中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于视觉定位的牧场奶牛自动跟踪定位系统研究 黑龙江畜牧兽医 2015 (21) 43-47+287
Position: Home > Articles > Study on automatic tracking and location system for dairy cows from a ranch based on visual positioning Heilongjiang Animal Science and Veterinary Medicine 2015 (21) 43-47+287

基于视觉定位的牧场奶牛自动跟踪定位系统研究

作  者：
王红君;施楠;赵辉;岳有军
单  位：
天津理工大学自动化学院;天津理工大学天津市复杂系统控制理论与应用重点实验室天津农学院;天津市复杂系统控制理论与应用重点实验室/天津理工大学天津农学院
关键词：
牧场;图像预处理;高斯金字塔LK光流法;运动估计;特征点检测
摘  要：
机器视觉已经成为现代畜牧业中的一个重要应用技术,这主要是得益于近年来图像处理技术的快速发展以及计算机的硬件成本不断下降和其运算速度的飞速提升。随着近几年具有高科技的大型奶牛养殖基地的不断兴起,基于机器视觉的奶牛自动定位系统成为新的研究课题。为了解决在牧场中对特定奶牛的定位跟踪问题,笔者提出采用视觉机器人,而视觉定位系统是整个机器人系统的核心和关键。本研究利用高斯金字塔LK光流法实现对奶牛的目标定位及运动跟踪,对传统算法的不足之处进行了总结分析,提出了改进的Harris特征点检测算法。结果表明:改进后的算法不仅在特征点提取效果方面有显著提高,同时具有处理速度快的优点,可为移动奶牛的准确定位做好准备。
译  名：
Study on automatic tracking and location system for dairy cows from a ranch based on visual positioning
作  者：
WANG Hong-jun;SHI Nan;ZHAO Hui;YUE You-jun;Tianjin Key Laboratory of Control Theory&Applications in Complicated Systems ,Tianjin University of Technology;Tianjin Agricultural University;
关键词：
ranch;;image processing;;Gaussian pyramid LK optical flow method;;motion estimation;;feature point detection
摘  要：
Machine vision has become an important technical application in modern livestock technology,which is mainly due to the rapid development of image processing technology,as well as the computer hardware costs continuing to decline and the rapid increase in computing speed.With the constant rise of large-scale and high-tech dairy cow breeding base,the automatic dairy cow positioning system has become a new research topic based on machine vision. To solve the positioning and tracking problem for specific dairy cows in the ranch,the author proposed the use of visual robot,while the vision positioning system is the core and key to the whole robot system. The study achieved the target positioning and motion tracking to the dairy cows by Gaussian pyramid LK optical flow method. The inadequacies of traditional algorithms were summarized and analyzed in this study,and then an improved Harris feature point detection algorithm was proposed. The results showed that the improved algorithm not only had a significant increase in aspect of the extraction effect of feature point,but also has the advantage of fast processing speed,which can be ready for accurate positioning of moving dairy cows.

相似文章

导出引用
计量
文章访问数: 8
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46