A method and device for collecting backfat of animals

Abstract

A method and system for collecting backfat of veterinary use. This method generates a robotic arm control instruction based on the coordinate positioning value and the back distance value from the depth camera to the collection object, and sends the robotic arm control instruction to a multi-axis robotic arm. The multi-axis robotic arm moves to the coupling agent container according to the robotic arm control instruction along a preset trajectory to dip the coupling agent. After dipping the coupling agent, it controls the backfat B-ultrasound probe installed at the top of the multi-axis robotic arm to reach the measurement point of the collection object and fit the skin of the collection object. When the backfat B-ultrasound probe reaches the backfat measurement point, it repeats the collection of backfat B-ultrasound data according to the set number of times, and transmits the collected B-ultrasound data to the main control cabinet in the form of a video. The present invention can achieve automated collection, greatly saving labor costs; can accurately locate the backfat measurement position of pigs; reduces the human-animal contact link, improves the biosafety level, and reduces the risk of infectious diseases brought by humans.

Description

Technical Field

[0001] The present invention belongs to the technical field of backfat collection, and particularly relates to a method and device for collecting backfat of animals for veterinary use. Background Art

[0002] Currently, manual measurement of the backfat of pigs is mainly carried out by manually using a veterinary B-ultrasound instrument. In the measurement work, a specific cage needs to be placed in a fixed venue, and then the pigs to be measured for backfat are driven into the specific cage one by one. Then, the staff locates the backfat measurement point of the pig based on experience. Next, B-ultrasound monitoring is carried out. If the experience is insufficient, it may take several minutes or more than ten minutes to find it. During the process of finding the backfat measurement point, it is very likely to cause an excessive reaction of the pig. After finding the backfat measurement point, the staff then uses a handheld B-ultrasound instrument to perform B-ultrasound detection on the pig, and then operates the handheld instrument to measure the backfat value, and makes a manual record after the operation is completed.

[0003] In this working process, pigs are prone to stress reactions due to leaving their original environment and being driven, and become more irritable during the measurement work. Therefore, the backfat measurement work is sometimes very difficult. In addition, the backfat measurement position is manually located based on experience, but due to different experiences of the staff, the measurement point is often mispositioned, often resulting in a large error in the measurement data. Summary of the Invention

[0004] Therefore, the present invention provides a method and device for collecting backfat of animals for veterinary use, which solves the problems of long time, high difficulty, and low data accuracy in traditional veterinary backfat collection.

[0005] In order to achieve the above object, the present invention provides the following technical solution: A method for collecting backfat of animals for veterinary use, comprising:

[0006] S1. During the feeding process of the collection object, the electronic ear tag reader / writer is used to identify the electronic ear tag on the ear of the collection object, and the number of the electronic ear tag of the collection object is obtained;

[0007] S2. When the main control cabinet receives the number of the electronic ear tag of the collection object, the depth camera is started to perform image collection on the collection object, and the backfat measurement point recognition model is used to perform coordinate positioning on the backfat measurement point on the collected image;

[0008] S3. According to the coordinate positioning value and the back distance value from the depth camera to the back of the collection object, a robotic arm control instruction is generated, and the robotic arm control instruction is sent to the multi-axis robotic arm. The multi-axis robotic arm moves to the coupling agent container according to the robotic arm control instruction and dips the coupling agent according to the preset trajectory;

[0009] S4. After dipping the coupling agent, control the multi-axis robotic arm to move to a given coordinate position at a first speed until the distance sensor on the multi-axis robotic arm detects that the backfat B-ultrasound probe mounted on the top of the multi-axis robotic arm reaches the point on the back of the acquisition object where backfat measurement is required, and then control the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object;

[0010] S5. After the backfat B-ultrasound probe reaches the backfat measurement point, collect backfat B-ultrasound data repeatedly according to the set number of times, and transmit the collected B-ultrasound data to the main control cabinet in the form of a video.

[0011] As a preferred solution of the veterinary backfat acquisition method, in step S2, the training process of the backfat measurement point recognition model includes:

[0012] Obtain the back image data of the acquisition object;

[0013] Annotate the image data of the back of the acquisition object;

[0014] Load the YoLov4-tiny model for model training;

[0015] Use the test set to test the trained model;

[0016] Evaluate the test results, and if the set requirements are met, end the training.

[0017] As a preferred solution of the veterinary backfat acquisition method, in step S4, after controlling the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object, continue to control the multi-axis robotic arm to move so that the skin of the acquisition object in contact is pressed down by a preset distance.

[0018] As a preferred solution of the veterinary backfat acquisition method, step S4 further includes judging whether the position of the acquisition object has moved. If the position of the acquisition object has moved, adjust the position of the multi-axis robotic arm according to the movement of the acquisition object so that the backfat B-ultrasound probe continues to be completely in contact with the back of the acquisition object.

[0019] As a preferred solution of the veterinary backfat acquisition method, in step S5, when the collection of backfat B-ultrasound data reaches the set number of times, control the backfat B-ultrasound probe to stop data collection; if the acquisition object changes the feeding position, re-measure the backfat of the acquisition object;

[0020] In step S5, store the collected B-ultrasound data locally and generate a chart including the measurement date, ear tag number, and B-ultrasound image content.

[0021] The present invention also provides a veterinary backfat acquisition system, including:

[0022] An ear tag number acquisition module, which is used to identify the electronic ear tag on the ear of the collection object through an electronic ear tag reader during the feeding process of the collection object, and acquire the number of the electronic ear tag of the collection object;

[0023] An image acquisition module, which is used to start a depth camera to acquire images of the collection object when the main control cabinet receives the number of the electronic ear tag of the collection object;

[0024] A coordinate positioning module, which is used to perform coordinate positioning on the backfat measurement points on the acquired image by using a backfat measurement point recognition model;

[0025] A robotic arm control instruction generation module, which is used to generate a robotic arm control instruction according to the coordinate positioning value and the value of the distance from the depth camera to the back of the collection object;

[0026] A coupling agent dipping control module, which is used to send the robotic arm control instruction to a multi-axis robotic arm, and the multi-axis robotic arm moves to a coupling agent container to dip the coupling agent according to the robotic arm control instruction along a preset trajectory;

[0027] A robotic arm motion control module, which is used to control the multi-axis robotic arm to move to a given coordinate position at a first speed after dipping the coupling agent, and when the distance sensor on the top of the multi-axis robotic arm detects that the backfat B-ultrasound probe installed on the top of the multi-axis robotic arm reaches the point on the back of the collection object where backfat measurement is required, control the multi-axis robotic arm to move at a second speed until it fits the skin of the collection object;

[0028] A backfat B-ultrasound data acquisition module, which is used to repeatedly acquire backfat B-ultrasound data a set number of times after the backfat B-ultrasound probe reaches the backfat measurement point, and transmit the acquired B-ultrasound data to the main control cabinet in the form of a video.

[0029] As a preferred solution of the veterinary backfat collection system, it further includes a model training module for training the backfat measurement point recognition model; the model training module includes:

[0030] An image loading sub-module, which is used to acquire the back image data of the collection object;

[0031] An image data annotation sub-module, which is used to annotate the image data on the back of the collection object;

[0032] A model loading sub-module, which is used to load the YoLov4-tiny model for model training;

[0033] A model testing sub-module, which is used to test the trained model by using a test set;

[0034] A test evaluation sub-module is used to evaluate the test results. If the set requirements are met, the training is ended.

[0035] As an optimal solution for the veterinary backfat collection system, the robotic arm motion control module is further configured to control the multi-axis robotic arm to move at a second speed until it fits against the skin of the collection object, and then continue to control the multi-axis robotic arm to move so that the skin of the collection object in contact is pressed down by a preset distance.

[0036] As an optimal solution for the veterinary backfat collection system, it further includes a robotic arm position adjustment module, which is used to determine whether the position of the collection object has moved. If the position of the collection object has moved, the multi-axis robotic arm is adjusted according to the movement of the collection object so that the backfat B-ultrasound probe continues to be in full contact with the back of the collection object.

[0037] As an optimal solution for the veterinary backfat collection system, in the backfat B-ultrasound data collection module, when the backfat B-ultrasound data is collected a set number of times, the backfat B-ultrasound probe is controlled to stop data collection work; if the collection object changes the feeding position, the backfat of the collection object is measured and collected again.

[0038] It further includes a data storage module, which is used to locally store the collected B-ultrasound data and generate a chart containing the measurement date, ear tag number, and B-ultrasound image content.

[0039] The beneficial effects of the present invention are as follows: during the eating process of the collection object, the electronic ear tag on the ear of the collection object is identified by the electronic ear tag reader / writer, and the number of the electronic ear tag of the collection object is obtained; after the main control cabinet receives the number of the electronic ear tag of the collection object, the depth camera is started to collect images of the collection object, and the back fat measurement point recognition model is used to coordinate the back fat measurement point on the collected image; according to the coordinate positioning value and the distance value from the depth camera to the back of the collection object, a robot arm control instruction is generated, and the robot arm control instruction is sent to the multi-axis robot arm, and the multi-axis robot arm is based on the robot The arm control instruction moves to the coupling agent container according to a preset trajectory to dip the coupling agent; after dipping the coupling agent, the multi-axis robotic arm is controlled to move to a given coordinate position at a first speed until the distance sensor on the multi-axis robotic arm detects that the back fat B-ultrasound probe installed on the top of the multi-axis robotic arm reaches the point on the back of the collection object where back fat measurement is required, and the multi-axis robotic arm is controlled to move at a second speed until it fits the skin of the collection object; when the back fat B-ultrasound probe reaches the back fat measurement point, the back fat B-ultrasound data is repeatedly collected according to the set number of times, and the collected B-ultrasound data is transmitted to the main control cabinet in the form of video. The present invention can realize automatic collection, greatly saving labor costs; can accurately locate the back fat measurement position of pigs; can perform image collection work during the measurement process and save the measurement images during B-ultrasound measurement, which is convenient for staff at all levels to review the measurement data; automatically perform back fat measurement during the feeding stage of the collection object, which can greatly reduce the stress effect on the collection object during the measurement work; reduce the human-animal contact link, improve the biosafety level, and reduce the risk of infectious diseases brought by humans. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the implementation of the present invention or the technical solution in the prior art, the following briefly introduces the drawings required for the implementation or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0041] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0042] Figure 1Flowchart of the method for collecting backfat of animals provided by the embodiments of the present invention;

[0043] Figure 2 Schematic diagram of the model training process of the method for collecting backfat of animals provided by the embodiments of the present invention;

[0044] Figure 3 Schematic diagram of the hardware deployment of the method for collecting backfat of animals provided by the embodiments of the present invention;

[0045] Figure 4 Schematic diagram of the system architecture of the method for collecting backfat of animals provided by the embodiments of the present invention. Detailed implementation manners

[0046] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in the art can easily understand the other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment 1

[0048] Refer to Figure 1 and Figure 2 Embodiment 1 of the present invention provides a method for collecting backfat of animals, including the following steps:

[0049] S1. During the feeding process of the collection object, the electronic ear tag reader is used to identify the electronic ear tag on the ear of the collection object, and the number of the electronic ear tag of the collection object is obtained;

[0050] S2. After the main control cabinet receives the number of the electronic ear tag of the collection object, the depth camera is started to collect images of the collection object, and the backfat measurement point recognition model is used to locate the coordinates of the backfat measurement points on the collected images;

[0051] S3. According to the coordinate positioning value and the distance value from the depth camera to the back of the collection object, a robotic arm control instruction is generated, and the robotic arm control instruction is sent to the multi-axis robotic arm. The multi-axis robotic arm moves to the coupling agent container according to the robotic arm control instruction to dip the coupling agent according to the preset trajectory;

[0052] S4. After dipping the coupling agent, control the multi-axis robotic arm to move to the given coordinate position at the first speed until the distance sensor on the multi-axis robotic arm detects that the backfat B-ultrasound probe installed on the top of the multi-axis robotic arm reaches the point on the back of the collection object where backfat measurement is required, and then control the multi-axis robotic arm to move at the second speed until it fits the skin of the collection object;

[0053] S5. After the backfat B-ultrasound probe reaches the backfat measurement point, collect the backfat B-ultrasound data repeatedly according to the set number of times, and transmit the collected B-ultrasound data to the main control cabinet in the form of a video.

[0054] In this embodiment, in step S1, taking the target pig as an example, when the pig's head reaches the hopper to eat, the electronic ear tag reader recognizes the electronic ear tag on the pig's ear, and then transmits the electronic ear tag number to the main control cabinet.

[0055] In step S2, when the main control cabinet receives the electronic ear tag number, it starts the depth camera to collect images of the pig's body, locates the coordinates of the backfat measurement point to be measured according to the backfat measurement point recognition model, obtains the distance value from the camera to the pig's back, and then transmits the positioning coordinates and distance value to the main control cabinet; the positioning method of the backfat measurement point is model training, which has very high accuracy.

[0056] In this embodiment, by reading and identifying the ear tag information, it is judged whether it is the livestock to be measured according to the measurement parameters. After it is determined as the livestock to be measured, the image data is obtained. According to the backfat measurement point recognition model in the local storage, the position information and size of the identified target livestock in the image are combined with the position of the P2 point of the actual backfat of the livestock, and the data is comprehensively calculated and analyzed to obtain the coordinate data of the P2 point to be measured on the back of the livestock. The image with additional coordinate points is stored in the local storage database, and an instruction is sent to the multi-axis robotic arm movement module according to the coordinate point information, driving the robotic arm to carry the backfat probe to reach the P2 point to be measured after dipping the coupling agent, receiving the video information from the backfat video data acquisition module, and storing it in the local storage database, which can be viewed and processed on the terminal data platform.

[0057] Among them, the unique identity information in the electronic ear tag corresponds to the age, weight, and the picture of the P2 point to be measured on the back of the livestock in the local storage database. The electronic ear tag reader is set in the detection area, and the read electronic ear tag information is analyzed. If the electronic ear tag information is received for the first time, the information recorded in the electronic ear tag is filled into the livestock backfat information database to form a new data entry.

[0058] In a possible embodiment, in step S2, the training process of the backfat measurement point recognition model includes:

[0059] Obtain the back image data of the acquisition object;

[0060] Annotate the image data of the back of the acquisition object;

[0061] Load the YoLov4-tiny model for model training;

[0062] Test the trained model using the test set;

[0063] Evaluate the test results. If the set requirements are met, end the training.

[0064] In this embodiment, in step S3, the main control cabinet aggregates the collected positioning coordinates and distance values into corresponding instructions and sends them to the multi-axis robotic arm. After receiving the instructions, the multi-axis robotic arm first moves to the coupling agent container according to the preset trajectory to dip the coupling agent.

[0065] In this embodiment, in step S4, control the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object, and then continue to control the multi-axis robotic arm to move so that the skin of the acquisition object that is in contact is pressed down by a preset distance; determine whether the position of the acquisition object has moved. If the position of the acquisition object has moved, adjust the position of the multi-axis robotic arm according to the movement of the acquisition object so that the backfat B-ultrasound probe continues to be in full contact with the back of the acquisition object.

[0066] Specifically, after dipping the coupling agent, continue to move towards the established coordinates transmitted by the main control cabinet until the distance sensor on the multi-axis robotic arm detects that the backfat B-ultrasound probe installed at the top of the multi-axis robotic arm is about to reach the point on the pig's back where backfat measurement is required. Then the multi-axis robotic arm starts to move slowly until it fits the pig's skin. However, to ensure that the backfat B-ultrasound probe is in full contact with the pig's back, the multi-axis robotic arm will continue to press down a certain distance; if the pig moves during the measurement work, the distance camera and the distance sensor will transmit the movement of the pig to the main control cabinet, and the main control cabinet will send corresponding instructions to move the multi-axis robotic arm to ensure that the backfat B-ultrasound probe continues to be in full contact with the pig's back.

[0067] In this embodiment, in step S5, when the collection of backfat B-ultrasound data reaches the set number of times, control the backfat B-ultrasound probe to stop data collection; if the acquisition object changes the feeding position, re-measure the backfat of the acquisition object.

[0068] Specifically, when the backfat B-ultrasound probe reaches the backfat measurement point, start collecting backfat B-ultrasound data and transmit the collected B-ultrasound data to the main control cabinet in the form of a video. The time for the backfat B-ultrasound probe to collect data once is about 20 seconds. When the backfat B-ultrasound probe finishes collecting data for the first time, as long as the electronic ear tag reader detects the electronic ear tag signal of the pig, it means that the pig is still feeding. Then the main control cabinet will continue to repeat the measurement work, and the backfat B-ultrasound probe will continue to work. The purpose of measuring the same pig multiple times is to mutually verify possible errors or misidentifications. If there are doubts about the finally collected B-ultrasound images, the multiple measured image information retained can be verified.

[0069] In this embodiment, in step S5, the collected B-ultrasound data is locally stored, and a chart including the measurement date, ear tag number, and B-ultrasound image content is generated.

[0070] Specifically, during the pig's feeding period, the measurement is repeated at most 4 times. If the same pig is still feeding after 4 measurements, the data collection work will be suspended. If 4 measurements have been reached or less than 4 measurements have been made and a different pig starts feeding, then the backfat measurement collection will be carried out on the newly feeding pig.

[0071] In this embodiment, when the backfat B-ultrasound probe captures a B-ultrasound image, the image will be sent to the main control cabinet in the form of a video. The main control cabinet will save the image video in the local memory and automatically generate a chart including the measurement date, ear tag number, B-ultrasound image, etc.

[0072] Among them, the main control cabinet is connected to the local network by wire or wirelessly. Therefore, through a computer connected to the local network in the office, the corresponding data can be viewed through the client supporting this invention, and the growth information such as the pig's weight and body length can be supplemented and improved in the chart. The backfat B-ultrasound image information is stored locally. If the memory is full, the earliest information will be automatically overwritten.

[0073] In summary, during the feeding process of the collection object, the electronic ear tag reader on the collection object's ear is used to identify the electronic ear tag, and the number of the electronic ear tag of the collection object is obtained. After receiving the number of the electronic ear tag of the collection object, the main control cabinet activates the depth camera to collect images of the collection object, and uses the backfat measurement point recognition model to locate the coordinates of the backfat measurement points on the collected images. According to the coordinate positioning values and the distance value from the depth camera to the back of the collection object, a robotic arm control instruction is generated and sent to the multi-axis robotic arm. The multi-axis robotic arm moves to the coupling agent container to dip the coupling agent according to the robotic arm control instruction along a preset trajectory. After dipping the coupling agent, the multi-axis robotic arm is controlled to move to a given coordinate position at a first speed until the distance sensor on the multi-axis robotic arm detects that the backfat B-ultrasound probe installed at the top of the multi-axis robotic arm reaches the point on the back of the collection object where backfat measurement is required, and then the multi-axis robotic arm is controlled to move at a second speed until it fits the skin of the collection object. When the backfat B-ultrasound probe reaches the backfat measurement point, the backfat B-ultrasound data is collected repeatedly according to the set number of times, and the collected B-ultrasound data is transmitted to the main control cabinet in the form of a video. The present invention reduces the human-animal contact link. After the pig enters the measurement station or feeding station, it is identified through the electronic ear tag and located through the depth camera, and then the multi-axis robotic arm is used to move the backfat B-ultrasound probe for detection. A series of actions are all autonomously operated by the machine without manual operation, greatly reducing the risk of infection of infectious diseases such as ASF caused by frequent human-animal contact; accurate positioning and efficient measurement; through the trained system, it can accurately identify and locate, which is more guaranteed compared with others; reduce the stress response of pigs. In the past, for backfat measurement, pigs needed to be driven to a strange fixed position, and the driving by personnel and the strange environment were all possible factors causing stress in pigs. In the present invention, the collection work is carried out when the pigs are eating in a familiar environment, and the resistance of the pigs is relatively very small and the cooperation degree is relatively high; the data preservation is more convenient and complete. In the past backfat measurement work, it was often recorded manually, and the data could not be saved in detail, the B-ultrasound image information of the measurement could not be saved or could not be completely saved or took a longer period. The present invention can automatically save and generate a report for personnel to consult.

[0074] In a possible embodiment, a sliding injection pipe is installed on the side of the backfat B-ultrasound probe. Before the backfat B-ultrasound probe measures, the coupling agent in the pipe is squeezed mechanically to make it spray out, and the sliding decoration is used to evenly apply the coupling agent to the backfat B-ultrasound probe.

[0075] In a possible embodiment, the main function of the distance sensor is to enable the backfat B-ultrasound probe to better fit the pig's back. This purpose can be achieved by using a pressure sensor instead. When the pressure sensor senses that the pressure of the backfat B-ultrasound probe is a certain value, it is considered that the backfat B-ultrasound probe has formed a complete fit with the pig's back. Therefore, sensors such as pressure sensors can also implement the related functions of the distance sensor.

[0076] In a possible embodiment, the electronic ear tag and the electronic ear tag reader can be replaced with a graphic tag. The graphic tag is pasted or fixed on the pig in other ways. The device is started by the camera identifying the graphic tag, and the pig is numbered and encoded using the graphic tag.

[0077] In a possible embodiment, the database data of the backfat automatic acquisition system is viewed and managed through the terminal data platform, including electronic ear tag information, P2 point recognition image data, backfat video data, filling in age data, weight data, backfat value data measured from the backfat image, setting measurement parameters, and the data export function. The measurement parameters include the total number of current livestock measurements per day, the number of single continuous measurements, the total number of times the coupling agent is used, and the number of remaining coupling agent alarm times.

[0078] See Figure 3 , which is an application scenario of the method of the embodiment of the present invention, where:

[0079] Client: View and manage the image data and video data of the backfat automatic acquisition system, and measure the backfat value of the backfat image.

[0080] Multi-axis robotic arm: A backfat probe and a distance sensor are installed at the end, and it moves to the point to be measured according to the instruction.

[0081] Distance sensor: Measures the distance from the backfat probe to the point to be measured, enabling the robotic arm to carry the probe to closely adhere to the skin of the point to be measured.

[0082] Backfat probe: Emits ultrasonic waves and receives the ultrasonic wave signals, converting them into electrical signals and transmitting them to the backfat main board.

[0083] Binocular depth camera: Obtains the color image and depth value of the livestock's back.

[0084] Electronic ear tag reader: Detects whether the livestock enters a specific position and obtains the ear tag identity information.

[0085] Electronic ear tag: The identity tag of the livestock.

[0086] Control cabinet: Loads the main board and supporting modules of the backfat automatic acquisition system.

[0087] The control cabinet is equipped with a system power supply, a control main board, a local storage unit (SSD solid-state drive), a switch, a backfat meter host, a USB video capture card, a relay module, and a USB to RS485 module.

[0088] System power supply: Provides various voltage requirements for the entire system.

[0089] Control main board: Receives sensor information and processes and issues control instructions.

[0090] Local storage unit (SSD solid-state drive): Stores the pictures collected by the binocular depth camera when calculating point P2, the pictures of the binocular depth camera during backfat measurement, and the video recordings collected during backfat meter measurement.

[0091] Switch: Controls the data forwarding of the control main board, the multi-axis robotic arm, and the client.

[0092] Backfat meter host: Receives the data from the backfat probe, processes it, and outputs video recordings.

[0093] USB video capture card: Performs interface conversion on the video signal of the backfat meter host.

[0094] Relay module: Controls the startup power supply of the backfat meter, shuts down after measurement to avoid damage to the backfat probe caused by long-term electrode polarization due to continuous power supply.

[0095] USB to RS485 module: Converts the signal interface of the electronic ear tag reader.

[0096] Embodiment 2

[0097] See Figure 4 , Embodiment 2 of the present invention provides a veterinary backfat collection system, including:

[0098] Ear tag number acquisition module 01, used to identify the electronic ear tag on the ear of the collection object through the electronic ear tag reader during the feeding process of the collection object, and obtain the number of the electronic ear tag of the collection object;

[0099] Image acquisition module 02, used to start the depth camera to perform image acquisition on the collection object when the main control cabinet receives the number of the electronic ear tag of the collection object;

[0100] Coordinate positioning module 03, used to perform coordinate positioning on the backfat measurement points on the acquired image by using the backfat measurement point recognition model;

[0101] Robotic arm control instruction generation module 04, used to generate robotic arm control instructions according to the coordinate positioning value and the back distance value from the depth camera to the back of the collection object;

[0102] The couplant dipping control module 05 is used to send the robotic arm control instruction to the multi-axis robotic arm, and the multi-axis robotic arm moves to the couplant container according to the robotic arm control instruction to dip the couplant along a preset trajectory;

[0103] The robotic arm motion control module 06 is used to control the multi-axis robotic arm to move to a given coordinate position at a first speed after dipping the couplant until the distance sensor on the multi-axis robotic arm detects that the backfat B-ultrasound probe mounted on the top of the multi-axis robotic arm reaches the point on the back of the acquisition object where backfat measurement is required, and then control the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object;

[0104] The backfat B-ultrasound data acquisition module 07 is used to repeatedly acquire backfat B-ultrasound data a set number of times after the backfat B-ultrasound probe reaches the backfat measurement point, and transmit the acquired B-ultrasound data to the main control cabinet in the form of a video.

[0105] In this embodiment, a model training module 08 is further included for training the backfat measurement point recognition model; the model training module 8 includes:

[0106] The image loading sub-module 81 is used to obtain the back image data of the acquisition object;

[0107] The image data annotation sub-module 82 is used to annotate the image data of the back of the acquisition object;

[0108] The model loading sub-module 83 is used to load the YoLov4-tiny model for model training;

[0109] The model testing sub-module 84 is used to test the trained model using a test set;

[0110] The test evaluation sub-module 85 is used to evaluate the test results, and if the set requirements are met, the training is ended.

[0111] In this embodiment, the robotic arm motion control module 06 is further used to continue to control the multi-axis robotic arm to move after the multi-axis robotic arm moves at a second speed until it fits the skin of the acquisition object, so that the skin of the acquisition object in contact is pressed down by a preset distance.

[0112] In this embodiment, a robotic arm position adjustment module 09 is further included for determining whether the position of the acquisition object has moved. If the position of the acquisition object has moved, the multi-axis robotic arm is positionally adjusted according to the movement of the acquisition object so that the backfat B-ultrasound probe continues to be in full contact with the back of the acquisition object.

[0113] In this embodiment, in the backfat B-ultrasound data acquisition module 07, when the backfat B-ultrasound data acquisition reaches the set number of times, the backfat B-ultrasound probe is controlled to stop data acquisition; if the acquisition object changes the feeding position, the backfat measurement and acquisition of the acquisition object are restarted.

[0114] It further includes a data storage module 10, which is used to locally store the acquired B-ultrasound data and generate a chart including the measurement date, ear tag number, and B-ultrasound image content.

[0115] It should be noted that for the information interaction, execution process, etc. between the above system modules, since they are based on the same concept as the method embodiment in Embodiment 1 of the present application, the technical effects brought by them are the same as those of the method embodiment of the present application. For the specific content, reference can be made to the description in the method embodiment shown above in the present application, and details will not be repeated here.

[0116] Embodiment 3

[0117] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which program codes of a veterinary backfat acquisition method are stored, and the program codes include instructions for executing the veterinary backfat acquisition method in Embodiment 1 or any possible implementation manner thereof.

[0118] The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrating one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state disk (SSD)), etc.

[0119] Embodiment 4

[0120] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0121] The processor and the memory complete communication with each other through a bus; the memory stores program instructions executable by the processor, and the processor can execute the veterinary backfat acquisition method in Embodiment 1 or any possible implementation manner thereof by calling the program instructions.

[0122] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor, which is implemented by reading the software code stored in the memory. The memory can be integrated in the processor or can exist independently outside the processor.

[0123] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.

[0124] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program code executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the present invention is not limited to any specific combination of hardware and software.

[0125] Although the present invention has been described in detail above with general descriptions and specific embodiments, based on the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of protection required by the present invention.

Claims

1. A method for collecting backfat of animals, characterized in that, Including: S1. During the feeding process of the collection object, the electronic ear tag reader is used to identify the electronic ear tag on the ear of the collection object, and the number of the electronic ear tag of the collection object is obtained; S2. When the main control cabinet receives the number of the electronic ear tag of the collection object, it starts the depth camera to collect images of the collection object, and uses the backfat measurement point recognition model to locate the coordinates of the backfat measurement points on the collected images; S3. According to the coordinate positioning value and the distance value from the depth camera to the back of the collection object, a robotic arm control instruction is generated, and the robotic arm control instruction is sent to the multi-axis robotic arm. The multi-axis robotic arm moves to the coupling agent container to dip the coupling agent according to the robotic arm control instruction along the preset trajectory; S4. After dipping the coupling agent, control the multi-axis robotic arm to move to the given coordinate position at the first speed until the distance sensor on the top of the multi-axis robotic arm detects that the backfat B-ultrasound probe installed on the top of the multi-axis robotic arm reaches the point on the back of the collection object where backfat measurement is required, and then control the multi-axis robotic arm to move at the second speed until it fits the skin of the collection object; S5. After the backfat B-ultrasound probe reaches the backfat measurement point, collect the backfat B-ultrasound data repeatedly according to the set number of times, and transmit the collected B-ultrasound data to the main control cabinet in the form of a video.

2. The method for collecting backfat of animals according to claim 1, characterized in that In step S2, the training process of the backfat measurement point recognition model includes: Obtaining the back image data of the collection object; Annotating the image data of the back of the collection object; Loading the YoLov4-tiny model for model training; Testing the trained model with the test set; Evaluating the test results, and if the set requirements are met, end the training.

3. The method for collecting backfat of livestock according to claim 1, characterized in that In step S4, after controlling the multi-axis robotic arm to move at the second speed until it fits the skin of the collection object, continue to control the multi-axis robotic arm to move so that the skin of the fitted collection object is pressed down by a preset distance.

4. A method for collecting backfat of animals according to claim 2, characterized in that, Step S4 also includes judging whether the position of the collection object has moved. If the position of the collection object has moved, adjust the position of the multi-axis robotic arm according to the movement situation of the collection object so that the backfat B-ultrasound probe continues to be completely attached to the back of the collection object.

5. A method for collecting backfat of animals according to claim 1, characterized in that, In step S5, when the backfat B-ultrasound data is collected up to the set number of times, control the backfat B-ultrasound probe to stop data collection; if the collection object changes the feeding position, re-measure the backfat of the collection object; In step S5, the collected B-ultrasound data is locally stored, and a chart containing the measurement date, ear tag number, and B-ultrasound image content is generated.

6. A veterinary backfat collection system, characterized in that, Including: An ear tag number acquisition module, which is used to identify the electronic ear tag on the ear of the collection object through an electronic ear tag reader during the feeding process of the collection object, and obtain the number of the electronic ear tag of the collection object; An image acquisition module, which is used to start the depth camera to collect images of the collection object when the main control cabinet receives the number of the electronic ear tag of the collection object; A coordinate positioning module, which is used to perform coordinate positioning on the backfat measurement points on the acquired image by using a backfat measurement point recognition model; A robotic arm control instruction generation module, which is used to generate a robotic arm control instruction according to the coordinate positioning value and the back distance value from the depth camera to the back of the acquisition object; A coupling agent dipping control module, which is used to send the robotic arm control instruction to a multi-axis robotic arm, and the multi-axis robotic arm moves to a coupling agent container to dip the coupling agent according to the robotic arm control instruction along a preset trajectory; A robotic arm motion control module, which is used to control the multi-axis robotic arm to move to a given coordinate position at a first speed after dipping the coupling agent until the distance sensor on the top of the multi-axis robotic arm detects that the backfat B-ultrasound probe mounted on the top of the multi-axis robotic arm reaches the point on the back of the acquisition object where backfat measurement is required, and then control the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object; A backfat B-ultrasound data acquisition module, which is used to repeatedly acquire backfat B-ultrasound data a set number of times after the backfat B-ultrasound probe reaches the backfat measurement point, and transmit the acquired B-ultrasound data to the main control cabinet in the form of a video.

7. The veterinary backfat collection system according to claim 6, characterized in that, It further includes a model training module, which is used for training the backfat measurement point recognition model; the model training module includes: An image loading sub-module, which is used to obtain the back image data of the acquisition object; An image data annotation sub-module, which is used to annotate the image data of the back of the acquisition object; A model loading sub-module, which is used to load the YoLov4-tiny model for model training; A model testing sub-module, which is used to test the trained model by using a test set; A test evaluation sub-module, which is used to evaluate the test result, and if the set requirements are met, end the training.

8. The veterinary backfat collection system according to claim 6, characterized in that, The robotic arm motion control module is further used to control the multi-axis robotic arm to move at a second speed until it fits the skin of the acquisition object, and then continue to control the multi-axis robotic arm to move so that the skin of the acquisition object in contact is pressed down by a preset distance.

9. The veterinary backfat collection system according to claim 7, characterized in that, It further includes a robotic arm position adjustment module, which is used to judge whether the position of the acquisition object has moved. If the position of the acquisition object has moved, the multi-axis robotic arm is adjusted according to the movement situation of the acquisition object so that the backfat B-ultrasound probe continues to be completely in contact with the back of the acquisition object.

10. The veterinary backfat collection system according to claim 6, characterized in that, In the backfat B-ultrasound data acquisition module, when the acquisition of backfat B-ultrasound data reaches the set number of times, control the backfat B-ultrasound probe to stop data acquisition work; if the acquisition object changes its feeding position, re-perform backfat measurement acquisition on the acquisition object; It further includes a data storage module, which is used to locally store the acquired B-ultrasound data and generate a chart containing the measurement date, ear tag number, and B-ultrasound image content.

Images