Method and system for identifying individual identities of sheep flock in sheep house based on YOLOv4

A technology for identification and flocking, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of low living density, high breeding density, and small activity range of cattle, and achieve small system scale and strong identification Accurate, versatile effect

Pending Publication Date: 2022-05-24
INNER MONGOLIA AGRICULTURAL UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Cows have a small living density, a small range of activities, and less mutual occlusion, while the breeding density in sheep houses is high, and the amount of activity is large, and mutual occlusion is serious; Liu Bing et al. published a patent "A Yolov4-Based Chicken Farm Raising Chicken Recognition Algorithm" proposed a detection method targeting farmed chickens in farms, but did not identify each individual chicken

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for identifying individual identities of sheep flock in sheep house based on YOLOv4
  • Method and system for identifying individual identities of sheep flock in sheep house based on YOLOv4
  • Method and system for identifying individual identities of sheep flock in sheep house based on YOLOv4

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] like figure 1 As shown, the embodiment of the present invention provides a method for identifying individual flocks in a sheep barn based on the YOLOv4 neural network model, comprising the following steps:

[0023] Step S1: collect the facial information of each sheep in the flock, preprocess the facial image, mark the sheep's face with a labeling frame, obtain a data set, and divide it into a training set and a test set;

[0024] Step S2: Build a sheep facial recognition neural network model based on YOLOv4, wherein the sheep facial recognition neural network model includes: Input, Backbone, Neck and Head: Backbone is used as the backbone feature extraction network, and CSPnet is added on the basis of Darknet53 to construct CSPDarknet53 , and uses the Mish activation function; Neck is used as the enhanced feature extraction network, and SSP and PANet are used to extract contextual features and parameter aggregation respectively; Head uses the Kmeans++ algorithm to reca...

Embodiment 2

[0070] like Figure 8 As shown, an embodiment of the present invention provides a system for individual identification of sheep in a sheep barn based on a YOLOv4 neural network model, including the following modules:

[0071] The acquisition data set module 41 is used for collecting the facial information of each sheep in the flock, preprocessing the facial pictures, and labeling the sheep faces with a labeling frame to obtain a data set, which is divided into a training set and a test set;

[0072] The building model module 42 is used to build a sheep facial recognition neural network model based on YOLOv4, wherein the sheep facial recognition neural network model includes: Input, Backbone, Neck and Head: Backbone is used as the backbone feature extraction network, on the basis of Darknet53 Add CSPnet to build CSPDarknet53, and use the Mish activation function; Neck is used as an enhanced feature extraction network, and SSP and PANet are used to extract contextual features an...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a YOLOv4 neural network model-based method and system for identifying the individual identity of a sheep flock in a sheep house, and the method comprises the steps: S1, collecting the face information of a sheep, carrying out the preprocessing of a face image, carrying out the labeling of a sheep face through a labeling box, obtaining a data set, and dividing the data set into a training set and a test set; s2, constructing a sheep face recognition neural network model based on YOLOv4, wherein the sheep face recognition neural network model comprises Input, Backbone, Neck and Head; s3, constructing a loss function, carrying out pre-training by using sheep face data, training the loss function by using the training set, taking model parameters obtained after pre-training as initial parameters of the sheep face recognition neural network model, and training the sheep face recognition neural network model by using the training set; and inputting the test set into the trained YOLOv4 neural network model, and evaluating the performance of the neural network model. The method provided by the invention adopts a non-contact identification method, and is low in cost, high in precision, safe and effective, so that the problems of label falling and easy stress of the sheep are avoided.

Description

technical field [0001] The invention relates to the field of modern intelligent animal husbandry, in particular to a method and system for individual identification of sheep in a sheep barn based on a YOLOv4 neural network model. Background technique [0002] In recent years, domestic and foreign animal husbandry is developing from a traditional model to an intelligent, precise and large-scale development. As an important livestock, sheep are an important part of today's animal husbandry. The identification of individual sheep has received extensive attention as an important aspect of large-scale and precise sheep farming. At present, the main sheep identification method in the sheep farming industry is the contact identification method, that is, the method of manual labeling or ear tagging. The most common sheep identification method used in large-scale large-scale farms is the radio frequency-based ear tag method. With the increase of breeding scale, the phenomenon of e...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/20G06N3/04G06N3/08G06V10/80G06V10/774G06V10/40
CPCG06N3/08G06N3/045G06F18/253G06F18/214
Inventor 于文波穆昕钰张春慧宣传忠张永安马彦华姬振生武佩
Owner INNER MONGOLIA AGRICULTURAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products