基于深度图像的奶牛体型评定指标获取技术
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

“十二五”国家科技支撑计划资助项目(2013BAD35B02)


Acquisition of Appraisal Traits for Dairy Cow Based on Depth Image
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:

    为提高现有奶牛体型线性评定指标获取技术的精度、效率及自动化程度,提出基于深度图像的重建奶牛评定性状相应部位,进而进行测量获取线性评定指标的研究方法,并选取Xtion PRO摄像头作为深度图像采集设备,基于OpenNI搭建的数据获取程序完成对奶牛随机部位的点云获取,并结合MeshLab完成对获得的点云数据进行可视化和测量处理,最后将人工测量与重建点云测量所得到的指标进行对比。结果表明,采用低成本的RGBD设备获取奶牛被评定性状相应部位的深度图像,通过从深度图像得到的点云进行测量获取线性评定指标的方法是可行的,在采集距离小于1m条件下,绝对误差小于10mm,相对误差小于9%。

    Abstract:

    In order to improve the accuracy, efficiency and automatic degree of existing acquisition techniques of dairy cow’s conformation linear appraisal traits, a research method based on depth image was proposed reconstructed the corresponding part with dairy cow’s conformation linear appraisal traits to measure and acquire linear appraisal indexes. Xtion PRO was chosen as raw data acquisition device. The experiment acquired point cloud from dairy cow’s body random position was completed by data acquisition program compiled based on OpenNI interface, and then measured by using MeshLab. The results showed that it was feasible to use low cost RGBD equipment to acquire a range image of corresponding part with the dairy cow’s conformation linear appraisal traits. And then, according to the point cloud acquired from range image, the dairy cow’s appraisal indexes were reconstructed and acquired. The relative error was less than 9% and the error was less than 10mm.

    参考文献
    相似文献
    引证文献
引用本文

郭浩,王鹏,马钦,朱德海,张胜利,郜允兵.基于深度图像的奶牛体型评定指标获取技术[J].农业机械学报,2013,44(Supp1):273-276,229.

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:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2013-10-22
  • 出版日期: