Sow estrus behavior detection method based on machine vision

A technology of sow estrus and machine vision, which is applied to instruments, computer components, character and pattern recognition, etc., can solve the problems that scholars have rarely studied, and achieve the effect of reducing labor intensity and increasing pig farm income

Active Publication Date: 2018-10-30
SOUTH CHINA AGRI UNIV
View PDF5 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the research papers on sow estrus are in the field of animal science, but in computer vision, there are few domestic and foreign scholars.

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
  • Sow estrus behavior detection method based on machine vision
  • Sow estrus behavior detection method based on machine vision
  • Sow estrus behavior detection method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] This embodiment discloses a method for detecting estrus behavior of sows based on machine vision, such as figure 1 As shown, the steps are as follows:

[0041] Step S1. Take multiple images of the sow when it is crawling through the camera arranged in the sow’s living area, and mark the crawling position of the sow in the image, and each image is marked by the crawling position of the sow The first training set is obtained, and the deep learning model is trained through the first training set to obtain the climbing behavior judgment model; wherein, in this step, when the first training set trains the deep learning model, it also includes the following steps: training sample Pre-processing is performed before inputting the deep learning model, specifically: each image in the first training set is first compressed through a median filter; the training sample image data is enhanced and then input to the deep learning model; the training sample image data is enhanced The proce...

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 discloses a sow estrus behavior detection method based on machine vision. Firstly, a mounting behavior judgment model is trained through sow life videos; displacement moving amount information of multiple estrus sows and proximity degrees to boars in cases of boar seduction are obtained through the sow life videos, and mounting behaviors of a certain number of estrus sows and frequency of the mounting behaviors are judged by the mounting behavior judgment model; the above obtained information of all the estrus sows are used as all training samples to train a neural network modelto obtain a sow estrus early-warning model; and when sow estrus behaviors need to be detected, displacement moving amount information of a sow, frequency of sow mounting behaviors and a proximity degree to a boar in a case of boar seduction are obtained through a sow video, and the above information is input into the sow estrus early-warning model to judge whether the sow is in estrus. According to the method, the estrus behaviors of the sow can be detected quickly and accurately, and pig farm incomes can be increased while labor intensity is alleviated.

Description

Technical field [0001] The invention relates to the technical field of video image processing, in particular to a method for detecting estrus behavior of sows based on machine vision. Background technique [0002] The timely detection of the sow's estrus behavior can more accurately fertilize it, and avoid missing the fertilization time due to untimely detection, which is very important to the income of the pig farm. At present, the domestic method of manual observation by skilled workers is used to check whether sows are in heat. These methods not only consume a lot of labor time and energy, but also consume a lot of mature workers' training, and the observation data obtained is highly subjective, and it is impossible to accurately and objectively find out which sow is in heat. With the rapid application and development of high-definition video network monitoring technology and image processing and analysis technology, the life of sows can be observed around the clock through s...

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): G06K9/00G06K9/46G06K9/34G06K9/62A01K29/00
CPCA01K29/005G06V20/10G06V10/267G06V10/44G06F18/2411
Inventor 肖德琴李泽森蔡家豪杨秋妹殷建军潘春华冯健昭张昌桢王诗吟刘勤
Owner SOUTH CHINA AGRI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap