引用本文:刘颖,张平,赵珺,吕政,王伟.基于尺度不变特征变换的浮选泡沫图像动态特性提取方法[J].控制理论与应用,2016,33(6):718~726.[点击复制]
LIU Ying,ZHANG Ping,ZHAO Jun,LV Zheng,WANG Wei.Dynamic characteristic extraction method of flotation froth image based on scale invariant feature transform[J].Control Theory and Technology,2016,33(6):718~726.[点击复制]
基于尺度不变特征变换的浮选泡沫图像动态特性提取方法
Dynamic characteristic extraction method of flotation froth image based on scale invariant feature transform
摘要点击 3971  全文点击 1138  投稿时间：2015-07-27  修订日期：2016-03-10
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2016.50648
  2016,33(6):718-726
中文关键词  尺度不变特征变换  动态特性  随机抽样一致  误匹配  浮选泡沫图像
英文关键词  scale invariant feature transform (SIFT)  dynamic characteristic  random sample consensus (RANSAC)  mismatching  flotation froth image
基金项目  国家自然科学基金项目(61304213, 61273037, 61473056), 国家“863”计划(2013AA040703)资助.
作者单位E-mail
刘颖* 大连理工大学 控制科学与工程学院 liuying8227@163.com 
张平 大连理工大学 控制科学与工程学院  
赵珺 大连理工大学 控制科学与工程学院  
吕政 大连理工大学 控制科学与工程学院  
王伟 大连理工大学 控制科学与工程学院  
中文摘要
      本文以矿物浮选过程为背景, 针对浮选泡沫不断运动变化导致泡沫图像动态特性难以提取的问题, 提出一 种基于尺度不变特征变换(scale invariant feature transform, SIFT)浮选泡沫图像动态特性提取方法. 首先, 依据浮选 泡沫独特的运动特性, 提出运动匹配区间的概念, 然后依据泡沫速度大小和方向对应分布范围改进SIFT算法匹配 条件, 在此基础上应用基于速率随机抽样一致(RANSAC)算法进一步剔除误匹配点, 最后, 根据匹配结果提出一种 泡沫崩塌率提取方法. 采用浮选现场实际泡沫图像进行验证, 实验结果表明本文所提方法能够准确提取浮选泡沫 速率、崩塌率等动态特性, 有效剔除误匹配, 同时降低了计算复杂度, 提高了计算实时性.
英文摘要
      As for the mineral flotation process, a new dynamic characteristic extraction method of flotation froth image based on scale invariant feature transform (SIFT) is proposed in this study, considering the difficulty to detect the dynamic characteristic resulted from continuous movement of flotation froth image. Firstly, a concept of motion matching region based on the unique characteristics of flotation froth is proposed, then according to the distribution range of magnitude and direction of bubble velocity to improve SIFT algorithm’s matching conditions and using random sample consensus (RANSAC) to further eliminate the mismatching. Finally, a new method of extracting the collapse rate of the froth is proposed based on the matching result. Verifying by flotation bubble real images on industrial scene, experimental results show the method proposed in the paper can accurately extract the dynamic characteristics of flotation froth, such as velocity, collapse rate, etc, and effectively eliminate the mismatching while reducing the computational complexity, improving the real-time.