浏览全部资源
扫码关注微信
1.福州大学 物理与信息工程学院,福建 福州 350108
2.福建金东矿业股份有限公司,福建 三明 365101
[ "廖一鹏(1982-),男,福建泉州人,博士生,讲师,2005年于福州大学获得学士学位,2008年于福州大学获得硕士学位,现为福州大学物理与信息工程学院教师,主要从事图像处理与模式识别方面的研究。E-mail: fzu_lyp@163.com" ]
[ "王卫星(1959-),男,湖南人,博士,教授,博士生导师,1982年和1985年分别在国内获得学士学位和工程硕士,1997年于瑞典皇家工学院获得博士学位,主要从事图像处理与模式识别、机器视觉应用等方面研究。E-mail: wxwwx@fzu.edu.cn" ]
收稿日期:2020-05-11,
修回日期:2020-06-28,
纸质出版日期:2020-12-15
移动端阅览
廖一鹏,陈诗媛,杨洁洁等.NSST域改进ORB的泡沫流动特征提取及加药状态识别[J].光学精密工程,2020,28(12):2684-2699.
LIAO Yi-peng,CHEN Shi-yuan,YANG Jie-jie,et al.Dosing status identification and froth flow feature extraction based on improved ORB in NSST domain[J].Optics and Precision Engineering,2020,28(12):2684-2699.
廖一鹏,陈诗媛,杨洁洁等.NSST域改进ORB的泡沫流动特征提取及加药状态识别[J].光学精密工程,2020,28(12):2684-2699. DOI: 10.37188/OPE.20202812.2684.
LIAO Yi-peng,CHEN Shi-yuan,YANG Jie-jie,et al.Dosing status identification and froth flow feature extraction based on improved ORB in NSST domain[J].Optics and Precision Engineering,2020,28(12):2684-2699. DOI: 10.37188/OPE.20202812.2684.
针对浮选泡沫表面图像动态变化、光照影响、噪声干扰导致流动特征难于提取的问题,提出了一种在NSST域改进ORB的泡沫流动特征提取方法,并应用于浮选加药状态识别。对相邻两帧泡沫图像NSST分解,对多尺度高频子带先通过尺度相关系数去除噪声再分为多个内层和外层,在各内层通过方向模极大值检测提取兴趣点,然后在本层和上下层通过非极大值抑制提取特征点,采用多尺度BRIEF描述子对特征点描述,结合泡沫的运动趋势动态调整搜索的匹配区域,根据匹配结果计算泡沫流动特征。最后,构建行列自编码极限学习机对泡沫形态、尺寸分布特征和流动特征进行融合,然后通过自适应随机森林对加药状态分类识别。实验结果表明,改进的ORB受噪声和光照影响小,流动特征检测精度和效率较现有方法有较大提高,能准确地表征不同加药状态下泡沫表面的流动特性,加药状态的平均识别精度达97.85%,较现有文献方法有较大提升,为后续的加药量优化控制奠定基础。
A froth-flow feature detection method based on an improved ORB in the NSST domain was developed and applied to flotation dosing state recognition to solve the problems of continuous movement, light effects, and noise interference of flotation surface images, which lead to difficulties in flow feature detection. First, two adjacent froth images were decomposed through NSST. Multiscale high-frequency sub-bands were denoised using a scale correlation coefficient and then divided into multiple inner and outer layers. The points of interest were subsequently extracted through modulus maxima detection in each inner layer, and the feature points were extracted through non-maximum suppression between the upper and lower layers. Second, a multiscale BRIEF descriptor was adopted to describe these feature points, the search matching area was dynamically adjusted according to the movement trend of the bubbles. The froth-flow features were then calculated based on the matching results. Finally, a line-and-column autoencoder extreme learning machine was constructed to fuse the foam shape, size distribution, and flow features, and the dosing state was recognized by the adaptive random forest method. The experimental results showed that the improved ORB was slightly affected by noise and illumination. The flow feature detection efficiency and the detection accuracy were significantly better than those of existing methods. The proposed method could characterize the flow characteristics of the froth surface accurately in different dosing states. The average accuracy of dosing state recognition reached 97.85%, which was significantly higher than those of existing methods. This study lays a foundation for future research on dosing quantity optimization control.
ZHANG J , TANG Z H , AI M X , et al . . Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein-Wiener model [J]. Minerals Engineering , 2018 , 120 ( 5 ): 19 - 28 .
AI M X , XIE Y F , XIE S W , et al . . Shape-weighted bubble size distribution based reagent predictive control for the antimony flotation process [J]. Chemometrics & Intelligent Laboratory Systems , 2019 , 192 ( 8 ): 103821 .
TANG Z H , TANG L Y , ZHANG G Y , et al . . Intelligent setting method of reagent dosage based on time series froth image in zinc flotation process [J]. Processes , 2020 , 8 ( 536 ): 8050536 .
LI Z M , GUI W H , ZHU J Y . Fault detection in flotation processes based on deep learning and support vector machine [J]. Journal of Central South University , 2019 , 26 ( 9 ): 2504 - 2515 .
CAO B F , XIE Y F , GUI W H , et al . . Coordinated optimization setting of reagent dosages in roughing-scavenging process of antimony flotation [J]. Journal of Central South University , 2018 , 25 ( 1 ): 95 - 106 .
陈良琴 , 王卫星 . 基于气泡跟踪与相位相关的浮选表面气泡平移运动估计 [J]. 四川大学学报(工程科学版) , 2016 , 48 ( 5 ): 143 - 152 .
CHEN L Q , WANG W X . Flotation surface bubble displacement motion estimation based on bubble tracking and phase correlation [J]. Journal of Sichuan University(Engineering Science Edition) , 2016 , 48 ( 5 ): 143 - 152 . (in Chinese)
WANG Y L , SUN B , ZHANG R Q , et al . . Sulfur flotation performance recognition based on hierarchical classification of local dynamic and static froth features [J]. IEEE Access , 2018 , 6 ( 3 ): 14019 - 14029 .
NAKHAEI F , IRANNAJAD M , MOHAMMADNEJAD S . Evaluation of column flotation froth behavior by image analysis: effects of operational factors in desulfurization of iron ore concentrate [J]. Energy Sources , Part A:Recovery , Utilization , and Environmental Effects , 2018 , 40 ( 19 ): 2286 - 2306 .
NAKHAEI F , IRANNAJAD M , MOHAMMADNEJAD S . Column flotation performance prediction: PCA,ANN and image analysis-based approaches [J]. Physicochemical Problems of Mineral Processing , 2019 , 55 ( 5 ): 1298 - 1310 .
RUBLEE E , RABAUND V , KONOLIGE K , et al .. ORB: An efficientalternative to SIFT or SURF [C].In t Conf on Computer Vision . Barcelona : IEEE , 2011 : 2564 - 2571 .
GANASALA P , PRASAD A D . Contrast enhanced multi sensor image fusion based on guided image filter and NSST [J]. IEEE Sensors Journal , 2020 , 20 ( 2 ): 339 - 346 .
廖一鹏 , 王卫星 , 付华栋 , 等 . 结合分数阶微分的浮选泡沫图像NSCT多尺度增强 [J]. 华南理工大学学报(自然科学版) , 2018 , 46 ( 3 ): 92 - 102 .
LIAO Y P , WANG W X , FU H D , et al . . Flotation foam image NSCT multi-scale enhancement with fractional differential [J]. Journal of South China University of Technology(Natural Science Edition) , 2018 , 46 ( 3 ): 92 - 102 . (in Chinese)
DONG Q , LIU J H , WANG C , et al . . Image mosaic algorithm based on improved BRISK [J]. Journal of Electronics& Information Technology , 2017 , 39 ( 2 ): 444 - 450 .
樊彦国 , 柴江龙 , 许明明 , 等 . 基于ORB与RANSAC融合改进的图像配准 [J]. 光学 精密工程 , 2019 , 27 ( 3 ): 702 - 717 .
FAN Y G , CHAI J L , XU M M , et al . .Improved fast Image registration algorithm based on ORB and RANSAC fusion [J]. Opt. Precision Eng. , 2019 , 27 ( 3 ): 702 - 717 . (in Chinese)
SONG J L , YANG J H , LIU F J , et al . . High temperature strain measurement method by combining digital image correlation of laser speckle and improved RANSAC smoothing algorithm [J]. Optics and Lasers in Engineering , 2018 , 111 : 8 - 18 .
黄凌霄 , 廖一鹏 . 浮选气泡NSCT域多尺度等效形态特征提取及识别 [J]. 光学 精密工程 , 2020 , 28 ( 3 ): 704 - 716 .
HUANG L X , LIAO Y P . Recognition and multiscale equivalent morphological features extraction of flotation bubbles in nsct domain [J]. Opt. Precision Eng. , 2020 , 28 ( 3 ): 704 - 716 . (in Chinese)
吴海滨 , 陈寅生 , 张庭豪 , 等 . 改进多尺度幅值感知排列熵与随机森林结合的滚动轴承故障诊断 [J]. 光学 精密工程 , 2020 , 28 ( 3 ): 621 - 631 .
WU H B , CHEN Y S , ZHANG T H , et al . .Rolling bearing fault diagnosis by improved multiscale amplitude-aware permutation entropy and random forest [J]. Opt. Precision Eng. , 2020 , 28 ( 3 ): 621 - 631 . (in Chinese)
CHENG Y S , ZHAO D W , WANG Y B , et al . . Multi-label learning with kernel extreme learning machine autoencoder [J]. Knowledge-Based Systems , 2019 , 178 : 1 - 10 .
廖一鹏 , 张进 , 王志刚 , 等 . 结合双模多尺度CNN特征及自适应深度KELM的浮选工况识别 [J]. 光学 精密工程 , 2020 , 28 ( 8 ): 1785 - 1798 .
LIAO Y P , ZHANG J , WANG ZH G , et al . .Flotation performance recognition based on dual-modality multiscale CNN features and adaptive deep learning KELM [J]. Opt. Precision Eng. , 2020 , 28 ( 8 ): 1785 - 1798 . (in Chinese)
牛燕雄 , 陈梦琪 , 张贺 . 基于尺度不变特征变换的快速景象匹配方法 [J]. 电子与信息学报 , 2019 , 41 ( 3 ): 626 - 631 .
NIU Y X , CHEN M Q , ZHANG H . Fast scene matching method based on scale invariant feature transform [J]. Journal of Electronics & Information Technology , 2019 , 41 ( 3 ): 626 - 631 . (in Chinese)
0
浏览量
512
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构