基于机器视觉的母猪分娩检测方法研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

公益性行业(农业)科研专项经费资助项目(201003011)和南京农业大学青年科技基金资助项目(KJ2011021)


Sows Parturition Detection Method Based on Machine Vision
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    检测母猪分娩需对分娩限位栏内的仔猪进行目标识别,分析了母猪分娩视频图像特征,提出首先利用半圆匹配算法进行母猪目标分割,排除母猪运动干扰,基于改进的单高斯模型的背景减除法进行运动目标检测,根据运动区域的颜色和面积特征,对仔猪进行目标识别。试验表明:基于半圆匹配算法的母猪目标识别方法能够有效分割出母猪目标,基于改进单高斯模型的运动目标检测方法,对面积较大、运动缓慢的仔猪目标检测较为完整,适用于母猪分娩检测场景。

    Abstract:

    Automation and industrialization is the trend of pig industry. Real time detection of parturition is one of the key technologies of sow automation farming. Video image features of sows parturition were analyzed to detect sows parturition by recognizing piglet. The moving objects were detected based on the improved single Gaussian model. Disturbance of sow moving was removed by the arithmetic of matching semi circle. According to the color and size characteristics of newborn piglets, targets were recognized. Test results showed that the sow object could be recognized effectively by the proposed approach. The moving objects detection method based on the improved single Gaussian model detected the slow moving piglet completely after eliminate interference.

    参考文献
    相似文献
    引证文献
引用本文

刘龙申,沈明霞,柏广宇,周 波,陆明洲,杨晓静.基于机器视觉的母猪分娩检测方法研究[J].农业机械学报,2014,45(3):237-242. Liu Longshen, Shen Mingxia, Bo Guangyu, Zhou Bo, Lu Mingzhou, Yang Xiaojing. Sows Parturition Detection Method Based on Machine Vision[J]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(3):237-242.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2013-03-14
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2014-03-10
  • 出版日期: 2014-02-10