CN112734730B - Livestock quantity identification method, device, equipment and storage medium - Google Patents

Livestock quantity identification method, device, equipment and storage medium Download PDF

Info

Publication number
CN112734730B
CN112734730B CN202110033017.7A CN202110033017A CN112734730B CN 112734730 B CN112734730 B CN 112734730B CN 202110033017 A CN202110033017 A CN 202110033017A CN 112734730 B CN112734730 B CN 112734730B
Authority
CN
China
Prior art keywords
livestock
model
identifying
video
photographing
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.)
Active
Application number
CN202110033017.7A
Other languages
Chinese (zh)
Other versions
CN112734730A (en
Inventor
张玉良
陶江辉
杜飞
蒋贞杰
陈烨
彭佳勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Muyuan Foods Co Ltd
Original Assignee
Muyuan Foods Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Muyuan Foods Co Ltd filed Critical Muyuan Foods Co Ltd
Priority to CN202110033017.7A priority Critical patent/CN112734730B/en
Publication of CN112734730A publication Critical patent/CN112734730A/en
Application granted granted Critical
Publication of CN112734730B publication Critical patent/CN112734730B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30242—Counting objects in image
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry

Abstract

The application discloses a method, a device, equipment and a storage medium for identifying the quantity of livestock, wherein the method comprises the steps of acquiring the condition that a livestock transport vehicle is stopped on a wagon balance, and photographing the livestock; carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number; acquiring the sliding condition of livestock from a slideway, and shooting a video of the livestock when the livestock slides down; identifying the number of livestock in the video to obtain a second number of livestock; when the number of the first livestock is equal to the number of the second livestock, the final number of the livestock is determined, so that the accuracy of identification data can be improved, the labor cost is reduced, the biosafety risk is reduced, and unmanned operation of a sales link is realized by using the method. The livestock quantity identification device, the equipment and the storage medium have the same advantages as the livestock quantity identification method.

Description

Livestock quantity identification method, device, equipment and storage medium
Technical Field
The invention belongs to the technical field of livestock breeding, and particularly relates to a method, a device, equipment and a storage medium for identifying the quantity of livestock.
Background
The livestock breeding industry is labor intensive industry, in the prior art, when the quantity of livestock is required to be checked, one is in a manual mode, but is time-consuming and labor-consuming, depends on personal quality of operators, is not easy to check the quantity of livestock correctly due to the influence of various factors, and the other is to identify the quantity of livestock by relying on an automation technology, wherein the automatic technology adopts a target detection method which comprises two types, namely, edge detection is carried out through a traditional opencv to obtain a target outline, but the method is difficult to adapt to the requirement of complex scene target detection, and the other is a deep learning method, but mainly aims at pictures of pedestrians, vehicles and the like, has lower accuracy and is not suitable for being applied to the field of livestock quantity identification.
Disclosure of Invention
In order to solve the problems, the invention provides a method, a device, equipment and a storage medium for identifying the quantity of livestock, which can improve the accuracy of identification data, reduce labor cost and biological safety risk and realize unmanned operation in a sales link.
The invention provides a livestock quantity identification method, which comprises the following steps:
acquiring the situation that the livestock carrier vehicle is stopped on the wagon balance, and photographing livestock;
carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number;
acquiring the sliding condition of livestock from a slideway, and shooting a video of the livestock when the livestock slides down;
identifying the number of livestock in the video to obtain a second number of livestock;
and when the first livestock number and the second livestock number are equal, determining the final livestock number.
Preferably, in the method for identifying the number of livestock, the identifying the number of livestock on the photo obtained by photographing includes:
and (5) carrying out livestock quantity identification on the photo obtained by photographing by using the trained mrcnn model.
Preferably, in the method for identifying the number of animals, the identifying the number of animals in the video to obtain the second number of animals includes:
and identifying the number of livestock in the video by using the trained mrcnn model and the tracking model.
Preferably, in the method for identifying the number of livestock, after the photographing the livestock, the method further comprises:
labeling the obtained photo, and taking the photo as a sample of an mrcnn model for deep learning;
expanding the sample by utilizing data enhancement to obtain a sample set for model training;
and adjusting the pictures in the sample set to the same size, acquiring real BBox position information of the pictures, obtaining predicted BBox information through an mrnn model, comparing the real BBox position information with the predicted BBox information, taking the sum of classification loss, confidence loss, location loss and iou loss as a final loss, and updating the weight by using a back propagation algorithm until the mrnn model converges or iteration termination conditions are met, so as to obtain the trained mrnn model.
Preferably, in the livestock quantity identification method, the expanding the sample by using data enhancement is:
the sample is expanded by means of mixup, flipping, translation, random clipping, and random noise addition.
Preferably, in the method for identifying the number of livestock, the livestock is photographed by using a visible light camera or an infrared camera, and the video when the livestock slides down is photographed by using the visible light camera or the infrared camera.
The invention provides a livestock quantity recognition device, which comprises:
the photographing component is used for obtaining the condition that the livestock transport vehicle is stopped on the wagon balance and photographing livestock;
the first livestock number identification component is used for identifying the number of the livestock to the photo obtained by photographing to obtain the first livestock number;
the video shooting component is used for acquiring the sliding condition of the livestock from the slideway and shooting videos of the livestock when the livestock slides down;
a second livestock number identification unit for identifying the number of livestock in the video to obtain a second livestock number;
and the livestock quantity determining component is used for determining the final livestock quantity when the first livestock quantity and the second livestock quantity are equal.
Preferably, in the above-mentioned livestock number identifying device, the first livestock number identifying unit is specifically configured to identify the number of livestock on the photograph obtained by taking the photograph using a trained mrcnn model.
The present invention provides a computer device comprising:
a memory for storing a computer program;
a processor for carrying out the steps of the method for identifying the number of animals as defined in any one of the preceding claims when executing said computer program.
The present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method for identifying the number of livestock as described in any of the above.
As can be seen from the above description, the method for identifying the number of livestock provided by the present invention includes firstly acquiring the situation that the livestock transporter is stopped on the wagon balance, and photographing the livestock; carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number; then acquiring the sliding condition of livestock from the slideway, and shooting a video of the livestock when sliding down; identifying the number of livestock in the video to obtain a second number of livestock; and finally, when the number of the first livestock is equal to the number of the second livestock, determining the final number of the livestock, and calculating the number in two ways can be adopted, so that the number of the livestock can be ensured to be calculated more accurately, the accuracy of identification data is improved, personnel participation is not needed in the whole process, the labor cost can be reduced, the biosafety risk is reduced, and unmanned operation of a sales link is realized. The livestock quantity identification device, the equipment and the storage medium provided by the invention have the same advantages as the method.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an embodiment of a method for identifying a number of livestock according to the present invention;
fig. 2 is a schematic view of an embodiment of a livestock quantity identification device provided by the invention;
fig. 3 is a schematic diagram of an embodiment of a computer device according to the present invention.
Detailed Description
The core of the invention is to provide a method, a device, equipment and a storage medium for identifying the quantity of livestock, which can improve the accuracy of identification data, reduce labor cost and biological safety risk, and realize unmanned operation of a sales link.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An embodiment of a method for identifying the number of livestock provided by the present invention is shown in fig. 1, and fig. 1 is a schematic diagram of an embodiment of a method for identifying the number of livestock provided by the present invention, where the method may include the following steps:
s1: acquiring the situation that the livestock carrier vehicle is stopped on the wagon balance, and photographing livestock;
it should be noted that, can install the camera above the wagon balance, after the livestock transport vechicle stops on the wagon balance and stops steadily, just can trigger PLC, this PLC can issue the instruction, triggers the camera SDK and shoots the livestock to upload the photo of taking to the server.
S2: carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number;
specifically, but not limited to, the trained mrcnn model is used to identify the number of the livestock in the photographed photo, so that the first number of the livestock is obtained through the photo, and the first number of the livestock is temporarily stored.
S3: acquiring the sliding condition of livestock from a slideway, and shooting a video of the livestock when the livestock slides down;
it should be noted that, in the occasion such as selling livestock, need to catch up with the slide with livestock, this slide top can install the camera, gets to this slide after the livestock transport vechicle leaves the wagon balance, and the staff is caught up with livestock, catches up with the slide with it, and the video acquisition switch obtains triggering this moment, drives the camera SDK and records the video to upload the video of recording to the server.
S4: identifying the number of livestock in the video to obtain a second number of livestock;
specifically, but not limited to, the number of animals in the video may be identified using a trained mrcnn model and a tracking model, which may preferably be a deepsort tracking model, such that a second number of animals may be obtained from the video and temporarily stored.
S5: and when the first livestock number and the second livestock number are equal, determining the final livestock number.
That is, the number of livestock is obtained by the above steps in two ways, when the two are equal, the number calculation can be considered to be correct, and the number is taken as the final livestock number, so that the manual counting is not needed, the workload is greatly reduced, the counting is more accurate, and in addition, when the two livestock numbers are unequal, the picture and the video are sent to staff for checking.
As can be seen from the above description, in the embodiment of the method for identifying the number of livestock provided by the present invention, the method includes taking a picture of the livestock by first acquiring a situation that the livestock transporter is stopped on a wagon balance; carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number; then acquiring the sliding condition of livestock from the slideway, and shooting a video of the livestock when sliding down; identifying the number of livestock in the video to obtain a second number of livestock; and finally, when the number of the first livestock is equal to the number of the second livestock, determining the number of the final livestock, and calculating the number in two ways, so that the number of the livestock can be ensured to be more accurate, the accuracy of identification data is improved, personnel participation is not needed in the whole process, the labor cost can be reduced, the biosafety risk is reduced, and unmanned operation of a sales link is realized.
In a specific embodiment of the above method for identifying the number of livestock, after photographing the livestock, the method further includes:
labeling the obtained photo, and taking the photo as a sample of an mrcnn model for deep learning;
expanding the sample by utilizing data enhancement to obtain a sample set for model training;
and adjusting the pictures in the sample set to the same size, acquiring real BBox position information of the pictures, obtaining predicted BBox information through the mrcnn model, comparing the real BBox position information with the predicted BBox information, taking the sum of classification loss, confidence loss, location loss and iou loss as a final loss, and updating the weight by using a back propagation algorithm until the mrcnn model converges or an iteration termination condition is met, so as to obtain the trained mrcnn model.
In this embodiment, a specific scheme of model training is described, because the mrnn model based on deep learning needs a certain amount of diversified samples, and the model can be used as knowledge to learn by manually marking the outline of livestock on a visible light image for the deep neural network model, after the mrnn model is trained, a photo is provided as an input of the model, after the mrnn model is processed, the number of livestock in the photo can be obtained, and of course, the model can be trained only in advance, and is not trained before each recognition. In the above embodiment, the augmentation of the sample utilization data enhancement may be specifically: the sample is expanded by means of mixup, overturn, translation, random clipping and random noise addition, so that more samples can be provided, and the model is more comprehensively trained.
In another specific embodiment of the above method for identifying the number of livestock, the livestock is photographed by using a visible light camera or an infrared camera, and the video of the livestock sliding down is photographed by using the visible light camera or the infrared camera. It should be noted that, when the quantity of livestock is identified at night, shadows appear sometimes to cause inaccurate identification, so that single-channel pictures shot by an infrared camera can be adopted at night for identification, the model is retrained, and the detection effect of the model can be further improved.
In summary, the method for identifying the number of livestock provided by the invention can be described by taking pigs as an example, but the method can also be applied to identifying the number of other livestock such as cattle or sheep, and the method is not limited herein. When the pig transporting vehicle reaches the wagon balance, triggering a shooting instruction, shooting a photo, uploading the photo to a cloud server, calling a related algorithm to calculate the head number of the pig, shooting a video when the pig slides down a slideway, uploading the video to the cloud server, calling the related algorithm to calculate the head number of the pig, checking the head number of the pig calculated in the two modes, and when the two modes are equal, recording the head number as the final correct head number, and if the two modes are unequal, manually counting.
An embodiment of an apparatus for identifying a number of livestock provided by the present invention is shown in fig. 2, and fig. 2 is a schematic diagram of an embodiment of an apparatus for identifying a number of livestock provided by the present invention, where the apparatus includes:
the photographing component 201 is configured to obtain a situation that the livestock carrier is stopped on the wagon balance, photograph the livestock, and it is required to be noted that a camera may be installed above the wagon balance, after the livestock carrier is stopped on the wagon balance, the PLC may be triggered, and the PLC may issue an instruction to trigger the camera SDK to photograph the livestock and upload the photographed photograph to the server;
a first livestock number identifying unit 202, configured to identify the number of livestock for the photo obtained by photographing, to obtain a first livestock number, specifically, but not limited to, using a trained mrcnn model to identify the number of livestock for the photo obtained by photographing, so that the first livestock number is obtained by the photo, and is temporarily stored;
the video shooting part 203 is used for acquiring the condition that livestock slides down from the slideway, shooting a video when the livestock slides down, and it is required to drive the livestock down the slideway in the occasions such as selling the livestock, wherein a camera can be arranged above the slideway, when the livestock transport vehicle leaves a wagon balance and reaches the slideway, a worker drives the livestock down the slideway, at the moment, a video acquisition switch is triggered, the camera SDK is driven to record the video, and the recorded video is uploaded to a server;
a second animal number identifying component 204, configured to identify the number of animals in the video, to obtain a second animal number, and specifically, may, but not limited to, identify the number of animals in the video using a trained mrcnn model and a tracking model, where the tracking model may be preferably a deepsorts tracking model, so that the second animal number can be obtained through the video and temporarily stored;
the animal number determining unit 205 is configured to determine the final animal number when the first animal number and the second animal number are equal, that is, the animal number is obtained by two methods, when the first animal number and the second animal number are equal, the number calculation is considered to be correct, and the number is regarded as the final animal number, so that the manual count is not needed, the workload is greatly reduced, the count is more accurate, and in addition, when the two animal numbers are unequal, the picture and the video are sent to the staff for verification.
The device can calculate the quantity in two ways, so that more accurate calculation of the quantity of livestock can be ensured, the accuracy of identification data is improved, no personnel participation is needed in the whole process, the labor cost can be reduced, the biosafety risk is reduced, and unmanned operation of a sales link is realized.
In another specific embodiment of the livestock quantity identifying device, the photographing component may be a visible light camera or an infrared camera, and the video photographing component may be a visible light camera or an infrared camera. It should be noted that, when the quantity of livestock is identified at night, shadows appear sometimes to cause inaccurate identification, so that single-channel pictures shot by an infrared camera can be adopted at night for identification, the model is retrained, and the detection effect of the model can be further improved.
Fig. 3 is a schematic diagram of an embodiment of a computer device according to the present invention, where the computer device includes:
a memory 301 for storing a computer program;
a processor 302 for implementing the steps of the method for identifying the number of animals as defined in any one of the above, when executing a computer program.
In an embodiment of the computer readable storage medium provided by the invention, a computer program is stored on the computer readable storage medium, and the computer program realizes the steps of any one of the livestock quantity identification methods when being executed by a processor.
In summary, according to the scheme, the number is identified once above the wagon balance and the number is identified once above the slideway, and the correct number is checked and determined through the two number checks, so that the sales link is unmanned, the number accuracy is improved, and the cost of manual counting is reduced.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use 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 (5)

1. A method for identifying the number of livestock, comprising:
acquiring the situation that the livestock carrier vehicle is stopped on the wagon balance, and photographing livestock;
carrying out livestock number identification on the photo obtained by photographing to obtain a first livestock number;
acquiring the sliding condition of livestock from a slideway, and shooting a video of the livestock when the livestock slides down;
identifying the number of livestock in the video to obtain a second number of livestock;
when the first livestock number is equal to the second livestock number, determining the final livestock number;
the step of identifying the number of the livestock on the photo obtained by photographing, the step of obtaining the first number of the livestock comprises the following steps:
carrying out livestock quantity identification on the photo obtained by shooting by using a trained mrcnn model;
the identifying the number of animals in the video, the obtaining a second number of animals includes:
identifying the number of livestock in the video by using the trained mrcnn model and tracking model;
after the photographing of the livestock, the method further comprises:
labeling the obtained photo, and taking the photo as a sample of an mrcnn model for deep learning;
expanding the sample by utilizing data enhancement to obtain a sample set for model training;
the pictures in the sample set are adjusted to the same size, real BBox position information of the pictures is obtained, predicted BBox information is obtained through an mrcnn model, the real BBox position information is compared with the predicted BBox information, the sum of classification loss, confidence loss, location loss and iou loss is taken as a final loss, and a counter-propagation algorithm is utilized to update weights until the mrcnn model converges or iteration termination conditions are met, so that the trained mrcnn model is obtained;
the expanding of the sample with data enhancement is:
the sample is expanded by means of mixup, flipping, translation, random clipping, and random noise addition.
2. The method for recognizing the number of livestock according to claim 1, wherein the livestock is photographed by a visible light camera or an infrared camera, and the video of the livestock sliding down is photographed by the visible light camera or the infrared camera.
3. An apparatus for identifying the number of livestock, comprising:
the photographing component is used for obtaining the condition that the livestock transport vehicle is stopped on the wagon balance and photographing livestock;
the first livestock number identification component is used for identifying the number of the livestock to the photo obtained by photographing to obtain the first livestock number;
the video shooting component is used for acquiring the sliding condition of the livestock from the slideway and shooting videos of the livestock when the livestock slides down;
a second livestock number identification unit for identifying the number of livestock in the video to obtain a second livestock number;
a livestock number determining unit configured to determine a final livestock number when the first livestock number and the second livestock number are equal;
the first livestock number identification component is specifically used for carrying out livestock number identification on the photo obtained by shooting by using the trained mrcnn model;
the second livestock number identification component is specifically configured to identify the number of livestock in the video by using a trained mrnnn model and a tracking model;
further comprises:
and the mrnn model training component is used for marking the obtained photo, expanding the sample by means of mixup, turnover, translation, random cutting and random noise addition to obtain a sample set for model training, adjusting the picture in the sample set to the same size, acquiring real BBox position information of the picture, obtaining predicted BBox information through the mrnn model, comparing the real BBox position information with the predicted BBox information, taking the sum of classification loss, confidence loss, location loss and iou loss as a final loss, and updating the weight by using a back propagation algorithm until the mrnn model converges or meets the iteration termination condition to obtain the trained mrnn model.
4. A computer device, comprising:
a memory for storing a computer program;
processor for implementing the steps of the method for identifying the number of animals according to any one of claims 1 to 2 when executing said computer program.
5. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for identifying the number of animals according to any one of claims 1 to 2.
CN202110033017.7A 2021-01-11 2021-01-11 Livestock quantity identification method, device, equipment and storage medium Active CN112734730B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110033017.7A CN112734730B (en) 2021-01-11 2021-01-11 Livestock quantity identification method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110033017.7A CN112734730B (en) 2021-01-11 2021-01-11 Livestock quantity identification method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112734730A CN112734730A (en) 2021-04-30
CN112734730B true CN112734730B (en) 2023-07-28

Family

ID=75590259

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110033017.7A Active CN112734730B (en) 2021-01-11 2021-01-11 Livestock quantity identification method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112734730B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113283322A (en) * 2021-05-14 2021-08-20 柳城牧原农牧有限公司 Livestock trauma detection method, device, equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945456A (en) * 2017-12-18 2018-04-20 翔创科技（北京）有限公司 Livestock monitoring system
CN109509073A (en) * 2019-01-14 2019-03-22 上海睿畜电子科技有限公司 A kind of intelligence sells pig system and control method
WO2020125057A1 (en) * 2018-12-20 2020-06-25 北京海益同展信息科技有限公司 Livestock quantity identification method and apparatus
CN111369378A (en) * 2020-02-25 2020-07-03 成都睿畜电子科技有限公司 Live pig supervision method and system based on computer vision recognition

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110455413B (en) * 2019-07-09 2021-01-15 中国科学院西安光学精密机械研究所 Temperature monitoring device and monitoring method for medium-large livestock farm
CN111008561B (en) * 2019-10-31 2023-07-21 重庆小雨点小额贷款有限公司 Method, terminal and computer storage medium for determining quantity of livestock
CN111680551A (en) * 2020-04-28 2020-09-18 平安国际智慧城市科技股份有限公司 Method and device for monitoring livestock quantity, computer equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945456A (en) * 2017-12-18 2018-04-20 翔创科技（北京）有限公司 Livestock monitoring system
WO2020125057A1 (en) * 2018-12-20 2020-06-25 北京海益同展信息科技有限公司 Livestock quantity identification method and apparatus
CN109509073A (en) * 2019-01-14 2019-03-22 上海睿畜电子科技有限公司 A kind of intelligence sells pig system and control method
CN111369378A (en) * 2020-02-25 2020-07-03 成都睿畜电子科技有限公司 Live pig supervision method and system based on computer vision recognition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Efficient Herd Outlier Detection in Livestock Monitoring System Based on Density Based Spatial Clustering;ZOOL HILMI ISMAIL;《SPECIAL SECTION ON NEW TECHNOLOGIES FOR SMART FARMING 4.0: RESEARCH CHALLENGES AND OPPORTUNITIES》;1-9 *
浅谈村防疫员在生猪养殖环节病死猪无害化处理工作中的职责;张庆凯;;山东畜牧兽医(04);全文 *

Also Published As

Publication number Publication date
CN112734730A (en) 2021-04-30

Similar Documents

Publication Publication Date Title
US11216690B2 (en) System and method for performing image processing based on a damage assessment image judgement model
US11010838B2 (en) System and method for optimizing damage detection results
CN108960737B (en) Automatic warehouse inspection system and method based on machine vision
CN113038018B (en) Method and device for assisting user in shooting vehicle video
CN107680080B (en) Sample library establishing method and checking method for livestock, storage medium and electronic equipment
CN104919794A (en) Method and system for metadata extraction from master-slave cameras tracking system
EP3531343A2 (en) Method and apparatus for human behavior recognition, and storage medium
CN111310596A (en) Animal diseased state monitoring system and method
US11468683B2 (en) Population density determination from multi-camera sourced imagery
CN113435355A (en) Multi-target cow identity identification method and system
CN111161265A (en) Animal counting and image processing method and device
CN112734730B (en) Livestock quantity identification method, device, equipment and storage medium
CN110991222B (en) Object state monitoring and sow oestrus monitoring method, device and system
Noe et al. Automatic detection and tracking of mounting behavior in cattle using a deep learning-based instance segmentation model
CN110427810B (en) Video damage assessment method, device, shooting end and machine-readable storage medium
CN112150467A (en) Method, system and device for determining quantity of goods
CN116110127A (en) Multi-linkage gas station cashing behavior recognition system
CN115147782A (en) Dead animal identification method and device
CN114373113A (en) Wild animal species image identification system based on AI technology
CN110008803B (en) Pedestrian detection method, device and equipment for training detector
KR20230104969A (en) System and method for nose-based companion animal identification
Bastiaansen et al. Continuous real-time cow identification by reading ear tags from live-stream video
Kawano et al. Toward building a data-driven system for detecting mounting actions of black beef cattle
CN113837087A (en) Animal target detection system and method based on YOLOv3
CN112560969B (en) Image processing method for human weight recognition, model training method and device

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
GR01 Patent grant
GR01 Patent grant