Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A computer vision-based method for estimating the average weight of pigs in the same pen

A technology of computer vision and body weight, applied in the field of computer vision, can solve the problems of consuming a lot of manpower and time, waste, driving pigs and prone to accidents, etc.

Active Publication Date: 2022-06-03
CHANGSHA PENGYANG INFORMATION TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if the pigs are driven manually every day and weighed by the weighbridge, it will take a lot of manpower and time, resulting in serious waste, and at the same time, accidents are prone to occur when driving the pigs

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
  • A computer vision-based method for estimating the average weight of pigs in the same pen
  • A computer vision-based method for estimating the average weight of pigs in the same pen
  • A computer vision-based method for estimating the average weight of pigs in the same pen

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention may be implemented in many different ways as defined and covered by the claims.

[0041] See figure 1 , the present embodiment provides a computer vision-based method for estimating the average weight of pigs in the same pen, comprising the following steps:

[0042] Step 1: Use the visual weight evaluation system for pigs in the same pen to collect images of pigs in real time. The visual weight evaluation system for pig herds in the same pen specifically includes installing a vertical downward shooting camera at the top of the center of the pig pen, and the installation height of the camera is sufficient to capture the entire pig pen; the camera is a network camera, preferably a high-definition ball. machine or gun.

[0043] Step 2: Establish an approximate camera imaging model, and complete the approximate conversion of ima...

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 method for estimating the average body weight of pigs in the same pen based on computer vision, which includes installing a camera, establishing an approximate camera imaging model, and establishing a height prior value table for each bone joint point of the pig. Pig detection and instance segmentation are performed on each image to obtain the rectangular frame position and edge contour information of the pig in the image, and each detected pig is detected for the bone joint point, and its posture is recognized by using the edge contour information of the pig; Skeleton joint points and posture information, estimate the size information of each part of the pig; use regression analysis to establish a correlation model between the weight of the pig and the size information of each part of the pig, so as to estimate the average weight of the pig. The invention effectively avoids the endless daily consumption of manpower to weigh a single pig, and realizes the non-contact weight estimation of pigs in the same pen, which has important practical application significance.

Description

technical field [0001] The invention relates to the field of computer vision and artificial intelligence technology, and in particular, to a method for estimating the average weight of pigs in the same pen based on computer vision. Background technique [0002] With the growing economy of our country, our demand for live pigs is increasing. In order to better manage pig farms, it is necessary to raise pigs more scientifically through technologies such as artificial intelligence, so the intelligence of pig farms needs to be improved urgently. In actual life, when pig farms are raising pigs in pens, they usually divide pigs of the same size and weight into a group and keep them in the same sty or in the same pen. This is because in the pig herd, in order to compete for food, powerful pigs often occupy the best resources in the pigsty, and there will be violent conflicts due to competition for food or drinking water. Under special circumstances, the big pigs are also prone to...

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 Patents(China)
IPC IPC(8): G06V40/10G06V10/28G06V10/44G06T7/11G06T7/50G06T7/73G06T7/60
CPCG06T7/11G06T7/50G06T7/73G06T7/60G06T2207/10004G06T2207/20081G06T2207/30004
Inventor 涂丹汪彦明朱为徐新文曹正午谢志恒徐东胡青霞王涛郑冰
Owner CHANGSHA PENGYANG INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com