: Beijing Xiaolongqianxing Technology Co ltd
Priority date: 2020-08-25
Filing date: 2020-08-25
Publication date: 2020-12-04

Abstract

The invention provides a monitoring method, a device and a system based on an identification code type pig ear tag. The acquisition module acquires a pig video acquired by the image acquisition equipment in real time; the processing module is used for processing the pig videos and acquiring pig images corresponding to each frame in the pig videos; the positioning module is used for positioning the identification codes in the pig images; and the identification module is used for identifying the positioned identification code to obtain the information of the pig corresponding to the identification code. The method can effectively identify the pig ear tag in a complex breeding environment and monitor the life and breeding of the pig. The pig ear tag is used for identifying the individual pig, so that the purpose of monitoring each pig is achieved, and the pig in the pig ear tag is known and the information of the pig is also known. And a tracing system for the processes of feeding, transporting, slaughtering, processing and the like can be realized. Meanwhile, the system can also be used for the management of breeding, epidemic prevention and vaccine in the live pig feeding process, and provides individual pig differentiation for accurate feeding.

Description

Monitoring method, device and system based on identification code type pig ear tag

Technical Field

The invention relates to a machine vision technology, in particular to a monitoring method, a monitoring device and a monitoring system based on an identification code type pig ear tag.

Background

Based on the large background of the rapid development of the current large-scale pig industry, the informatization and automatic management of the pig industry is a necessary trend. With the continuous reduction of the price and the continuous improvement of the cost performance of monitoring equipment (hardware such as computers, image acquisition equipment and the like), the arrangement of the monitoring equipment in a feeding farm has become a normal state. With the rapid development of artificial intelligence technology in recent years, it is possible that machine vision technology replaces manual observation to identify live pig behaviors. At present, domestic live pigs are mainly raised in groups, and the identification of the pigs raised in groups is also a key problem.

The traditional individual identification of the pigs mainly adopts an ear tag radio frequency identification (RFID for short) technology, but the technology can interfere the normal growth of the pigs to a certain extent, and the RFID identification range is within the range of 0.5m radius, so that the specific small range of the behavior identification of the pigs can be influenced to a certain extent.

People also propose a pig face identification method, but the pig face identification has particularity, the close breeding characteristics of pigs cause high individual similarity, and meanwhile, the pig faces which are not washed for a long time can cover the facial features of the pigs, so that great difficulty is brought to the pig face identification. The accuracy can reach 77% under the environment excellent state. However, this identification method is not suitable for use in a practically complex farm environment. Therefore, a method for automatically detecting and identifying the pig ear tag is urgently needed at present.

Disclosure of Invention

The embodiment of the invention provides a monitoring method, a monitoring device and a monitoring system based on an identification code type pig ear tag, which can effectively identify the pig ear tag in a complex breeding environment and monitor the life and breeding of pigs.

The first aspect of the embodiment of the invention provides a monitoring method based on an identification code type pig ear tag, which comprises the following steps:

acquiring a pig video acquired by image acquisition equipment in real time;

processing the pig video to obtain a pig image corresponding to each frame in the pig video;

positioning the identification codes in the pig images;

and identifying the positioned identification code to obtain the information of the pig corresponding to the identification code.

Optionally, in a possible implementation manner of the first aspect, the processing the pig video, and acquiring a pig image corresponding to each frame in the pig video includes:

sequentially carrying out up-sampling processing and noise reduction processing on the pig image;

and converting the pig images subjected to the up-sampling processing and the noise reduction processing into pig images with gray levels.

Optionally, in a possible implementation manner of the first aspect, the locating an identification code in the pig image, and identifying the located identification code to obtain pig information corresponding to the identification code includes:

respectively carrying out identification code positioning on all identification codes in the pig image, and storing the position where each identification code is positioned in a container;

and traversing and identifying each identification code in the container, and acquiring the pig information corresponding to each identification code.

Optionally, in a possible implementation manner of the first aspect, the traversing identifies each identifier in the container, and acquiring pig information corresponding to each identifier includes:

and comparing each identification code with identification codes in an identification code database, wherein all identification codes and information of pigs respectively corresponding to all identification codes are stored in the identification code database in advance.

Optionally, in a possible implementation manner of the first aspect, before the acquiring, in real time, a video of a pig acquired by an image acquisition device, the method includes:

receiving any one or more of time control information, image quantity information and individual quantity information input by a user;

and when any one or more of the time control information, the image quantity information and the individual quantity information reaches a preset condition, controlling the image acquisition equipment to stop acquiring the video of the pig.

receiving month time period information and single time information input by a user;

and controlling the image acquisition equipment to acquire the video of the pigs according to the time period of the month time period information, wherein the single time of each time of the video acquisition of the pigs is the single time information.

Optionally, in a possible implementation manner of the first aspect, the pig video is sent to an edge computing terminal;

the edge computing terminal writes data into a video format and processes the data at the same time, and the data acquired by different devices are put into different threads for real-time processing by using multiple threads.

Optionally, in a possible implementation manner of the second aspect, there is provided a monitoring apparatus based on an identification code type pig ear tag, including:

the acquisition module is used for acquiring the video of the pig acquired by the image acquisition equipment in real time;

the processing module is used for processing the pig videos and acquiring pig images corresponding to each frame in the pig videos;

a positioning module for positioning the identification code in the pig image

And the identification module is used for identifying the positioned identification code to obtain the information of the pig corresponding to the identification code.

Optionally, in a possible implementation manner of the third aspect, a monitoring system based on an identification code type pig ear tag is provided, and includes an image acquisition device and an edge algorithm terminal;

the image acquisition equipment is used for acquiring videos of pigs in real time;

the edge force calculation terminal is used for executing the method to process the pig video.

A fourth aspect of the embodiments of the present invention provides a readable storage medium, in which a computer program is stored, and the computer program is used for implementing the method according to the first aspect of the present invention and various possible designs of the first aspect of the present invention when the computer program is executed by a processor.

The monitoring method, the monitoring device and the monitoring system based on the identification code type pig ear tag can effectively identify the pig ear tag in a complex breeding environment and monitor the life and breeding of pigs. The pig ear tag is used for identifying the individual pig, so that the purpose of monitoring each pig is achieved, and the pig in the pig ear tag is known and the information of the pig is also known.

And a tracing system for the processes of feeding, transporting, slaughtering, processing and the like can be realized. Meanwhile, the system can also be used for the management of breeding, epidemic prevention and vaccine in the live pig feeding process, and provides individual pig differentiation for accurate feeding.

Drawings

FIG. 1 is a flow chart of a first embodiment of a method for monitoring pig ear tags based on identification codes;

FIG. 2 is a flow chart of a first embodiment of a method for monitoring pig ear tags based on identification codes;

FIG. 3 is a flow chart of a first embodiment of a method for monitoring pig ear tags based on identification codes;

FIG. 4 is a schematic diagram of an embodiment in which multiple columns share a camera;

FIG. 5 is a schematic view of an embodiment of a camera mounted in close proximity;

FIG. 6 is a schematic view of an embodiment of a remote mounting of a camera;

FIG. 7 is a flow chart of a first embodiment of an identification code based pig ear tag monitoring device;

fig. 8 is a flowchart of a first embodiment of an identification code based pig ear tag monitoring system.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.

It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.

As used herein, "if" may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context.

The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.

The RFID (radio frequency identification) ear tag is a main approach for individual identification of the group-breeding pigs at present. However, there are certain limitations to this approach. First, each pig is loaded with an electronic ear tag using an invasive method. Secondly, each area to be identified needs at least one set of card reader and identity identification, and the cost is high. More importantly, when the RFID earmarks are adopted, when multiple pigs enter the identification radius of the card reader at the same time, the identity of each pig is difficult to identify.

Identification codes such as two-dimensional bar codes (QR codes) are patterns which are distributed on a plane (two-dimensional direction) according to a certain rule by using a certain specific geometric figure, are alternated in black and white, and record data symbol information. The two-dimension code identification mode has the function of automatically identifying information of different rows and processing figure rotation change points at the same time. Meanwhile, the problem of the inclination angle of the ears caused by the behavior characteristics (such as eating, drinking and the like) of the pigs can be solved through the identification characteristics.

It is considered that the collecting device is bitten by pigs, and the two-dimension code pair is influenced by the distance factor. In order to solve the above problem, embodiments of the present invention provide a monitoring method, device and system based on an identification code type pig ear tag. The invention aims to adopt the latest picture recognition and machine learning technology to realize individual recognition of pigs by automatically acquiring and recognizing two-dimensional code pictures on ear tags of live pigs. Through the research and development of the invention, a tracing system for the processes of feeding, transporting, slaughtering, processing and the like can be realized. Meanwhile, the system can also be used for the management of breeding, epidemic prevention and vaccine in the live pig feeding process, and provides individual pig differentiation for accurate feeding. The embodiment of the invention not only can realize the automatic detection of the oestrus of the sow, but also has low cost, high efficiency and high detection accuracy. The scheme provided by the invention will be explained in detail by specific examples.

The invention provides a monitoring method based on an identification code type pig ear tag, which comprises the following steps of:

and S10, acquiring the video of the pig acquired by the image acquisition equipment in real time. The image acquisition equipment is used for acquiring real-time videos of the pigs when the pigs eat and drink water.

When carrying out pig video acquisition, need arrange image acquisition equipment above the swinery, wherein image acquisition equipment can be camera etc.. For example, the focusing RGB image acquisition device can be mounted above the pig drinking water fence, and the shooting range of the focal length position of the RGB image acquisition device is determined to be 30cm according to the image acquisition width and the picture definition. In addition, it should be noted that the height of the image acquisition device can be adjusted according to different application scenarios, for example, when monitoring the estrus of a sow, the estrus detection project involves the stay above different pigs, and the image acquisition device can be adjusted by considering the height of a pigsty.

And S20, processing the pig video to obtain a pig image corresponding to each frame in the pig video.

As shown in fig. 2, step S20 includes:

s201, sequentially carrying out up-sampling processing and noise reduction processing on the pig image. Wherein the step of treating comprises the steps of,

1) and processing the images of the pigs transmitted by the acquisition layer. By up-sampling the pig images (e.g., converting the 720 x 600 images to 1920 x 1080 images), the recognition accuracy can be improved by improving the sharpness of the images.

2) And (3) carrying out noise reduction processing (Gaussian noise reduction, salt and pepper noise reduction and the like) on the up-sampled pig image, and processing image blurring caused by light and camera cmos equipment. And the identification accuracy is improved.

3) The pig image subjected to noise reduction processing is converted into the gray pig image, and the gray pig image is converted to improve the identification speed due to the fact that the pig image is formed by pixel points.

S202, the pig image subjected to the up-sampling processing and the noise reduction processing is converted into a pig image with gray scale.

And S30, positioning the identification codes in the pig images.

As shown in fig. 3, step S30 includes:

s301, respectively positioning all identification codes in the pig image, and storing the position where each identification code is positioned in a container.

In the above steps, the matting of the identification codes is firstly realized, each identification code in the picture is positioned, the position is stored in a container, and the container is traversed during the identification. Each identifier has its own anchor point. The positioning point is a special positioning mark of the two-dimensional bar code. A typical two-dimensional code can see three corners as identical black and white containing squares, but the other corner is not, since three points can be represented to define a rectangular area and allow the identification device to identify it from the correct orientation, so that the identification code can be identified from either orientation.

And S40, identifying the positioned identification code to obtain the information of the pig corresponding to the identification code.

Step S40 includes:

s401, traversing and identifying each identification code in the container, and acquiring information of pigs corresponding to each identification code. And calling the related two-dimensional code recognition libraries, comparing the two-dimensional code recognition libraries in a plurality of different environments through early-stage investigation, and comparing the accuracy and the speed of the two-dimensional code recognition libraries to select the pyzbar two-dimensional code recognition library for recognition. And transmitting the identified result to an application layer, and combining according to different scenes.

Based on the steps, the technical scheme provided by the embodiment of the invention carries out frame processing according to the video acquired in real time, carries out up-sampling on the frame image to improve the definition of the identification code, carries out noise reduction processing on the up-sampled image, reduces the influence of the camera on the image, carries out gray processing on the image, reduces the image data and facilitates real-time detection. And positioning and identifying the identification code of the processed image, and transmitting the identification result to the edge force calculation terminal.

In the embodiment, when the pig ear tag is selected, the ear tag which is as large as possible under the condition that pigs cannot bite each other is selected, the identification code is printed on the ear tag, the fault tolerance rate of the identification code is maximum, the included characters are as few as possible, and the identification code of version2 version is mainly used.

In this embodiment, when performing visual ear tag data acquisition, it is necessary to arrange an image acquisition device above the pigsty, for example, a focusing RGB camera may be mounted above the pigsty, and the shooting range of the focal length position of the RGB camera is determined to be 30cm according to the image acquisition extent and the picture definition. In addition, it should be noted that the height of the camera can be adjusted according to different application scenarios, for example, when monitoring the estrus of a sow, the estrus detection item involves the stay above different pigs, and the camera can be adjusted by considering the height of a pigsty.

The edge computing terminal may be a server.

In this embodiment, data collected from the image collection device is transmitted to the data processing edge computational force terminal, and then the read ear tag data is subjected to up-sampling, noise reduction and graying on the image by frames. And identifying the two-dimensional code positioned on the two-dimensional code for the processed data.

In this embodiment, it should be noted that, compared with the method of detecting the identity of a pig by a sensor, the method of judging the identity of a pig by using a visual ear tag has the advantages of low cost, high automation degree, no emergency response, and high detection accuracy, so that the method can be practically popularized well.

In the following embodiments, data sample data of the pig in different shooting states is needed for identification of the visual ear tag, and therefore, a method and a process for acquiring the visual ear tag data test sample are provided below.

The software required: data acquisition platform software; the hardware required: RGB cameras (2); high performance computing and application service platform (configuration 1-2 GPU card)

Adopt RGB camera, carry out pig video acquisition according to diet and feed. In the pig video acquisition process, a professional focus-adjustable monitoring camera (or a professional focus-adjustable RGB camera) can be used, the pigsty environment is considered, and a dustproof and moistureproof camera is considered. As shown in fig. 4, multiple columns share one camera, so that the equipment cost and the maintenance workload are reduced (multiple piggeries are covered as much as possible according to the data shooting visual angle and the display of the pig breeding scene). The timing collection is based on food taking, related equipment (adopting a trigger mode) is opened 2 minutes before food taking, in addition, the pigsty is matched before the collection, a camera configuration scheme above the pigsty (adopting short-distance and long-distance shooting, the equipment is placed at a height of 0.5-0.7m away from a water outlet or a food outlet in a short distance, the long-distance equipment is placed at a height of 1.3-1.5m away from the water outlet or the food outlet) can adopt an RGB (red, green and blue) camera, the pigsty is placed right above the equipment, the short-distance installation is shown in figure 5, and the long-distance installation is shown in figure 6. In order to meet the application scene of the group culture fence. The pigs in the group breeding fence are mainly fattening pigs, and the scene is mostly applied to behavior identification of the pigs (such as monitoring the drinking and eating conditions of the pigs). Because the area of the pig activity region of the group raising fence is large, the size of the used visible ear tag two-dimensional code is within the range of 3.0cm x 3.0cm, and for shooting a clear identification code, cameras with different focal lengths can be adopted for fixed shooting.

Therefore, according to the scheme provided by the embodiment of the invention, the pig identity can be matched only by acquiring the pig image monitored by the sow and then performing background automatic processing, so that the automatic detection of the pig identity recognition is realized, and the whole detection process has the advantages of low cost, high detection efficiency and high detection accuracy.

Wherein the pig video can be collected by the following scheme, including:

1) firstly, a data acquisition field is established and part of representative pigs are selected.

2) A close-range data acquisition scheme:

the scheme adopts a high-definition RGB camera with a fixed focus range of 0.5m-0.7m and is placed right above a position 0.5m above a drinking trough/trough opening to shoot a top view. Shooting is carried out every day according to a set strategy, and data collection on the day is stopped at fixed time above each group rearing fence or after the number of pictures meeting the requirement/the number of individuals meeting the requirement are collected. As shown in fig. 5

3) Remote data acquisition scheme:

the acquisition scheme can be arranged in a range with the height of about 2.0m to shoot the pig diet, and is suitable for individual data information statistics of the pigs raised in a group. Mainly for the group breeding fence (pigsty with length of 5m and width of 3 m), the whole area cannot be shot due to the small visual field of the two-dimensional code recognition shooting, and the tripod head is introduced to shoot at fixed point and fixed time (such as fixed speed rotation shooting), as shown in fig. 6.

Sampling period:

collecting day data of 1 month according to the above requirements, collecting 10 seconds for each pig, collecting data for different behavior habits and different illumination for seven years, respectively, collecting data for 24 hours all day, and collecting only day data of a specified time period if controllable.

When a pig video is collected:

1) identifying the identity of each pig per day, i.e. feeding start time-end time (data for this interval is stored separately);

2) identify who each pig was ready to drink on a daily basis start time-end time (data for this interval was stored separately);

3) picture naming rules, identity of pigs-month, day, minute and second.

In a possible embodiment, the traversing identifies each identification code in the container, and the obtaining pig information corresponding to each identification code includes:

In one embodiment, before the real-time acquiring of the pig video acquired by the image acquisition device, the method comprises the following steps:

In one embodiment, the pig video is sent to an edge computing terminal;

In the scheme, the collected real-time data are transmitted to the edge force computing terminal, wherein the real-time data comprise a pig video, the edge force computing terminal processes the real-time data while writing the real-time data into a video format, multithreading is used for putting the data collected by different devices into different threads for real-time processing, the collecting terminal collects 25 frames per second only when the collecting device is communicated with the edge force computing terminal through a TCP/IP protocol, and each collected frame image is transmitted to the edge force computing terminal, namely the real-time frame image is obtained at the edge force computing terminal.

The invention also provides a monitoring device based on the identification code type pig ear tag, as shown in fig. 7, comprising:

a positioning module for positioning the identification code in the pig image

The invention provides a monitoring system based on an identification code type pig ear tag, which comprises an image acquisition device and an edge force calculation terminal, as shown in figure 8;

the image acquisition equipment is used for acquiring videos of pigs in real time; the image acquisition equipment is provided with a camera which can comprise a plurality of cameras.

The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC may reside in user equipment. Of course, the processor and the readable storage medium may also reside as discrete components in a communication device. The readable storage medium may be a read-only memory (ROM), a random-access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the methods provided by the various embodiments described above.

In the above-mentioned embodiments of the terminal or the edge computing terminal, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring method based on an identification code type pig ear tag is characterized by comprising the following steps:

acquiring a pig video acquired by image acquisition equipment in real time;

positioning the identification codes in the pig images;

2. The monitoring method according to claim 1,

processing the pig video, and acquiring a pig image corresponding to each frame in the pig video comprises the following steps:

3. The monitoring method according to claim 1,

the positioning the identification code in the pig image, and identifying the positioned identification code to obtain the pig information corresponding to the identification code comprises:

4. The monitoring method according to claim 1,

the traversing identification of each identification code in the container, and the obtaining of the pig information corresponding to each identification code comprises:

5. The monitoring method according to claim 1,

before the real-time acquisition of the video of the pig acquired by the image acquisition equipment, the method comprises the following steps:

6. The monitoring method according to claim 1,

7. The monitoring method according to claim 1,

sending the pig video to an edge force calculation terminal;

8. The utility model provides a monitoring device based on identification code formula pig ear tag which characterized in that includes:

a positioning module for positioning the identification code in the pig image

9. A monitoring system based on an identification code type pig ear tag is characterized by comprising image acquisition equipment and an edge force calculation terminal;

the edge force terminal is used for processing the pig video by executing the method of any one of claims 1 to 7.

10. A readable storage medium, in which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.